Compare commits

..

1 Commits

Author SHA1 Message Date
Slavi Pantaleev
f6700ed601 Switch back to upstream async-openai
Once async-openai v0.31.0 gets released as a final version,
we'll be able top pull it from crates.io.

This does not quite compile yet, because of https://github.com/64bit/async-openai/issues/465
2025-11-08 13:33:46 +02:00
24 changed files with 1300 additions and 995 deletions

View File

@@ -1,41 +1,3 @@
# (2025-12-21) Version 1.12.0
- (**Improvement**) Upgrade [async-openai](https://crates.io/crates/async-openai) (0.31.1 -> 0.32.2) and add support for OpenAI's `gpt-image-1.5` model ([08c689a](https://github.com/etkecc/baibot/commit/08c689a), [f7bf3d7](https://github.com/etkecc/baibot/commit/f7bf3d7))
- (**Internal Improvement**) Dependency updates
# (2025-12-15) Version 1.11.0
- (**Feature**) Add support for custom avatars via file path and for keeping the already-set avatar (for those who wish to manage it by themselves via other means). See the [sample config](./etc/app/config.yml.dist) for details. ([062fbbb](https://github.com/etkecc/baibot/commit/062fbbb8ef9ad600db483a431c5c782402191023))
- (**Internal Improvement**) Dependency updates ([99bde53](https://github.com/etkecc/baibot/commit/99bde53ef648a5a9086a96778fde4a9dbc1ede58))
- (**Internal Improvement**) Documentation updates ([b3fd8e5](https://github.com/etkecc/baibot/commit/b3fd8e548f83fe46398ced4760d7e2bb7588c24d))
- (**Internal Improvement**) Upgrade Rust compiler (1.91.1 -> 1.92.0) ([22906aa](https://github.com/etkecc/baibot/commit/22906aa2d3cae51815fad2560a545eaa69c247b6))
# (2025-12-06) Version 1.10.0
- (**Internal Improvement**) Dependency updates. This version is based on [mxlink](https://crates.io/crates/mxlink)@1.11.0 (which is based on the newly released [matrix-sdk](https://crates.io/crates/matrix-sdk)@[0.16.0](https://github.com/matrix-org/matrix-rust-sdk/releases/tag/matrix-sdk-0.16.0).
# (2025-11-30) Version 1.9.0
- (**Internal Improvement**) Upgrade [async-openai](https://crates.io/crates/async-openai) from our own etkecc fork (0.28.1-patched) to the official upstream version 0.31.1. This upgrade required some code adaptations to the new module structure, etc. While tested, regressions are possible.
# (2025-11-28) Version 1.8.3
- (**Improvement**) Add support for the `BAIBOT_PERSISTENCE_SESSION_ENCRYPTION_KEY` environment variable for configuring `persistence.session_encryption_key`
- (**Improvement**) Add support for the `BAIBOT_USER_ENCRYPTION_RECOVERY_RESET_ALLOWED` environment variable for configuring `user.encryption.recovery_reset_allowed`
- (**Internal Improvement**) Dependency updates.
# (2025-11-20) Version 1.8.2
- (**Internal Improvement**) Dependency and compiler updates (Rust 1.89.0 -> 1.91.1).
# (2025-09-12) Version 1.8.1 # (2025-09-12) Version 1.8.1
- (**Internal Improvement**) Dependency updates. - (**Internal Improvement**) Dependency updates.

1862
Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -7,7 +7,7 @@ license = "AGPL-3.0-or-later"
readme = "README.md" readme = "README.md"
keywords = ["matrix", "chat", "bot", "AI", "LLM"] keywords = ["matrix", "chat", "bot", "AI", "LLM"]
include = ["/etc/assets/baibot-torso-768.png", "/src", "/README.md", "/CHANGELOG.md", "/LICENSE"] include = ["/etc/assets/baibot-torso-768.png", "/src", "/README.md", "/CHANGELOG.md", "/LICENSE"]
version = "1.12.0" version = "1.8.1"
edition = "2024" edition = "2024"
[lib] [lib]
@@ -17,24 +17,23 @@ path = "src/lib.rs"
[dependencies] [dependencies]
anthropic = { git = "https://github.com/etkecc/anthropic-rs.git", branch = "fix-content-block-image" } anthropic = { git = "https://github.com/etkecc/anthropic-rs.git", branch = "fix-content-block-image" }
anyhow = "1.0.*" anyhow = "1.0.*"
async-openai = { version = "0.32.2", features = ["audio", "chat-completion", "image"] } async-openai = { git = "https://github.com/64bit/async-openai", branch = "main" }
base64 = "0.22.*" base64 = "0.22.*"
chrono = { version = "0.4.*", default-features = false, features = ["std", "now"] } chrono = { version = "0.4.*", default-features = false, features = ["std", "now"] }
# We'd rather not depend on this, but we cannot use the ruma-events EventContent macro without it. # We'd rather not depend on this, but we cannot use the ruma-events EventContent macro without it.
# We add the `native-tls` feature, because of https://github.com/etkecc/rust-mxlink/issues/1 # We add the `native-tls` feature, because of https://github.com/etkecc/rust-mxlink/issues/1
matrix-sdk = { version = "0.16.0", default-features = false, features = ["native-tls"] } matrix-sdk = { version = "0.14.0", default-features = false, features = ["native-tls"] }
mime_guess = "2.0.*"
mxidwc = "1.0.*" mxidwc = "1.0.*"
mxlink = ">=1.11.0" mxlink = ">=1.10.0"
etke_openai_api_rust = "0.1.*" etke_openai_api_rust = "0.1.*"
quick_cache = "0.6.*" quick_cache = "0.6.*"
regex = "1.12.*" regex = "1.11.*"
serde = { version = "1.0.*", features = ["derive"], default-features = false } serde = { version = "1.0.*", features = ["derive"], default-features = false }
serde_json = "1.0.*" serde_json = "1.0.*"
serde_yaml = "0.9.*" serde_yaml = "0.9.*"
tempfile = "3.23.*" tempfile = "3.21.*"
tiktoken-rs = { version = "0.9.*", default-features = false } tiktoken-rs = { version = "0.7.*", default-features = false }
tokio = { version = "1.48.*", features = ["rt", "rt-multi-thread", "macros"] } tokio = { version = "1.47.*", features = ["rt", "rt-multi-thread", "macros"] }
tracing = "0.1.*" tracing = "0.1.*"
tracing-subscriber = { version = "0.3.*", features = ["env-filter"] } tracing-subscriber = { version = "0.3.*", features = ["env-filter"] }
url = "2.5.*" url = "2.5.*"

View File

@@ -4,7 +4,7 @@
# # # #
####################################### #######################################
FROM docker.io/rust:1.92.0-slim-trixie AS build FROM docker.io/rust:1.90.0-slim-trixie AS build
RUN apt-get update && apt-get install -y build-essential pkg-config libssl-dev libsqlite3-dev RUN apt-get update && apt-get install -y build-essential pkg-config libssl-dev libsqlite3-dev

View File

@@ -4,7 +4,7 @@
# # # #
####################################### #######################################
FROM docker.io/rust:1.92.0-slim-trixie AS build FROM docker.io/rust:1.90.0-slim-trixie AS build
RUN apt-get update && apt-get install -y build-essential pkg-config libssl-dev libsqlite3-dev RUN apt-get update && apt-get install -y build-essential pkg-config libssl-dev libsqlite3-dev

View File

@@ -43,8 +43,7 @@ Administrators cannot be changed without adjusting the bot's configuration on th
Room-local agent managers are users privileged to **create their own [agents](./agents.md)** (see `!bai agent`) in rooms. Room-local agent managers are users privileged to **create their own [agents](./agents.md)** (see `!bai agent`) in rooms.
> [!WARNING] **⚠️ WARNING**: Letting regular users create agents which contact arbitrary network services **may be a security issue**.
> Letting regular users create agents which contact arbitrary network services **may be a security issue**.
The following commands are available: The following commands are available:
- **Show** the currently allowed users: `!bai access room-local-agent-managers` - **Show** the currently allowed users: `!bai access room-local-agent-managers`

View File

@@ -12,15 +12,12 @@ This file is created from the template found in [etc/app/config.yml.dist](../../
Certain keys can be left unset, in which case [📝 hardcoded defaults](../../src/entity/cfg/defaults.rs) would be used. Certain keys can be left unset, in which case [📝 hardcoded defaults](../../src/entity/cfg/defaults.rs) would be used.
Some configuration keys found in the YAML configuration can be overridden by setting an environment variable (dots should be replaced with `_`). Example: Each configuration key found in the YAML configuration can be overridden by setting an environment variable (dots should be replaced with `_`). Example:
- to override `command_prefix`, set an environment variable `BAIBOT_COMMAND_PREFIX` - to override `command_prefix`, set an environment variable `BAIBOT_COMMAND_PREFIX`
- to override `homeserver.server_name`, set an environment variable `BAIBOT_HOMESERVER_SERVER_NAME` - to override `homeserver.server_name`, set an environment variable `BAIBOT_HOMESERVER_SERVER_NAME`
You can see the list of supported environment variables in the [🦀 src/entity/cfg/env.rs](../../src/entity/cfg/env.rs) file. The static configuration contains an `initial_global_config` key, which is used to populate the bot's global configuration (stored as [dynamic configuration](#dynamic-configuration)) the first time the bot starts. Modifying this subsequently will not have any effect. After initial global configuration creation, it's expected to be managed dynamically via chat commands.
> [!WARNING]
> The static configuration contains an `initial_global_config` key, which is used to populate the bot's global configuration (stored as [dynamic configuration](#dynamic-configuration)) the first time the bot starts. Modifying this subsequently will not have any effect. After initial global configuration creation, it's expected to be managed dynamically via chat commands.
### Dynamic configuration ### Dynamic configuration

View File

@@ -125,7 +125,10 @@ For services which are not fully compatible with the OpenAI API, consider using
- create a room-local agent: `!bai agent create-room-local openai my-openai-agent` - create a room-local agent: `!bai agent create-room-local openai my-openai-agent`
- create a global agent: `!bai agent create-global openai my-openai-agent` - create a global agent: `!bai agent create-global openai my-openai-agent`
💡 When creating an agent, the bot will show you an up-to-date sample configuration for this provider which looks [like this](./sample-provider-configs/openai.yml). 💡 When creating an agent, the bot will show you an up-to-date sample configuration for this provider which:
- in the general case looks [like this](./sample-provider-configs/openai.yml)
- for the [o1](https://platform.openai.com/docs/models/o1) models needs to look [like this](./sample-provider-configs/openai-o1.yml)
### OpenAI Compatible ### OpenAI Compatible

View File

@@ -0,0 +1,24 @@
base_url: https://api.openai.com/v1
api_key: YOUR_API_KEY_HERE
text_generation:
model_id: o1-mini
# o1 models do not support a system prompt
prompt: null
temperature: 1.0
# o1 models do not support max_response_tokens.
# They use `max_completion_tokens` as an alternative
max_response_tokens: null
max_completion_tokens: 16384
max_context_tokens: 128000
speech_to_text:
model_id: whisper-1
text_to_speech:
model_id: tts-1-hd
voice: onyx
speed: 1.0
response_format: opus
image_generation:
model_id: gpt-image-1
style: null
size: null
quality: null

View File

@@ -1,14 +1,11 @@
base_url: https://api.openai.com/v1 base_url: https://api.openai.com/v1
api_key: YOUR_API_KEY_HERE api_key: YOUR_API_KEY_HERE
text_generation: text_generation:
model_id: gpt-5.2 model_id: gpt-5
prompt: "You are a brief, but helpful bot called {{ baibot_name }} powered by the {{ baibot_model_id }} model. The date/time of this conversation's start is: {{ baibot_conversation_start_time_utc }}." prompt: "You are a brief, but helpful bot called {{ baibot_name }} powered by the {{ baibot_model_id }} model. The date/time of this conversation's start is: {{ baibot_conversation_start_time_utc }}."
temperature: 1.0 temperature: 1.0
# Reasoning models need to use `max_completion_tokens` instead of `max_response_tokens`. max_response_tokens: 16384
# If you're dealing with a non-reasoning model, specify `max_response_tokens` and unset `max_completion_tokens`. max_context_tokens: 128000
max_response_tokens: null
max_completion_tokens: 128000
max_context_tokens: 400000
speech_to_text: speech_to_text:
model_id: whisper-1 model_id: whisper-1
text_to_speech: text_to_speech:
@@ -17,7 +14,7 @@ text_to_speech:
speed: 1.0 speed: 1.0
response_format: opus response_format: opus
image_generation: image_generation:
model_id: gpt-image-1.5 model_id: gpt-image-1
style: null style: null
size: null size: null
quality: null quality: null

View File

@@ -11,12 +11,6 @@ user:
# Leave empty to use the default (baibot). # Leave empty to use the default (baibot).
name: baibot name: baibot
# An optional path to an image file to be used as a custom avatar image.
# - null or empty string: use the default avatar
# - "keep": don't touch the avatar, keep whatever is already set
# - any other value: path to a custom avatar image file
avatar: null
encryption: encryption:
# An optional passphrase to use for backing up and recovering the bot's encryption keys. # An optional passphrase to use for backing up and recovering the bot's encryption keys.
# You can use any string here. # You can use any string here.
@@ -82,12 +76,11 @@ agents:
# base_url: https://api.openai.com/v1 # base_url: https://api.openai.com/v1
# api_key: "" # api_key: ""
# text_generation: # text_generation:
# model_id: gpt-5.2 # model_id: gpt-5
# prompt: "You are a brief, but helpful bot called {{ baibot_name }} powered by the {{ baibot_model_id }} model. The date/time of this conversation's start is: {{ baibot_conversation_start_time_utc }}." # prompt: "You are a brief, but helpful bot called {{ baibot_name }} powered by the {{ baibot_model_id }} model. The date/time of this conversation's start is: {{ baibot_conversation_start_time_utc }}."
# temperature: 1.0 # temperature: 1.0
# max_response_tokens: ~
# # Reasoning models need to use `max_completion_tokens` instead of `max_response_tokens`. # # Reasoning models need to use `max_completion_tokens` instead of `max_response_tokens`.
# # If you're dealing with a non-reasoning model, specify `max_response_tokens` and unset `max_completion_tokens`.
# max_response_tokens: null
# max_completion_tokens: 128000 # max_completion_tokens: 128000
# max_context_tokens: 400000 # max_context_tokens: 400000
# speech_to_text: # speech_to_text:
@@ -98,7 +91,7 @@ agents:
# speed: 1.0 # speed: 1.0
# response_format: opus # response_format: opus
# image_generation: # image_generation:
# model_id: gpt-image-1.5 # model_id: gpt-image-1
# style: null # style: null
# size: null # size: null
# quality: null # quality: null

View File

@@ -1,6 +1,6 @@
services: services:
postgres: postgres:
image: docker.io/postgres:18.1-alpine image: docker.io/postgres:18.0-alpine
user: ${UID}:${GID} user: ${UID}:${GID}
restart: unless-stopped restart: unless-stopped
environment: environment:
@@ -14,7 +14,7 @@ services:
- /etc/passwd:/etc/passwd:ro - /etc/passwd:/etc/passwd:ro
synapse: synapse:
image: ghcr.io/element-hq/synapse:v1.144.0 image: ghcr.io/element-hq/synapse:v1.140.0
user: "${UID}:${GID}" user: "${UID}:${GID}"
restart: unless-stopped restart: unless-stopped
entrypoint: python entrypoint: python
@@ -27,7 +27,7 @@ services:
- ./synapse/media-store:/media-store - ./synapse/media-store:/media-store
element-web: element-web:
image: ghcr.io/element-hq/element-web:v1.12.7 image: ghcr.io/element-hq/element-web:v1.12.2
user: "${UID}:${GID}" user: "${UID}:${GID}"
restart: unless-stopped restart: unless-stopped
environment: environment:

View File

@@ -1,6 +1,6 @@
services: services:
ollama: ollama:
image: docker.io/ollama/ollama:0.13.5 image: docker.io/ollama/ollama:0.12.6
restart: unless-stopped restart: unless-stopped
ports: ports:
- "${SERVICE_OLLAMA_BIND_PORT_HTTP}:11434" - "${SERVICE_OLLAMA_BIND_PORT_HTTP}:11434"

View File

@@ -56,8 +56,8 @@ impl ImageSource {
} }
} }
impl From<ImageSource> for async_openai::types::images::ImageInput { impl From<ImageSource> for async_openai::types::ImageInput {
fn from(value: ImageSource) -> Self { fn from(value: ImageSource) -> Self {
async_openai::types::images::ImageInput::from_vec_u8(value.filename, value.bytes) async_openai::types::ImageInput::from_vec_u8(value.filename, value.bytes)
} }
} }

View File

@@ -1,6 +1,6 @@
use serde::{Deserialize, Serialize}; use serde::{Deserialize, Serialize};
use super::OPENAI_IMAGE_MODEL_GPT_IMAGE_1_DOT_5; use super::OPENAI_IMAGE_MODEL_GPT_IMAGE_1;
use crate::agent::{default_prompt, provider::ConfigTrait}; use crate::agent::{default_prompt, provider::ConfigTrait};
#[derive(Debug, Clone, Serialize, Deserialize)] #[derive(Debug, Clone, Serialize, Deserialize)]
@@ -80,7 +80,7 @@ impl Default for TextGenerationConfig {
} }
fn default_text_model_id() -> String { fn default_text_model_id() -> String {
"gpt-5.2".to_owned() "gpt-5".to_owned()
} }
#[derive(Debug, Clone, Serialize, Deserialize)] #[derive(Debug, Clone, Serialize, Deserialize)]
@@ -150,19 +150,19 @@ pub struct ImageGenerationConfig {
pub model_id: String, pub model_id: String,
#[serde(default = "default_image_style")] #[serde(default = "default_image_style")]
pub style: Option<async_openai::types::images::ImageStyle>, pub style: Option<async_openai::types::ImageStyle>,
#[serde(default = "default_image_size")] #[serde(default = "default_image_size")]
pub size: Option<async_openai::types::images::ImageSize>, pub size: Option<async_openai::types::ImageSize>,
#[serde(default = "default_image_quality")] #[serde(default = "default_image_quality")]
pub quality: Option<async_openai::types::images::ImageQuality>, pub quality: Option<async_openai::types::ImageQuality>,
} }
impl Default for ImageGenerationConfig { impl Default for ImageGenerationConfig {
fn default() -> Self { fn default() -> Self {
Self { Self {
model_id: OPENAI_IMAGE_MODEL_GPT_IMAGE_1_DOT_5.to_owned(), model_id: OPENAI_IMAGE_MODEL_GPT_IMAGE_1.to_owned(),
style: default_image_style(), style: default_image_style(),
size: default_image_size(), size: default_image_size(),
quality: default_image_quality(), quality: default_image_quality(),
@@ -173,28 +173,23 @@ impl Default for ImageGenerationConfig {
impl ImageGenerationConfig { impl ImageGenerationConfig {
pub fn model_id_as_openai_image_model( pub fn model_id_as_openai_image_model(
&self, &self,
) -> Result<async_openai::types::images::ImageModel, String> { ) -> Result<async_openai::types::ImageModel, String> {
match self.model_id.as_str() { match self.model_id.as_str() {
"dall-e-2" => Ok(async_openai::types::images::ImageModel::DallE2), "dall-e-2" => Ok(async_openai::types::ImageModel::DallE2),
"dall-e-3" => Ok(async_openai::types::images::ImageModel::DallE3), "dall-e-3" => Ok(async_openai::types::ImageModel::DallE3),
"gpt-image-1" => Ok(async_openai::types::images::ImageModel::GptImage1), other => Ok(async_openai::types::ImageModel::Other(other.to_owned())),
"gpt-image-1.5" => Ok(async_openai::types::images::ImageModel::GptImage1dot5),
"gpt-image-1-mini" => Ok(async_openai::types::images::ImageModel::GptImage1Mini),
other => Ok(async_openai::types::images::ImageModel::Other(
other.to_owned(),
)),
} }
} }
} }
fn default_image_style() -> Option<async_openai::types::images::ImageStyle> { fn default_image_style() -> Option<async_openai::types::ImageStyle> {
None None
} }
fn default_image_size() -> Option<async_openai::types::images::ImageSize> { fn default_image_size() -> Option<async_openai::types::ImageSize> {
None None
} }
fn default_image_quality() -> Option<async_openai::types::images::ImageQuality> { fn default_image_quality() -> Option<async_openai::types::ImageQuality> {
None None
} }

View File

@@ -4,12 +4,10 @@ use async_openai::{
Client as OpenAIClient, Client as OpenAIClient,
config::OpenAIConfig, config::OpenAIConfig,
types::{ types::{
ChatCompletionRequestMessage, CreateChatCompletionRequestArgs, CreateImageEditRequestArgs,
CreateImageRequestArgs,
DallE2ImageSize, Image, ImageModel, ImageResponseFormat,
audio::{AudioInput, CreateSpeechRequestArgs, CreateTranscriptionRequestArgs}, audio::{AudioInput, CreateSpeechRequestArgs, CreateTranscriptionRequestArgs},
chat::{ChatCompletionRequestMessage, CreateChatCompletionRequestArgs},
images::{
CreateImageEditRequestArgs, CreateImageRequestArgs,
Image, ImageInput, ImageModel, ImageResponseFormat,
},
}, },
}; };
@@ -41,6 +39,8 @@ use crate::{
use super::config::Config; use super::config::Config;
use super::OPENAI_IMAGE_MODEL_GPT_IMAGE_1;
#[derive(Debug, Clone)] #[derive(Debug, Clone)]
pub struct Controller { pub struct Controller {
config: Config, config: Config,
@@ -252,12 +252,11 @@ impl ControllerTrait for Controller {
let model = if params.cheaper_model_switching_allowed { let model = if params.cheaper_model_switching_allowed {
// Switch to a cheaper model // Switch to a cheaper model
match original_model { match original_model {
ImageModel::DallE2 => ImageModel::DallE2, async_openai::types::ImageModel::DallE2 => async_openai::types::ImageModel::DallE2,
ImageModel::DallE3 => ImageModel::DallE2, async_openai::types::ImageModel::DallE3 => async_openai::types::ImageModel::DallE2,
ImageModel::Other(_) => { async_openai::types::ImageModel::Other(_) => {
ImageModel::DallE2 async_openai::types::ImageModel::DallE2
} }
_ => original_model.clone(),
} }
} else { } else {
original_model original_model
@@ -267,24 +266,24 @@ impl ControllerTrait for Controller {
// Switch to a cheaper quality // Switch to a cheaper quality
match &image_generation_config.quality { match &image_generation_config.quality {
Some(quality) => match quality { Some(quality) => match quality {
async_openai::types::images::ImageQuality::Standard => { async_openai::types::ImageQuality::Standard => {
Some(async_openai::types::images::ImageQuality::Standard) Some(async_openai::types::ImageQuality::Standard)
} }
async_openai::types::images::ImageQuality::HD => { async_openai::types::ImageQuality::HD => {
Some(async_openai::types::images::ImageQuality::Standard) Some(async_openai::types::ImageQuality::Standard)
} }
// New quality levels - keep as-is or downgrade to Standard // New quality levels - keep as-is or downgrade to Standard
async_openai::types::images::ImageQuality::High => { async_openai::types::ImageQuality::High => {
Some(async_openai::types::images::ImageQuality::Standard) Some(async_openai::types::ImageQuality::Standard)
} }
async_openai::types::images::ImageQuality::Medium => { async_openai::types::ImageQuality::Medium => {
Some(async_openai::types::images::ImageQuality::Medium) Some(async_openai::types::ImageQuality::Medium)
} }
async_openai::types::images::ImageQuality::Low => { async_openai::types::ImageQuality::Low => {
Some(async_openai::types::images::ImageQuality::Low) Some(async_openai::types::ImageQuality::Low)
} }
async_openai::types::images::ImageQuality::Auto => { async_openai::types::ImageQuality::Auto => {
Some(async_openai::types::images::ImageQuality::Auto) Some(async_openai::types::ImageQuality::Auto)
} }
}, },
None => None, None => None,
@@ -295,18 +294,18 @@ impl ControllerTrait for Controller {
let size = params let size = params
.size_override .size_override
.map(|s| convert_string_to_enum::<async_openai::types::images::ImageSize>(&s).unwrap()) .map(|s| convert_string_to_enum::<async_openai::types::ImageSize>(&s).unwrap())
.or(image_generation_config.size); .or(image_generation_config.size);
let response_format = match model.clone() { let response_format = match model.clone() {
ImageModel::DallE2 => Some(ImageResponseFormat::B64Json), ImageModel::DallE2 => Some(ImageResponseFormat::B64Json),
ImageModel::DallE3 => Some(ImageResponseFormat::B64Json), ImageModel::DallE3 => Some(ImageResponseFormat::B64Json),
// gpt-image-1 only outputs base64 and we don't need to specify the response format. ImageModel::Other(model_str) => match model_str.as_str() {
// In fact, specifying the response format results in an error. // gpt-image-1 only outputs base64 and we don't need to specify the response format.
ImageModel::GptImage1 => None, // In fact, specifying the response format results in an error.
ImageModel::GptImage1Mini => None, OPENAI_IMAGE_MODEL_GPT_IMAGE_1 => None,
ImageModel::GptImage1dot5 => None, _ => Some(ImageResponseFormat::B64Json),
ImageModel::Other(_) => Some(ImageResponseFormat::B64Json), },
}; };
let mut request_builder = CreateImageRequestArgs::default(); let mut request_builder = CreateImageRequestArgs::default();
@@ -340,15 +339,15 @@ impl ControllerTrait for Controller {
"Sending OpenAI image generation API request" "Sending OpenAI image generation API request"
); );
let response = self.client.images().generate(request).await?; let response = self.client.images().create(request).await?;
if let Some(image) = response.data.into_iter().next() { if let Some(image) = response.data.into_iter().next() {
match image.deref() { match image.deref() {
Image::B64Json { async_openai::types::Image::B64Json {
b64_json, b64_json,
revised_prompt, revised_prompt,
} => { } => {
let bytes = base64_decode(b64_json.as_ref())?; let bytes = base64_decode(b64_json)?;
return Ok(ImageGenerationResult { return Ok(ImageGenerationResult {
bytes, bytes,
@@ -385,15 +384,15 @@ impl ControllerTrait for Controller {
return Err(anyhow::anyhow!("No image sources provided")); return Err(anyhow::anyhow!("No image sources provided"));
} }
let mut image_inputs: Vec<ImageInput> = Vec::new(); let mut image_inputs = Vec::new();
for image in images { for image in images {
image_inputs.push(image.into()); image_inputs.push(image.into());
} }
let dalle2_size = match image_generation_config.size { let dalle2_size = match image_generation_config.size {
Some(async_openai::types::images::ImageSize::S256x256) => Some(async_openai::types::images::ImageSize::S256x256), Some(async_openai::types::ImageSize::S256x256) => Some(DallE2ImageSize::S256x256),
Some(async_openai::types::images::ImageSize::S512x512) => Some(async_openai::types::images::ImageSize::S512x512), Some(async_openai::types::ImageSize::S512x512) => Some(DallE2ImageSize::S512x512),
Some(async_openai::types::images::ImageSize::S1024x1024) => Some(async_openai::types::images::ImageSize::S1024x1024), Some(async_openai::types::ImageSize::S1024x1024) => Some(DallE2ImageSize::S1024x1024),
_ => None, _ => None,
}; };
@@ -402,18 +401,16 @@ impl ControllerTrait for Controller {
.map_err(|err| anyhow::anyhow!(err))?; .map_err(|err| anyhow::anyhow!(err))?;
let response_format = match model.clone() { let response_format = match model.clone() {
ImageModel::DallE2 => { async_openai::types::ImageModel::DallE2 => {
Some(ImageResponseFormat::B64Json) Some(async_openai::types::ImageResponseFormat::B64Json)
} }
ImageModel::DallE3 => { async_openai::types::ImageModel::DallE3 => {
Some(ImageResponseFormat::B64Json) Some(async_openai::types::ImageResponseFormat::B64Json)
} }
// gpt-image-1 only outputs base64 and we don't need to specify the response format. async_openai::types::ImageModel::Other(model_str) => match model_str.as_str() {
// In fact, specifying the response format results in an error. OPENAI_IMAGE_MODEL_GPT_IMAGE_1 => None,
ImageModel::GptImage1 => None, _ => Some(async_openai::types::ImageResponseFormat::B64Json),
ImageModel::GptImage1Mini => None, },
ImageModel::GptImage1dot5 => None,
ImageModel::Other(_) => Some(ImageResponseFormat::B64Json),
}; };
let mut request_builder = CreateImageEditRequestArgs::default(); let mut request_builder = CreateImageEditRequestArgs::default();
@@ -442,12 +439,12 @@ impl ControllerTrait for Controller {
"Sending OpenAI image edit API request" "Sending OpenAI image edit API request"
); );
let response = self.client.images().edit(request).await?; let response = self.client.images().create_edit(request).await?;
if let Some(image_data) = response.data.into_iter().next() { if let Some(image_data) = response.data.into_iter().next() {
match image_data.deref() { match image_data.deref() {
Image::B64Json { b64_json, .. } => { Image::B64Json { b64_json, .. } => {
let bytes = base64_decode(b64_json.as_ref())?; let bytes = base64_decode(b64_json)?;
return Ok(ImageEditResult { return Ok(ImageEditResult {
bytes, bytes,
mime_type: mxlink::mime::IMAGE_PNG, mime_type: mxlink::mime::IMAGE_PNG,

View File

@@ -16,7 +16,7 @@ use super::super::AgentInstantiationResult;
use super::ConfigTrait; use super::ConfigTrait;
use super::controller::ControllerType; use super::controller::ControllerType;
pub const OPENAI_IMAGE_MODEL_GPT_IMAGE_1_DOT_5: &str = "gpt-image-1.5"; pub const OPENAI_IMAGE_MODEL_GPT_IMAGE_1: &str = "gpt-image-1";
pub fn create_controller_from_yaml_value_config( pub fn create_controller_from_yaml_value_config(
agent_id: &str, agent_id: &str,

View File

@@ -1,12 +1,8 @@
use async_openai::types::{ use async_openai::types::{
chat::{ ChatCompletionRequestAssistantMessageArgs, ChatCompletionRequestMessage,
ChatCompletionRequestAssistantMessageArgs, ChatCompletionRequestMessage, ChatCompletionRequestMessageContentPartImage, ChatCompletionRequestSystemMessageArgs,
ChatCompletionRequestMessageContentPartImage, ChatCompletionRequestUserMessageArgs, ChatCompletionRequestUserMessageContent,
ChatCompletionRequestSystemMessageArgs, ChatCompletionRequestUserMessageContentPart, ImageUrlArgs,
ChatCompletionRequestUserMessageArgs, ChatCompletionRequestUserMessageContent,
ChatCompletionRequestUserMessageContentPart,
ImageUrlArgs,
},
}; };
use crate::conversation::llm::{ use crate::conversation::llm::{

View File

@@ -224,7 +224,7 @@ impl TryInto<OpenAIImageGenerationConfig> for ImageGenerationConfig {
fn try_into(self) -> Result<OpenAIImageGenerationConfig, Self::Error> { fn try_into(self) -> Result<OpenAIImageGenerationConfig, Self::Error> {
let size = if let Some(size) = &self.size { let size = if let Some(size) = &self.size {
Some(convert_string_to_enum::<async_openai::types::images::ImageSize>( Some(convert_string_to_enum::<async_openai::types::ImageSize>(
size, size,
)?) )?)
} else { } else {
@@ -232,7 +232,7 @@ impl TryInto<OpenAIImageGenerationConfig> for ImageGenerationConfig {
}; };
let style = if let Some(style) = &self.style { let style = if let Some(style) = &self.style {
Some(convert_string_to_enum::<async_openai::types::images::ImageStyle>( Some(convert_string_to_enum::<async_openai::types::ImageStyle>(
style, style,
)?) )?)
} else { } else {
@@ -240,7 +240,7 @@ impl TryInto<OpenAIImageGenerationConfig> for ImageGenerationConfig {
}; };
let quality = if let Some(quality) = &self.quality { let quality = if let Some(quality) = &self.quality {
Some(convert_string_to_enum::<async_openai::types::images::ImageQuality>( Some(convert_string_to_enum::<async_openai::types::ImageQuality>(
quality, quality,
)?) )?)
} else { } else {

View File

@@ -1,4 +1,3 @@
use std::fs;
use std::sync::Arc; use std::sync::Arc;
use std::{future::Future, pin::Pin}; use std::{future::Future, pin::Pin};
@@ -19,13 +18,12 @@ use mxlink::helpers::account_data_config::{
RoomConfigManager as AccountDataRoomConfigManager, RoomConfigManager as AccountDataRoomConfigManager,
}; };
use mxlink::helpers::encryption::Manager as EncryptionManager; use mxlink::helpers::encryption::Manager as EncryptionManager;
use mxlink::mime::Mime;
use crate::agent::Manager as AgentManager; use crate::agent::Manager as AgentManager;
use crate::entity::catch_up_marker::{ use crate::entity::catch_up_marker::{
CatchUpMarker, CatchUpMarkerManager, DelayedCatchUpMarkerManager, CatchUpMarker, CatchUpMarkerManager, DelayedCatchUpMarkerManager,
}; };
use crate::entity::cfg::{Avatar, Config}; use crate::entity::cfg::Config;
use crate::entity::globalconfig::{GlobalConfig, GlobalConfigurationManager}; use crate::entity::globalconfig::{GlobalConfig, GlobalConfigurationManager};
use crate::entity::roomconfig::{RoomConfig, RoomConfigurationManager}; use crate::entity::roomconfig::{RoomConfig, RoomConfigurationManager};
@@ -318,72 +316,34 @@ impl Bot {
} }
} }
let desired_avatar: Option<(Vec<u8>, Mime)> = match &self.inner.config.user.avatar { let should_update_avatar = match &current_avatar_url {
Avatar::Keep => { Some(avatar_url) => {
tracing::info!("Avatar configured to keep current, skipping avatar management"); let request = MediaRequestParameters {
None source: MediaSource::Plain(avatar_url.to_owned()),
} format: MediaFormat::File,
Avatar::Default => { };
tracing::info!("Avatar configured to use default");
Some(( let content = media
LOGO_BYTES.to_vec(), .get_media_content(&request, true)
LOGO_MIME_TYPE .await
.parse() .map_err(|e| anyhow::anyhow!("Failed fetching existing avatar: {:?}", e))?;
.expect("Failed parsing mime type for logo"),
)) content.as_slice() != LOGO_BYTES
}
Avatar::Custom(avatar_path) => {
tracing::info!(?avatar_path, "Avatar configured to use custom path");
let bytes = fs::read(avatar_path).map_err(|e| {
anyhow::anyhow!("Failed reading avatar from {:?}: {:?}", avatar_path, e)
})?;
let mime = mime_guess::from_path(avatar_path).first_or_octet_stream();
tracing::debug!(?mime, bytes_len = bytes.len(), "Loaded custom avatar");
Some((bytes, mime))
} }
None => true,
}; };
if let Some((desired_bytes, mime_type)) = desired_avatar { if should_update_avatar {
let should_update_avatar = match &current_avatar_url { tracing::info!("Updating avatar..");
Some(avatar_url) => {
tracing::debug!(?avatar_url, "Fetching current avatar to compare");
let request = MediaRequestParameters {
source: MediaSource::Plain(avatar_url.to_owned()),
format: MediaFormat::File,
};
let content = media let mime_type = LOGO_MIME_TYPE
.get_media_content(&request, true) .parse()
.await .expect("Failed parsing mime type for logo");
.map_err(|e| anyhow::anyhow!("Failed fetching existing avatar: {:?}", e))?;
let needs_update = content.as_slice() != desired_bytes; account
.upload_avatar(&mime_type, LOGO_BYTES.to_vec())
tracing::debug!( .await
current_bytes_len = content.len(), .map_err(|e| anyhow::anyhow!("Failed uploading avatar: {:?}", e))?;
desired_bytes_len = desired_bytes.len(),
?needs_update,
"Compared current and desired avatar"
);
needs_update
}
None => {
tracing::debug!("No current avatar set, will upload");
true
}
};
if should_update_avatar {
tracing::info!("Updating avatar..");
account
.upload_avatar(&mime_type, desired_bytes)
.await
.map_err(|e| anyhow::anyhow!("Failed uploading avatar: {:?}", e))?;
tracing::info!("Avatar updated successfully");
} else {
tracing::debug!("Avatar already up to date, skipping upload");
}
} }
Ok(()) Ok(())

View File

@@ -5,7 +5,7 @@ use anyhow::anyhow;
use crate::agent::AgentPurpose; use crate::agent::AgentPurpose;
pub use crate::entity::cfg::{Avatar, Config, defaults as cfg_defaults, env as cfg_env}; pub use crate::entity::cfg::{Config, defaults as cfg_defaults, env as cfg_env};
pub fn load() -> anyhow::Result<Config> { pub fn load() -> anyhow::Result<Config> {
let config_file_path = env::var(cfg_env::BAIBOT_CONFIG_FILE_PATH) let config_file_path = env::var(cfg_env::BAIBOT_CONFIG_FILE_PATH)
@@ -33,13 +33,7 @@ pub fn load() -> anyhow::Result<Config> {
cfg_env::BAIBOT_USER_ENCRYPTION_RECOVERY_PASSPHRASE => { cfg_env::BAIBOT_USER_ENCRYPTION_RECOVERY_PASSPHRASE => {
config.user.encryption.recovery_passphrase = Some(value); config.user.encryption.recovery_passphrase = Some(value);
} }
cfg_env::BAIBOT_USER_ENCRYPTION_RECOVERY_RESET_ALLOWED => {
config.user.encryption.recovery_reset_allowed = value.parse::<bool>()?;
}
cfg_env::BAIBOT_USER_NAME => config.user.name = value, cfg_env::BAIBOT_USER_NAME => config.user.name = value,
cfg_env::BAIBOT_USER_AVATAR => {
config.user.avatar = Avatar::from_string(value);
}
cfg_env::BAIBOT_COMMAND_PREFIX => config.command_prefix = value, cfg_env::BAIBOT_COMMAND_PREFIX => config.command_prefix = value,
cfg_env::BAIBOT_ROOM_POST_JOIN_SELF_INTRODUCTION_ENABLED => { cfg_env::BAIBOT_ROOM_POST_JOIN_SELF_INTRODUCTION_ENABLED => {
config.room.post_join_self_introduction_enabled = value.parse::<bool>()?; config.room.post_join_self_introduction_enabled = value.parse::<bool>()?;
@@ -57,9 +51,6 @@ pub fn load() -> anyhow::Result<Config> {
cfg_env::BAIBOT_PERSISTENCE_DATA_DIR_PATH => { cfg_env::BAIBOT_PERSISTENCE_DATA_DIR_PATH => {
config.persistence.data_dir_path = Some(value); config.persistence.data_dir_path = Some(value);
} }
cfg_env::BAIBOT_PERSISTENCE_SESSION_ENCRYPTION_KEY => {
config.persistence.session_encryption_key = Some(value);
}
cfg_env::BAIBOT_PERSISTENCE_CONFIG_ENCRYPTION_KEY => { cfg_env::BAIBOT_PERSISTENCE_CONFIG_ENCRYPTION_KEY => {
config.persistence.config_encryption_key = Some(value); config.persistence.config_encryption_key = Some(value);
} }

View File

@@ -1,7 +1,7 @@
use std::path::PathBuf; use std::path::PathBuf;
use mxlink::helpers::encryption::EncryptionKey; use mxlink::helpers::encryption::EncryptionKey;
use serde::{Deserialize, Deserializer, Serialize}; use serde::{Deserialize, Serialize};
use crate::{ use crate::{
agent::{AgentDefinition, AgentPurpose, PublicIdentifier}, agent::{AgentDefinition, AgentPurpose, PublicIdentifier},
@@ -83,52 +83,6 @@ impl ConfigHomeserver {
} }
} }
/// Configuration for the bot's avatar.
///
/// - `Default`: Use the built-in default avatar (null, empty string, or missing in config)
/// - `Keep`: Don't touch the avatar, keep whatever is already set ("keep" in config)
/// - `Custom(String)`: Use a custom avatar from the specified file path
#[derive(Debug, Clone, PartialEq, Serialize)]
pub enum Avatar {
/// Use the built-in default avatar
Default,
/// Keep the current avatar, don't change it
Keep,
/// Use a custom avatar from the specified file path
Custom(String),
}
impl Default for Avatar {
fn default() -> Self {
Avatar::Default
}
}
impl<'de> Deserialize<'de> for Avatar {
fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>
where
D: Deserializer<'de>,
{
let value: Option<String> = Option::deserialize(deserializer)?;
Ok(match value {
None => Avatar::Default,
Some(s) => Avatar::from_string(s),
})
}
}
impl Avatar {
pub fn from_string(value: String) -> Self {
if value.is_empty() {
Avatar::Default
} else if value.eq_ignore_ascii_case("keep") {
Avatar::Keep
} else {
Avatar::Custom(value)
}
}
}
#[derive(Debug, Serialize, Deserialize)] #[derive(Debug, Serialize, Deserialize)]
pub struct ConfigUser { pub struct ConfigUser {
pub mxid_localpart: String, pub mxid_localpart: String,
@@ -139,9 +93,6 @@ pub struct ConfigUser {
#[serde(default)] #[serde(default)]
pub encryption: ConfigUserEncryption, pub encryption: ConfigUserEncryption,
#[serde(default)]
pub avatar: Avatar,
} }
impl ConfigUser { impl ConfigUser {

View File

@@ -6,11 +6,8 @@ pub const BAIBOT_HOMESERVER_URL: &str = "BAIBOT_HOMESERVER_URL";
pub const BAIBOT_USER_MXID_LOCALPART: &str = "BAIBOT_USER_MXID_LOCALPART"; pub const BAIBOT_USER_MXID_LOCALPART: &str = "BAIBOT_USER_MXID_LOCALPART";
pub const BAIBOT_USER_PASSWORD: &str = "BAIBOT_USER_PASSWORD"; pub const BAIBOT_USER_PASSWORD: &str = "BAIBOT_USER_PASSWORD";
pub const BAIBOT_USER_NAME: &str = "BAIBOT_USER_NAME"; pub const BAIBOT_USER_NAME: &str = "BAIBOT_USER_NAME";
pub const BAIBOT_USER_AVATAR: &str = "BAIBOT_USER_AVATAR";
pub const BAIBOT_USER_ENCRYPTION_RECOVERY_PASSPHRASE: &str = pub const BAIBOT_USER_ENCRYPTION_RECOVERY_PASSPHRASE: &str =
"BAIBOT_USER_ENCRYPTION_RECOVERY_PASSPHRASE"; "BAIBOT_USER_ENCRYPTION_RECOVERY_PASSPHRASE";
pub const BAIBOT_USER_ENCRYPTION_RECOVERY_RESET_ALLOWED: &str =
"BAIBOT_USER_ENCRYPTION_RECOVERY_RESET_ALLOWED";
pub const BAIBOT_COMMAND_PREFIX: &str = "BAIBOT_COMMAND_PREFIX"; pub const BAIBOT_COMMAND_PREFIX: &str = "BAIBOT_COMMAND_PREFIX";

View File

@@ -2,4 +2,4 @@ mod config;
pub mod defaults; pub mod defaults;
pub mod env; pub mod env;
pub use config::{Avatar, Config}; pub use config::Config;