++

backend/app/services/citizen_generator.py

@@ -10,6 +10,7 @@ from app.models.agent import (
 from app.models.demographics import DemographicProfile
 from app.models.world import WorldBlueprint
 from app.services.llm import LLMClient, parse_json
+from app.services.i18n import language_directive
 
 logger = logging.getLogger(__name__)
 
@@ -242,8 +243,21 @@ Return ONLY valid JSON. No markdown, no explanation."""
 
 
 class CitizenGenerator:
-    def __init__(self, llm: LLMClient):
+    def __init__(self, llm: LLMClient, locale: str = "en"):
         self.llm = llm
+        self._locale = locale
+
+    def set_locale(self, locale: str) -> None:
+        self._locale = locale
+
+    @staticmethod
+    def _has_cjk(text: str) -> bool:
+        return any("\u4e00" <= ch <= "\u9fff" for ch in text)
+
+    def _directive(self, system_prompt: str) -> str:
+        """Wrap a system prompt with the language directive (head + tail)."""
+        head, tail = language_directive(self._locale)
+        return head + "\n\n" + system_prompt + "\n\n" + tail
 
     async def generate(
         self,
@@ -337,7 +351,7 @@ class CitizenGenerator:
             ) or "  (not available)"
             char_line = f"CITY CHARACTER: {demographics.city_character}" if demographics.city_character else ""
 
-            system_prompt = DEMOGRAPHIC_CAST_PROMPT.format(
+            base = DEMOGRAPHIC_CAST_PROMPT.format(
                 city_name=demographics.city_name,
                 state=demographics.state,
                 population=demographics.population,
@@ -350,8 +364,9 @@ class CitizenGenerator:
                 eth_dist=eth_dist,
                 city_character=char_line,
             )
+            system_prompt = self._directive(base)
         else:
-            system_prompt = CAST_SYSTEM_PROMPT
+            system_prompt = self._directive(CAST_SYSTEM_PROMPT)
 
         user_text = f"{world_context}\n\nGenerate exactly {count} citizens."
         if proposed_change:
@@ -367,7 +382,7 @@ class CitizenGenerator:
             system=system_prompt,
             user=user_text,
             json_mode=True,
-            max_tokens=3000,
+            max_tokens=4000,
         )
 
         data = parse_json(response)
@@ -378,17 +393,50 @@ class CitizenGenerator:
         else:
             cast = []
 
+        # If the user picked a Chinese locale but the LLM ignored our language
+        # directive and returned English names, retry once with a stronger nudge.
+        if (
+            self._locale == "zh"
+            and cast
+            and not any(self._has_cjk(str(c.get("name", ""))) for c in cast)
+        ):
+            logger.warning("Cast generation returned non-CJK names despite zh locale, retrying. Names: %s", [c.get('name') for c in cast])
+            retry_user = user_text + (
+                "\n\n[STRICT REMINDER] All names, roles, personality hooks, and "
+                "stances MUST be written in Chinese characters. Do NOT use English."
+            )
+            response = await self.llm.generate(
+                system=system_prompt,
+                user=retry_user,
+                json_mode=True,
+                max_tokens=3000,
+            )
+            data = parse_json(response)
+            if isinstance(data, dict) and "citizens" in data:
+                cast = data["citizens"]
+            elif isinstance(data, list):
+                cast = data
+
         if len(cast) < count:
             logger.warning("Cast generation returned %d/%d citizens, padding", len(cast), count)
             while len(cast) < count:
                 idx = len(cast)
-                cast.append({
-                    "name": f"Citizen {idx + 1}",
-                    "role": "Laborer",
-                    "age": 30 + (idx % 40),
-                    "personality_hook": "A quiet person trying to get by",
-                    "stance": "Indifferent to the rules",
-                })
+                if self._locale == "zh":
+                    cast.append({
+                        "name": f"居民{idx + 1}号",
+                        "role": "劳动者",
+                        "age": 30 + (idx % 40),
+                        "personality_hook": "一个安静过日子的人",
+                        "stance": "对规则漠不关心",
+                    })
+                else:
+                    cast.append({
+                        "name": f"Citizen {idx + 1}",
+                        "role": "Laborer",
+                        "age": 30 + (idx % 40),
+                        "personality_hook": "A quiet person trying to get by",
+                        "stance": "Indifferent to the rules",
+                    })
 
         return cast[:count]
 
@@ -418,7 +466,7 @@ class CitizenGenerator:
                     f"Personality hook: {member.get('personality_hook', '')}\n"
                     f"Stance on tensions: {member.get('stance', 'unknown')}"
                 )
-                prompts.append((PERSONA_SYSTEM_PROMPT, f"{world_ctx}\n\n{citizen_ctx}"))
+                prompts.append((self._directive(PERSONA_SYSTEM_PROMPT), f"{world_ctx}\n\n{citizen_ctx}"))
 
             responses = await self.llm.generate_batch(prompts, json_mode=True, max_tokens=800)
 
@@ -482,7 +530,7 @@ class CitizenGenerator:
         )
 
         response = await self.llm.generate(
-            system=RELATIONSHIPS_SYSTEM_PROMPT,
+            system=self._directive(RELATIONSHIPS_SYSTEM_PROMPT),
             user=f"World: {blueprint.name}\nRules: {'; '.join(blueprint.rules)}\n\nCitizens:\n{agent_summaries}",
             json_mode=True,
             max_tokens=3000,
@@ -551,7 +599,7 @@ class CitizenGenerator:
             prompts = []
             for agent in batch:
                 num_events = self._num_formative_events(agent.age)
-                system = LIFE_HISTORY_PROMPT.format(num_events=num_events)
+                system = self._directive(LIFE_HISTORY_PROMPT.format(num_events=num_events))
                 world_ctx = (
                     f"World: {blueprint.name}\n"
                     f"Rules: {'; '.join(blueprint.rules)}\n"