feat(meet-kevin): prompt v2 — forward-looking action + expected_move field

User reported that the old prompt could emit 'sell' on backward-looking
capitulation ('Kevin sold after a 20% drop') — exactly the false signal
to avoid. v2 reframes every per-ticker field as forward-looking and
adds an explicit expected_move enum for the trading bot to weight.

Changes:
- New ExpectedMove enum (up_strong/up_mild/sideways/down_mild/
  down_strong/unknown) in shared/schemas + shared/models, with
  matching kevin_expected_move Postgres enum + column on
  kevin_stock_mentions (migration e5f6a7b8c9d0). NOT NULL with
  server_default 'unknown' so existing rows backfill cleanly.
- SYSTEM_PROMPT rewritten: action semantics now require a FORWARD
  view; reactive sells get downgraded to 'watch' or skipped; the
  rationale_quote must contain forward reasoning. Quality
  checklist updated.
- _ANALYSIS_TOOL JSON schema gains expected_move (required).
- prompt_version v1 → v2 in config + infra + ad-hoc CLI default.
- pipeline.py persists ticker.expected_move into the new column.

Migration safety: the column is NOT NULL DEFAULT 'unknown' so 96
existing mentions auto-fill with 'unknown' (no forward call known
for backward analyses) without breaking any reads.

Cost to backfill the 27 existing analyses with v2 prompt: ~$3 LLM
spend. A follow-up reanalyze script will replay them after this
ships.

alembic/versions/e5f6a7b8c9d0_kevin_expected_move.py

@@ -0,0 +1,44 @@
+"""Add expected_move column to kevin_stock_mentions (prompt v2).
+
+Adds the KevinExpectedMove enum and a NOT NULL column with default
+'unknown' so existing rows keep loading. New analyses produced by the
+v2 prompt will populate it with a real directional view.
+
+Revision ID: e5f6a7b8c9d0
+Revises: d4e5f6a7b8c9
+Create Date: 2026-05-28
+"""
+
+from __future__ import annotations
+
+import sqlalchemy as sa
+from alembic import op
+from sqlalchemy.dialects import postgresql
+
+revision = "e5f6a7b8c9d0"
+down_revision = "d4e5f6a7b8c9"
+branch_labels = None
+depends_on = None
+
+_ENUM_NAME = "kevin_expected_move"
+_VALUES = ("up_strong", "up_mild", "sideways", "down_mild", "down_strong", "unknown")
+
+
+def upgrade() -> None:
+    enum_type = postgresql.ENUM(*_VALUES, name=_ENUM_NAME, create_type=False)
+    enum_type.create(op.get_bind(), checkfirst=True)
+
+    op.add_column(
+        "kevin_stock_mentions",
+        sa.Column(
+            "expected_move",
+            enum_type,
+            nullable=False,
+            server_default="unknown",
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("kevin_stock_mentions", "expected_move")
+    op.execute(f"DROP TYPE IF EXISTS {_ENUM_NAME}")