chore: version up to 2.80.37 and package with response recovery

package.json

@@ -2,7 +2,7 @@
   "name": "astra",
   "displayName": "Astra",
   "description": "The personal intelligence layer for Antigravity and VS Code. A private cognitive partner for deep project context, memory, and proactive strategic decision-making.",
-  "version": "2.80.36",
+  "version": "2.80.37",
   "publisher": "g1nation",
   "license": "MIT",
   "icon": "assets/icon.png",
@@ -229,6 +229,23 @@
           "minimum": 0,
           "description": "When a small model (≤4B parameters, detected from the model name) is selected, budget the prompt against this smaller effective context window instead of g1nation.contextLength — small models often emit an empty/EOS response on prompts that nominally fit but exceed their real capability. Set 0 to disable. Default: 8192"
         },
+        "g1nation.autoContinueOnOutputLimit": {
+          "type": "boolean",
+          "default": true,
+          "description": "When a reply is cut off because it hit the output-token limit, Astra continues it internally (compressed request — original question + the answer so far, not the whole context again) and shows one merged answer, instead of asking you to say \"이어서 작성해줘\". Default: true"
+        },
+        "g1nation.maxAutoContinuations": {
+          "type": "number",
+          "default": 3,
+          "minimum": 0,
+          "maximum": 10,
+          "description": "Maximum number of automatic continuation rounds per reply (prevents runaway loops). Set 0 to disable auto-continuation. Default: 3"
+        },
+        "g1nation.finalOnlyRetryOnThoughtLeak": {
+          "type": "boolean",
+          "default": true,
+          "description": "If the model emits only hidden reasoning (<think>, <|channel|>thought, \"Thinking Process:\" …) and no user-visible answer, Astra silently re-asks it for the final answer only. Hidden reasoning is never shown either way. Default: true"
+        },
         "g1nation.lmStudio.idleTimeoutMs": {
           "type": "number",
           "default": 300000,