i18n: prepend a strong language directive for portfolio + chat

Reports that portfolio AI analysis was coming back in English even
for IT-toggled users. Traced the chain (DB user.lang IS set to it,
router passes it into the payload, parse_request reads it, build_prompt
appends respond_in_clause), so the wiring is correct end-to-end. The
model was simply ignoring the single-sentence tail nudge: when the
system prompt is hundreds of lines of English and the user message
adds more English context, "Respond in Italian." at the end is easy
to drop on the floor.

Add a new services/i18n.language_directive_lead() that returns a
strong, explicit top-of-prompt block — "# LANGUAGE — write everything
in <X>" plus the verbatim-tickers-and-numbers carve-out — meant to
be PREPENDED so the model anchors on the target language before it
reads the bulk of the instructions. Combined with the existing tail
clause it's belt-and-suspenders: top + bottom of the prompt both
say "in this language".

Applied to portfolio_analysis.build_prompt() and chat.py — the two
surfaces that generate user-facing prose in real time (the strategic
log + indicator summaries get post-hoc translation via translate(),
so the directive isn't needed there).

Empty-string return for en / unknown lang means callers can wire
it in unconditionally; no extra plumbing in i18n callsites.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

app/routers/chat.py

@@ -21,7 +21,7 @@ from app.db import get_session, utcnow
 from app.jobs._market_context import REFERENCE_LINE
 from app.models import AICall, Headline, Quote, StrategicLog
 from app.routers.api import _md_to_html
-from app.services.i18n import respond_in_clause
+from app.services.i18n import language_directive_lead, respond_in_clause
 from app.services.llm_prompts import build_chat_system_prompt
 from app.services.openrouter import call_llm, month_start
 from app.services.output_review import review_read
@@ -165,13 +165,17 @@ async def chat(
         headlines=headlines,
         reference_line=REFERENCE_LINE,
     )
-    # Respect the user's interface language preference: append a single
-    # localized "respond in" nudge so the assistant answers in IT when
-    # the user has lang=it. The prompt + history (which includes the
-    # user's own question, often in their language) are usually enough,
-    # but the nudge guarantees the first reply lands correctly.
+    # Respect the user's interface language preference. The tail
+    # "Respond in X" clause is easy for the model to drop when the
+    # rest of the prompt is English (long log content, English
+    # market data, English headlines), so we ALSO prepend a stronger
+    # language directive at the top — see services/i18n.
     user_lang = principal.user.lang if principal and principal.user else "en"
-    system_prompt = system_prompt + respond_in_clause(user_lang)
+    system_prompt = (
+        language_directive_lead(user_lang)
+        + system_prompt
+        + respond_in_clause(user_lang)
+    )
 
     msgs = [{"role": "system", "content": system_prompt}]
     for m in history: