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/services/portfolio_analysis.py

@@ -31,7 +31,7 @@ from app.config import get_settings
 from app.db import utcnow
 from app.logging import get_logger
 from app.models import AICall
-from app.services.i18n import LANGUAGES, respond_in_clause
+from app.services.i18n import LANGUAGES, language_directive_lead, respond_in_clause
 from app.services.llm_prompts import build_system_prompt
 from app.services.output_review import review_read
 from app.services.openrouter import (
@@ -282,7 +282,18 @@ def build_prompt(req: AnalysisRequest) -> tuple[str, str]:
     head = enriched[:MAX_POSITIONS_INLINED]
     tail_count = max(0, len(enriched) - MAX_POSITIONS_INLINED)
 
-    system = build_system_prompt(req.tone, req.analysis) + "\n\n" + _SYSTEM_OVERRIDES + respond_in_clause(req.lang)
+    # Language directive both prepended (so the model anchors on the
+    # target language before reading the long English instruction
+    # block) and appended (defence in depth — a tail nudge alone
+    # was being ignored by deepseek-v4-flash when most of the
+    # context is English).
+    system = (
+        language_directive_lead(req.lang)
+        + build_system_prompt(req.tone, req.analysis)
+        + "\n\n"
+        + _SYSTEM_OVERRIDES
+        + respond_in_clause(req.lang)
+    )
 
     user_parts = [
         f"# Portfolio commentary request — {utcnow().strftime('%Y-%m-%d')}",