pi-multimodal-proxy 1.16.0 → 1.17.0

package/CHANGELOG.md

@@ -4,6 +4,23 @@ All notable changes to this project will be documented in this file.
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
 
+## [1.17.0] - 2026-08-27
+
+### Changed
+
+- **Default vision model is now GLM 5.3 Flash (`zai/glm-5.3-flash`).** `DEFAULT_CONFIG` ships `zai/glm-5.3-flash` (image input, 1M context, $0.075/M input — $0.25/M output) as the default image-description model, replacing `anthropic/claude-sonnet-5`. Implicit configs keep tracking the package default: `anthropic/claude-sonnet-5` was added to `LEGACY_DEFAULT_MODELS` (so configs that merely inherited Sonnet 5 upgrade to GLM 5.3 Flash once it's in the catalog), `DEFAULT_MODEL_FALLBACKS` now tries `anthropic/claude-sonnet-5` and then `anthropic/claude-sonnet-4-5` on catalogs without GLM 5.3 Flash, and explicit choices (`modelExplicit`, `PI_VISION_PROXY_MODEL`) are never rewritten. README (What's new, env-table default, privacy note, requirements) and the `/multimodal-proxy model` usage example updated to the new default.
+
+## [1.16.1] - 2026-08-22
+
+### Fixed
+
+- **Syntax error in the interactive config menu** (v1.16.0 regression): the "Fallback model" handler opened `ctx.ui.input(` with a stray trailing quote, making the whole `vision-proxy.ts` extension unparseable for pi's jiti/oxc loader (`Unterminated string constant` at `vision-proxy.ts:3790`). Every pi process loading the package crashed at startup — daemons crash-looped until the extension was removed or the file hand-patched. `node --check` (swc) accepts the broken construct, so it slipped through the existing gates.
+- The shipped file is now byte-identical to the hand-patched copy that has been running in production.
+
+### Added
+
+- **Syntax gate for shipped extensions** (`npm run check`, `tools/check-syntax.mjs`): parses every `.ts` under `extensions/` with the TypeScript parser and fails on any parse diagnostic — a parser that actually rejects the class of error that shipped. Wired into `release.yml` before `npm test`, so an unparseable extension can no longer reach npm.
+
 ## [1.16.0] - 2026-08-17
 
 ### Added

package/README.md

@@ -8,6 +8,10 @@ When **video or audio files** are detected, they are routed to a **multimodal mo
 
 **YouTube links** are detected too: paste a URL (`youtube.com/watch?v=…`, `youtu.be/…`, `/shorts/…`, etc.) and the video is downloaded with [`yt-dlp`](https://github.com/yt-dlp/yt-dlp) and analyzed exactly like a local file.
 
+## What's new in 1.17.0
+
+- **Default vision model is now GLM 5.3 Flash** (`zai/glm-5.3-flash`) — fast, cheap image description ($0.075/M input, $0.25/M output) with a 1M-token context window. Models you never chose explicitly track the package default: configs that merely inherited the old default (`anthropic/claude-sonnet-5`) are upgraded when GLM 5.3 Flash is in the catalog, and on Pi versions without it the default falls back to `anthropic/claude-sonnet-5` (then `anthropic/claude-sonnet-4-5` on the oldest catalogs). Models chosen explicitly — via `/multimodal-proxy model`, `pick`, or `PI_VISION_PROXY_MODEL` — are never rewritten. **Heads-up:** the default provider is now Z.ai — you need a `zai` API key and will be asked for first-use data-egress consent unless you pin a different model (e.g. `/multimodal-proxy model anthropic/claude-sonnet-5`).
+
 ## What's new in 1.16.0
 
 Reliability features borrowed from a survey of [atlas-vision-mcp](https://github.com/QuangThai/vision-bridge-mcp) (ideas worth stealing, implementation our own):
@@ -157,7 +161,7 @@ Legacy alias: /vision-proxy <args> works identically.
 | Variable | Values | Default |
 |----------|--------|---------|
 | `PI_VISION_PROXY_MODE` | `fallback`, `always`, `off` | `fallback` |
-| `PI_VISION_PROXY_MODEL` | `provider/model-id` | `anthropic/claude-sonnet-5` |
+| `PI_VISION_PROXY_MODEL` | `provider/model-id` | `zai/glm-5.3-flash` |
 | `PI_VISION_PROXY_INCLUDE_CONTEXT` | bool | `true` |
 | `PI_VISION_PROXY_TOOL` | `on`, `off` | `on` |
 | `PI_VISION_PROXY_MAX_IMAGES_PER_CALL` | 1–20 | `10` |
@@ -306,7 +310,7 @@ When a model is in the grounding registry, a format-specific instruction is appe
 
 ## Privacy & security
 
-This extension **sends data to a third-party provider**. By default that is `anthropic/claude-sonnet-5` for images (`anthropic/claude-sonnet-4-5` on older Pi versions without Sonnet 5 in the catalog) and `xai/grok-4.3` for video/audio. Be aware:
+This extension **sends data to a third-party provider**. By default that is `zai/glm-5.3-flash` for images (`anthropic/claude-sonnet-5` on older Pi versions without GLM 5.3 Flash in the catalog, then `anthropic/claude-sonnet-4-5`) and `xai/grok-4.3` for video/audio. Be aware:
 
 1. **Image and video data is uploaded** to the configured provider on every proxied request. Crop coordinates are applied locally before upload — only the cropped region is sent.
 2. **Recent conversation context** (last 8 messages, truncated) is uploaded with the image unless you set `/multimodal-proxy context off` or `PI_VISION_PROXY_INCLUDE_CONTEXT=false`. Disable it for sensitive sessions.
@@ -325,7 +329,7 @@ For the full security audit see [`SECURITY-REVIEW.md`](./SECURITY-REVIEW.md).
 
 ## Requirements
 
-- A vision-capable model with a valid API key (e.g. Claude, GPT-4o, Gemini, Qwen-VL)
+- A vision-capable model with a valid API key (e.g. GLM 5.3 Flash, Claude, GPT-4o, Gemini, Qwen-VL)
 - For video/audio: a multimodal model that supports video input (e.g. Grok 4.3, Gemini 2.5 Pro)
 - The models must be registered in Pi (built-in or via `models.json`)
 

package/extensions/internal.ts

@@ -681,8 +681,8 @@ export const DEFAULT_VIDEO_SYSTEM_PROMPT = [
 
 export const DEFAULT_CONFIG: VisionConfig = {
 	mode: "fallback",
-	provider: "anthropic",
-	modelId: "claude-sonnet-5",
+	provider: "zai",
+	modelId: "glm-5.3-flash",
 	systemPrompt: [
 		"You are a precise image analysis assistant.",
 		"Describe the image factually for a downstream agent that may act on the description.",
@@ -1261,9 +1261,10 @@ export function resolveConfig(
 
 /**
  * Ordered fallbacks tried when the built-in default vision model is missing
- * from the model registry — e.g. Pi < 0.80.3 catalogs without Claude Sonnet 5.
+ * from the model registry — e.g. Pi catalogs that predate GLM 5.3 Flash.
  */
 export const DEFAULT_MODEL_FALLBACKS: ReadonlyArray<{ provider: string; modelId: string }> = [
+	{ provider: "anthropic", modelId: "claude-sonnet-5" },
 	{ provider: "anthropic", modelId: "claude-sonnet-4-5" },
 ];
 
@@ -1274,6 +1275,7 @@ export const DEFAULT_MODEL_FALLBACKS: ReadonlyArray<{ provider: string; modelId:
  * model" and may track the current package default.
  */
 export const LEGACY_DEFAULT_MODELS: ReadonlyArray<{ provider: string; modelId: string }> = [
+	{ provider: "anthropic", modelId: "claude-sonnet-5" },
 	{ provider: "anthropic", modelId: "claude-sonnet-4-5" },
 ];
 

package/extensions/vision-proxy.ts

@@ -2653,7 +2653,7 @@ export default function (pi: ExtensionAPI) {
 				const parsed = parseModelString(value);
 				if (!parsed) {
 					ctx.ui.notify(
-						"Usage: /multimodal-proxy model provider/model-id\nExample: /multimodal-proxy model anthropic/claude-sonnet-5",
+						"Usage: /multimodal-proxy model provider/model-id\nExample: /multimodal-proxy model zai/glm-5.3-flash",
 						"warning",
 					);
 					return;
@@ -3787,7 +3787,7 @@ Use "*" or "all" to grant consent for all providers globally.`,
 					ctx.ui.notify("[multimodal-proxy] Env override active for fallback-model.", "warning");
 					return;
 				}
-				const val = await ctx.ui.input("
+				const val = await ctx.ui.input(
 					"Fallback vision model (provider/model-id, or empty to clear)",
 					effective.fallbackProvider ? `${effective.fallbackProvider}/${effective.fallbackModelId}` : "",
 				);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-multimodal-proxy",
-  "version": "1.16.0",
+  "version": "1.17.0",
   "description": "Automatic image, video and audio description for any model in Pi. Routes media to a multimodal model and injects descriptions into context.",
   "keywords": [
     "pi-package"
@@ -14,6 +14,7 @@
   "type": "module",
   "scripts": {
     "test": "node --experimental-strip-types --no-warnings --test extensions/__tests__/*.test.ts",
+    "check": "node tools/check-syntax.mjs",
     "prepublishOnly": "node -e \"if(!process.env.CI)throw new Error('publish via release.yml CI: push a v* tag. Manual npm publish is blocked.')\""
   },
   "pi": {
@@ -41,5 +42,8 @@
     "README.md",
     "CHANGELOG.md",
     "SECURITY-REVIEW.md"
-  ]
+  ],
+  "devDependencies": {
+    "typescript": "5.9"
+  }
 }