fix(llm): log and handle non-STOP finish_reason from Gemini

When Gemini stops generation early (e.g. due to safety filters or
thinking-model quirks), finish_reason != STOP but no exception is raised,
causing the caller to receive truncated JSON and a confusing 502 "invalid
JSON" error. Now:
- finish_reason is extracted from candidates[0] and stored in ai_call_logs
- any non-STOP finish_reason raises HTTP 502 with a clear message
- Alembic migration adds the finish_reason column to ai_call_logs

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

backend/alembic/versions/b2c3d4e5f6a1_add_finish_reason_to_ai_call_logs.py

@@ -0,0 +1,29 @@
+"""add_finish_reason_to_ai_call_logs
+
+Revision ID: b2c3d4e5f6a1
+Revises: a1b2c3d4e5f6
+Create Date: 2026-03-01 00:00:00.000000
+
+"""
+
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+
+from alembic import op
+
+revision: str = "b2c3d4e5f6a1"
+down_revision: Union[str, None] = "a1b2c3d4e5f6"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "ai_call_logs",
+        sa.Column("finish_reason", sa.Text(), nullable=True),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("ai_call_logs", "finish_reason")