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.
`gpt-4o` will point to `gpt-4o-2024-08-06` after 2nd of October 2024
anyway. At that time, we can revert to pointing to `gpt-4o`.
The reason `gpt-4o-2024-08-06` was chosen now instead of `gpt-4o`:
- the `max_response_tokens` configuration was set to 16k, which matches
`gpt-4o-2024-08-06`, but is too large for `gpt-4o` (max 4k)
- baibot's own configs for dynamically created agents, as well as static
config examples use `gpt-4o-2024-08-06` and the larger
`max_response_tokens` value
The playbook did not use to define a prompt for statically-defined
agents.
Since prompt variables support landed in v1.1.0
(see 2a5a2d6a4d)
it makes sense to make use of it for a better out-of-the-box experience
(see https://github.com/etkecc/baibot/issues/10).
* Add a global config option for Docker network MTU
* Upgrade systemd_docker_base (v1.2.0-0 -> v1.3.0-0)
The new version includes `devture_systemd_docker_base_container_networks_driver_options`
due to 3cc7d12396
Related to https://github.com/spantaleev/matrix-docker-ansible-deploy/pull/3502
* Switch from passing matrix_playbook_docker_network_mtu to respecting devture_systemd_docker_base_container_networks_driver_options
Related to:
- 3cc7d12396
- https://github.com/spantaleev/matrix-docker-ansible-deploy/pull/3502
* Update all roles to versions that respect `devture_systemd_docker_base_container_networks_driver_options`
---------
Co-authored-by: Slavi Pantaleev <slavi@devture.com>
Seems like `default` is not a supported value and will not
make the bridge autoconfigure itself with the correct prefix anymore.
A value of `default` would be taken literally.
We'be already been going against upstream defaults and have been
enabling backfilling for a few other bridges (Messenger, Instagram, Telegram, Twitter).
Now I'm enabling backfilling by default for the remaining ones, for
consistency.
While working on upgrading the Meta bridges to bridgev2, I've noticed
that {% raw %} and {% endraw %} on lines like that (immediately
preceding `username_template` may cause YAML indentation issues.
