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>
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)
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
