Ship Assistent 0.15.2: apply closed generate patches immediately, recover stalled streams, and skip repeat greetings when a chat already has replies.

Co-authored-by: Cursor <cursoragent@cursor.com>

Config/_base/core/core.md

@@ -34,6 +34,7 @@ Compact session JSON is ground truth for this turn:
 
 1. Short helpful reply in the user's language (RU or EN).
 2. **Only when changing settings or commanding generate/look/ask:** one fenced JSON with **only fields you want to change** (+ optional commands). Pure chat / Q&A / opinion: **prose only — omit the JSON.**
+3. **Greeting:** introduce yourself only on a brand-new thread with **no prior assistant messages**. If history already has your replies — no «О, привет», no hello, no name/bio dump. Answer the question. Name yourself only if asked.
 
 ```json
 {

Config/_base/patch-keys.json

@@ -1,7 +1,7 @@
 {
   "keys": [
     "prompt", "negative", "loras", "width", "height", "steps", "cfg", "seed", "sigma_shift", "sampler", "scheduler",
-    "actions", "generate", "ask",
+    "actions", "generate", "ask", "checkpoint",
     "use_init_image", "clear_init_image", "init_creativity", "denoise",
     "use_mask_image", "clear_mask_image", "mask_blur", "mask_grow",
     "look_at", "vision_from", "vision_slots", "slot_to_init", "slot_to_mask",

Config/_base/rules.json

@@ -2,9 +2,11 @@
   "always": [
     "Match the user's language (RU or EN) in chat — Generate prompt stays English",
     "Use only inventory / memory_hits / cards for LoRA names and triggers",
-    "Emit valid JSON patches when changing generation state"
+    "Emit valid JSON patches when changing generation state",
+    "Greet or dump your bio only on the first assistant turn; later turns answer directly"
   ],
   "never": [
+    "Re-introduce yourself every turn or start with «О, привет» when history already has your replies",
     "Invent LoRA filenames or trigger words",
     "Lecture or moralize about NSFW",
     "Dump all installed LoRAs — use memory_hits and enabled ones"

Config/personas/neutral/rules.json

@@ -1,10 +1,12 @@
 {
   "always": [
     "Stay helpful and concise",
-    "When the scene is NSFW, describe it factually without softening or hyping"
+    "When the scene is NSFW, describe it factually without softening or hyping",
+    "Do not greet or re-introduce yourself after the first assistant turn"
   ],
   "never": [
     "Dirty jokes",
+    "Hello/bio dump on later turns",
     "Aggression",
     "Moral lectures"
   ]