[NOTICKET] fix(help): lock reply language to user's language on button path

src/agents/handlers/help.py

@@ -29,6 +29,7 @@ SEAMS:
 
 from __future__ import annotations
 
+import re
 from collections.abc import AsyncIterator
 from dataclasses import dataclass, field
 from pathlib import Path
@@ -49,8 +50,63 @@ _PROMPT_DIR = Path(__file__).resolve().parent.parent.parent / "config" / "prompt
 _SYSTEM_PROMPT_PATH = _PROMPT_DIR / "help.md"
 _GUARDRAILS_PATH = _PROMPT_DIR / "guardrails.md"
 
-# Neutral human turn when Help is triggered by a slash command with no real content.
-_DEFAULT_TRIGGER = "What should I do next?"
+# Neutral human turn when Help is triggered by a slash command with no real content
+# (button path passes message=None). Per language, so the synthetic turn never drags the
+# reply toward English — without this the only human-turn signal on the button path would
+# be an English sentence, and the model mirrors the last human turn's language.
+_DEFAULT_TRIGGERS = {
+    "Indonesian": "Apa yang sebaiknya saya lakukan selanjutnya?",
+    "English": "What should I do next?",
+}
+_FALLBACK_LANGUAGE = "Indonesian"  # team default when no human turn exists yet
+
+# Lightweight, LLM-free language detection over the last human turn. The result is LOCKED
+# into the prompt via a `[Reply language]` directive (see `_build_context_block`), so
+# replying in the user's language is deterministic/mandatory — not a soft prompt hint that
+# an English system prompt + English default trigger can override.
+_ID_MARKERS = frozenset({
+    "yang", "dan", "apa", "gimana", "bagaimana", "kenapa", "mengapa", "aku", "saya",
+    "tolong", "ini", "itu", "nih", "dong", "kah", "untuk", "dengan", "pada", "adalah",
+    "tidak", "enggak", "nggak", "bisa", "mau", "buat", "dari", "kamu", "ya",
+    "berapa", "kapan", "siapa", "dimana", "juga", "sudah", "belum", "akan",
+})
+_EN_MARKERS = frozenset({
+    "the", "what", "how", "why", "please", "this", "that", "is", "are", "can", "could",
+    "should", "for", "with", "of", "and", "you", "do", "does", "when", "where",
+    "who", "which", "my", "me", "your", "have", "has", "want", "next",
+})
+
+
+def _last_human_text(history: list[BaseMessage] | None) -> str:
+    """Return the text of the most recent human turn in history, or '' if none."""
+    for msg in reversed(history or []):
+        if getattr(msg, "type", None) == "human":
+            content = msg.content
+            return content if isinstance(content, str) else str(content)
+    return ""
+
+
+def _detect_reply_language(
+    history: list[BaseMessage] | None, message: str | None = None
+) -> str:
+    """Detect the reply language from the last human turn (deterministic, no LLM).
+
+    Prefers an explicit `message` (intent path — the user's real turn) over the last
+    human turn in `history` (button path, where `message` is None). Counts Indonesian vs
+    English marker words; ties or no signal fall back to Indonesian (the team default).
+    Returns "Indonesian" or "English".
+    """
+    text = (message or _last_human_text(history)).lower()
+    if not text.strip():
+        return _FALLBACK_LANGUAGE
+    tokens = re.findall(r"[a-z']+", text)
+    id_hits = sum(1 for t in tokens if t in _ID_MARKERS)
+    en_hits = sum(1 for t in tokens if t in _EN_MARKERS)
+    if en_hits > id_hits:
+        return "English"
+    if id_hits > en_hits:
+        return "Indonesian"
+    return _FALLBACK_LANGUAGE
 
 
 @dataclass
@@ -107,13 +163,20 @@ def _build_context_block(
     state: AnalysisState,
     report_ready: ReportReadiness,
     available_actions: list[str],
+    reply_language: str = _FALLBACK_LANGUAGE,
 ) -> str:
-    """Compose the deterministic context the prompt's 'never misguide' rule trusts."""
+    """Compose the deterministic context the prompt's 'never misguide' rule trusts.
+
+    `reply_language` is a hard directive: the prompt is told to reply ONLY in this
+    language, so the answer matches the user's language even on the button path (where
+    the synthetic human turn would otherwise pull the reply toward English).
+    """
     return "\n\n".join(
         [
             _format_state(state),
             _format_report_ready(report_ready),
             "[Available actions]\n" + ", ".join(available_actions),
+            f"[Reply language]\nRespond ONLY in: {reply_language}",
         ]
     )
 
@@ -178,17 +241,20 @@ class HelpAgent:
         """
         readiness = report_ready or ReportReadiness()
         actions = available_actions or _derive_available_actions(state, readiness)
+        reply_language = _detect_reply_language(history, message)
         logger.info(
             "help guidance",
             report_ready=readiness.ready,
             available_actions=actions,
+            reply_language=reply_language,
         )
 
         chain = self._ensure_chain()
+        default_trigger = _DEFAULT_TRIGGERS.get(reply_language, _DEFAULT_TRIGGERS[_FALLBACK_LANGUAGE])
         payload: dict[str, Any] = {
-            "message": message or _DEFAULT_TRIGGER,
+            "message": message or default_trigger,
             "history": history or [],
-            "context": _build_context_block(state, readiness, actions),
+            "context": _build_context_block(state, readiness, actions, reply_language),
         }
         if callbacks:
             async for token in chain.astream(payload, config={"callbacks": callbacks}):

src/config/prompts/help.md

@@ -23,6 +23,7 @@ You are given context, never raw user prose to analyze:
   - `ready` (bool) — whether there is enough analysis to generate a report.
   - `missing` (list) — if not ready, the gaps to fill.
 - **`available_actions`** *(optional)* — which actions are actually wired right now. If present, **only suggest actions listed here.**
+- **`[Reply language]`** — the language you MUST reply in (detected deterministically from the user's last turn). This is an instruction, not a suggestion — see the hard rule below.
 
 > **Hard rule — never misguide.** Trust the signals above for *what is possible*, not your
 > own guess. If `report_ready.ready` is `false`, do **not** tell the user to generate a
@@ -72,8 +73,13 @@ Do not over-promise the report's depth.
 ## Tone
 
 Plain, warm, and encouraging — like a helpful guide, **not** a hype trailer. No exclamation
-spam, no overselling. Respond in the **user's language** (match `chat_history` — Indonesian or
-English). A few sentences is usually enough.
+spam, no overselling. A few sentences is usually enough.
+
+> **Hard rule — reply language.** Reply **only** in the language named in `[Reply language]`.
+> This is mandatory and overrides the language of this prompt, its examples, and the trigger
+> question. If `[Reply language]` says `Indonesian`, answer entirely in Indonesian even though
+> these instructions are in English; if it says `English`, answer in English. Never mix
+> languages or switch mid-reply.
 
 ## Constraints