retoorandClaude Sonnet 5 8ae3f628c7 Make AI model configurable per feature, and split news grading/formatting models ...

Every AI-calling feature (content correction, the @ai modifier, quiz grading,
SEO metadata generation, the AI Usage Analyzer, and DeepSearch) can now name
its own model via admin-editable configuration, defaulting to the gateway's
default model when left blank. The gateway a feature talks to stays fixed to
the internal endpoint either way, only the model name is a knob, so the best
model can be picked per task.

Also splits the news service's shared AI grading/formatting config into two
independent endpoint/model/key pairs: reformatting no longer requires
repointing (and thereby breaking) the free, scoring-only grading model.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FZ5x6KZTxZjbJqsEkxGbxG

2026-09-03 08:47:57 +02:00

..

__init__.py

Quiiz system

2026-07-26 16:46:41 +02:00

documents.py

Add the trust and safety subsystem and the App Store compliance work

2026-08-09 00:18:20 +02:00

grading.py

Make AI model configurable per feature, and split news grading/formatting models

2026-09-03 08:47:57 +02:00

scoreboard.py

Add the trust and safety subsystem and the App Store compliance work

2026-08-09 00:18:20 +02:00

scoring.py

Quiiz system

2026-07-26 16:46:41 +02:00

store.py

Add the trust and safety subsystem and the App Store compliance work

2026-08-09 00:18:20 +02:00