Make gpt-image-2 the default image-generation model and add it to the
recognized model-id mapping, updating the sample provider configs to match.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add a per-room/global `sender_context_mode` setting that optionally
prefixes conversation messages with sender metadata before sending them
to the model provider.
This helps models distinguish between participants in multi-user rooms.
Three modes are supported:
- `disabled` (default, no change)
- `matrix_user_id` (prefixes with `[sender=@user:server]`)
- `matrix_user_id_and_timestamp` (adds `send_at`; Example: `[sender=@user:server sent_at=<ISO 8601>]`)
Sender context is applied to user and assistant text messages only,
skipping system prompts and non-text content.
Mixed-sender merged turns (something we intentionally do for Anthropic)
have their `sender_id` cleared to avoid misattribution.
Files sent as m.file Matrix messages are now downloaded, MIME-detected,
and forwarded to LLM providers alongside the conversation context,
similar to how m.image is already handled.
- OpenAI provider: sends files inline as base64 data URLs
- Anthropic provider: skips files with a warning (library limitation)
- OpenAI-compat provider: skips files with a warning (library limitation)
Controller routing respects the existing prefix requirement setting.
MIME detection expanded to cover PDF, text, code, and document formats.
Docs updated to reflect file support and known limitations.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add a dedicated configuration/authentication doc covering password and access-token setup,
including environment-variable mappings and token-generation example.
Link to it from configuration docs and align the sample config wording with Matrix Authentication Service/OIDC terminology.
The dev environment previously hardcoded Synapse (bundled with Postgres
and Element Web) in a monolithic etc/services/core/ directory.
With Continuwuity now available as a lighter alternative (no external DB),
this refactors the service layout so developers choose their homeserver
once and everything derives from that choice. Continuwuity is the new
default for its smaller footprint.
Key changes:
- Break etc/services/core/ into etc/services/synapse/ and
etc/services/element-web/, each with their own compose.yml
- Add `homeserver` variable in justfile (reads var/homeserver,
defaults to continuwuity)
- Add `homeserver-init` recipe to persist the choice
- Use placeholders (__HOMESERVER_SERVER_NAME__, __HOMESERVER_URL__,
__HOMESERVER_CLIENT_URL__) in config templates, resolved at
prepare time based on the chosen homeserver
- Make services-start/stop/prepare/tail-logs delegate to the chosen
homeserver's recipes + element-web
- Make users-prepare delegate to {homeserver}-users-prepare
- Update docs/development.md for the new homeserver choice flow
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Document the new tools feature in README, features.md, and providers.md.
Update the `!bai providers` command output to show vision/tools support
consistently for all providers.
Based on #62 by @yeslayla which migrated the OpenAI provider to the
Responses API.
See: https://github.com/etkecc/baibot/pull/62
This is a huge patch which does some major refactoring like:
- renaming "Image Generation" to "Image Creation" in most places,
to better match its new command (`!bai image create`)
- relocating image creation command (`!bai image` -> `!bai image create`),
so it wouldn't conflict with the new image editing command (`!bai image edit`)
- introducing a new image editing command (`!bai image edit`), which
is meant to work only with the OpenAI provider, but doesn't fully work yet
due to https://github.com/64bit/async-openai/issues/364, though a next patch will fix it
- adding support for reading images off of Matrix conversations and forwarding them to
text conversations. Works for OpenAI, but not for Anthropic yet
(requires custom patches) and not for OpenAI-Compat (no support for
images there)
- relocating some utils around (base64, mime)
When speech-to-text/flow-type = `only_transcribe`, the bot will now send
text messages by default, not notices.
While notice messages may be less desirable with other bots in the room,
it's probably a better default for most people who enable "transcribe-only" mode.
This is an improvement related to https://github.com/etkecc/baibot/issues/14
This patch introduces a new `baibot_conversation_start_time_utc`
variable which indicates the time the conversation got started.
Using `baibot_now_utc` is still possible, but given that the current
time is a moving target, its use is in conflict with prompt caching.
Because the new `baibot_conversation_start_time_utc` prompt variable
is a more reasonable default, we're now using it in all sample configs.
The other prerequisite seems to be not using a `prompt` (`prompt: null`),
but we already supported this.
It'd be nice to add an optional `max_completion_tokens` parameter as
well, for the benefit of the o1 models, but this is not yet supported by
async-openai.
Possibly tracked here: https://github.com/64bit/async-openai/issues/272
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.
This feature went through a few iterations. At some point,
a `(local timezone/time: unknown)` suffix was part of the
`baibot_now_utc` variable (hoping it improves the model's awareness that
it doesn't know the current local time), but the suffix was ultimately removed
as unnecessary.
Fixes https://github.com/etkecc/baibot/issues/10
This also includes them in the default prompts (for newly-created agents),
so that people can get a better experience out of the box.
