docs(readme): document model ID overrides (#22)

- Add modelIdOverrides to the settings table with a valid settings.json example
- Clean out/ before packaging to avoid stale compiled files in the VSIX

Author: Vizards

README.md

@@ -84,11 +84,23 @@ Both support optional thinking mode, tool calling, and 1M token context.
 |---|---|---|
 | `deepseek-copilot.baseUrl` | `https://api.deepseek.com` | API endpoint — change for self-hosted / proxied deployments |
 | `deepseek-copilot.maxTokens` | `0` | Max output tokens (`0` = no limit). Useful for cost control |
+| `deepseek-copilot.modelIdOverrides` | prefilled official ID map | API model IDs to send for DeepSeek V4 Flash / Pro. Change only for compatible third-party APIs with different model names |
 | `deepseek-copilot.visionModel` | *(auto)* | Which Copilot model to proxy images through |
 | `deepseek-copilot.visionPrompt` | *(built-in)* | Prompt used to describe image attachments |
 
 Thinking Effort is configured from Copilot Chat's model picker for each DeepSeek model.
 
+Example `settings.json` override for compatible API proxies:
+
+```json
+{
+  "deepseek-copilot.modelIdOverrides": {
+    "deepseek-v4-flash": "your-flash-model-id",
+    "deepseek-v4-pro": "your-pro-model-id"
+  }
+}
+```
+
 ## Compared to alternatives
 
 | | This extension | Local proxy (e.g. LiteLLM) | Standalone DeepSeek extensions |

package.json

@@ -154,7 +154,8 @@
     }
   },
   "scripts": {
-    "vscode:prepublish": "npm run compile",
+    "clean": "node -e \"require('node:fs').rmSync('out', { recursive: true, force: true, maxRetries: process.platform === 'win32' ? 10 : 0 })\"",
+    "vscode:prepublish": "npm run clean && npm run compile",
     "compile": "tsc -p ./",
     "watch": "tsc -watch -p ./",
     "lint": "oxlint",