Signed-off-by: Suguru Hirahara <acioustick@noreply.codeberg.org>

Signed-off-by: Suguru Hirahara <acioustick@noreply.codeberg.org>

Closes https://github.com/spantaleev/matrix-docker-ansible-deploy/issues/3538

See: https://github.com/spantaleev/matrix-docker-ansible-deploy/issues/3538#issuecomment-2405780285

Provoked by https://github.com/mother-of-all-self-hosting/mash-playbook/pull/280

Cinny has added a service worker to support authenticated media and requires /sw,js to resolve to the serviceworker js file

* Update matrixdotorg/mjolnir Docker tag to v1.8.1

* Upgrade Mjolnir to v1.8.3

---------

Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
Co-authored-by: Slavi Pantaleev <slavi@devture.com>

The new prompt makes use of the new `baibot_conversation_start_time_utc`
prompt variable, which is not a moving target (like `baibot_now_utc`)
and as such allows prompt caching to work.

Ref: https://platform.openai.com/docs/guides/prompt-caching

Since 2024-10-02, `gpt-4o` is actually the same as `gpt-4o-2024-08-06`.

We previously used `gpt-4o-2024-08-06`, because it was pointing to a
much better (longer context) model. Since they're both the same now,
we'd better stick to the unpinned model and make it easier for future
users to get upgrades.