feat(brain): add OUTPUT_LANGUAGE reply-language lock

Add an optional OUTPUT_LANGUAGE env var that forces every reply into a
single language. When set, output_language_directive() injects a "respond
only in <language>" instruction (also forbidding other scripts) into the
chat loop's system prompt, next to the existing TTS English-only lock.
Empty (default) keeps the multilingual "reply in the user's language"
behaviour, so upstream is unaffected.

For the Korean-only deployment this also suppresses the occasional trailing
CJK/Hanja fragment qwen2.5:3b leaks on free-form chit-chat.

- system_prompt.py: language-agnostic output_language_directive() helper
- engine.py: read OUTPUT_LANGUAGE, append directive in _build_initial_system_message
- docker-compose.yml + .env.example: document/pass the new var
- docs/llm_contexts.md: note the new gating on the main reply context
- tests: cover unset/set/agnostic/whitespace cases

.env.example

@@ -59,6 +59,12 @@ OLLAMA_CHAT_MODEL=qwen2.5:3b
 OLLAMA_EMBED_MODEL=nomic-embed-text
 WHISPER_MODEL=small
 
+# Lock every reply to one language, e.g. OUTPUT_LANGUAGE=Korean. Leave BLANK to
+# keep the default behaviour of replying in whatever language the user wrote in.
+# A fixed value also suppresses stray characters from other scripts (e.g. the
+# occasional trailing CJK fragment small models leak on free-form chat).
+OUTPUT_LANGUAGE=
+
 # ---------------------------------------------------------------------------
 # Docker desktop (VNC) — used only by the container image
 # ---------------------------------------------------------------------------

docker-compose.yml

@@ -65,6 +65,8 @@ services:
       WHISPER_MODEL: ${WHISPER_MODEL:-small}
       WHISPER_DEVICE: ${WHISPER_DEVICE:-cuda}
       WHISPER_COMPUTE_TYPE: ${WHISPER_COMPUTE_TYPE:-float16}
+      # Optional single-language lock for replies (empty = user's own language).
+      OUTPUT_LANGUAGE: ${OUTPUT_LANGUAGE:-}
       BRIDGE_URL: http://127.0.0.1:8765
     depends_on:
       - ollama

docs/llm_contexts.md

@@ -12,7 +12,7 @@ Every distinct LLM call in Jarvis, what feeds it, what consumes it, and how it i
 - **Inputs**:
   - Redacted user query
   - Recent dialogue (last 5 minutes), including in-loop tool-call + tool-role messages from prior replies within the active conversation (tool carryover, `DialogueMemory.record_tool_turn` / `get_recent_turns_with_tools` in [src/jarvis/memory/conversation.py](src/jarvis/memory/conversation.py); per-prompt cap via `cfg.tool_carryover_max_turns` / `tool_carryover_per_entry_chars`; storage cap `_tool_turns_max_storage = 16`; cleared on `stop` signal AND on new-conversation entry; UNTRUSTED WEB EXTRACT fence markers preserved on truncation; both `content` and `tool_calls[*].function.arguments` scrubbed on write)
-  - Unified system prompt from [src/jarvis/system_prompt.py](src/jarvis/system_prompt.py) + ASR note + tool-protocol guidance
+  - Unified system prompt from [src/jarvis/system_prompt.py](src/jarvis/system_prompt.py) + ASR note + tool-protocol guidance. When the `OUTPUT_LANGUAGE` env var is set, `output_language_directive()` appends a "respond only in `<language>`" instruction (also forbids other scripts, suppressing trailing CJK leakage on small models); empty (default) keeps the multilingual "reply in the user's language" behaviour. Gated in `_build_initial_system_message()` at [engine.py](src/jarvis/reply/engine.py) alongside the TTS English-only lock.
   - **Warm profile block** (query-agnostic User + Directives excerpt from the knowledge graph, composed by `build_warm_profile()` / `format_warm_profile_block()` in [src/jarvis/memory/graph_ops.py](src/jarvis/memory/graph_ops.py) at Step 3.5 of `reply()`; no LLM call, pure SQLite read; injected unconditionally so personalisation is the default; result cached in `DialogueMemory._hot_cache` under `DialogueMemory.WARM_PROFILE_CACHE_KEY` for the lifetime of the active conversation. Invalidated on `stop`, on new-conversation entry, AND on User/Directives graph mutations via the listener registered in [src/jarvis/daemon.py](src/jarvis/daemon.py) against `register_graph_mutation_listener` in [src/jarvis/memory/graph.py](src/jarvis/memory/graph.py); World-branch writes are ignored)
   - Digested memory enrichment (optional, see #4)
   - Time + location context (re-injected each turn)

src/jarvis/reply/engine.py

@@ -5,10 +5,11 @@ Handles memory enrichment, tool planning and execution.
 """
 
 from __future__ import annotations
+import os
 from typing import Optional, TYPE_CHECKING
 
 from ..utils.redact import redact
-from ..system_prompt import build_system_prompt
+from ..system_prompt import build_system_prompt, output_language_directive
 from ..tools.registry import run_tool_with_retries, generate_tools_description, generate_tools_json_schema, BUILTIN_TOOLS
 from ..tools.builtin.stop import STOP_SIGNAL
 from ..debug import debug_log
@@ -1441,6 +1442,14 @@ def run_reply_engine(db: "Database", cfg, tts: Optional[Any],
                 "Always respond in English regardless of the language the user speaks in."
             )
 
+        # Deployment-level output-language lock (OUTPUT_LANGUAGE). When set,
+        # force every reply into that single language and forbid stray
+        # characters from other scripts. Empty (default) keeps the
+        # multilingual behaviour of replying in the user's own language.
+        _lang_directive = output_language_directive(os.environ.get("OUTPUT_LANGUAGE"))
+        if _lang_directive:
+            guidance.append(_lang_directive)
+
         if warm_profile_block:
             # Pre-query, query-agnostic user context. Lives OUTSIDE the
             # conversation-history section because it isn't a history

src/jarvis/system_prompt.py

@@ -6,6 +6,8 @@ who renames the wake word (e.g. "Friday") gets a butler with the matching
 name rather than a persona hardcoded to "Jarvis".
 """
 
+from typing import Optional
+
 _SYSTEM_PROMPT_TEMPLATE: str = (
     "Persona: you are a British butler named {name} — polite, composed, quietly amused, and "
     "quietly enjoying yourself. Default voice is dry, witty, and lightly sarcastic: you notice "
@@ -87,3 +89,26 @@ def build_system_prompt(assistant_name: str = "Jarvis") -> str:
     """
     name = (assistant_name or "Jarvis").strip() or "Jarvis"
     return _SYSTEM_PROMPT_TEMPLATE.format(name=name)
+
+
+def output_language_directive(language: Optional[str]) -> Optional[str]:
+    """Return a 'respond only in <language>' instruction, or None when unset.
+
+    Deployments that serve a single language set ``OUTPUT_LANGUAGE`` (read by
+    the reply engine). When it is empty/None the assistant keeps its default
+    multilingual behaviour of replying in whatever language the user wrote in,
+    so this returns ``None`` and no directive is injected.
+
+    The instruction is language-agnostic — it names whatever language string it
+    is given — and forbids mixing in other scripts. That exclusivity also
+    suppresses the occasional trailing CJK/Hanja fragment some small models
+    leak on free-form chit-chat.
+    """
+    lang = (language or "").strip()
+    if not lang:
+        return None
+    return (
+        f"Always respond only in {lang}, regardless of the language the user "
+        f"writes in. Do not mix in words, characters, or punctuation from any "
+        f"other language or script."
+    )

tests/test_system_prompt.py

@@ -5,7 +5,7 @@ wake word to e.g. "Friday" produces a butler named Friday, not one still
 hardcoded to Jarvis.
 """
 
-from jarvis.system_prompt import build_system_prompt
+from jarvis.system_prompt import build_system_prompt, output_language_directive
 
 
 class TestBuildSystemPrompt:
@@ -26,3 +26,35 @@ class TestBuildSystemPrompt:
         assert "named Jarvis" in build_system_prompt("")
         assert "named Jarvis" in build_system_prompt("   ")
         assert "named Jarvis" in build_system_prompt(None)  # type: ignore[arg-type]
+
+
+class TestOutputLanguageDirective:
+    """A deployment may lock replies to a single language via OUTPUT_LANGUAGE.
+
+    Unset (the default) must keep the assistant's multilingual behaviour of
+    replying in the user's own language, so the helper returns None and no
+    directive is injected.
+    """
+
+    def test_unset_returns_none(self):
+        assert output_language_directive(None) is None
+        assert output_language_directive("") is None
+        assert output_language_directive("   ") is None
+
+    def test_set_language_is_named_and_exclusive(self):
+        directive = output_language_directive("Korean")
+        assert directive is not None
+        assert "Korean" in directive
+        # Must force exclusivity, not merely prefer the language.
+        assert "only" in directive.lower()
+
+    def test_language_agnostic(self):
+        # The helper takes any language string — no hardcoded single language.
+        assert "French" in (output_language_directive("French") or "")
+        assert "日本語" in (output_language_directive("日本語") or "")
+
+    def test_strips_surrounding_whitespace(self):
+        directive = output_language_directive("  Korean  ")
+        assert directive is not None
+        assert "Korean" in directive
+        assert "  Korean" not in directive