dsh-codex-share 0.4.2 → 0.4.3

package/README.md

@@ -32,7 +32,7 @@ The plugin intentionally does not refresh a stale token. When Codex writes a rep
 
 When `GLM_API_KEY` is non-empty in the Harness launch environment, this plugin also adds **GLM Coding Plan (global)** to the model picker under the `glm-coding-global` provider route. It uses pi-ai's installed Z.AI model catalog and the global Coding Plan endpoint, `https://api.z.ai/api/coding/paas/v4` (not the China endpoint or the standard pay-as-you-go API).
 
-Export your Coding Plan key before launching the Harness, or set it in a Harness launch `.env` file, and restart the profile. No manual model/provider configuration is needed. With no key, or an empty/whitespace-only key, the GLM route is omitted. `ZAI_API_KEY` does not enable this route. GLM requests use only `GLM_API_KEY` and do not require a Codex login; Codex requests continue to use the local Codex credential file. The key is not written to plugin settings. Available models follow the installed pi-ai catalog; endpoint access depends on your plan.
+Export your Coding Plan key before launching the Harness, or set it in a Harness launch `.env` file, and restart the profile. No manual model/provider configuration is needed. With no key, or an empty/whitespace-only key, the GLM route is omitted. `ZAI_API_KEY` does not enable this route. GLM requests use only `GLM_API_KEY` and do not require a Codex login; Codex requests continue to use the local Codex credential file. The key is not written to plugin settings. Available models follow the installed pi-ai catalog, plus **GLM-5.3 Flash X** (`glm-5.3-flashx`) when upstream does not yet list it. Flash X inherits Flash's 1M context, 128K maximum output, image input, and reasoning capabilities; its cost estimate is left at zero until upstream supplies model-specific pricing (this does not imply free usage). [Z.AI's documentation](https://docs.z.ai/guides/vlm/glm-5.3-flash) currently says FlashX is not yet available on the Coding Plan; it is listed for forward compatibility, but requests may be rejected until your plan supports it.
 
 ## Development
 

package/dist/index.mjs

@@ -115,6 +115,22 @@ function apply(ctx, config = Config({})) {
 	};
 	const glmKey = launchEnvironmentOf(ctx).get("GLM_API_KEY")?.value;
 	const glmUpstream = glmKey?.trim() ? zaiProvider() : void 0;
+	const glmCatalog = glmUpstream ? [...glmUpstream.getModels()] : [];
+	if (glmUpstream && !glmCatalog.some((model) => model.id === "glm-5.3-flashx")) {
+		const flash = glmCatalog.find((model) => model.id === "glm-5.3-flash");
+		if (flash === void 0) throw new TypeError("The Z.AI catalog must include GLM-5.3-Flash");
+		glmCatalog.push({
+			...flash,
+			id: "glm-5.3-flashx",
+			name: "GLM-5.3 Flash X",
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0
+			}
+		});
+	}
 	const glmProfile = glmUpstream && {
 		...profileBase,
 		provider: "glm-coding-global",
@@ -124,7 +140,7 @@ function apply(ctx, config = Config({})) {
 			id: "glm-coding-global",
 			name: "GLM Coding Plan (global)",
 			auth: { apiKey: envApiKeyAuth("GLM Coding Plan API key", []) },
-			getModels: () => [...glmUpstream.getModels()].map((model) => ({
+			getModels: () => glmCatalog.map((model) => ({
 				...model,
 				provider: "glm-coding-global"
 			}))

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dsh-codex-share",
-  "version": "0.4.2",
+  "version": "0.4.3",
   "description": "Use the local Codex CLI ChatGPT subscription login as a DeepSeek Harness LLM provider",
   "type": "module",
   "license": "MIT",