review: reject financial advice in indicator-summary reads

Adds a new UNCLEAN criterion to the reviewer agent's system prompt:
direct recommendation language (buy/sell/hold/accumulate/trim/rotate),
allocation guidance (overweight/underweight, "X% in bonds"), price
targets, and personalised framing ("you should", "investors should")
all trigger a reject.

The operator is not licensed to give investment advice; this is
editorial commentary on public data. The generator's system prompt
already forbids buy/sell language, but a prompt-only constraint is
not an enforcement layer. The reviewer agent — already in the
pipeline for chain-of-thought / truncation / meta-commentary — is the
right place to enforce the regulatory boundary structurally: rows
that drift into advice get dropped, and the API falls back to the
previous compliant row.

Descriptive / interpretive language about market state remains
explicitly allowed ("valuations are stretched", "real yields are
restrictive"). The criterion is state vs action: states publish,
actions don't.

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

app/services/output_review.py

@@ -60,7 +60,22 @@ Mark UNCLEAN if the text contains ANY of:
 - Partial / truncated content. Starts mid-word, mid-number, mid-clause.
 - Visible internal numbers without clear meaning ("change 1y +5.9%?"),
   raw column names ("as_of 2026-01-01"), or any debug-like fragments.
-- Anything other than the finished, publishable interpretation.
+- FINANCIAL ADVICE or any phrasing that recommends an action the
+  reader should take. This service is editorial commentary on public
+  data, not investment advice; the operator is not licensed to give
+  it. Reject any of:
+    * Buy/sell/hold/accumulate/trim/exit/enter/rotate language.
+    * Allocation guidance ("overweight", "underweight",
+      "X% in bonds", "increase exposure to").
+    * Price targets or specific level predictions ("will reach $X",
+      "target Y", "expect Z by year-end").
+    * Personalised framing ("you should", "investors should",
+      "consider buying", "we recommend").
+  DESCRIPTIVE / INTERPRETIVE language about market state is fine —
+  "valuations are stretched", "real yields are restrictive", "rates
+  and credit disagree". The test: does the text describe a STATE, or
+  does it suggest an ACTION? States are fine; actions are not.
+- Anything else other than the finished, publishable interpretation.
 
 Return ONLY a JSON object with this exact shape:
 {"clean": true | false, "reason": "<≤20 words, plain text>"}