Release 1.8.3

Update dependencies
Upgrade services
2025-11-28 14:40:38 +02:00 · 2025-11-28 14:23:07 +02:00 · 2025-11-28 14:19:59 +02:00 · 2025-11-28 14:18:35 +02:00 · 2025-11-28 14:17:23 +02:00 · 2025-11-20 06:00:52 +02:00
142 changed files with 4316 additions and 1574 deletions
--- a/.github/workflows/workflow.yml
+++ b/.github/workflows/workflow.yml
@@ -3,13 +3,14 @@ on:
  push:
    branches: [ "main" ]
    tags: [ "v*" ]
-  schedule:
-    - cron: '0 0 * * 1'
 permissions:
  checks: write
  contents: write
  packages: write
  pull-requests: read
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: false
 jobs:
  test-and-clippy:
    name: Unit testing and linting
@@ -17,20 +18,46 @@ jobs:
    steps:
      - uses: actions/checkout@v4
      - uses: dtolnay/rust-toolchain@stable
+      - name: Install SQLite3
+        run: sudo apt-get update && sudo apt-get install -y libsqlite3-dev
      - run: cargo test --all-features
      - run: cargo clippy

-  build-publish:
-    name: Build and Publish
-    runs-on: self-hosted
+  docker-clean-metadata:
+    runs-on: ubuntu-latest
+    outputs:
+      json: ${{ steps.meta.outputs.json }}
    steps:
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v5
        with:
-          platforms: arm64
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v1
-      - name: Login to ghcr.io
+          images: |
+            ghcr.io/${{ github.repository }}
+          tags: |
+            type=raw,value=latest,enable=${{ github.ref_name == 'main' }}
+            type=semver,pattern={{raw}}
+
+  docker-build:
+    permissions:
+      contents: read
+      packages: write
+      attestations: write
+      id-token: write
+    strategy:
+      matrix:
+        include:
+          - os: self-hosted
+            arch: amd64
+          - os: ubuntu-24.04-arm
+            arch: arm64
+
+    runs-on: ${{ matrix.os }}
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Log in to the GitHub Container registry
        uses: docker/login-action@v3
        with:
          registry: ghcr.io
@@ -40,17 +67,41 @@ jobs:
        id: meta
        uses: docker/metadata-action@v5
        with:
-          images: |
-            ghcr.io/${{ github.repository }}
-            registry.etke.cc/${{ github.repository }}
          tags: |
            type=raw,value=latest,enable=${{ github.ref_name == 'main' }}
            type=semver,pattern={{raw}}
-      - name: Build and push
+          flavor: |
+            latest=auto
+            suffix=-${{ matrix.arch }},onlatest=true
+          images: |
+            ghcr.io/${{ github.repository }}
+
+      - name: Build and push Docker images
        uses: docker/build-push-action@v6
        with:
-          platforms: linux/amd64,linux/arm64
          push: true
          tags: ${{ steps.meta.outputs.tags }}
          labels: ${{ steps.meta.outputs.labels }}
-          file: Dockerfile.ci
+
+  docker-manifest:
+    needs:
+      - docker-build
+      - docker-clean-metadata
+    runs-on: ubuntu-latest
+
+    strategy:
+      matrix:
+        image: ${{ fromJson(needs.docker-clean-metadata.outputs.json).tags }}
+
+    steps:
+      - name: Log in to the GitHub Container registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Create and push manifest
+        run: |
+          docker manifest create ${{ matrix.image }} ${{ matrix.image }}-amd64 ${{ matrix.image }}-arm64
+          docker manifest push ${{ matrix.image }}
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,9 +1,100 @@
+# (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
+
+- (**Internal Improvement**) Dependency updates.
+
+# (2025-09-08) Version 1.8.0
+
+- (**Internal Improvement**) Upgrade [mxlink](https://crates.io/crates/mxlink) (1.9.0 -> 1.10.0) and [matrix-sdk](https://crates.io/crates/matrix-sdk) (0.13.0 -> 0.14.0)
+
+- (**Internal Improvement**) Upgrade [Rust](https://www.rust-lang.org/) (1.88.0 -> 1.89.0)
+
+- (**Internal Improvement**) Upgrade Debian base for container images (12/bookworm -> 13/trixie)
+
+# (2025-07-11) Version 1.7.6
+
+- (**Internal Improvement**) Dependency updates. This version is based on [mxlink](https://crates.io/crates/mxlink)@1.9.0 (which is based on the newly released [matrix-sdk](https://crates.io/crates/matrix-sdk)@[0.13.0](https://github.com/matrix-org/matrix-rust-sdk/releases/tag/matrix-sdk-0.13.0), which contains fixes for some security vulnerabilities)
+
+# (2025-06-10) Version 1.7.5
+
+- (**Internal Improvement**) Dependency and compiler updates (Rust 1.86 -> 1.86).
+
+# (2025-06-10) Version 1.7.4
+
+- (**Internal Improvement**) Dependency updates.
+
+# (2025-06-10) Version 1.7.3
+
+- (**Internal Improvement**) Dependency updates. This version is based on [mxlink](https://crates.io/crates/mxlink)@1.8.0 (which is based on the newly released [matrix-sdk](https://crates.io/crates/matrix-sdk)@[0.12.0](https://github.com/matrix-org/matrix-rust-sdk/releases/tag/matrix-sdk-0.12.0), which contains fixes for important security vulnerabilities)
+
+# (2025-05-11) Version 1.7.2
+
+- (**Bugfix**) Allow `image_generation.size` configuration value for OpenAI to be `null` to allow the model to choose the size automatically and default to that
+
+# (2025-05-11) Version 1.7.1
+
+- (**Bugfix**) Fix lack of documentation for the new [image-editing](./docs/features.md#-image-editing) feature in the `!bai usage` command's output
+
+# (2025-05-10) Version 1.7.0
+
+- (**Feature**) Add vision support to the OpenAI and Anthropic providers. You can now mix text and images in your conversations - fixes [issue #5](https://github.com/etkecc/baibot/issues/5)
+
+- (**Feature**) Add [image-editing](./docs/features.md#-image-editing) support to the OpenAI provider
+
+- (**Improvement**) Add compatibility with OpenAI's `gpt-image-1` model - fixes [issue #40](https://github.com/etkecc/baibot/issues/40)
+
+- (**Change**) Rework [image-creation](./docs/features.md#-image-creation) to avoid command conflicts with [image-editing](./docs/features.md#-image-editing). The image-creation command syntax is now `!bai image create <prompt>` (previously: `!bai image <prompt>`).
+
+- (**Internal Improvement**) Dependency and compiler updates
+
+> [!WARNING]
+> Unlike other releases, this release is not published to [crates.io](https://crates.io), because it relies on multiple library forks (`async-openai` and `anthropic-rs`) sourced from Github.
+
+
+# (2025-04-12) Version 1.6.0
+
+- (**Internal Improvement**) Dependency updates. This version is based on [mxlink](https://crates.io/crates/mxlink)@1.7.0 (which is based on the newly released [matrix-sdk](https://crates.io/crates/matrix-sdk)@[0.11.0](https://github.com/matrix-org/matrix-rust-sdk/releases/tag/matrix-sdk-0.11.0))
+
+
+# (2025-03-31) Version 1.5.1
+
+- (**Internal Improvement**) Dependency updates
+
+# (2025-02-27) Version 1.5.0
+
+- (**Feature**) Add support for sending Speech-to-Text replies for [Transcribe-only mode](./docs/features.md#transcribe-only-mode) as regular text messages instead of notices and doing it so by default ([a1bd292752](https://github.com/etkecc/baibot/commit/a1bd292752bdd37a196788c73d00b5619e843a78)) - improvement for [issue #14](https://github.com/etkecc/baibot/issues/14). See [🦻 Speech-to-Text / 🪄 Message Type for non-threaded only-transcribed messages](./docs/configuration/speech-to-text.md#-message-type-for-non-threaded-only-transcribed-messages) for details.
+
+- (**Feature**) Add config setting controlling if a self-introduction message is posted after joining a room ([c051da2f4a](https://github.com/etkecc/baibot/commit/c051da2f4a161de0974ebb917f7a52d01f5a001f)) - fixes [issue #32](https://github.com/etkecc/baibot/issues/32). You may wish to add a `room.post_join_self_introduction_enabled` property to your configuration. See the [sample config](./etc/app/config.yml.dist) for details. If unspecified, it defaults to `true` anyway which preserves the old behavior.
+
+- (**Feature**) Add support for configuring `max_completion_tokens` for OpenAI ([47d8edea70](https://github.com/etkecc/baibot/commit/47d8edea705a44aa25a9bfaec4888c0f9ea8700e))
+
+- (**Improvement**) Dependency updates. This version is based on [mxlink](https://crates.io/crates/mxlink)@1.6.1 (which is based on the newly released [matrix-sdk](https://crates.io/crates/matrix-sdk)@[0.10.0](https://github.com/matrix-org/matrix-rust-sdk/releases/tag/matrix-sdk-0.10.0))
+
+- (**Improvement**) Populate image/audio attachment `body` with a filename, not with text to avoid incorrect rendering in Element Web, etc. ([ec1879d212](https://github.com/etkecc/baibot/commit/ec1879d212fa8d6e5f8590486e94c72abfcb75a5))
+
+- (**Improvement**) Replace Anthropic library ([anthropic-rs](https://crates.io/crates/anthropic-rs) -> [anthropic](https://crates.io/crates/anthropic)) and switch default recommended model (`claude-3-5-sonnet-20240620` -> `claude-3-7-sonnet-20250219`) ([692d61b239](https://github.com/etkecc/baibot/commit/692d61b2398f073b81d32d4cbe8145ab3929e48c)) - fixes [issue #22](https://github.com/etkecc/baibot/issues/22)
+
+- (**Internal Improvement**) Switch to native building of `arm64` container images to decrease total build times from ~40 minutes to ~8 minutes ([6719538530b](https://github.com/etkecc/baibot/commit/6719538530bf76b3ff2d24077b2a7fa868276b79))
+
+- (**Internal Improvement**) Various other internal changes, including upgrading [Rust from 1.82 to 1.85 and switching to Rust edition 2024](https://blog.rust-lang.org/2025/02/20/Rust-1.85.0.html)
+
+
+# (2024-12-12) Version 1.4.1
+
+- (**Bugfix**) Fix detection for whether the bot is the last member in a room, to avoid incorrectly leaving multi-user rooms that have had at least one person `leave` ([3c47d40781](https://github.com/etkecc/baibot/commit/3c47d407819aa9c0121117a411858238724f06da))
+
+
 # (2024-11-19) Version 1.4.0

 - (**Improvement**) Dependency updates. This version is based on [mxlink](https://crates.io/crates/mxlink)@1.4.0 (which is based on the newly released [matrix-sdk](https://crates.io/crates/matrix-sdk)@[0.8.0](https://github.com/matrix-org/matrix-rust-sdk/releases/tag/matrix-sdk-0.8.0)). Once you run this version at least once and your matrix-sdk datastore gets upgraded to the new schema, **you will not be able to downgrade to older baibot versions** (based on the older matrix-sdk), unless you start with an empty datastore.

 - (**Bugfix**) Add missing typing notices sending functionality while generating images ([9d166e35ba](https://github.com/etkecc/baibot/commit/9d166e35ba6fc0daaf69318870e92436f3302056))

+- (**Feature**) Support for [Matrix authenticated media](https://matrix.org/docs/spec-guides/authed-media-servers/), thanks to upgrading [mxlink](https://crates.io/crates/mxlink) / [matrix-sdk](https://crates.io/crates/matrix-sdk) - fixes [issue #12](https://github.com/etkecc/baibot/issues/12)
+

 # (2024-11-12) Version 1.3.2

--- a/Cargo.lock
+++ b/Cargo.lock
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -7,32 +7,33 @@ license = "AGPL-3.0-or-later"
 readme = "README.md"
 keywords = ["matrix", "chat", "bot", "AI", "LLM"]
 include = ["/etc/assets/baibot-torso-768.png", "/src", "/README.md", "/CHANGELOG.md", "/LICENSE"]
-version = "1.4.0"
-edition = "2021"
+version = "1.8.3"
+edition = "2024"

 [lib]
 name = "baibot"
 path = "src/lib.rs"

 [dependencies]
-anthropic-rs = "0.1.*"
+anthropic = { git = "https://github.com/etkecc/anthropic-rs.git", branch = "fix-content-block-image" }
 anyhow = "1.0.*"
-async-openai = "0.26.*"
+async-openai = { git = "https://github.com/etkecc/async-openai", branch = "async-openai-v0.28.1-patched" }
 base64 = "0.22.*"
 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.
-matrix-sdk = { version = "0.8.0", default-features = false }
+# We add the `native-tls` feature, because of https://github.com/etkecc/rust-mxlink/issues/1
+matrix-sdk = { version = "0.14.0", default-features = false, features = ["native-tls"] }
 mxidwc = "1.0.*"
-mxlink = ">=1.4.0"
+mxlink = ">=1.10.0"
 etke_openai_api_rust = "0.1.*"
 quick_cache = "0.6.*"
-regex = "1.11.*"
+regex = "1.12.*"
 serde = { version = "1.0.*", features = ["derive"], default-features = false }
 serde_json = "1.0.*"
 serde_yaml = "0.9.*"
-tempfile = "3.14.*"
-tiktoken-rs = { version = "0.6.*", features = ["async-openai"] }
-tokio = { version = "1.41.*", features = ["rt", "rt-multi-thread", "macros"] }
+tempfile = "3.23.*"
+tiktoken-rs = { version = "0.9.*", default-features = false }
+tokio = { version = "1.48.*", features = ["rt", "rt-multi-thread", "macros"] }
 tracing = "0.1.*"
 tracing-subscriber = { version = "0.3.*", features = ["env-filter"] }
 url = "2.5.*"
--- a/4
+++ b/4
@@ -4,7 +4,7 @@
 #                                     #
 #######################################

-FROM docker.io/rust:1.82.0-slim-bookworm AS build
+FROM docker.io/rust:1.91.1-slim-trixie AS build

 RUN apt-get update && apt-get install -y build-essential pkg-config libssl-dev libsqlite3-dev

@@ -39,7 +39,7 @@ RUN --mount=type=cache,target=/target,sharing=locked \
 #                                     #
 #######################################

-FROM docker.io/debian:bookworm-slim
+FROM docker.io/debian:trixie-slim

 RUN apt-get update && apt-get install -y ca-certificates sqlite3 && \
    apt-get clean && \
--- a/Dockerfile.ci
+++ b/Dockerfile.ci
@@ -4,7 +4,7 @@
 #                                     #
 #######################################

-FROM docker.io/rust:1.82.0-slim-bookworm AS build
+FROM docker.io/rust:1.91.1-slim-trixie AS build

 RUN apt-get update && apt-get install -y build-essential pkg-config libssl-dev libsqlite3-dev

@@ -20,7 +20,7 @@ RUN cargo build --release
 #                                     #
 #######################################

-FROM docker.io/debian:bookworm-slim
+FROM docker.io/debian:trixie-slim

 RUN apt-get update && apt-get install -y ca-certificates sqlite3 && \
    apt-get clean && \
--- a/README.md
+++ b/README.md
@@ -17,10 +17,10 @@ It's influenced by [chaz](https://github.com/arcuru/chaz), but does **not** use

 - Supports **different use purposes** (depending on the [☁️ provider](./docs/providers.md) & model):

-  - [💬 text-generation](./docs/features.md#-text-generation): communicating with you via text
+  - [💬 text-generation](./docs/features.md#-text-generation): communicating with you via text (though certain models may "see" images as well)
  - [🦻 speech-to-text](./docs/features.md#-speech-to-text): turning your voice messages into text
  - [🗣️ text-to-speech](./docs/features.md#%EF%B8%8F-text-to-speech): turning bot or users text messages into voice messages
-  - [🖌️ image-generation](./docs/features.md#%EF%B8%8F-image-generation): generating images based on instructions
+  - [🖌️ image-generation](./docs/features.md#image-generation): creating and editing images based on instructions

 - 🪄 Supports [seamless voice interaction](./docs/features.md#seamless-voice-interaction) (turning user voice messages into text, answering in text, then turning that text back into voice)

--- a/docs/agents.md
+++ b/docs/agents.md
@@ -35,7 +35,7 @@ Depending on where the agent is defined (within a room, globally, or [statically

 When creating an agent, you will be given some sample [YAML](https://en.wikipedia.org/wiki/YAML) configuration which you can use to customize the agent's behavior.

-This configuration varies depending on the [☁️ provider](./providers.md) used and the capabilities of the agent. Based on the configuration keys you pass, certain features will be enabled or disabled. For example, if you skip the `image_generation` key for an [OpenAI](./providers.md#openai) agent, it won't be able to generate images (see [🖌️ Image Generation](./features.md#-image-generation)).
+This configuration varies depending on the [☁️ provider](./providers.md) used and the capabilities of the agent. Based on the configuration keys you pass, certain features will be enabled or disabled. For example, if you skip the `image_generation` key for an [OpenAI](./providers.md#openai) agent, it won't be able to generate images (see [🖌️ Image Creation](./features.md#-image-creation), [🎨 Image Editing](./features.md#-image-editing), [🫵 Sticker Creation](./features.md#-sticker-creation)).

 After making your modifications to the sample YAML, you submit it back to the bot and the new agent will be created.

--- a/docs/configuration/README.md
+++ b/docs/configuration/README.md
@@ -40,7 +40,7 @@ You can adjust the following settings per room and/or globally:
 - [💬 Text Generation](text-generation.md)
 - [🦻 Speech-to-Text](speech-to-text.md)
 - [🗣️ Text-to-Speech](text-to-speech.md)
- [🖌️ Image Generation](image-generation.md)
+- [🖌️ Image Creation](image-generation.md)
 - [🤝 Handlers](handlers.md)

 Refer to the bot's help messages (as a response to a `!bai config` help command) for the most up-to-date information on what Room Settings can be configured.
--- a/docs/configuration/handlers.md
+++ b/docs/configuration/handlers.md
@@ -8,10 +8,10 @@ You can also use **different models within the same room** (e.g. [💬 text-gene

 The bot supports the following use-purposes:

- [💬 text-generation](../features.md#-text-generation): communicating with you via text
+- [💬 text-generation](../features.md#-text-generation): communicating with you via text (though certain models may "see" images as well)
 - [🦻 speech-to-text](../features.md#-speech-to-text): turning your voice messages into text
 - [🗣️ text-to-speech](../features.md#️-text-to-speech): turning bot or users text messages into voice messages
- [🖌️ image-generation](../features.md#-image-generation): generating images based on instructions
+- [🖌️ image-generation](../features.md#image-generation): generating images based on instructions

 In a given room, each different purpose can be served by a different [provider](../providers.md) and model. This combination of provider and model configuration is called an [🤖 agent](../agents.md). Each purpose can be served by a different **handler** agent.

--- a/docs/configuration/image-generation.md
+++ b/docs/configuration/image-generation.md
@@ -1,9 +1,11 @@

-## 🖌️ Image Generation
+## Image Generation

-The Image Generation feature is not configurable at this moment.
+The Image Creation and Image Editing features are not configurable at this moment.

 You may also wish to see:

- [🌟 Features / 🖌️ Image Generation](../features.md#-image-generation) for a higher-level introduction to the Image Generation features
- [📖 Usage / 🖌️ Image Generation](../usage.md#-image-generation) section for more details on how to use the bot for Image Generation in a room
+- [🌟 Features / Image Generation / 🖌️ Image Creation](../features.md#-image-creation) for a higher-level introduction to the Image Creation features
+- [🌟 Features / Image Generation / 🎨 Image Editing](../features.md#-image-editing) for a higher-level introduction to the Image Editing features
+- [📖 Usage / Image Generation / 🖌️ Creating Images](../usage.md#-creating-images) section for more details on how to use the bot for Image Creation in a room
+- [📖 Usage / Image Generation / 🎨 Editing images](../usage.md#-editing-images) section for more details on how to use the bot for Image Editing in a room
--- a/docs/configuration/speech-to-text.md
+++ b/docs/configuration/speech-to-text.md
@@ -23,6 +23,19 @@ The following configuration values are recognized:
 Example: `!bai config room speech-to-text set-flow-type ignore` (this can also be set globally, see [🛠️ Room Settings](./README.md#room-settings))


+### 🪄 Message Type for non-threaded only-transcribed messages
+
+Controls how the transcribed text of voice messages is sent to the chat when Flow Type = `only_transcribe`.
+
+The following configuration values are recognized:
+
+- (default) `text`: the transcribed text is sent as a regular message. This is more convenient if you'd like to forward the transcribed message to other rooms.
+
+- `notice`: the transcribed text is sent as a notice message. This provides better compatibility with other bots in the room, as they are less likely to interact with messages of type notice.
+
+Example: `!bai config room speech-to-text set-msg-type-for-non-threaded-only-transcribed-messages notice` (this can also be set globally, see [🛠️ Room Settings](./README.md#room-settings))
+
+
 ### 🔤 Language

 Lets you specify the language of the input voice messages, to avoid using auto-detection.
--- a/docs/development.md
+++ b/docs/development.md
@@ -93,7 +93,7 @@ For getting started most quickly (and locally), we recommend using [LocalAI](#lo

 **Ollama is most lightweight** (~2GB for the container image + ~1.6GB for the model), but supports only [💬 text-generation](./features.md#-text-generation).

-**LocalAI requires 4x more disk space** (~6GB for the container image + ~12GB for the models), but supports [💬 text-generation](./features.md#-text-generation), [🗣️ text-to-speech](./features.md#️-text-to-speech), [🦻 speech-to-text](./features.md#-speech-to-text) and [🖼️ image-generation](./features.md#️-image-generation).
+**LocalAI requires 4x more disk space** (~6GB for the container image + ~12GB for the models), but supports [💬 text-generation](./features.md#-text-generation), [🗣️ text-to-speech](./features.md#️-text-to-speech), [🦻 speech-to-text](./features.md#-speech-to-text) and [🖼️ image-generation](./features.md#️-image-creation).

 **OpenAI supports all of these capabilities** as well and does not require powerful hardware or lots of disk space. However, it requires signup and an API key.

--- a/docs/features.md
+++ b/docs/features.md
@@ -8,7 +8,7 @@ You can also use **different models within the same room** (e.g. [💬 text-gene

 The bot supports the following use-purposes:

- [💬 text-generation](#-text-generation): communicating with you via text
+- [💬 text-generation](#-text-generation): communicating with you via text (though certain models may "see" images as well)
 - [🦻 speech-to-text](#-speech-to-text): turning your voice messages into text
 - [🗣️ text-to-speech](#%EF%B8%8F-text-to-speech): turning bot or users text messages into voice messages
 - [🖌️ image-generation](#%EF%B8%8F-image-generation): generating images based on instructions
@@ -22,10 +22,12 @@ For more information about configuring handlers, see the [🤝 Handlers / Config

 ### 💬 Text Generation

-Text Generation is the bot's ability to **respond to users' text messages with text**.
+Text Generation is the bot's ability to **respond to users' messages with text**.

 ![Screenshot of Text Generation - a user sends a message and the bot replies in a new conversation thread](./screenshots/text-generation.webp)

+Some models also support vision, so you may be able to mix text and images in the same conversation.
+
 In multi-user (group) rooms, to avoid disturbing the normal conversation between people, the bot is auto-configured to only respond to messages starting with the command prefix (`!bai`) or direct mentions via the [💬 Text Generation / 🗟 Prefix Requirement Type](./configuration/text-generation.md#-prefix-requirement-type) setting.

 Normally, the bot only responds to allowed [👥 Users](./access.md#-users). In certain cases, it's useful for an allowed user to provoke the bot to respond even in foreign threads or reply chains. You can learn more about this feature in the [On-demand involvement](./features.md#on-demand-involvement) section below.
@@ -136,27 +138,45 @@ To operate in this mode, you can:

 - adjust the [🦻 Speech-to-Text / 🪄 Flow Type](./configuration/speech-to-text.md#-flow-type) setting to make the bot only transcribe (without doing [💬 Text Generation](#-text-generation)): `!bai config room speech-to-text set-flow-type only_transcribe`

+- optionally adjust [🦻 Speech-to-Text / 🪄 Message Type for non-threaded only-transcribed messages](./configuration/speech-to-text.md#-message-type-for-non-threaded-only-transcribed-messages), if you'd like to bot to send messages of type `notice` (for better compatibility with other bots in the room) instead of sending regular `text` messages (default)

-### 🖌️ Image Generation

-Image generation is the bot's ability to **generate images** based on text prompts.
+### Image Generation

-See a [🖼️ Screenshot of the Image Generation feature](./screenshots/image-generation.webp).
+#### 🖌️ Image Creation
+
+Image creation is the bot's ability to **create images** based on text prompts.
+
+See a [🖼️ Screenshot of the Image Creation feature](./screenshots/image-creation.webp).

 You may also wish to see:

 - [🛠️ Configuration / 🖌️ Image Generation](./configuration/image-generation.md) for configuration options related to Image Generation
- [📖 Usage / 🖌️ Image Generation](./usage.md#-image-generation) section for more details on how to use the bot for Image Generation in a room
- [🫵 Sticker Generation](#-sticker-generation) - a special case of Image Generation
+- [📖 Usage / Image Generation / 🖌️ Creating Images](./usage.md#-creating-images) section for more details on how to use the bot for Image Creation in a room
+- [🖌️ Image Editing](#️-image-editing) - another image generation feature
+- [🫵 Sticker Creation](#-sticker-creation) - a special case of Image Creation


-### 🫵 Sticker Generation
+#### 🎨 Image Editing

-Sticker generation is the bot's ability to **generate sticker** images based on text prompts. It's a special case of [🖌️ Image Generation](#️-image-generation).
+Image editing is the bot's ability to **edit images** based on a prompt and one or more existing images.

-See a [🖼️ Screenshot of the Sticker Generation feature](./screenshots/sticker-generation.webp).
+See a [🖼️ Screenshot of the Image Editing feature (manipulating a single image)](./screenshots/image-editing-single-image.webp) and a [🖼️ Screenshot of the Image Editing feature (manipulating multiple images)](./screenshots/image-editing-multiple-images.webp).

-See [📖 Usage / 🖌️ Image Generation / Generating Stickers](./usage.md#generating-stickers) for details.
+You may also wish to see:
+
+- [🛠️ Configuration / 🖌️ Image Generation](./configuration/image-generation.md) for configuration options related to Image Generation
+- [📖 Usage / Image Generation / 🎨 Editing images](./usage.md#-editing-images) section for more details on how to use the bot for Image Editing in a room
+- [🖌️ Image Creation](#️-image-creation) - another image generation feature
+
+
+#### 🫵 Sticker Creation
+
+Sticker generation is the bot's ability to **generate sticker** images based on text prompts. It's a special case of [🖌️ Image Creation](#️-image-creation).
+
+See a [🖼️ Screenshot of the Sticker Creation feature](./screenshots/sticker-generation.webp).
+
+See [📖 Usage / Image Generation / 🫵 Creating Stickers](./usage.md#-creating-stickers) for details.


 ### 🔒 Encryption
--- a/docs/installation.md
+++ b/docs/installation.md
@@ -53,6 +53,7 @@ CONTAINER_IMAGE_NAME=ghcr.io/etkecc/baibot:v1.0.0
  --env BAIBOT_PERSISTENCE_DATA_DIR_PATH=/data \
  --mount type=bind,src=/path/to/config.yml,dst=/app/config.yml,ro \
  --mount type=bind,src=/path/to/data,dst=/data \
+  --tmpfs=/tmp:rw,noexec,nosuid,size=1024m \
  $CONTAINER_IMAGE_NAME
 ```

--- a/docs/providers.md
+++ b/docs/providers.md
@@ -23,7 +23,7 @@ The list of supported providers is below.

 ### How to choose a provider

-If you're not sure which provider to start with, **we recommend [OpenAI](#openai)** as it's the most popular and has the **widest range of capabilities**: [💬 text-generation](./features.md#-text-generation), [🖌️ image-generation](./features.md#️-image-generation), [🦻 speech-to-text](./features.md#-speech-to-text), [🗣️ text-to-speech](./features.md#️-text-to-speech).
+If you're not sure which provider to start with, **we recommend [OpenAI](#openai)** as it's the most popular and has the **widest range of capabilities**: [💬 text-generation](./features.md#-text-generation) (no vision), [🖌️ image-generation](./features.md#️image-generation), [🦻 speech-to-text](./features.md#-speech-to-text), [🗣️ text-to-speech](./features.md#️-text-to-speech).

 You don't need to choose just one though. The bot supports [mixing & matching models](./features.md#-mixing--matching-models), so you can use multiple providers at the same time.

@@ -47,7 +47,7 @@ You don't need to choose just one though. The bot supports [mixing & matching mo

 - 🆔 Identifier: `anthropic`
 - 🔗 Links: [🏠 Home page](https://www.anthropic.com/), [🌐 Wiki](https://en.wikipedia.org/wiki/Anthropic), [👤 Sign up](https://console.anthropic.com/), [📋 Models list](https://docs.anthropic.com/en/docs/about-claude/models)
- 🌟 Capabilities: [💬 text-generation](./features.md#-text-generation)
+- 🌟 Capabilities: [💬 text-generation](./features.md#-text-generation) (incl. vision)
 - 🗲 Quick start:
  - create a room-local agent: `!bai agent create-room-local anthropic my-anthropic-agent`
  - create a global agent: `!bai agent create-global anthropic my-anthropic-agent`
@@ -61,7 +61,7 @@ You don't need to choose just one though. The bot supports [mixing & matching mo

 - 🆔 Identifier: `groq`
 - 🔗 Links: [🏠 Home page](https://groq.com/), [🌐 Wiki](https://en.wikipedia.org/wiki/Groq), [👤 Sign up](https://console.groq.com/login), [📋 Models list](https://console.groq.com/docs/models)
- 🌟 Capabilities: [💬 text-generation](./features.md#-text-generation), [🦻 speech-to-text](./features.md#-speech-to-text)
+- 🌟 Capabilities: [💬 text-generation](./features.md#-text-generation) (no vision), [🦻 speech-to-text](./features.md#-speech-to-text)
 - 🗲 Quick start:
  - create a room-local agent: `!bai agent create-room-local groq my-groq-agent`
  - create a global agent: `!bai agent create-global groq my-groq-agent`
@@ -75,7 +75,7 @@ You don't need to choose just one though. The bot supports [mixing & matching mo

 - 🆔 Identifier: `localai`
 - 🔗 Links: [🏠 Home page](https://localai.io/), [📋 Models list](https://localai.io/gallery.html)
- 🌟 Capabilities: [💬 text-generation](./features.md#-text-generation), [🗣️ text-to-speech](./features.md#️-text-to-speech), [🦻 speech-to-text](./features.md#-speech-to-text)
+- 🌟 Capabilities: [💬 text-generation](./features.md#-text-generation) (no vision), [🗣️ text-to-speech](./features.md#️-text-to-speech), [🦻 speech-to-text](./features.md#-speech-to-text)
 - 🗲 Quick start:
  - create a room-local agent: `!bai agent create-room-local localai my-localai-agent`
  - create a global agent: `!bai agent create-global localai my-localai-agent`
@@ -89,7 +89,7 @@ You don't need to choose just one though. The bot supports [mixing & matching mo

 - 🆔 Identifier: `mistral`
 - 🔗 Links: [🏠 Home page](https://mistral.ai/), [🌐 Wiki](https://en.wikipedia.org/wiki/Mistral_AI), [👤 Sign up](https://auth.mistral.ai/ui/registration), [📋 Models list](https://docs.mistral.ai/getting-started/models/)
- 🌟 Capabilities: [💬 text-generation](./features.md#-text-generation)
+- 🌟 Capabilities: [💬 text-generation](./features.md#-text-generation) (no vision)
 - 🗲 Quick start:
  - create a room-local agent: `!bai agent create-room-local mistral my-mistral-agent`
  - create a global agent: `!bai agent create-global mistral my-mistral-agent`
@@ -103,7 +103,7 @@ You don't need to choose just one though. The bot supports [mixing & matching mo

 - 🆔 Identifier: `ollama`
 - 🔗 Links: [🏠 Home page](https://ollama.com/), [📋 Models list](https://ollama.com/library)
- 🌟 Capabilities: [💬 text-generation](./features.md#-text-generation)
+- 🌟 Capabilities: [💬 text-generation](./features.md#-text-generation) (no vision)
 - 🗲 Quick start:
  - create a room-local agent: `!bai agent create-room-local ollama my-ollama-agent`
  - create a global agent: `!bai agent create-global ollama my-ollama-agent`
@@ -120,15 +120,12 @@ For services which are not fully compatible with the OpenAI API, consider using

 - 🆔 Identifier: `openai`
 - 🔗 Links: [🏠 Home page](https://openai.com/), [🌐 Wiki](https://en.wikipedia.org/wiki/OpenAI), [👤 Sign up](https://platform.openai.com/signup), [📋 Models list](https://platform.openai.com/docs/models)
- 🌟 Capabilities: [🖌️ image-generation](./features.md#️-image-generation), [💬 text-generation](./features.md#-text-generation), [🗣️ text-to-speech](./features.md#️-text-to-speech), [🦻 speech-to-text](./features.md#-speech-to-text)
+- 🌟 Capabilities: [🖌️ image-generation](./features.md#️-image-creation), [💬 text-generation](./features.md#-text-generation) (incl. vision), [🗣️ text-to-speech](./features.md#️-text-to-speech), [🦻 speech-to-text](./features.md#-speech-to-text)
 - 🗲 Quick start:
  - 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`

-💡 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)
+💡 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).


 ### OpenAI Compatible
@@ -140,7 +137,7 @@ Some of these popular services already have **shortcut** providers (leading to t
 This provider is just as featureful as the [OpenAI](#openai) provider, but is more compatible with services which do not fully adhere to the [OpenAI API spec](https://github.com/openai/openai-openapi/).

 - 🆔 Identifier: `openai-compatible`
- 🌟 Capabilities: [🖌️ image-generation](./features.md#️-image-generation), [💬 text-generation](./features.md#-text-generation), [🗣️ text-to-speech](./features.md#️-text-to-speech), [🦻 speech-to-text](./features.md#-speech-to-text)
+- 🌟 Capabilities: [🖌️ image-generation](./features.md#️-image-creation), [💬 text-generation](./features.md#-text-generation) (no vision), [🗣️ text-to-speech](./features.md#️-text-to-speech), [🦻 speech-to-text](./features.md#-speech-to-text)
 - 🗲 Quick start:
  - create a room-local agent: `!bai agent create-room-local openai-compatible my-openai-compatible-agent`
  - create a global agent: `!bai agent create-global openai-compatible my-openai-compatible-agent`
@@ -154,7 +151,7 @@ This provider is just as featureful as the [OpenAI](#openai) provider, but is mo

 - 🆔 Identifier: `openrouter`
 - 🔗 Links: [🏠 Home page](https://openrouter.ai/), [👤 Sign up](https://openrouter.ai/), [📋 Models list](https://openrouter.ai/models)
- 🌟 Capabilities: [💬 text-generation](./features.md#-text-generation)
+- 🌟 Capabilities: [💬 text-generation](./features.md#-text-generation) (no vision)
 - 🗲 Quick start:
  - create a room-local agent: `!bai agent create-room-local openrouter my-openrouter-agent`
  - create a global agent: `!bai agent create-global openrouter my-openrouter-agent`
@@ -168,7 +165,7 @@ This provider is just as featureful as the [OpenAI](#openai) provider, but is mo

 - 🆔 Identifier: `together-ai`
 - 🔗 Links: [🏠 Home page](https://www.together.ai/), [👤 Sign up](https://api.together.ai/signup), [📋 Models list](https://api.together.xyz/models)
- 🌟 Capabilities: [💬 text-generation](./features.md#-text-generation)
+- 🌟 Capabilities: [💬 text-generation](./features.md#-text-generation) (no vision)
 - 🗲 Quick start:
  - create a room-local agent: `!bai agent create-room-local together-ai my-together-ai-agent`
  - create a global agent: `!bai agent create-global together-ai my-together-ai-agent`
--- a/docs/sample-provider-configs/anthropic.yml
+++ b/docs/sample-provider-configs/anthropic.yml
@@ -1,7 +1,7 @@
 base_url: https://api.anthropic.com/v1
 api_key: YOUR_API_KEY_HERE
 text_generation:
-  model_id: claude-3-5-sonnet-20240620
+  model_id: claude-3-7-sonnet-20250219
  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
  max_response_tokens: 8192
--- a/docs/sample-provider-configs/openai-o1.yml
+++ b/docs/sample-provider-configs/openai-o1.yml
@@ -1,24 +0,0 @@
-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,
-  # but we don't support it yet (see https://github.com/64bit/async-openai/issues/272).
-  max_response_tokens: null
-  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: dall-e-3
-  style: vivid
-  size: 1024x1024
-  quality: standard
--- a/docs/sample-provider-configs/openai.yml
+++ b/docs/sample-provider-configs/openai.yml
@@ -1,11 +1,14 @@
 base_url: https://api.openai.com/v1
 api_key: YOUR_API_KEY_HERE
 text_generation:
-  model_id: gpt-4o
+  model_id: gpt-5.1
  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
-  max_response_tokens: 16384
-  max_context_tokens: 128000
+  # 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_context_tokens: 400000
 speech_to_text:
  model_id: whisper-1
 text_to_speech:
@@ -14,7 +17,7 @@ text_to_speech:
  speed: 1.0
  response_format: opus
 image_generation:
-  model_id: dall-e-3
-  style: vivid
-  size: 1024x1024
-  quality: standard
+  model_id: gpt-image-1
+  style: null
+  size: null
+  quality: null
--- a/docs/screenshots/image-creation.webp
+++ b/docs/screenshots/image-creation.webp
--- a/docs/screenshots/image-editing-multiple-images.webp
+++ b/docs/screenshots/image-editing-multiple-images.webp
--- a/docs/screenshots/image-editing-single-image.webp
+++ b/docs/screenshots/image-editing-single-image.webp
--- a/docs/screenshots/image-generation.webp
+++ b/docs/screenshots/image-generation.webp
--- a/docs/screenshots/speech-to-text-transcribe-only-mode.webp
+++ b/docs/screenshots/speech-to-text-transcribe-only-mode.webp
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -11,6 +11,8 @@ This is related to the [💬 Text Generation](./features.md#-text-generation) fe

 If there's a text-generation handler agent configured, the bot **may** respond to messages sent in the room.

+Some models also support vision, so you may be able to mix text and images in the same conversation.
+
 See screenshots of:

 - 🖼️ [the default Text Generation flow](./screenshots/text-generation.webp) in 1:1 rooms
@@ -64,34 +66,48 @@ The speech-to-text feature triggers automatically by default, but can be adjuste
 If all your messages are in the same language, you can improve accuracy & latency by configuring the language (see [🦻 Speech-to-Text / 🔤 Language](./configuration/speech-to-text.md#-language)).


-### 🖌️ Image Generation
-
-This is related to the [🖌️ Image Generation](./features.md#️-image-generation) feature.
+### Image Generation

 This feature is not configurable at the moment. The configuration (size, quality, style) specified at the [🤖 agent](./agents.md) level will be used.

+Capabilities depend on the [☁️ provider](./providers.md) and model used.

-#### Generating images

-Simply send a command like `!bai image A beautiful sunset over the ocean` and the bot will start a threaded conversation and post an image based on your prompt.
+#### 🖌️ Creating images

-See a [🖼️ Screenshot of the Image Generation feature](./screenshots/image-generation.webp).
+Simply send a command like `!bai image create A beautiful sunset over the ocean` and the bot will start a threaded conversation and post an image based on your prompt.

-You can then, respond in the same message thread with:
+See a [🖼️ Screenshot of the Image Creation feature](./screenshots/image-creation.webp).
+
+You can then respond in the same message thread with:

 - more messages, to add more criteria to your prompt.
 - a message saying `again`, to generate one more image with the current prompt.


-#### Generating stickers
+#### 🎨 Editing images

-A variation of [generating images](#generating-images) is to generate "sticker images".
+Simply send a command like `!bai image edit Turn the following image into an anime-style drawing` and the bot will start a threaded conversation asking for more details.

-See a [🖼️ Screenshot of the Sticker Generation feature](./screenshots/sticker-generation.webp).
+See a [🖼️ Screenshot of the Image Editing feature (manipulating a single image)](./screenshots/image-editing-single-image.webp) and a [🖼️ Screenshot of the Image Editing feature (manipulating multiple images)](./screenshots/image-editing-multiple-images.webp).

-To generate a sticker, send a command like `!bai sticker A huge ramen bowl with lots of chashu and a mountain of beansprouts on top`.
+You can then respond in the same message thread with:

-The difference from [generating images](#generating-images) is that the bot will:
+- more messages, to add more criteria to your prompt.
+- one or more images, to provide the images that the bot will operate on.
+- a message saying `go`, to start the image generation process.
+- a message saying `again`, to prompt the bot to generate one more image edit with the current prompt.
+
+
+#### 🫵 Creating stickers
+
+A variation of [creating images](#creating-images) is creating "sticker images".
+
+See a [🖼️ Screenshot of the Sticker Creation feature](./screenshots/sticker-generation.webp).
+
+To create a sticker, send a command like `!bai sticker A huge ramen bowl with lots of chashu and a mountain of beansprouts on top`.
+
+The difference from [creating images](#creating-images) is that the bot will:

 - generate a smaller-resolution image (currently hardcoded to `256x256`) - smaller/quicker, but still good enough for a sticker
 - potentially switch to a different (cheaper or otherwise more suitable) model, if available
--- a/etc/app/config.yml.dist
+++ b/etc/app/config.yml.dist
@@ -32,6 +32,10 @@ user:
 # Command prefix. Leave empty to use the default (!bai).
 command_prefix: "!bai"

+room:
+  # Whether the bot should send an introduction message after joining a room.
+  post_join_self_introduction_enabled: true
+
 access:
  # Space-separated list of MXID patterns which specify who is an admin.
  admin_patterns:
@@ -72,11 +76,14 @@ agents:
    #     base_url: https://api.openai.com/v1
    #     api_key: ""
    #     text_generation:
-    #       model_id: gpt-4o
+    #       model_id: gpt-5.1
    #       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
-    #       max_response_tokens: 16384
-    #       max_context_tokens: 128000
+    #       # 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_context_tokens: 400000
    #     speech_to_text:
    #       model_id: whisper-1
    #     text_to_speech:
@@ -85,10 +92,10 @@ agents:
    #       speed: 1.0
    #       response_format: opus
    #     image_generation:
-    #       model_id: dall-e-3
-    #       style: vivid
-    #       size: 1024x1024
-    #       quality: standard
+    #       model_id: gpt-image-1
+    #       style: null
+    #       size: null
+    #       quality: null
    #
    # - id: localai
    #   provider: localai
--- a/etc/services/core/compose.yml
+++ b/etc/services/core/compose.yml
@@ -1,6 +1,6 @@
 services:
  postgres:
-    image: docker.io/postgres:16.4-alpine
+    image: docker.io/postgres:18.1-alpine
    user: ${UID}:${GID}
    restart: unless-stopped
    environment:
@@ -8,12 +8,13 @@ services:
     POSTGRES_PASSWORD: synapse-password
     POSTGRES_DB: homeserver
     POSTGRES_INITDB_ARGS: --lc-collate C --lc-ctype C --encoding UTF8
+     PGDATA: /data
    volumes:
-    - ./postgres:/var/lib/postgresql/data
+    - ./postgres:/data
    - /etc/passwd:/etc/passwd:ro

  synapse:
-    image: ghcr.io/element-hq/synapse:v1.118.0
+    image: ghcr.io/element-hq/synapse:v1.143.0
    user: "${UID}:${GID}"
    restart: unless-stopped
    entrypoint: python
@@ -26,14 +27,20 @@ services:
    - ./synapse/media-store:/media-store

  element-web:
-    image: docker.io/vectorim/element-web:v1.11.84
+    image: ghcr.io/element-hq/element-web:v1.12.4
    user: "${UID}:${GID}"
    restart: unless-stopped
+    environment:
+      ELEMENT_WEB_PORT: 8080
    ports:
      - "${SERVICE_ELEMENT_WEB_BIND_PORT_HTTP}:8080"
    volumes:
-    - ../../etc/services/core/element-web/nginx.conf:/etc/nginx/nginx.conf:ro
    - ../../etc/services/core/element-web/config.json:/app/config.json:ro
+    tmpfs:
+      - /var/cache/nginx:rw,mode=777
+      - /var/run:rw,mode=777
+      - /tmp/element-web-config:rw,mode=777
+      - /etc/nginx/conf.d:rw,mode=777

 networks:
  default:
--- a/etc/services/core/element-web/config.json
+++ b/etc/services/core/element-web/config.json
@@ -3,7 +3,7 @@
    "default_is_url": "https://vector.im",
    "integrations_ui_url": "https://scalar.vector.im/",
    "integrations_rest_url": "https://scalar.vector.im/api",
-    "bug_report_endpoint_url": "https://riot.im/bugreports/submit",
+    "bug_report_endpoint_url": "https://element.io/bugreports/submit",
    "enableLabs": true,
    "roomDirectory": {
        "servers": [
--- a/etc/services/core/element-web/nginx.conf
+++ b/etc/services/core/element-web/nginx.conf
@@ -1,60 +0,0 @@
-# This is a custom nginx configuration file that we use in the container (instead of the default one),
-# because it allows us to run nginx with a non-root user.
-#
-# For this to work, the default vhost file (`/etc/nginx/conf.d/default.conf`) also needs to be removed.
-# (mounting `/dev/null` over `/etc/nginx/conf.d/default.conf` works well)
-#
-# The following changes have been done compared to a default nginx configuration file:
-# - default server port is changed (80 -> 8080), so that a non-root user can bind it
-# - various temp paths are changed to `/tmp`, so that a non-root user can write to them
-# - the `user` directive was removed, as we don't want nginx to switch users
-
-worker_processes  1;
-
-error_log /var/log/nginx/error.log warn;
-pid /tmp/nginx.pid;
-
-
-events {
-	worker_connections  1024;
-}
-
-
-http {
-	client_body_temp_path /tmp/client_body_temp;
-	proxy_temp_path /tmp/proxy_temp;
-	fastcgi_temp_path /tmp/fastcgi_temp;
-	uwsgi_temp_path /tmp/uwsgi_temp;
-	scgi_temp_path /tmp/scgi_temp;
-
-	include       /etc/nginx/mime.types;
-	default_type  application/octet-stream;
-
-	log_format  main  '$remote_addr - $remote_user [$time_local] "$request" '
-					  '$status $body_bytes_sent "$http_referer" '
-					  '"$http_user_agent" "$http_x_forwarded_for"';
-
-	access_log  /var/log/nginx/access.log  main;
-
-	sendfile        on;
-	#tcp_nopush     on;
-
-	keepalive_timeout  65;
-
-	#gzip  on;
-
-	server {
-		listen       8080;
-		server_name  localhost;
-
-		location / {
-			root   /usr/share/nginx/html;
-			index  index.html index.htm;
-		}
-
-		error_page   500 502 503 504  /50x.html;
-		location = /50x.html {
-			root   /usr/share/nginx/html;
-		}
-	}
-}
--- a/etc/services/core/synapse/config/homeserver.yaml
+++ b/etc/services/core/synapse/config/homeserver.yaml
@@ -579,9 +579,7 @@ rc_login:
 #
 #federation_rr_transactions_per_room_per_second: 50

-# Authenticated media is not supported yet.
-# See: https://github.com/etkecc/baibot/issues/12
-enable_authenticated_media: false
+enable_authenticated_media: true

 # Directory where uploaded images and attachments are stored.
 #
--- a/etc/services/ollama/compose.yml
+++ b/etc/services/ollama/compose.yml
@@ -1,6 +1,6 @@
 services:
  ollama:
-    image: docker.io/ollama/ollama:0.4.1
+    image: docker.io/ollama/ollama:0.13.0
    restart: unless-stopped
    ports:
      - "${SERVICE_OLLAMA_BIND_PORT_HTTP}:11434"
--- a/4
+++ b/4
@@ -32,6 +32,10 @@ run-in-container *extra_args: app-container-prepare build-container-image-debug
 test *extra_args:
 	RUST_BACKTRACE=1 cargo test {{ extra_args }}

+# Formats the code
+fmt:
+	RUST_BACKTRACE=1 cargo fmt --all
+
 # Builds a debug binary (target/debug/*)
 build-debug *extra_args:
 	RUST_BACKTRACE=1 cargo build {{ extra_args }}
--- a/src/agent/instantiation.rs
+++ b/src/agent/instantiation.rs
@@ -1,6 +1,6 @@
 use super::{
-    provider::{self, ControllerType},
    AgentDefinition, AgentProvider, PublicIdentifier,
+    provider::{self, ControllerType},
 };

 // Dead-code is allowed. We do not use these enum struct payloads directly,
--- a/src/agent/manager.rs
+++ b/src/agent/manager.rs
@@ -1,7 +1,7 @@
-use super::instantiation;
-use super::instantiation::AgentInstance;
 use super::AgentDefinition;
 use super::PublicIdentifier;
+use super::instantiation;
+use super::instantiation::AgentInstance;
 use crate::entity::RoomConfigContext;

 #[derive(Debug)]
--- a/src/agent/mod.rs
+++ b/src/agent/mod.rs
@@ -11,11 +11,11 @@ pub use manager::Manager;

 pub use definition::AgentDefinition;

-pub use instantiation::create_from_provider_and_yaml_value_config;
-pub use instantiation::default_config_for_provider;
 pub use instantiation::AgentInstance;
 pub use instantiation::Error as AgentInstantiationError;
 pub use instantiation::Result as AgentInstantiationResult;
+pub use instantiation::create_from_provider_and_yaml_value_config;
+pub use instantiation::default_config_for_provider;

 pub use provider::{AgentProvider, AgentProviderInfo, ControllerTrait};
 pub use purpose::AgentPurpose;
--- a/src/agent/provider/anthropic/config.rs
+++ b/src/agent/provider/anthropic/config.rs
@@ -1,7 +1,5 @@
 use serde::{Deserialize, Serialize};

-use anthropic_rs::models::claude::ClaudeModel;
-
 use crate::agent::{default_prompt, provider::ConfigTrait};

 #[derive(Debug, Clone, Serialize, Deserialize)]
@@ -28,6 +26,9 @@ impl ConfigTrait for Config {
        if self.base_url.is_empty() {
            return Err("The base URL must not be empty.".to_owned());
        }
+        if !self.base_url.ends_with("/v1") {
+            return Err("The base URL must end with '/v1'.".to_owned());
+        }
        if self.api_key.is_empty() {
            return Err("The API key must not be empty.".to_owned());
        }
@@ -67,5 +68,5 @@ impl Default for TextGenerationConfig {
 }

 fn default_text_model_id() -> String {
-    ClaudeModel::Claude35Sonnet.as_str().to_owned()
+    "claude-3-7-sonnet-20250219".to_owned()
 }
--- a/src/agent/provider/anthropic/controller.rs
+++ b/src/agent/provider/anthropic/controller.rs
@@ -1,30 +1,28 @@
 use std::fmt::Debug;
-use std::str::FromStr;
 use std::sync::Arc;

-use anthropic_rs::completion::message::{ContentType, System};
-use anthropic_rs::{
-    client::Client as AnthropicClient, config::Config as AnthropicConfig,
-    models::claude::ClaudeModel,
-};
+use anthropic::client::{Client, ClientBuilder};
+use anthropic::types::ContentBlock;

 use super::super::ControllerTrait;
-use crate::agent::provider::entity::{
-    ImageGenerationResult, PingResult, TextGenerationParams, TextGenerationResult,
-    TextToSpeechParams, TextToSpeechResult,
-};
-use crate::agent::provider::{ImageGenerationParams, SpeechToTextParams, SpeechToTextResult};
 use crate::agent::AgentPurpose;
+use crate::agent::provider::entity::{
+    ImageEditResult, ImageGenerationResult, ImageSource, PingResult, TextGenerationParams,
+    TextGenerationResult, TextToSpeechParams, TextToSpeechResult,
+};
+use crate::agent::provider::{
+    ImageEditParams, ImageGenerationParams, SpeechToTextParams, SpeechToTextResult,
+};
 use crate::conversation::llm::{
-    shorten_messages_list_to_context_size, Author as LLMAuthor, Conversation as LLMConversation,
-    Message as LLMMessage,
+    Author as LLMAuthor, Conversation as LLMConversation, Message as LLMMessage,
+    MessageContent as LLMMessageContent, shorten_messages_list_to_context_size,
 };
 use crate::strings;

 use super::config::Config;

 struct ControllerInner {
-    client: AnthropicClient,
+    client: Client,
 }

 #[derive(Clone)]
@@ -43,18 +41,20 @@ impl Debug for Controller {

 impl Controller {
    pub fn new(config: Config) -> anyhow::Result<Self> {
-        let anthropic_config =
-            AnthropicConfig::new(config.api_key.clone()).with_base_url(config.base_url.clone());
-
-        let client = match AnthropicClient::new(anthropic_config) {
-            Ok(client) => client,
-            Err(err) => {
-                return Err(anyhow::anyhow!(
-                    "Failed to create Anthropic client: {}",
-                    err.to_string()
-                ));
+        // The previous library that we used expected a base URL that ends with "/v1"
+        // (e.g. "https://api.anthropic.com/v1"), while the new one doesn't.
+        //
+        // To keep backward compatibility, we don't ask people to change their configuration
+        // and rather adapt by removing the "/v1" from the base URL.
+        if !config.base_url.ends_with("/v1") {
+            return Err(anyhow::anyhow!("base_url must end with '/v1'"));
        }
-        };
+
+        let base_url = &config.base_url[..config.base_url.len() - 3];
+        let client = ClientBuilder::default()
+            .api_base(base_url.to_string())
+            .api_key(config.api_key.clone())
+            .build()?;

        Ok(Self {
            config,
@@ -71,7 +71,7 @@ impl ControllerTrait for Controller {

        let messages = vec![LLMMessage {
            author: LLMAuthor::User,
-            message_text: "Hello!".to_string(),
+            content: LLMMessageContent::Text("Hello!".to_string()),
            timestamp: chrono::Utc::now(),
        }];

@@ -108,7 +108,7 @@ impl ControllerTrait for Controller {
        } else {
            Some(LLMMessage {
                author: LLMAuthor::Prompt,
-                message_text: prompt_text,
+                content: LLMMessageContent::Text(prompt_text),
                timestamp: chrono::Utc::now(),
            })
        };
@@ -142,29 +142,19 @@ impl ControllerTrait for Controller {

        let mut request = super::utils::create_anthropic_message_request(conversation_messages);

-        let model = match ClaudeModel::from_str(&text_generation_config.model_id) {
-            Ok(model) => model,
-            Err(err) => {
-                tracing::debug!(?err, "Failed to parse model ID");
-
-                return Err(anyhow::anyhow!(
-                    "Failed to parse model ID: {}",
-                    &text_generation_config.model_id
-                ));
-            }
-        };
-
        let temperature = params
            .temperature_override
            .unwrap_or(text_generation_config.temperature);

        if let Some(prompt_message) = prompt_message {
-            request.system = Some(System::Text(prompt_message.message_text));
+            if let LLMMessageContent::Text(text) = &prompt_message.content {
+                request.system = text.clone();
+            }
        }

-        request.model = model;
-        request.temperature = Some(temperature);
-        request.max_tokens = text_generation_config.max_response_tokens;
+        request.model = text_generation_config.model_id.clone();
+        request.temperature = Some(temperature as f64);
+        request.max_tokens = text_generation_config.max_response_tokens as usize;

        if let Ok(request_as_json) = serde_json::to_string(&request) {
            tracing::trace!(
@@ -175,19 +165,20 @@ impl ControllerTrait for Controller {
            );
        }

-        let response = self.inner.client.create_message(request).await?;
+        let response = self.inner.client.messages(request).await?;

        tracing::trace!(?response, "Got response from Anthropic create message API");

        // response.content usually contains a single element, but we support handling multiple to account for all possibilities
        let mut text_parts = vec![];
        for content in response.content {
-            let content_type = content.content_type;
-
-            match content_type {
-                ContentType::Text => {
-                    text_parts.push(content.text);
-                } // There are no other content types to handle yet, but there may be in the future
+            match content {
+                ContentBlock::Text { text } => {
+                    text_parts.push(text);
+                }
+                ContentBlock::Image { .. } => {
+                    text_parts.push("The model responded with an image".to_string());
+                }
            }
        }

@@ -219,6 +210,15 @@ impl ControllerTrait for Controller {
        Err(anyhow::anyhow!("Image generation not supported"))
    }

+    async fn create_image_edit(
+        &self,
+        _prompt: &str,
+        _images: Vec<ImageSource>,
+        _params: ImageEditParams,
+    ) -> anyhow::Result<ImageEditResult> {
+        Err(anyhow::anyhow!("Image editing is not supported"))
+    }
+
    async fn text_to_speech(
        &self,
        _input: &str,
--- a/src/agent/provider/anthropic/mod.rs
+++ b/src/agent/provider/anthropic/mod.rs
@@ -7,8 +7,8 @@ pub use controller::Controller;

 use super::super::AgentInstantiationError;
 use super::super::AgentInstantiationResult;
-use super::controller::ControllerType;
 use super::ConfigTrait;
+use super::controller::ControllerType;

 pub fn create_controller_from_yaml_value_config(
    agent_id: &str,
--- a/src/agent/provider/anthropic/utils.rs
+++ b/src/agent/provider/anthropic/utils.rs
@@ -1,8 +1,12 @@
-use anthropic_rs::completion::message::{Content, ContentType, Message, MessageRequest, Role};
+use anthropic::types::{
+    ContentBlock, ImageSource, Message, MessagesRequest, MessagesRequestBuilder, Role,
+};

-use crate::conversation::llm::{Author as LLMAuthor, Message as LLMMessage};
+use crate::conversation::llm::{
+    Author as LLMAuthor, Message as LLMMessage, MessageContent as LLMMessageContent,
+};

-pub(super) fn create_anthropic_message_request(llm_messages: Vec<LLMMessage>) -> MessageRequest {
+pub(super) fn create_anthropic_message_request(llm_messages: Vec<LLMMessage>) -> MessagesRequest {
    let mut messages = vec![];

    for message in llm_messages {
@@ -14,19 +18,26 @@ pub(super) fn create_anthropic_message_request(llm_messages: Vec<LLMMessage>) ->
            }
        };

-        let content = vec![Content {
-            content_type: ContentType::Text,
-            text: message.message_text,
-        }];
+        let content = match &message.content {
+            LLMMessageContent::Text(text) => vec![ContentBlock::Text { text: text.clone() }],
+            LLMMessageContent::Image(image_details) => {
+                vec![ContentBlock::Image {
+                    source: ImageSource::Base64 {
+                        media_type: image_details.mime.to_string(),
+                        data: crate::utils::base64::base64_encode(&image_details.data),
+                    },
+                }]
+            }
+        };

        let message = Message { role, content };

        messages.push(message);
    }

-    MessageRequest {
-        stream: false,
-        messages,
-        ..Default::default()
-    }
+    MessagesRequestBuilder::default()
+        .messages(messages)
+        .stream(false)
+        .build()
+        .expect("Failed to build messages request")
 }
--- a/src/agent/provider/controller.rs
+++ b/src/agent/provider/controller.rs
@@ -1,11 +1,11 @@
 use crate::{agent::AgentPurpose, conversation::llm::Conversation};

 use super::{
+    ImageEditParams, ImageGenerationParams, SpeechToTextParams, SpeechToTextResult,
    entity::{
-        ImageGenerationResult, PingResult, TextGenerationParams, TextGenerationResult,
-        TextToSpeechParams, TextToSpeechResult,
+        ImageEditResult, ImageGenerationResult, ImageSource, PingResult, TextGenerationParams,
+        TextGenerationResult, TextToSpeechParams, TextToSpeechResult,
    },
-    ImageGenerationParams, SpeechToTextParams, SpeechToTextResult,
 };

 pub trait ControllerTrait {
@@ -42,6 +42,13 @@ pub trait ControllerTrait {
        params: ImageGenerationParams,
    ) -> impl std::future::Future<Output = anyhow::Result<ImageGenerationResult>> + Send;

+    fn create_image_edit(
+        &self,
+        prompt: &str,
+        images: Vec<ImageSource>,
+        params: ImageEditParams,
+    ) -> impl std::future::Future<Output = anyhow::Result<ImageEditResult>> + Send;
+
    fn text_to_speech(
        &self,
        text: &str,
@@ -166,6 +173,25 @@ impl ControllerTrait for ControllerType {
        }
    }

+    async fn create_image_edit(
+        &self,
+        prompt: &str,
+        images: Vec<ImageSource>,
+        params: ImageEditParams,
+    ) -> anyhow::Result<ImageEditResult> {
+        match &self {
+            ControllerType::OpenAI(controller) => {
+                controller.create_image_edit(prompt, images, params).await
+            }
+            ControllerType::OpenAICompat(controller) => {
+                controller.create_image_edit(prompt, images, params).await
+            }
+            ControllerType::Anthropic(controller) => {
+                controller.create_image_edit(prompt, images, params).await
+            }
+        }
+    }
+
    async fn text_to_speech(
        &self,
        text: &str,
--- a/src/agent/provider/entity/agent_provider.rs
+++ b/src/agent/provider/entity/agent_provider.rs
@@ -67,9 +67,8 @@ impl AgentProvider {
                wiki_url: Some("https://en.wikipedia.org/wiki/Anthropic"),
                sign_up_url: Some("https://console.anthropic.com/"),
                models_list_url: Some("https://docs.anthropic.com/en/docs/about-claude/models"),
-                supported_purposes: vec![
-                    AgentPurpose::TextGeneration,
-                ],
+                supported_purposes: vec![AgentPurpose::TextGeneration],
+                text_generation_supports_vision: true,
            },
            Self::Groq => AgentProviderInfo {
                id: Self::Groq.to_static_str(),
@@ -79,10 +78,8 @@ impl AgentProvider {
                wiki_url: Some("https://en.wikipedia.org/wiki/Groq"),
                sign_up_url: Some("https://console.groq.com/login"),
                models_list_url: Some("https://console.groq.com/docs/models"),
-                supported_purposes: vec![
-                    AgentPurpose::TextGeneration,
-                    AgentPurpose::SpeechToText,
-                ],
+                supported_purposes: vec![AgentPurpose::TextGeneration, AgentPurpose::SpeechToText],
+                text_generation_supports_vision: false,
            },
            Self::LocalAI => AgentProviderInfo {
                id: Self::LocalAI.to_static_str(),
@@ -97,6 +94,7 @@ impl AgentProvider {
                    AgentPurpose::TextToSpeech,
                    AgentPurpose::SpeechToText,
                ],
+                text_generation_supports_vision: false,
            },
            Self::Mistral => AgentProviderInfo {
                id: Self::Mistral.to_static_str(),
@@ -106,9 +104,8 @@ impl AgentProvider {
                wiki_url: Some("https://en.wikipedia.org/wiki/Mistral_AI"),
                sign_up_url: Some("https://auth.mistral.ai/ui/registration"),
                models_list_url: Some("https://docs.mistral.ai/getting-started/models/"),
-                supported_purposes: vec![
-                    AgentPurpose::TextGeneration,
-                ],
+                supported_purposes: vec![AgentPurpose::TextGeneration],
+                text_generation_supports_vision: false,
            },
            Self::Ollama => AgentProviderInfo {
                id: Self::Ollama.to_static_str(),
@@ -118,9 +115,8 @@ impl AgentProvider {
                wiki_url: None,
                sign_up_url: None,
                models_list_url: Some("https://ollama.com/library"),
-                supported_purposes: vec![
-                    AgentPurpose::TextGeneration,
-                ],
+                supported_purposes: vec![AgentPurpose::TextGeneration],
+                text_generation_supports_vision: false,
            },
            Self::OpenAI => AgentProviderInfo {
                id: Self::OpenAI.to_static_str(),
@@ -136,6 +132,7 @@ impl AgentProvider {
                    AgentPurpose::TextToSpeech,
                    AgentPurpose::SpeechToText,
                ],
+                text_generation_supports_vision: true,
            },
            Self::OpenAICompat => AgentProviderInfo {
                id: Self::OpenAICompat.to_static_str(),
@@ -151,6 +148,7 @@ impl AgentProvider {
                    AgentPurpose::TextToSpeech,
                    AgentPurpose::SpeechToText,
                ],
+                text_generation_supports_vision: false,
            },
            Self::OpenRouter => AgentProviderInfo {
                id: Self::OpenRouter.to_static_str(),
@@ -160,9 +158,8 @@ impl AgentProvider {
                wiki_url: None,
                sign_up_url: Some("https://openrouter.ai/"),
                models_list_url: Some("https://openrouter.ai/models"),
-                supported_purposes: vec![
-                    AgentPurpose::TextGeneration,
-                ],
+                supported_purposes: vec![AgentPurpose::TextGeneration],
+                text_generation_supports_vision: false,
            },
            Self::TogetherAI => AgentProviderInfo {
                id: Self::TogetherAI.to_static_str(),
@@ -172,9 +169,8 @@ impl AgentProvider {
                wiki_url: None,
                sign_up_url: Some("https://api.together.ai/signup"),
                models_list_url: Some("https://api.together.xyz/models"),
-                supported_purposes: vec![
-                    AgentPurpose::TextGeneration,
-                ],
+                supported_purposes: vec![AgentPurpose::TextGeneration],
+                text_generation_supports_vision: false,
            },
        }
    }
@@ -195,4 +191,5 @@ pub struct AgentProviderInfo {
    pub sign_up_url: Option<&'static str>,
    pub models_list_url: Option<&'static str>,
    pub supported_purposes: Vec<AgentPurpose>,
+    pub text_generation_supports_vision: bool,
 }
--- a/src/agent/provider/entity/image_generation.rs
+++ b/src/agent/provider/entity/image_generation.rs
@@ -1,3 +1,5 @@
+use mxlink::mime;
+
 #[derive(Default)]
 pub struct ImageGenerationParams {
    pub size_override: Option<String>,
@@ -26,6 +28,40 @@ impl ImageGenerationParams {

 pub struct ImageGenerationResult {
    pub bytes: Vec<u8>,
-    pub mime_type: mxlink::mime::Mime,
+    pub mime_type: mime::Mime,
    pub revised_prompt: Option<String>,
 }
+
+#[derive(Default)]
+pub struct ImageEditParams {}
+
+pub struct ImageEditResult {
+    pub bytes: Vec<u8>,
+    pub mime_type: mime::Mime,
+}
+
+pub struct ImageSource {
+    pub filename: String,
+    pub bytes: Vec<u8>,
+    pub mime_type: mime::Mime,
+}
+
+impl ImageSource {
+    pub fn new(filename: String, bytes: Vec<u8>, mime_type: mime::Mime) -> Self {
+        Self {
+            filename,
+            bytes,
+            mime_type,
+        }
+    }
+}
+
+impl From<ImageSource> for async_openai::types::ImageInput {
+    fn from(value: ImageSource) -> Self {
+        async_openai::types::ImageInput::from_vec_u8(
+            value.filename,
+            value.bytes,
+            value.mime_type.to_string(),
+        )
+    }
+}
--- a/src/agent/provider/entity/mod.rs
+++ b/src/agent/provider/entity/mod.rs
@@ -1,12 +1,14 @@
 mod agent_provider;
-mod image_generation;
+mod image;
 mod ping;
 mod speech_to_text;
 mod text_generation;
 mod text_to_speech;

 pub use agent_provider::{AgentProvider, AgentProviderInfo};
-pub use image_generation::{ImageGenerationParams, ImageGenerationResult};
+pub use image::{
+    ImageEditParams, ImageEditResult, ImageGenerationParams, ImageGenerationResult, ImageSource,
+};
 pub use ping::PingResult;
 pub use speech_to_text::{SpeechToTextParams, SpeechToTextResult};
 pub use text_generation::{
--- a/src/agent/provider/mod.rs
+++ b/src/agent/provider/mod.rs
@@ -20,6 +20,7 @@ pub use controller::{ControllerTrait, ControllerType};
 pub use config::ConfigTrait;

 pub use entity::{
-    AgentProvider, AgentProviderInfo, ImageGenerationParams, PingResult, SpeechToTextParams,
-    SpeechToTextResult, TextGenerationParams, TextGenerationPromptVariables, TextToSpeechParams,
+    AgentProvider, AgentProviderInfo, ImageEditParams, ImageGenerationParams, ImageSource,
+    PingResult, SpeechToTextParams, SpeechToTextResult, TextGenerationParams,
+    TextGenerationPromptVariables, TextToSpeechParams,
 };
--- a/src/agent/provider/openai/config.rs
+++ b/src/agent/provider/openai/config.rs
@@ -1,5 +1,6 @@
 use serde::{Deserialize, Serialize};

+use super::OPENAI_IMAGE_MODEL_GPT_IMAGE_1;
 use crate::agent::{default_prompt, provider::ConfigTrait};

 #[derive(Debug, Clone, Serialize, Deserialize)]
@@ -58,6 +59,9 @@ pub struct TextGenerationConfig {
    #[serde(default)]
    pub max_response_tokens: Option<u32>,

+    #[serde(default)]
+    pub max_completion_tokens: Option<u32>,
+
    #[serde(default)]
    pub max_context_tokens: u32,
 }
@@ -68,14 +72,15 @@ impl Default for TextGenerationConfig {
            model_id: default_text_model_id(),
            prompt: Some(default_prompt().to_owned()),
            temperature: super::super::default_temperature(),
-            max_response_tokens: Some(16_384),
-            max_context_tokens: 128_000,
+            max_response_tokens: None,
+            max_completion_tokens: Some(128_000),
+            max_context_tokens: 400_000,
        }
    }
 }

 fn default_text_model_id() -> String {
-    "gpt-4o".to_owned()
+    "gpt-5.1".to_owned()
 }

 #[derive(Debug, Clone, Serialize, Deserialize)]
@@ -145,19 +150,19 @@ pub struct ImageGenerationConfig {
    pub model_id: String,

    #[serde(default = "default_image_style")]
-    pub style: async_openai::types::ImageStyle,
+    pub style: Option<async_openai::types::ImageStyle>,

    #[serde(default = "default_image_size")]
-    pub size: async_openai::types::ImageSize,
+    pub size: Option<async_openai::types::ImageSize>,

    #[serde(default = "default_image_quality")]
-    pub quality: async_openai::types::ImageQuality,
+    pub quality: Option<async_openai::types::ImageQuality>,
 }

 impl Default for ImageGenerationConfig {
    fn default() -> Self {
        Self {
-            model_id: "dall-e-3".to_owned(),
+            model_id: OPENAI_IMAGE_MODEL_GPT_IMAGE_1.to_owned(),
            style: default_image_style(),
            size: default_image_size(),
            quality: default_image_quality(),
@@ -177,14 +182,14 @@ impl ImageGenerationConfig {
    }
 }

-fn default_image_style() -> async_openai::types::ImageStyle {
-    async_openai::types::ImageStyle::Vivid
+fn default_image_style() -> Option<async_openai::types::ImageStyle> {
+    None
 }

-fn default_image_size() -> async_openai::types::ImageSize {
-    async_openai::types::ImageSize::S1024x1024
+fn default_image_size() -> Option<async_openai::types::ImageSize> {
+    None
 }

-fn default_image_quality() -> async_openai::types::ImageQuality {
-    async_openai::types::ImageQuality::Standard
+fn default_image_quality() -> Option<async_openai::types::ImageQuality> {
+    None
 }
--- a/src/agent/provider/openai/controller.rs
+++ b/src/agent/provider/openai/controller.rs
@@ -1,41 +1,45 @@
 use std::ops::Deref;

 use async_openai::{
+    Client as OpenAIClient,
    config::OpenAIConfig,
    types::{
-        ChatCompletionRequestMessage, CreateChatCompletionRequestArgs, CreateImageRequestArgs,
-        CreateSpeechRequestArgs, CreateTranscriptionRequestArgs,
+        ChatCompletionRequestMessage, CreateChatCompletionRequestArgs, CreateImageEditRequestArgs,
+        CreateImageRequestArgs, CreateSpeechRequestArgs, CreateTranscriptionRequestArgs,
+        DallE2ImageSize, Image, ImageModel, ImageResponseFormat,
    },
-    Client as OpenAIClient,
 };

 use super::super::ControllerTrait;
 use crate::{
-    agent::{
-        provider::{
-            entity::{ImageGenerationResult, PingResult, TextToSpeechParams, TextToSpeechResult},
-            openai::utils::convert_string_to_enum,
+    agent::provider::{
+        ImageEditParams, ImageGenerationParams, SpeechToTextParams, SpeechToTextResult,
+        entity::{TextGenerationParams, TextGenerationResult},
    },
-        AgentPurpose,
+    conversation::llm::{
+        Author as LLMAuthor, Conversation as LLMConversation, Message as LLMMessage,
+        MessageContent as LLMMessageContent, shorten_messages_list_to_context_size,
    },
-    strings,
+    utils::base64::base64_decode,
 };
 use crate::{
    agent::{
+        AgentPurpose,
        provider::{
-            entity::{TextGenerationParams, TextGenerationResult},
-            ImageGenerationParams, SpeechToTextParams, SpeechToTextResult,
+            entity::{
+                ImageEditResult, ImageGenerationResult, ImageSource, PingResult,
+                TextToSpeechParams, TextToSpeechResult,
            },
-        utils::base64_decode,
+            openai::utils::convert_string_to_enum,
        },
-    conversation::llm::{
-        shorten_messages_list_to_context_size, Author as LLMAuthor,
-        Conversation as LLMConversation, Message as LLMMessage,
    },
+    strings,
 };

 use super::config::Config;

+use super::OPENAI_IMAGE_MODEL_GPT_IMAGE_1;
+
 #[derive(Debug, Clone)]
 pub struct Controller {
    config: Config,
@@ -62,7 +66,7 @@ impl ControllerTrait for Controller {

        let messages = vec![LLMMessage {
            author: LLMAuthor::User,
-            message_text: "Hello!".to_string(),
+            content: LLMMessageContent::Text("Hello!".to_string()),
            timestamp: chrono::Utc::now(),
        }];

@@ -99,7 +103,7 @@ impl ControllerTrait for Controller {
        } else {
            Some(LLMMessage {
                author: LLMAuthor::Prompt,
-                message_text: prompt_text,
+                content: LLMMessageContent::Text(prompt_text),
                timestamp: chrono::Utc::now(),
            })
        };
@@ -144,6 +148,10 @@ impl ControllerTrait for Controller {
            request_builder.max_tokens(max_response_tokens);
        }

+        if let Some(max_completion_tokens) = text_generation_config.max_completion_tokens {
+            request_builder.max_completion_tokens(max_completion_tokens);
+        }
+
        let request = request_builder.build()?;

        if let Ok(request_as_json) = serde_json::to_string(&request) {
@@ -201,12 +209,11 @@ impl ControllerTrait for Controller {

        let request = CreateTranscriptionRequestArgs::default()
            .model(&speech_to_text_config.model_id)
-            .file(async_openai::types::AudioInput {
-                source: async_openai::types::InputSource::VecU8 {
+            .file(async_openai::types::AudioInput::from_vec_u8(
                filename,
-                    vec: media,
-                },
-            })
+                media,
+                mime_type.to_string(),
+            ))
            .language(language.clone())
            .build()?;

@@ -261,12 +268,15 @@ impl ControllerTrait for Controller {
        let quality = if params.cheaper_quality_switching_allowed {
            // Switch to a cheaper quality
            match &image_generation_config.quality {
+                Some(quality) => match quality {
                    async_openai::types::ImageQuality::Standard => {
-                    async_openai::types::ImageQuality::Standard
+                        Some(async_openai::types::ImageQuality::Standard)
                    }
                    async_openai::types::ImageQuality::HD => {
-                    async_openai::types::ImageQuality::Standard
+                        Some(async_openai::types::ImageQuality::Standard)
                    }
+                },
+                None => None,
            }
        } else {
            image_generation_config.quality.clone()
@@ -274,20 +284,41 @@ impl ControllerTrait for Controller {

        let size = params
            .size_override
-            .map(|s| {
-                convert_string_to_enum::<async_openai::types::ImageSize>(&s)
-                    .unwrap_or(image_generation_config.size)
-            })
-            .unwrap_or(image_generation_config.size);
+            .map(|s| convert_string_to_enum::<async_openai::types::ImageSize>(&s).unwrap())
+            .or(image_generation_config.size);

-        let request = CreateImageRequestArgs::default()
-            .model(model)
-            .prompt(prompt.to_owned())
-            .response_format(async_openai::types::ImageResponseFormat::B64Json)
-            .size(size)
-            .style(image_generation_config.style.clone())
-            .quality(quality)
-            .build()?;
+        let response_format = match model.clone() {
+            ImageModel::DallE2 => Some(ImageResponseFormat::B64Json),
+            ImageModel::DallE3 => Some(ImageResponseFormat::B64Json),
+            ImageModel::Other(model_str) => match model_str.as_str() {
+                // gpt-image-1 only outputs base64 and we don't need to specify the response format.
+                // In fact, specifying the response format results in an error.
+                OPENAI_IMAGE_MODEL_GPT_IMAGE_1 => None,
+                _ => Some(ImageResponseFormat::B64Json),
+            },
+        };
+
+        let mut request_builder = CreateImageRequestArgs::default();
+
+        request_builder.model(model).prompt(prompt.to_owned());
+
+        if let Some(response_format) = response_format {
+            request_builder.response_format(response_format);
+        }
+
+        if let Some(style) = &image_generation_config.style {
+            request_builder.style(style.clone());
+        }
+
+        if let Some(quality) = quality {
+            request_builder.quality(quality.clone());
+        }
+
+        if let Some(size) = size {
+            request_builder.size(size);
+        }
+
+        let request = request_builder.build()?;

        tracing::trace!(
            ?prompt,
@@ -325,6 +356,104 @@ impl ControllerTrait for Controller {
        ))
    }

+    async fn create_image_edit(
+        &self,
+        prompt: &str,
+        images: Vec<ImageSource>,
+        _params: ImageEditParams,
+    ) -> anyhow::Result<ImageEditResult> {
+        let Some(image_generation_config) = &self.config.image_generation else {
+            return Err(anyhow::anyhow!(
+                strings::agent::no_configuration_for_purpose_so_cannot_be_used(
+                    &AgentPurpose::ImageGeneration
+                ),
+            ));
+        };
+
+        if images.is_empty() {
+            return Err(anyhow::anyhow!("No image sources provided"));
+        }
+
+        let mut image_inputs = Vec::new();
+        for image in images {
+            image_inputs.push(image.into());
+        }
+
+        let dalle2_size = match image_generation_config.size {
+            Some(async_openai::types::ImageSize::S256x256) => Some(DallE2ImageSize::S256x256),
+            Some(async_openai::types::ImageSize::S512x512) => Some(DallE2ImageSize::S512x512),
+            Some(async_openai::types::ImageSize::S1024x1024) => Some(DallE2ImageSize::S1024x1024),
+            _ => None,
+        };
+
+        let model = image_generation_config
+            .model_id_as_openai_image_model()
+            .map_err(|err| anyhow::anyhow!(err))?;
+
+        let response_format = match model.clone() {
+            async_openai::types::ImageModel::DallE2 => {
+                Some(async_openai::types::ImageResponseFormat::B64Json)
+            }
+            async_openai::types::ImageModel::DallE3 => {
+                Some(async_openai::types::ImageResponseFormat::B64Json)
+            }
+            async_openai::types::ImageModel::Other(model_str) => match model_str.as_str() {
+                OPENAI_IMAGE_MODEL_GPT_IMAGE_1 => None,
+                _ => Some(async_openai::types::ImageResponseFormat::B64Json),
+            },
+        };
+
+        let mut request_builder = CreateImageEditRequestArgs::default();
+
+        request_builder
+            .image(image_inputs)
+            .prompt(prompt.to_owned())
+            .model(model);
+
+        if let Some(size) = dalle2_size {
+            request_builder.size(size);
+        }
+
+        if let Some(response_format) = response_format {
+            request_builder.response_format(response_format);
+        }
+
+        let request = request_builder
+            .build()
+            .map_err(|e| anyhow::anyhow!("Failed to build CreateImageEditRequest: {}", e))?;
+
+        tracing::trace!(
+            model = format!("{:?}", request.model),
+            size = format!("{:?}", request.size),
+            response_format = format!("{:?}", request.response_format),
+            "Sending OpenAI image edit API request"
+        );
+
+        let response = self.client.images().create_edit(request).await?;
+
+        if let Some(image_data) = response.data.into_iter().next() {
+            match image_data.deref() {
+                Image::B64Json { b64_json, .. } => {
+                    let bytes = base64_decode(b64_json)?;
+                    return Ok(ImageEditResult {
+                        bytes,
+                        mime_type: mxlink::mime::IMAGE_PNG,
+                    });
+                }
+                Image::Url { url, .. } => {
+                    tracing::warn!(?url, "Received URL instead of B64Json for image edit");
+                    return Err(anyhow::anyhow!(
+                        "Unexpected image type (URL) when B64Json was requested"
+                    ));
+                }
+            }
+        }
+
+        Err(anyhow::anyhow!(
+            "The OpenAI image edit API returned no images"
+        ))
+    }
+
    async fn text_to_speech(
        &self,
        input: &str,
--- a/src/agent/provider/openai/mod.rs
+++ b/src/agent/provider/openai/mod.rs
@@ -13,8 +13,10 @@ pub(super) use config::TextToSpeechConfig;

 use super::super::AgentInstantiationError;
 use super::super::AgentInstantiationResult;
-use super::controller::ControllerType;
 use super::ConfigTrait;
+use super::controller::ControllerType;
+
+pub const OPENAI_IMAGE_MODEL_GPT_IMAGE_1: &str = "gpt-image-1";

 pub fn create_controller_from_yaml_value_config(
    agent_id: &str,
--- a/src/agent/provider/openai/utils.rs
+++ b/src/agent/provider/openai/utils.rs
@@ -1,9 +1,14 @@
 use async_openai::types::{
    ChatCompletionRequestAssistantMessageArgs, ChatCompletionRequestMessage,
-    ChatCompletionRequestSystemMessageArgs, ChatCompletionRequestUserMessageArgs,
+    ChatCompletionRequestMessageContentPartImage, ChatCompletionRequestSystemMessageArgs,
+    ChatCompletionRequestUserMessageArgs, ChatCompletionRequestUserMessageContent,
+    ChatCompletionRequestUserMessageContentPart, ImageUrlArgs,
 };

-use crate::conversation::llm::{Author as LLMAuthor, Message as LLMMessage};
+use crate::conversation::llm::{
+    Author as LLMAuthor, Message as LLMMessage, MessageContent as LLMMessageContent,
+};
+use crate::utils::base64::base64_encode;

 pub fn convert_llm_messages_to_openai_messages(
    conversation_messages: Vec<LLMMessage>,
@@ -12,29 +17,71 @@ pub fn convert_llm_messages_to_openai_messages(
        Vec::with_capacity(conversation_messages.len());

    for message in conversation_messages {
-        openai_conversation_messages.push(convert_llm_message_to_openai_message(message));
+        let openai_message = convert_llm_message_to_openai_message(message);
+        if let Some(openai_message) = openai_message {
+            openai_conversation_messages.push(openai_message);
+        }
    }

    openai_conversation_messages
 }

-fn convert_llm_message_to_openai_message(llm_message: LLMMessage) -> ChatCompletionRequestMessage {
-    match llm_message.author {
+fn convert_llm_message_to_openai_message(
+    llm_message: LLMMessage,
+) -> Option<ChatCompletionRequestMessage> {
+    match &llm_message.content {
+        LLMMessageContent::Text(text) => Some(match llm_message.author {
            LLMAuthor::Prompt => ChatCompletionRequestSystemMessageArgs::default()
-            .content(llm_message.message_text)
+                .content(text.clone())
                .build()
                .expect("Failed building OpenAI system message")
                .into(),
            LLMAuthor::Assistant => ChatCompletionRequestAssistantMessageArgs::default()
-            .content(llm_message.message_text)
+                .content(text.clone())
                .build()
                .expect("Failed building OpenAI assistant message")
                .into(),
            LLMAuthor::User => ChatCompletionRequestUserMessageArgs::default()
-            .content(llm_message.message_text)
+                .content(text.clone())
                .build()
                .expect("Failed building OpenAI user message")
                .into(),
+        }),
+        LLMMessageContent::Image(image_details) => {
+            let image_url = format!(
+                "data:{};base64,{}",
+                image_details.mime,
+                base64_encode(&image_details.data)
+            );
+
+            let part = ChatCompletionRequestUserMessageContentPart::ImageUrl(
+                ChatCompletionRequestMessageContentPartImage {
+                    image_url: ImageUrlArgs::default()
+                        .url(image_url)
+                        .build()
+                        .expect("Failed building OpenAI image url"),
+                },
+            );
+
+            let message_content = ChatCompletionRequestUserMessageContent::Array(vec![part]);
+
+            match llm_message.author {
+                LLMAuthor::User => Some(
+                    ChatCompletionRequestUserMessageArgs::default()
+                        .content(message_content)
+                        .build()
+                        .expect("Failed building OpenAI user message")
+                        .into(),
+                ),
+                _ => {
+                    tracing::warn!(
+                        "OpenAI API does not support image content for messages authored by {:?}. This message part will be skipped.",
+                        llm_message.author
+                    );
+                    None
+                }
+            }
+        }
    }
 }

--- a/src/agent/provider/openai_compat/config.rs
+++ b/src/agent/provider/openai_compat/config.rs
@@ -93,6 +93,7 @@ impl TryInto<OpenAITextGenerationConfig> for TextGenerationConfig {
            prompt: self.prompt,
            temperature: self.temperature,
            max_response_tokens: self.max_response_tokens,
+            max_completion_tokens: None,
            max_context_tokens: self.max_context_tokens,
        })
    }
@@ -223,21 +224,27 @@ impl TryInto<OpenAIImageGenerationConfig> for ImageGenerationConfig {

    fn try_into(self) -> Result<OpenAIImageGenerationConfig, Self::Error> {
        let size = if let Some(size) = &self.size {
-            convert_string_to_enum::<async_openai::types::ImageSize>(size)?
+            Some(convert_string_to_enum::<async_openai::types::ImageSize>(
+                size,
+            )?)
        } else {
-            async_openai::types::ImageSize::S1024x1024
+            None
        };

        let style = if let Some(style) = &self.style {
-            convert_string_to_enum::<async_openai::types::ImageStyle>(style)?
+            Some(convert_string_to_enum::<async_openai::types::ImageStyle>(
+                style,
+            )?)
        } else {
-            async_openai::types::ImageStyle::Vivid
+            None
        };

        let quality = if let Some(quality) = &self.quality {
-            convert_string_to_enum::<async_openai::types::ImageQuality>(quality)?
+            Some(convert_string_to_enum::<async_openai::types::ImageQuality>(
+                quality,
+            )?)
        } else {
-            async_openai::types::ImageQuality::Standard
+            None
        };

        Ok(OpenAIImageGenerationConfig {
--- a/src/agent/provider/openai_compat/controller.rs
+++ b/src/agent/provider/openai_compat/controller.rs
@@ -4,23 +4,25 @@ use etke_openai_api_rust::images::{ImagesApi, ImagesBody};
 use etke_openai_api_rust::{Auth, Message, OpenAI};

 use super::super::ControllerTrait;
-use crate::agent::utils::base64_decode;
+use crate::utils::base64::base64_decode;
 use crate::{
    agent::provider::{
+        ImageEditParams, ImageGenerationParams, ImageSource, SpeechToTextParams,
+        SpeechToTextResult,
        entity::{TextGenerationParams, TextGenerationResult},
-        ImageGenerationParams, SpeechToTextParams, SpeechToTextResult,
    },
    conversation::llm::{
-        shorten_messages_list_to_context_size, Author as LLMAuthor,
-        Conversation as LLMConversation, Message as LLMMessage,
+        Author as LLMAuthor, Conversation as LLMConversation, Message as LLMMessage,
+        MessageContent as LLMMessageContent, shorten_messages_list_to_context_size,
    },
 };
 use crate::{
    agent::{
-        provider::entity::{
-            ImageGenerationResult, PingResult, TextToSpeechParams, TextToSpeechResult,
-        },
        AgentPurpose,
+        provider::entity::{
+            ImageEditResult, ImageGenerationResult, PingResult, TextToSpeechParams,
+            TextToSpeechResult,
+        },
    },
    strings,
 };
@@ -60,7 +62,7 @@ impl ControllerTrait for Controller {

        let messages = vec![LLMMessage {
            author: LLMAuthor::User,
-            message_text: "Hello!".to_string(),
+            content: LLMMessageContent::Text("Hello!".to_string()),
            timestamp: chrono::Utc::now(),
        }];

@@ -97,7 +99,7 @@ impl ControllerTrait for Controller {
        } else {
            Some(LLMMessage {
                author: LLMAuthor::Prompt,
-                message_text: prompt_text,
+                content: LLMMessageContent::Text(prompt_text),
                timestamp: chrono::Utc::now(),
            })
        };
@@ -366,6 +368,17 @@ impl ControllerTrait for Controller {
        ))
    }

+    async fn create_image_edit(
+        &self,
+        _prompt: &str,
+        _images: Vec<ImageSource>,
+        _params: ImageEditParams,
+    ) -> anyhow::Result<ImageEditResult> {
+        Err(anyhow::anyhow!(
+            "The OpenAI image edit API is not supported by the OpenAI-compat provider"
+        ))
+    }
+
    async fn text_to_speech(
        &self,
        input: &str,
--- a/src/agent/provider/openai_compat/mod.rs
+++ b/src/agent/provider/openai_compat/mod.rs
@@ -21,8 +21,8 @@ pub use controller::Controller;

 use super::super::AgentInstantiationError;
 use super::super::AgentInstantiationResult;
-use super::controller::ControllerType;
 use super::ConfigTrait;
+use super::controller::ControllerType;

 pub fn create_controller_from_yaml_value_config(
    agent_id: &str,
--- a/src/agent/provider/openai_compat/utils.rs
+++ b/src/agent/provider/openai_compat/utils.rs
@@ -2,7 +2,9 @@ use etke_openai_api_rust::{Message, Role};

 use crate::agent::provider::openai::Config as OpenAIConfig;

-use crate::conversation::llm::{Author as LLMAuthor, Message as LLMMessage};
+use crate::conversation::llm::{
+    Author as LLMAuthor, Message as LLMMessage, MessageContent as LLMMessageContent,
+};

 pub fn convert_llm_messages_to_openai_messages(
    conversation_messages: Vec<LLMMessage>,
@@ -11,22 +13,33 @@ pub fn convert_llm_messages_to_openai_messages(
        Vec::with_capacity(conversation_messages.len());

    for message in conversation_messages {
-        openai_conversation_messages.push(convert_llm_message_to_openai_message(message));
+        let openai_message = convert_llm_message_to_openai_message(message);
+        if let Some(openai_message) = openai_message {
+            openai_conversation_messages.push(openai_message);
+        }
    }

    openai_conversation_messages
 }

-fn convert_llm_message_to_openai_message(llm_message: LLMMessage) -> Message {
+fn convert_llm_message_to_openai_message(llm_message: LLMMessage) -> Option<Message> {
    let role = match llm_message.author {
        LLMAuthor::Prompt => Role::System,
        LLMAuthor::Assistant => Role::Assistant,
        LLMAuthor::User => Role::User,
    };

-    Message {
+    match &llm_message.content {
+        LLMMessageContent::Text(text) => Some(Message {
            role,
-        content: llm_message.message_text,
+            content: text.clone(),
+        }),
+        LLMMessageContent::Image(_image_details) => {
+            tracing::warn!(
+                "The OpenAI-compat provider's library does not support image content. This image message will be skipped."
+            );
+            None
+        }
    }
 }

--- a/src/agent/utils.rs
+++ b/src/agent/utils.rs
@@ -1,5 +1,3 @@
-use base64::{engine::general_purpose::STANDARD, Engine as _};
-
 use crate::{
    agent::{
        AgentInstance, AgentPurpose, ControllerTrait, Manager as AgentManager, PublicIdentifier,
@@ -140,7 +138,3 @@ async fn get_global_agent_id_for_purpose(
        .handler
        .get_by_purpose_with_catch_all_fallback(purpose)
 }
-
-pub(crate) fn base64_decode(base64_string: &str) -> Result<Vec<u8>, base64::DecodeError> {
-    STANDARD.decode(base64_string)
-}
--- a/src/bot/implementation.rs
+++ b/src/bot/implementation.rs
@@ -1,11 +1,12 @@
 use std::sync::Arc;
 use std::{future::Future, pin::Pin};

+use mxlink::matrix_sdk::Room;
 use mxlink::matrix_sdk::media::{MediaFormat, MediaRequestParameters};
 use mxlink::matrix_sdk::ruma::{
-    events::room::MediaSource, MilliSecondsSinceUnixEpoch, OwnedUserId,
+    MilliSecondsSinceUnixEpoch, OwnedUserId, events::room::MediaSource,
 };
-use mxlink::matrix_sdk::Room;
+use mxlink::matrix_sdk::ruma::api::client::profile::{AvatarUrl, DisplayName};

 use mxlink::{
    InitConfig, LoginConfig, LoginCredentials, LoginEncryption, MatrixLink, PersistenceConfig,
@@ -140,6 +141,10 @@ impl Bot {
        &self.inner.config.command_prefix
    }

+    pub(crate) fn post_join_self_introduction_enabled(&self) -> bool {
+        self.inner.config.room.post_join_self_introduction_enabled
+    }
+
    pub(crate) fn homeserver_name(&self) -> &str {
        &self.inner.config.homeserver.server_name
    }
@@ -281,24 +286,27 @@ impl Bot {
    async fn do_prepare_profile(&self) -> anyhow::Result<()> {
        tracing::debug!("Preparing profile..");

+        let desired_display_name = self.inner.config.user.name.clone();
+
        let account = self.inner.matrix_link.client().account();
        let media = self.inner.matrix_link.client().media();

-        let desired_display_name = self.inner.config.user.name.clone();
-
        let profile = account
            .fetch_user_profile()
            .await
            .map_err(|e| anyhow::anyhow!("Failed fetching profile: {:?}", e))?;

-        let should_update_display_name = match &profile.displayname {
+        let current_display_name = profile.get_static::<DisplayName>()?;
+        let current_avatar_url = profile.get_static::<AvatarUrl>()?;
+
+        let should_update_display_name = match &current_display_name {
            Some(displayname) => displayname != &desired_display_name,
            None => true,
        };

        if should_update_display_name {
            tracing::info!(
-                ?profile.displayname,
+                ?current_display_name,
                ?desired_display_name,
                "Updating display name.."
            );
@@ -308,7 +316,7 @@ impl Bot {
            }
        }

-        let should_update_avatar = match &profile.avatar_url {
+        let should_update_avatar = match &current_avatar_url {
            Some(avatar_url) => {
                let request = MediaRequestParameters {
                    source: MediaSource::Plain(avatar_url.to_owned()),
--- a/src/bot/load_config.rs
+++ b/src/bot/load_config.rs
@@ -5,7 +5,7 @@ use anyhow::anyhow;

 use crate::agent::AgentPurpose;

-pub use crate::entity::cfg::{defaults as cfg_defaults, env as cfg_env, Config};
+pub use crate::entity::cfg::{Config, defaults as cfg_defaults, env as cfg_env};

 pub fn load() -> anyhow::Result<Config> {
    let config_file_path = env::var(cfg_env::BAIBOT_CONFIG_FILE_PATH)
@@ -33,8 +33,14 @@ pub fn load() -> anyhow::Result<Config> {
            cfg_env::BAIBOT_USER_ENCRYPTION_RECOVERY_PASSPHRASE => {
                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_COMMAND_PREFIX => config.command_prefix = value,
+            cfg_env::BAIBOT_ROOM_POST_JOIN_SELF_INTRODUCTION_ENABLED => {
+                config.room.post_join_self_introduction_enabled = value.parse::<bool>()?;
+            }
            cfg_env::BAIBOT_LOGGING => {
                config.logging = value;
            }
@@ -48,6 +54,9 @@ pub fn load() -> anyhow::Result<Config> {
            cfg_env::BAIBOT_PERSISTENCE_DATA_DIR_PATH => {
                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 => {
                config.persistence.config_encryption_key = Some(value);
            }
--- a/src/bot/messaging.rs
+++ b/src/bot/messaging.rs
@@ -1,9 +1,9 @@
 use mxlink::matrix_sdk::{
-    ruma::{
-        api::client::receipt::create_receipt::v3::ReceiptType,
-        events::room::message::OriginalSyncRoomMessageEvent, OwnedEventId,
-    },
    Room,
+    ruma::{
+        OwnedEventId, api::client::receipt::create_receipt::v3::ReceiptType,
+        events::room::message::OriginalSyncRoomMessageEvent,
+    },
 };

 use mxlink::{CallbackError, MessageResponseType};
--- a/src/bot/reacting.rs
+++ b/src/bot/reacting.rs
@@ -1,12 +1,12 @@
 use mxlink::matrix_sdk::{
-    ruma::{
-        events::{
-            room::message::Relation, AnySyncMessageLikeEvent, AnySyncTimelineEvent,
-            SyncMessageLikeEvent,
-        },
-        OwnedEventId, OwnedUserId,
-    },
    Room,
+    ruma::{
+        OwnedEventId, OwnedUserId,
+        events::{
+            AnySyncMessageLikeEvent, AnySyncTimelineEvent, SyncMessageLikeEvent,
+            room::message::Relation,
+        },
+    },
 };

 use mxlink::CallbackError;
--- a/src/bot/rooms.rs
+++ b/src/bot/rooms.rs
@@ -1,9 +1,9 @@
 use mxlink::{
-    matrix_sdk::{
-        ruma::events::{room::member::StrippedRoomMemberEvent, AnySyncTimelineEvent},
-        Room,
-    },
    InvitationDecision,
+    matrix_sdk::{
+        Room,
+        ruma::events::{AnySyncTimelineEvent, room::member::StrippedRoomMemberEvent},
+    },
 };

 use mxlink::CallbackError;
--- a/src/controller/access/dispatching.rs
+++ b/src/controller/access/dispatching.rs
@@ -1,6 +1,6 @@
 use mxlink::MessageResponseType;

-use crate::{entity::MessageContext, strings, Bot};
+use crate::{Bot, entity::MessageContext, strings};

 use super::AccessControllerType;

--- a/src/controller/access/help.rs
+++ b/src/controller/access/help.rs
@@ -1,6 +1,6 @@
 use mxlink::MessageResponseType;

-use crate::{entity::MessageContext, strings, Bot};
+use crate::{Bot, entity::MessageContext, strings};

 pub async fn handle(bot: &Bot, message_context: &MessageContext) -> anyhow::Result<()> {
    let mut message = String::new();
--- a/src/controller/access/mod.rs
+++ b/src/controller/access/mod.rs
@@ -4,5 +4,5 @@ pub mod help;
 mod room_local_agent_managers;
 mod users;

-pub use determination::{determine_controller, AccessControllerType};
+pub use determination::{AccessControllerType, determine_controller};
 pub use dispatching::dispatch_controller;
--- a/src/controller/access/room_local_agent_managers.rs
+++ b/src/controller/access/room_local_agent_managers.rs
@@ -1,6 +1,6 @@
 use mxlink::MessageResponseType;

-use crate::{entity::MessageContext, strings, Bot};
+use crate::{Bot, entity::MessageContext, strings};

 pub async fn handle_get(bot: &Bot, message_context: &MessageContext) -> anyhow::Result<()> {
    let message = match &message_context
--- a/src/controller/access/users.rs
+++ b/src/controller/access/users.rs
@@ -1,6 +1,6 @@
 use mxlink::MessageResponseType;

-use crate::{entity::MessageContext, strings, Bot};
+use crate::{Bot, entity::MessageContext, strings};

 pub async fn handle_get(bot: &Bot, message_context: &MessageContext) -> anyhow::Result<()> {
    let message = match &message_context.global_config().access.user_patterns {
--- a/src/controller/agent/create/mod.rs
+++ b/src/controller/agent/create/mod.rs
@@ -3,15 +3,15 @@ mod tests;

 use mxlink::MessageResponseType;

-use crate::agent::provider::{ControllerTrait, PingResult};
 use crate::agent::PublicIdentifier;
-use crate::agent::{create_from_provider_and_yaml_value_config, AgentDefinition};
+use crate::agent::provider::{ControllerTrait, PingResult};
+use crate::agent::{AgentDefinition, create_from_provider_and_yaml_value_config};
 use crate::agent::{AgentInstance, AgentProvider};
 use crate::controller::utils::get_text_body_or_complain;
 use crate::entity::globalconfig::GlobalConfigurationManager;
 use crate::entity::roomconfig::RoomConfigurationManager;
 use crate::strings;
-use crate::{entity::MessageContext, Bot};
+use crate::{Bot, entity::MessageContext};

 struct ParsedAgentConfig {
    agent: AgentInstance,
--- a/src/controller/agent/delete/mod.rs
+++ b/src/controller/agent/delete/mod.rs
@@ -1,9 +1,9 @@
 use mxlink::MessageResponseType;

 use crate::entity::{
-    globalconfig::GlobalConfigurationManager, roomconfig::RoomConfigurationManager, MessageContext,
+    MessageContext, globalconfig::GlobalConfigurationManager, roomconfig::RoomConfigurationManager,
 };
-use crate::{agent::PublicIdentifier, strings, Bot};
+use crate::{Bot, agent::PublicIdentifier, strings};

 pub async fn handle(
    bot: &Bot,
--- a/src/controller/agent/details/mod.rs
+++ b/src/controller/agent/details/mod.rs
@@ -1,6 +1,6 @@
 use mxlink::MessageResponseType;

-use crate::{agent::PublicIdentifier, entity::MessageContext, strings, Bot};
+use crate::{Bot, agent::PublicIdentifier, entity::MessageContext, strings};

 pub async fn handle(
    bot: &Bot,
--- a/src/controller/agent/help/mod.rs
+++ b/src/controller/agent/help/mod.rs
@@ -1,6 +1,6 @@
 use mxlink::MessageResponseType;

-use crate::{entity::MessageContext, strings, Bot};
+use crate::{Bot, entity::MessageContext, strings};

 pub async fn handle(bot: &Bot, message_context: &MessageContext) -> anyhow::Result<()> {
    // Anyone can access this help command, because certain subcommands ("list")
--- a/src/controller/agent/list/mod.rs
+++ b/src/controller/agent/list/mod.rs
@@ -2,7 +2,7 @@ use mxlink::MessageResponseType;

 use crate::agent::AgentPurpose;
 use crate::strings;
-use crate::{entity::MessageContext, Bot};
+use crate::{Bot, entity::MessageContext};

 pub async fn handle(bot: &Bot, message_context: &MessageContext) -> anyhow::Result<()> {
    let agents = bot
--- a/src/controller/agent/mod.rs
+++ b/src/controller/agent/mod.rs
@@ -1,4 +1,4 @@
-use crate::{entity::MessageContext, Bot};
+use crate::{Bot, entity::MessageContext};

 pub mod create;
 pub mod delete;
@@ -7,7 +7,7 @@ pub mod determination;
 pub mod help;
 pub mod list;

-pub use determination::{determine_controller, AgentControllerType};
+pub use determination::{AgentControllerType, determine_controller};

 pub async fn dispatch_controller(
    handler: &AgentControllerType,
--- a/src/controller/cfg/common/generic_setting.rs
+++ b/src/controller/cfg/common/generic_setting.rs
@@ -1,6 +1,6 @@
 use mxlink::MessageResponseType;

-use crate::{entity::MessageContext, strings, Bot};
+use crate::{Bot, entity::MessageContext, strings};

 pub async fn handle_get<T>(
    bot: &Bot,
--- a/src/controller/cfg/controller_type.rs
+++ b/src/controller/cfg/controller_type.rs
@@ -1,7 +1,8 @@
 use crate::{
    agent::{AgentPurpose, PublicIdentifier},
    entity::roomconfig::{
-        SpeechToTextFlowType, TextGenerationAutoUsage, TextGenerationPrefixRequirementType,
+        SpeechToTextFlowType, SpeechToTextMessageTypeForNonThreadedOnlyTranscribedMessages,
+        TextGenerationAutoUsage, TextGenerationPrefixRequirementType,
        TextToSpeechBotMessagesFlowType, TextToSpeechUserMessagesFlowType,
    },
 };
@@ -54,6 +55,11 @@ pub enum ConfigSpeechToTextSettingRelatedControllerType {
    GetFlowType,
    SetFlowType(Option<SpeechToTextFlowType>),

+    GetMsgTypeForNonThreadedOnlyTranscribedMessages,
+    SetMsgTypeForNonThreadedOnlyTranscribedMessages(
+        Option<SpeechToTextMessageTypeForNonThreadedOnlyTranscribedMessages>,
+    ),
+
    GetLanguage,
    SetLanguage(Option<String>),
 }
--- a/src/controller/cfg/determination/speech_to_text/mod.rs
+++ b/src/controller/cfg/determination/speech_to_text/mod.rs
@@ -1,7 +1,13 @@
 #[cfg(test)]
 mod tests;

-use crate::{controller::ControllerType, entity::roomconfig::SpeechToTextFlowType, strings};
+use crate::{
+    controller::ControllerType,
+    entity::roomconfig::{
+        SpeechToTextFlowType, SpeechToTextMessageTypeForNonThreadedOnlyTranscribedMessages,
+    },
+    strings,
+};

 use super::super::controller_type::ConfigSpeechToTextSettingRelatedControllerType;

@@ -48,6 +54,53 @@ pub(super) fn determine(
        ));
    }

+    // msg_type_for_non_threaded_only_transcribed_messages
+
+    if let Some(remaining_text) =
+        text.strip_prefix("msg-type-for-non-threaded-only-transcribed-messages")
+    {
+        let remaining_text = remaining_text.trim();
+
+        if !remaining_text.is_empty() {
+            return Err(ControllerType::Error(
+                strings::cfg::configuration_getter_used_with_extra_text(
+                    "msg-type-for-non-threaded-only-transcribed-messages",
+                    remaining_text,
+                )
+                .to_owned(),
+            ));
+        }
+
+        return Ok(ConfigSpeechToTextSettingRelatedControllerType::GetMsgTypeForNonThreadedOnlyTranscribedMessages);
+    }
+
+    if let Some(value_string) =
+        text.strip_prefix("set-msg-type-for-non-threaded-only-transcribed-messages")
+    {
+        let value_string = value_string.trim().to_owned();
+
+        let value_choice = if value_string.is_empty() {
+            None
+        } else {
+            let value_choice =
+                SpeechToTextMessageTypeForNonThreadedOnlyTranscribedMessages::from_str(
+                    &value_string.to_lowercase(),
+                );
+
+            if value_choice.is_none() {
+                return Err(ControllerType::Error(
+                    strings::cfg::configuration_value_unrecognized(&value_string).to_owned(),
+                ));
+            }
+
+            value_choice
+        };
+
+        return Ok(ConfigSpeechToTextSettingRelatedControllerType::SetMsgTypeForNonThreadedOnlyTranscribedMessages(
+            value_choice,
+        ));
+    }
+
    // Language

    if let Some(remaining_text) = text.strip_prefix("language") {
--- a/src/controller/cfg/dispatching/mod.rs
+++ b/src/controller/cfg/dispatching/mod.rs
@@ -1,5 +1,5 @@
 use crate::strings;
-use crate::{entity::MessageContext, Bot};
+use crate::{Bot, entity::MessageContext};
 use mxlink::MessageResponseType;

 use super::controller_type::{
--- a/src/controller/cfg/dispatching/speech_to_text.rs
+++ b/src/controller/cfg/dispatching/speech_to_text.rs
@@ -1,5 +1,8 @@
-use crate::entity::roomconfig::{RoomSettings, SpeechToTextFlowType};
-use crate::{entity::MessageContext, Bot};
+use crate::entity::roomconfig::{
+    RoomSettings, SpeechToTextFlowType,
+    SpeechToTextMessageTypeForNonThreadedOnlyTranscribedMessages,
+};
+use crate::{Bot, entity::MessageContext};

 use super::super::controller_type::{
    ConfigSpeechToTextSettingRelatedControllerType, SettingsStorageSource,
@@ -52,6 +55,39 @@ pub(super) async fn dispatch(
            }
        }

+        ConfigSpeechToTextSettingRelatedControllerType::GetMsgTypeForNonThreadedOnlyTranscribedMessages => {
+            let value = &room_settings.speech_to_text.msg_type_for_non_threaded_only_transcribed_messages;
+            setting_get::<SpeechToTextMessageTypeForNonThreadedOnlyTranscribedMessages>(bot, message_context, value).await
+        }
+        ConfigSpeechToTextSettingRelatedControllerType::SetMsgTypeForNonThreadedOnlyTranscribedMessages(value) => {
+            let value = value.to_owned();
+
+            let setter_callback = Box::new(move |room_settings: &mut RoomSettings| {
+                room_settings.speech_to_text.msg_type_for_non_threaded_only_transcribed_messages = value;
+            });
+
+            match config_type {
+                SettingsStorageSource::Room => {
+                    room_setting_set::<SpeechToTextMessageTypeForNonThreadedOnlyTranscribedMessages>(
+                        bot,
+                        message_context,
+                        &value,
+                        setter_callback,
+                    )
+                    .await
+                }
+                SettingsStorageSource::Global => {
+                    global_setting_set::<SpeechToTextMessageTypeForNonThreadedOnlyTranscribedMessages>(
+                        bot,
+                        message_context,
+                        &value,
+                        setter_callback,
+                    )
+                    .await
+                }
+            }
+        }
+
        ConfigSpeechToTextSettingRelatedControllerType::GetLanguage => {
            let value = &room_settings.speech_to_text.language;
            setting_get::<String>(bot, message_context, value).await
--- a/src/controller/cfg/dispatching/text_generation.rs
+++ b/src/controller/cfg/dispatching/text_generation.rs
@@ -1,7 +1,7 @@
 use crate::entity::roomconfig::{
    RoomSettings, TextGenerationAutoUsage, TextGenerationPrefixRequirementType,
 };
-use crate::{entity::MessageContext, Bot};
+use crate::{Bot, entity::MessageContext};

 use super::super::controller_type::{
    ConfigTextGenerationSettingRelatedControllerType, SettingsStorageSource,
--- a/src/controller/cfg/dispatching/text_to_speech.rs
+++ b/src/controller/cfg/dispatching/text_to_speech.rs
@@ -1,7 +1,7 @@
 use crate::entity::roomconfig::{
    RoomSettings, TextToSpeechBotMessagesFlowType, TextToSpeechUserMessagesFlowType,
 };
-use crate::{entity::MessageContext, Bot};
+use crate::{Bot, entity::MessageContext};

 use super::super::controller_type::{
    ConfigTextToSpeechSettingRelatedControllerType, SettingsStorageSource,
--- a/src/controller/cfg/global_config/generic_setting.rs
+++ b/src/controller/cfg/global_config/generic_setting.rs
@@ -1,7 +1,7 @@
 use mxlink::MessageResponseType;

-use crate::entity::{roomconfig::RoomSettings, MessageContext};
-use crate::{strings, Bot};
+use crate::entity::{MessageContext, roomconfig::RoomSettings};
+use crate::{Bot, strings};

 pub async fn handle_set<T>(
    bot: &Bot,
--- a/src/controller/cfg/global_config/handler.rs
+++ b/src/controller/cfg/global_config/handler.rs
@@ -1,9 +1,10 @@
 use mxlink::MessageResponseType;

 use crate::{
+    Bot,
    agent::{AgentPurpose, PublicIdentifier},
-    entity::{globalconfig::GlobalConfigurationManager, MessageContext},
-    strings, Bot,
+    entity::{MessageContext, globalconfig::GlobalConfigurationManager},
+    strings,
 };

 pub async fn handle_get(
--- a/src/controller/cfg/help.rs
+++ b/src/controller/cfg/help.rs
@@ -1,14 +1,16 @@
 use mxlink::MessageResponseType;

 use crate::{
+    Bot,
    entity::{
+        MessageContext,
        roomconfig::{
-            SpeechToTextFlowType, TextGenerationAutoUsage, TextGenerationPrefixRequirementType,
+            SpeechToTextFlowType, SpeechToTextMessageTypeForNonThreadedOnlyTranscribedMessages,
+            TextGenerationAutoUsage, TextGenerationPrefixRequirementType,
            TextToSpeechBotMessagesFlowType, TextToSpeechUserMessagesFlowType,
        },
-        MessageContext,
    },
-    strings, Bot,
+    strings,
 };

 pub async fn handle(bot: &Bot, message_context: &MessageContext) -> anyhow::Result<()> {
@@ -346,6 +348,46 @@ fn build_section_speech_to_text(command_prefix: &str) -> String {
    ));
    message.push_str("\n\n");

+    // Msg Type For Non Threaded Only Transcribed Messages
+
+    message.push_str(&format!(
+        "#### {}",
+        strings::help::cfg::speech_to_text_msg_type_for_non_threaded_only_transcribed_messages_heading()
+    ));
+    message.push_str("\n\n");
+    message.push_str(strings::help::cfg::speech_to_text_msg_type_for_non_threaded_only_transcribed_messages_intro());
+    message.push('\n');
+    message.push_str(
+        &strings::help::cfg::the_following_configuration_values_are_recognized(
+            SpeechToTextMessageTypeForNonThreadedOnlyTranscribedMessages::choices(),
+        ),
+    );
+    message.push_str("\n\n");
+    message.push_str(&format!(
+        "- {}",
+        &strings::help::cfg::current_setting_show(
+            command_prefix,
+            "speech-to-text msg-type-for-non-threaded-only-transcribed-messages"
+        )
+    ));
+    message.push('\n');
+    message.push_str(&format!(
+        "- {}",
+        &strings::help::cfg::current_setting_set(
+            command_prefix,
+            "speech-to-text set-msg-type-for-non-threaded-only-transcribed-messages VALUE"
+        )
+    ));
+    message.push('\n');
+    message.push_str(&format!(
+        "- {}",
+        &strings::help::cfg::current_setting_unset(
+            command_prefix,
+            "speech-to-text set-msg-type-for-non-threaded-only-transcribed-messages"
+        )
+    ));
+    message.push_str("\n\n");
+
    // Language

    message.push_str(&format!(
--- a/src/controller/cfg/room_config/generic_setting.rs
+++ b/src/controller/cfg/room_config/generic_setting.rs
@@ -1,7 +1,7 @@
 use mxlink::MessageResponseType;

-use crate::entity::{roomconfig::RoomSettings, MessageContext};
-use crate::{strings, Bot};
+use crate::entity::{MessageContext, roomconfig::RoomSettings};
+use crate::{Bot, strings};

 pub async fn handle_set<T>(
    bot: &Bot,
--- a/src/controller/cfg/room_config/handler.rs
+++ b/src/controller/cfg/room_config/handler.rs
@@ -1,9 +1,10 @@
 use mxlink::MessageResponseType;

 use crate::{
+    Bot,
    agent::{AgentPurpose, PublicIdentifier},
    entity::MessageContext,
-    strings, Bot,
+    strings,
 };

 use crate::entity::roomconfig::RoomConfigurationManager;
--- a/src/controller/cfg/status.rs
+++ b/src/controller/cfg/status.rs
@@ -1,15 +1,16 @@
 use mxlink::MessageResponseType;

 use crate::{
+    Bot,
    agent::{
-        utils::get_effective_agent_for_purpose, AgentInstance, AgentPurpose, ControllerTrait,
-        Manager as AgentManager, PublicIdentifier,
+        AgentInstance, AgentPurpose, ControllerTrait, Manager as AgentManager, PublicIdentifier,
+        utils::get_effective_agent_for_purpose,
    },
    entity::{
-        roomconfig::{RoomConfig, RoomSettingsHandler},
        MessageContext, RoomConfigContext,
+        roomconfig::{RoomConfig, RoomSettingsHandler},
    },
-    strings, Bot,
+    strings,
 };

 pub async fn handle(bot: &Bot, message_context: &MessageContext) -> anyhow::Result<()> {
@@ -68,7 +69,7 @@ pub async fn handle(bot: &Bot, message_context: &MessageContext) -> anyhow::Resu
    );
    message.push_str("\n\n");

-    // Image Generation
+    // Image Creation
    message.push_str(
        &generate_image_generation_section(agent_manager, message_context.room_config_context())
            .await,
@@ -507,6 +508,35 @@ async fn generate_speech_to_text_section(
        flow_type_set_where,
    ));

+    // Msg Type For Non Threaded Only Transcribed Messages
+
+    let effective_msg_type_for_non_threaded_only_transcribed_messages =
+        room_config_context.speech_to_text_msg_type_for_non_threaded_only_transcribed_messages();
+    let room_config_msg_type_for_non_threaded_only_transcribed_messages = room_config_context
+        .room_config
+        .settings
+        .speech_to_text
+        .msg_type_for_non_threaded_only_transcribed_messages;
+    let global_config_msg_type_for_non_threaded_only_transcribed_messages = room_config_context
+        .global_config
+        .fallback_room_settings
+        .speech_to_text
+        .msg_type_for_non_threaded_only_transcribed_messages;
+
+    let msg_type_for_non_threaded_only_transcribed_messages_set_where =
+        if room_config_msg_type_for_non_threaded_only_transcribed_messages.is_some() {
+            strings::cfg::status_badge_set_in_room_config()
+        } else if global_config_msg_type_for_non_threaded_only_transcribed_messages.is_some() {
+            strings::cfg::status_badge_set_in_global_config()
+        } else {
+            strings::cfg::status_badge_using_hardcoded_default()
+        };
+
+    message.push_str(&strings::cfg::status_speech_to_text_entry_msg_type_for_non_threaded_only_transcribed_messages(
+        effective_msg_type_for_non_threaded_only_transcribed_messages,
+        msg_type_for_non_threaded_only_transcribed_messages_set_where,
+    ));
+
    // Language

    let effective_language = room_config_context.speech_to_text_language();
--- a/src/controller/chat_completion/mod.rs
+++ b/src/controller/chat_completion/mod.rs
@@ -1,30 +1,31 @@
-use mxlink::matrix_sdk::ruma::events::room::message::AudioMessageEventContent;
 use mxlink::matrix_sdk::ruma::OwnedEventId;
+use mxlink::matrix_sdk::ruma::events::room::message::AudioMessageEventContent;
 use mxlink::{MatrixLink, MessageResponseType};

 use tracing::Instrument;

-use crate::agent::provider::{
-    SpeechToTextParams, TextGenerationParams, TextGenerationPromptVariables,
-};
 use crate::agent::AgentInstance;
 use crate::agent::AgentPurpose;
 use crate::agent::ControllerTrait;
+use crate::agent::provider::{
+    SpeechToTextParams, TextGenerationParams, TextGenerationPromptVariables,
+};
 use crate::controller::utils::agent::get_effective_agent_for_purpose_or_complain;
 use crate::conversation::matrix::MatrixMessageProcessingParams;
-use crate::entity::roomconfig::{
-    SpeechToTextFlowType, TextToSpeechBotMessagesFlowType, TextToSpeechUserMessagesFlowType,
-};
 use crate::entity::MessagePayload;
+use crate::entity::roomconfig::{
+    SpeechToTextFlowType, SpeechToTextMessageTypeForNonThreadedOnlyTranscribedMessages,
+    TextToSpeechBotMessagesFlowType, TextToSpeechUserMessagesFlowType,
+};
 use crate::strings;
 use crate::utils::text_to_speech::create_transcribed_message_text;
 use crate::{
+    Bot,
    conversation::{
        create_llm_conversation_for_matrix_reply_chain, create_llm_conversation_for_matrix_thread,
        matrix::create_list_of_bot_user_prefixes_to_strip,
    },
    entity::MessageContext,
-    Bot,
 };

 #[derive(Debug, PartialEq)]
@@ -38,6 +39,8 @@ pub enum ChatCompletionControllerType {

    Audio,

+    Image,
+
    ThreadMention,
    ReplyMention,
 }
@@ -71,21 +74,35 @@ pub async fn handle(
    if let MessagePayload::Audio(audio_content) = &message_context.payload() {
        original_message_is_audio = true;

-        let response_type = match speech_to_text_flow_type {
+        let (response_type, msg_type) = match speech_to_text_flow_type {
            SpeechToTextFlowType::Ignore => {
                tracing::debug!("Intentionally ignoring audio message");
                return Ok(());
            }
            SpeechToTextFlowType::TranscribeAndGenerateText => {
                tracing::debug!("Will be transcribing and possibly generating text..");
-                MessageResponseType::InThread(message_context.thread_info().clone())
+                (
+                    MessageResponseType::InThread(message_context.thread_info().clone()),
+                    SpeechToTextMessageTypeForNonThreadedOnlyTranscribedMessages::Notice,
+                )
            }
            SpeechToTextFlowType::OnlyTranscribe => {
                tracing::debug!("Will only be transcribing audio to text..");
                if message_context.thread_info().is_thread_root_only() {
-                    MessageResponseType::Reply(message_context.thread_info().root_event_id.clone())
+                    let msg_type = message_context
+                        .room_config_context()
+                        .speech_to_text_msg_type_for_non_threaded_only_transcribed_messages();
+                    (
+                        MessageResponseType::Reply(
+                            message_context.thread_info().root_event_id.clone(),
+                        ),
+                        msg_type,
+                    )
                } else {
-                    MessageResponseType::InThread(message_context.thread_info().clone())
+                    (
+                        MessageResponseType::InThread(message_context.thread_info().clone()),
+                        SpeechToTextMessageTypeForNonThreadedOnlyTranscribedMessages::Notice,
+                    )
                }
            }
        };
@@ -94,8 +111,14 @@ pub async fn handle(
            _typing_notice_guard = Some(bot.start_typing_notice(message_context.room()).await);
        }

-        let Some(speech_to_text_created_event_id_result) =
-            handle_stage_speech_to_text(bot, message_context, audio_content, response_type).await
+        let Some(speech_to_text_created_event_id_result) = handle_stage_speech_to_text(
+            bot,
+            message_context,
+            audio_content,
+            response_type,
+            msg_type,
+        )
+        .await
        else {
            return Ok(());
        };
@@ -282,6 +305,7 @@ async fn handle_stage_speech_to_text(
    message_context: &MessageContext,
    audio_content: &AudioMessageEventContent,
    response_type: MessageResponseType,
+    msg_type: SpeechToTextMessageTypeForNonThreadedOnlyTranscribedMessages,
 ) -> Option<OwnedEventId> {
    let agent = get_effective_agent_for_purpose_or_complain(
        bot,
@@ -302,7 +326,7 @@ async fn handle_stage_speech_to_text(
        .react_no_fail(
            message_context.room(),
            message_context.event_id().clone(),
-            AgentPurpose::SpeechToText.emoji().to_owned(),
+            strings::PROGRESS_INDICATOR_EMOJI.to_owned(),
        )
        .await;

@@ -312,6 +336,7 @@ async fn handle_stage_speech_to_text(
        &agent,
        audio_content,
        response_type.clone(),
+        msg_type,
    )
    .await;

@@ -393,7 +418,8 @@ async fn handle_stage_text_generation(
        ChatCompletionControllerType::TextCommand
        | ChatCompletionControllerType::TextMention
        | ChatCompletionControllerType::TextDirect
-        | ChatCompletionControllerType::Audio => {
+        | ChatCompletionControllerType::Audio
+        | ChatCompletionControllerType::Image => {
            Some(message_context.combined_admin_and_user_regexes())
        }

@@ -415,6 +441,7 @@ async fn handle_stage_text_generation(
        // When we're triggered via a reply mention, the context is the whole reply chain upward of the message that triggered us.
        ChatCompletionControllerType::ReplyMention => {
            create_llm_conversation_for_matrix_reply_chain(
+                &matrix_link,
                &bot.room_event_fetcher().clone(),
                message_context.room(),
                message_context.thread_info().last_event_id.clone(),
@@ -426,7 +453,7 @@ async fn handle_stage_text_generation(
        // Everything else is happening in a thread, so the context is the whole thread.
        _ => {
            create_llm_conversation_for_matrix_thread(
-                matrix_link.clone(),
+                &matrix_link,
                message_context.room(),
                message_context.thread_info().root_event_id.clone(),
                &params,
@@ -572,6 +599,7 @@ async fn handle_stage_speech_to_text_actual_transcribing(
    agent: &AgentInstance,
    audio_content: &AudioMessageEventContent,
    response_type: MessageResponseType,
+    msg_type: SpeechToTextMessageTypeForNonThreadedOnlyTranscribedMessages,
 ) -> anyhow::Result<OwnedEventId> {
    let src = &audio_content.source;

@@ -626,9 +654,6 @@ async fn handle_stage_speech_to_text_actual_transcribing(
    //
    // When sending a bare reply, we'd better annotate the message with a 🦻 reaction instead,
    // to make it clear to users that it's a transcription.
-    //
-    // Regardless of how we post this message, it will be posted as a notice,
-    // which can indicate to the bot (for potential future text-generation purposes) that this message is not a bot message.
    let (transcribed_text, annotate_message_with_reaction) =
        if let MessageResponseType::InThread(_) = response_type {
            (
@@ -639,10 +664,22 @@ async fn handle_stage_speech_to_text_actual_transcribing(
            (speech_to_text_result.text, true)
        };

-    let result = bot
-        .messaging()
-        .send_notice_markdown_no_fail(message_context.room(), transcribed_text, response_type)
-        .await;
+    let result = match msg_type {
+        SpeechToTextMessageTypeForNonThreadedOnlyTranscribedMessages::Text => {
+            bot.messaging()
+                .send_text_markdown_no_fail(message_context.room(), transcribed_text, response_type)
+                .await
+        }
+        SpeechToTextMessageTypeForNonThreadedOnlyTranscribedMessages::Notice => {
+            bot.messaging()
+                .send_notice_markdown_no_fail(
+                    message_context.room(),
+                    transcribed_text,
+                    response_type,
+                )
+                .await
+        }
+    };

    let event_id = result
        .map(|result| result.event_id)
--- a/src/controller/controller_type.rs
+++ b/src/controller/controller_type.rs
@@ -23,5 +23,6 @@ pub enum ControllerType {
    ChatCompletion(super::chat_completion::ChatCompletionControllerType),

    ImageGeneration(String),
+    ImageEdit(String),
    StickerGeneration(String),
 }
--- a/src/controller/determination/mod.rs
+++ b/src/controller/determination/mod.rs
@@ -4,8 +4,8 @@ mod tests;
 use super::chat_completion::ChatCompletionControllerType;
 use crate::{
    entity::{
-        roomconfig::TextGenerationPrefixRequirementType, InteractionTrigger, MessageContext,
-        MessagePayload,
+        InteractionTrigger, MessageContext, MessagePayload,
+        roomconfig::TextGenerationPrefixRequirementType,
    },
    strings,
 };
@@ -36,6 +36,18 @@ pub fn determine_controller(
                first_thread_message.is_mentioning_bot,
            )
        }
+        MessagePayload::Image(_image_message_content) => {
+            let prefix_requirement_type = message_context
+                .room_config_context()
+                .text_generation_prefix_requirement_type();
+
+            match prefix_requirement_type {
+                TextGenerationPrefixRequirementType::CommandPrefix => ControllerType::Ignore,
+                TextGenerationPrefixRequirementType::No => {
+                    ControllerType::ChatCompletion(ChatCompletionControllerType::Image)
+                }
+            }
+        }
        MessagePayload::Encrypted(thread_info) => {
            if thread_info.is_thread_root_only() {
                ControllerType::Error(strings::error::message_is_encrypted().to_owned())
@@ -84,7 +96,7 @@ fn determine_text_controller(
    }

    if let Some(prompt) = text.strip_prefix(&format!("{command_prefix} image")) {
-        return ControllerType::ImageGeneration(prompt.trim().to_owned());
+        return super::image::determine_controller(prompt.trim());
    }

    if let Some(prompt) = text.strip_prefix(&format!("{command_prefix} sticker")) {
--- a/src/controller/determination/tests.rs
+++ b/src/controller/determination/tests.rs
@@ -84,9 +84,17 @@ fn determine_text_controller() {
            expected: ControllerType::Config(controller::cfg::ConfigControllerType::Help),
        },
        TestCase {
-            name: "Image generation",
+            name: "Generic image command causes usage help",
            input: "!bai image Draw a cat!",
            is_mentioning_bot: false,
+            room_text_generation_prefix_requirement_type:
+                super::TextGenerationPrefixRequirementType::No,
+            expected: ControllerType::UsageHelp,
+        },
+        TestCase {
+            name: "Image generation",
+            input: "!bai image create Draw a cat!",
+            is_mentioning_bot: false,
            room_text_generation_prefix_requirement_type:
                super::TextGenerationPrefixRequirementType::No,
            expected: ControllerType::ImageGeneration("Draw a cat!".to_owned()),
@@ -142,8 +150,7 @@ fn determine_text_controller() {
        // This test case is the same as the one above, just with a different prefix requirement setting.
        // We expect the same result.
        TestCase {
-            name:
-                "Regular message with bot mention triggers completion (command prefix requirement)",
+            name: "Regular message with bot mention triggers completion (command prefix requirement)",
            input: "Regular text goes here",
            is_mentioning_bot: true,
            room_text_generation_prefix_requirement_type:
--- a/src/controller/dispatching.rs
+++ b/src/controller/dispatching.rs
@@ -1,6 +1,6 @@
 use mxlink::MessageResponseType;

-use crate::{entity::MessageContext, strings, Bot};
+use crate::{Bot, entity::MessageContext, strings};

 use super::ControllerType;

@@ -77,6 +77,10 @@ pub async fn dispatch_controller(
            )
            .await
        }
+        ControllerType::ImageEdit(prompt) => {
+            super::image::edit::handle(bot, bot.matrix_link().clone(), message_context, prompt)
+                .await
+        }
        ControllerType::StickerGeneration(prompt) => {
            super::image::generation::handle_sticker(
                bot,
--- a/src/controller/help/mod.rs
+++ b/src/controller/help/mod.rs
@@ -1,6 +1,6 @@
 use mxlink::MessageResponseType;

-use crate::{entity::MessageContext, strings, Bot};
+use crate::{Bot, entity::MessageContext, strings};

 pub async fn handle(bot: &Bot, message_context: &MessageContext) -> anyhow::Result<()> {
    let sender_can_manage_global_config = message_context.sender_can_manage_global_config();
--- a/src/controller/image/determination/mod.rs
+++ b/src/controller/image/determination/mod.rs
@@ -0,0 +1,16 @@
+use crate::controller::ControllerType;
+mod tests;
+
+pub fn determine_controller(text: &str) -> ControllerType {
+    let text = text.trim();
+
+    if let Some(prompt) = text.strip_prefix("create") {
+        return ControllerType::ImageGeneration(prompt.trim().to_owned());
+    }
+
+    if let Some(prompt) = text.strip_prefix("edit") {
+        return ControllerType::ImageEdit(prompt.trim().to_owned());
+    }
+
+    ControllerType::UsageHelp
+}
--- a/src/controller/image/determination/tests.rs
+++ b/src/controller/image/determination/tests.rs
@@ -0,0 +1,38 @@
+#[test]
+fn determine_controller() {
+    struct TestCase {
+        name: &'static str,
+        input: &'static str,
+        expected: super::ControllerType,
+    }
+
+    let test_cases = vec![
+        TestCase {
+            name: "Top-level is usage help",
+            input: "",
+            expected: super::ControllerType::UsageHelp,
+        },
+        TestCase {
+            name: "Top-level with some text is usage help",
+            input: "Some text",
+            expected: super::ControllerType::UsageHelp,
+        },
+        TestCase {
+            name: "Image generation triggered by create prefix",
+            input: "create Some prompt",
+            expected: super::ControllerType::ImageGeneration("Some prompt".to_owned()),
+        },
+        TestCase {
+            name: "Image edit triggered by edit prefix",
+            input: "edit Turn this into an anime-style image",
+            expected: super::ControllerType::ImageEdit(
+                "Turn this into an anime-style image".to_owned(),
+            ),
+        },
+    ];
+
+    for test_case in test_cases {
+        let result = super::determine_controller(test_case.input);
+        assert_eq!(result, test_case.expected, "Test case: {}", test_case.name);
+    }
+}
--- a/src/controller/image/edit.rs
+++ b/src/controller/image/edit.rs
@@ -0,0 +1,162 @@
+use mxlink::{MatrixLink, MessageResponseType};
+
+use tracing::Instrument;
+
+use crate::agent::AgentPurpose;
+use crate::agent::ControllerTrait;
+use crate::agent::provider::ImageEditParams;
+use crate::agent::provider::ImageSource;
+use crate::controller::utils::agent::get_effective_agent_for_purpose_or_complain;
+use crate::conversation::create_llm_conversation_for_matrix_thread;
+use crate::conversation::matrix::MatrixMessageProcessingParams;
+use crate::strings;
+use crate::utils::mime::get_file_extension;
+use crate::{Bot, entity::MessageContext};
+
+pub async fn handle(
+    bot: &Bot,
+    matrix_link: MatrixLink,
+    message_context: &MessageContext,
+    original_prompt: &str,
+) -> anyhow::Result<()> {
+    let response_type = MessageResponseType::InThread(message_context.thread_info().clone());
+
+    let Some(agent) = get_effective_agent_for_purpose_or_complain(
+        bot,
+        message_context,
+        AgentPurpose::ImageGeneration,
+        response_type.clone(),
+        true,
+    )
+    .await
+    else {
+        return Ok(());
+    };
+
+    if message_context.thread_info().is_thread_root_only() {
+        return send_guide(bot, message_context).await;
+    }
+
+    let _typing_notice_guard = bot.start_typing_notice(message_context.room()).await;
+
+    let params = MatrixMessageProcessingParams::new(
+        bot.user_id().to_owned(),
+        Some(message_context.combined_admin_and_user_regexes()),
+    );
+
+    let conversation = create_llm_conversation_for_matrix_thread(
+        &matrix_link,
+        message_context.room(),
+        message_context.thread_info().root_event_id.clone(),
+        &params,
+    )
+    .await?;
+
+    let prompt = if conversation.messages.len() >= 2 {
+        // Skip the first message, which contains the original prompt (which we already have)
+        let other_messages = conversation.messages.iter().skip(1).cloned().collect();
+
+        super::prompt::build(original_prompt, other_messages)
+    } else {
+        original_prompt.to_owned()
+    };
+
+    let got_go_signal = conversation.messages.iter().any(|message| {
+        if let crate::conversation::llm::MessageContent::Text(text) = &message.content {
+            text.to_lowercase() == "go"
+        } else {
+            false
+        }
+    });
+
+    let image_sources: Vec<ImageSource> = conversation
+        .messages
+        .iter()
+        .filter_map(|message| {
+            if let crate::conversation::llm::MessageContent::Image(image_content) = &message.content
+            {
+                Some(image_content.clone().into())
+            } else {
+                None
+            }
+        })
+        .collect();
+
+    if !got_go_signal || image_sources.is_empty() {
+        // We don't send the guide again here to avoid being annoying.
+        return Ok(());
+    }
+
+    let span = tracing::debug_span!("image_edit", agent_id = agent.identifier().as_string());
+
+    let result = agent
+        .controller()
+        .create_image_edit(&prompt, image_sources, ImageEditParams::default())
+        .instrument(span)
+        .await;
+
+    let response = match result {
+        Ok(response) => response,
+        Err(err) => {
+            tracing::warn!(
+                "Error in room {} while trying to generate image edit via agent {}: {:?}",
+                message_context.room_id(),
+                agent.identifier(),
+                err,
+            );
+
+            bot.messaging()
+                .send_error_markdown_no_fail(
+                    message_context.room(),
+                    &strings::agent::error_while_serving_purpose(
+                        agent.identifier(),
+                        &AgentPurpose::ImageGeneration,
+                        &err,
+                    ),
+                    response_type,
+                )
+                .await;
+
+            return Ok(());
+        }
+    };
+
+    let attachment_body_text = format!(
+        "generated-image-edit.{}",
+        get_file_extension(&response.mime_type)
+    );
+
+    let mut event_content = matrix_link
+        .media()
+        .upload_and_prepare_event_content(
+            message_context.room(),
+            &response.mime_type,
+            response.bytes,
+            &attachment_body_text,
+        )
+        .await
+        .map_err(|e| anyhow::anyhow!("Failed to upload and prepare event: {}", e))?;
+
+    matrix_link
+        .messaging()
+        .send_event(
+            message_context.room(),
+            &mut event_content,
+            response_type.clone(),
+        )
+        .await?;
+
+    Ok(())
+}
+
+async fn send_guide(bot: &Bot, message_context: &MessageContext) -> anyhow::Result<()> {
+    bot.messaging()
+        .send_text_markdown_no_fail(
+            message_context.room(),
+            strings::image_edit::guide_how_to_proceed(),
+            MessageResponseType::InThread(message_context.thread_info().clone()),
+        )
+        .await;
+
+    Ok(())
+}
--- a/src/controller/image/generation.rs
+++ b/src/controller/image/generation.rs
@@ -2,14 +2,15 @@ use mxlink::{MatrixLink, MessageResponseType};

 use tracing::Instrument;

-use crate::agent::provider::ImageGenerationParams;
 use crate::agent::AgentPurpose;
 use crate::agent::ControllerTrait;
+use crate::agent::provider::ImageGenerationParams;
 use crate::controller::utils::agent::get_effective_agent_for_purpose_or_complain;
 use crate::conversation::create_llm_conversation_for_matrix_thread;
 use crate::conversation::matrix::MatrixMessageProcessingParams;
 use crate::strings;
-use crate::{entity::MessageContext, Bot};
+use crate::utils::mime::get_file_extension;
+use crate::{Bot, entity::MessageContext};

 // We may make this configurable (per room, etc.) in the future, but for now it's hardcoded.
 const STICKER_SIZE: &str = "256x256";
@@ -42,7 +43,7 @@ pub async fn handle_image(
    );

    let conversation = create_llm_conversation_for_matrix_thread(
-        matrix_link.clone(),
+        &matrix_link,
        message_context.room(),
        message_context.thread_info().root_event_id.clone(),
        &params,
@@ -63,11 +64,37 @@ pub async fn handle_image(
        agent_id = agent.identifier().as_string()
    );

-    let response = agent
+    let result = agent
        .controller()
        .generate_image(&prompt, ImageGenerationParams::default())
        .instrument(span)
-        .await?;
+        .await;
+
+    let response = match result {
+        Ok(response) => response,
+        Err(err) => {
+            tracing::warn!(
+                "Error in room {} while trying to generate image via agent {}: {:?}",
+                message_context.room_id(),
+                agent.identifier(),
+                err,
+            );
+
+            bot.messaging()
+                .send_error_markdown_no_fail(
+                    message_context.room(),
+                    &strings::agent::error_while_serving_purpose(
+                        agent.identifier(),
+                        &AgentPurpose::ImageGeneration,
+                        &err,
+                    ),
+                    response_type,
+                )
+                .await;
+
+            return Ok(());
+        }
+    };

    let actual_prompt = response.revised_prompt.as_deref().unwrap_or(&prompt);

@@ -81,7 +108,10 @@ pub async fn handle_image(
            .await;
    }

-    let attachment_body_text = format!("Generated image based on: {}", actual_prompt);
+    let attachment_body_text = format!(
+        "generated-image.{}",
+        get_file_extension(&response.mime_type)
+    );

    let mut event_content = matrix_link
        .media()
@@ -151,13 +181,42 @@ pub async fn handle_sticker(
        .with_cheaper_model_switching_allowed(true)
        .with_cheaper_quality_switching_allowed(true);

-    let response = agent
+    let result = agent
        .controller()
        .generate_image(original_prompt, params)
        .instrument(span)
-        .await?;
+        .await;

-    let attachment_body_text = format!("Generated sticker image based on: {}", original_prompt);
+    let response = match result {
+        Ok(response) => response,
+        Err(err) => {
+            tracing::warn!(
+                "Error in room {} while trying to generate sticker via agent {}: {:?}",
+                message_context.room_id(),
+                agent.identifier(),
+                err,
+            );
+
+            bot.messaging()
+                .send_error_markdown_no_fail(
+                    message_context.room(),
+                    &strings::agent::error_while_serving_purpose(
+                        agent.identifier(),
+                        &AgentPurpose::ImageGeneration,
+                        &err,
+                    ),
+                    response_type,
+                )
+                .await;
+
+            return Ok(());
+        }
+    };
+
+    let attachment_body_text = format!(
+        "generated-sticker.{}",
+        get_file_extension(&response.mime_type)
+    );

    let mut event_content = matrix_link
        .media()
--- a/src/controller/image/mod.rs
+++ b/src/controller/image/mod.rs
@@ -1,2 +1,6 @@
+mod determination;
+pub mod edit;
 pub mod generation;
 mod prompt;
+
+pub use determination::determine_controller;
--- a/src/controller/image/prompt.rs
+++ b/src/controller/image/prompt.rs
@@ -1,11 +1,11 @@
-use crate::conversation::llm::{Author, Message};
+use crate::conversation::llm::{Author, Message, MessageContent};

 /// Builds a prompt from the original prompt and other messages in the conversation.
 ///
 /// Only messages authored by the user are considered.
 ///
-/// Messages that say "Again" (regardless of casing) are ignored. They are considered special messages
-/// which trigger re-generation, but do not need to be included in the prompt criteria.
+/// Messages that say "Again" or "Go" (regardless of casing) are ignored. They are considered special messages
+/// which trigger re-generation and "start" respectively, and do not need to be included in the prompt criteria.
 pub fn build(original_prompt: &str, other_messages: Vec<Message>) -> String {
    let mut prompt = original_prompt.to_owned();

@@ -14,7 +14,11 @@ pub fn build(original_prompt: &str, other_messages: Vec<Message>) -> String {
        .into_iter()
        .filter(|message| {
            if let Author::User = message.author {
-                message.message_text.to_lowercase() != "again"
+                if let MessageContent::Text(text) = &message.content {
+                    text.to_lowercase() != "again" && text.to_lowercase() != "go"
+                } else {
+                    false
+                }
            } else {
                false
            }
@@ -24,9 +28,9 @@ pub fn build(original_prompt: &str, other_messages: Vec<Message>) -> String {
    if !other_messages.is_empty() {
        prompt.push_str("\nOther criteria:");
        for message in other_messages {
-            prompt.push_str(
-                format!("\n- {}", message.message_text.replace("\n", ". ").as_str()).as_str(),
-            );
+            if let MessageContent::Text(text) = &message.content {
+                prompt.push_str(format!("\n- {}", text.replace("\n", ". ").as_str()).as_str());
+            }
        }
    }

@@ -36,7 +40,7 @@ pub fn build(original_prompt: &str, other_messages: Vec<Message>) -> String {
 #[cfg(test)]
 mod tests {
    use super::build;
-    use super::{Author, Message};
+    use super::{Author, Message, MessageContent};

    struct TestCase {
        original_prompt: &'static str,
@@ -60,7 +64,7 @@ mod tests {
                original_prompt: "Generate a picture of a dog",
                messages: vec![Message {
                    author: Author::User,
-                    message_text: "Must be blue".to_owned(),
+                    content: MessageContent::Text("Must be blue".to_owned()),
                    timestamp,
                }],
                expected_prompt: "Generate a picture of a dog\nOther criteria:\n- Must be blue",
@@ -68,46 +72,52 @@ mod tests {
            // Multiple complex user messages dispersed with assistant messages
            TestCase {
                original_prompt: "Generate a picture of an elephant",
-                messages: vec![Message {
+                messages: vec![
+                    Message {
                        author: Author::User,
-                    message_text: "Must be blue".to_owned(),
+                        content: MessageContent::Text("Must be blue".to_owned()),
                        timestamp,
                    },
                    Message {
                        author: Author::Assistant,
-                    message_text: "Whatever".to_owned(),
+                        content: MessageContent::Text("Whatever".to_owned()),
                        timestamp,
                    },
                    Message {
                        author: Author::User,
-                    message_text: "Must be 3-legged.\nMust be flying.".to_owned(),
+                        content: MessageContent::Text(
+                            "Must be 3-legged.\nMust be flying.".to_owned(),
+                        ),
                        timestamp,
-                }],
+                    },
+                ],
                expected_prompt: "Generate a picture of an elephant\nOther criteria:\n- Must be blue\n- Must be 3-legged.. Must be flying.",
            },
            // "Again" is ignored.
            TestCase {
                original_prompt: "Generate a picture of a grizzly bear",
-                messages: vec![Message {
+                messages: vec![
+                    Message {
                        author: Author::User,
-                    message_text: "Must be blue".to_owned(),
+                        content: MessageContent::Text("Must be blue".to_owned()),
                        timestamp,
                    },
                    Message {
                        author: Author::Assistant,
-                    message_text: "Whatever".to_owned(),
+                        content: MessageContent::Text("Whatever".to_owned()),
                        timestamp,
                    },
                    Message {
                        author: Author::User,
-                    message_text: "Again".to_owned(),
+                        content: MessageContent::Text("Again".to_owned()),
                        timestamp,
                    },
                    Message {
                        author: Author::User,
-                    message_text: "again".to_owned(),
+                        content: MessageContent::Text("again".to_owned()),
                        timestamp,
-                }],
+                    },
+                ],
                expected_prompt: "Generate a picture of a grizzly bear\nOther criteria:\n- Must be blue",
            },
        ];
--- a/src/controller/join/mod.rs
+++ b/src/controller/join/mod.rs
@@ -1,13 +1,21 @@
 use mxlink::MessageResponseType;

 use crate::entity::RoomConfigContext;
-use crate::{strings, Bot};
+use crate::{Bot, strings};

 pub async fn handle(
    bot: &Bot,
    room: &mxlink::matrix_sdk::Room,
    room_config_context: &RoomConfigContext,
 ) -> anyhow::Result<()> {
+    if !bot.post_join_self_introduction_enabled() {
+        tracing::debug!(
+            "Post-join self-introduction is disabled - not sending introduction message"
+        );
+
+        return Ok(());
+    }
+
    let agent_manager = bot.agent_manager();

    bot.messaging()
--- a/src/controller/provider/mod.rs
+++ b/src/controller/provider/mod.rs
@@ -1,6 +1,6 @@
 use mxlink::MessageResponseType;

-use crate::{agent::AgentProvider, entity::MessageContext, strings, Bot};
+use crate::{Bot, agent::AgentProvider, entity::MessageContext, strings};

 use super::ControllerType;

--- a/src/controller/reaction/mod.rs
+++ b/src/controller/reaction/mod.rs
@@ -3,9 +3,9 @@ use std::ops::Deref;
 use mxlink::MatrixLink;

 use crate::{
+    Bot,
    agent::AgentPurpose,
    entity::{MessageContext, MessagePayload},
-    Bot,
 };

 mod text_to_speech;
--- a/src/controller/reaction/text_to_speech.rs
+++ b/src/controller/reaction/text_to_speech.rs
@@ -1,7 +1,7 @@
 use mxlink::{MatrixLink, MessageResponseType};

 use mxlink::matrix_sdk::ruma::{
-    events::room::message::TextMessageEventContent, OwnedEventId, OwnedUserId,
+    OwnedEventId, OwnedUserId, events::room::message::TextMessageEventContent,
 };

 use crate::entity::roomconfig::{
@@ -9,8 +9,8 @@ use crate::entity::roomconfig::{
 };

 use crate::{
-    agent::AgentPurpose, controller::utils::agent::get_effective_agent_for_purpose_or_complain,
-    entity::MessageContext, Bot,
+    Bot, agent::AgentPurpose,
+    controller::utils::agent::get_effective_agent_for_purpose_or_complain, entity::MessageContext,
 };

 pub(super) async fn handle(
@@ -34,7 +34,9 @@ pub(super) async fn handle(
        reacted_to_event_sender_id,
        matrix_link.user_id(),
    ) {
-        tracing::debug!("Ignoring request for on-demand text-to-speech (via reaction) due to room configuration");
+        tracing::debug!(
+            "Ignoring request for on-demand text-to-speech (via reaction) due to room configuration"
+        );
        return Ok(());
    }

--- a/src/controller/usage/mod.rs
+++ b/src/controller/usage/mod.rs
@@ -1,6 +1,6 @@
 use mxlink::MessageResponseType;

-use crate::{entity::MessageContext, strings, Bot};
+use crate::{Bot, entity::MessageContext, strings};

 use super::ControllerType;

--- a/src/controller/utils/agent.rs
+++ b/src/controller/utils/agent.rs
@@ -1,16 +1,17 @@
 use mxlink::MessageResponseType;

 use crate::{
+    Bot,
    agent::{
-        utils::{get_effective_agent_for_purpose, AgentForPurposeDeterminationError},
        AgentInstance, AgentPurpose,
+        utils::{AgentForPurposeDeterminationError, get_effective_agent_for_purpose},
    },
    entity::MessageContext,
-    strings, Bot,
+    strings,
 };

-pub async fn get_effective_agent_for_purpose_or_complain<'a>(
-    bot: &'a Bot,
+pub async fn get_effective_agent_for_purpose_or_complain(
+    bot: &Bot,
    message_context: &MessageContext,
    agent_purpose: AgentPurpose,
    response_type: MessageResponseType,
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Slavi Pantaleev	0a8f9fc3e5	Release 1.8.3	2025-11-28 14:40:38 +02:00
Slavi Pantaleev	1ac3b2e060	Update dependencies	2025-11-28 14:23:07 +02:00
Slavi Pantaleev	a3ef9fd1bf	Upgrade services	2025-11-28 14:19:59 +02:00
Slavi Pantaleev	df507eb201	Make use of the `BAIBOT_USER_ENCRYPTION_RECOVERY_RESET_ALLOWED` environment variable for configuring `config.user.encryption.recovery_reset_allowed`	2025-11-28 14:18:35 +02:00
Slavi Pantaleev	4dcd9eff40	Make use of the `BAIBOT_PERSISTENCE_SESSION_ENCRYPTION_KEY` environment variable for configuring `config.persistence.session_encryption_key` Seems like we already had a constant defined, but weren't making use of it.	2025-11-28 14:17:23 +02:00
Slavi Pantaleev	ea760ce755	Release 1.8.2	2025-11-20 06:00:52 +02:00
Slavi Pantaleev	1528df6a55	Upgrade Rust (1.90.0 -> 1.91.1)	2025-11-20 05:51:45 +02:00
Slavi Pantaleev	b0fa024297	Update services	2025-11-20 05:50:36 +02:00
Slavi Pantaleev	3ec203128a	Update dependencies	2025-11-20 05:49:15 +02:00
Slavi Pantaleev	da97361e1b	Bump default OpenAI text-generation model (`gpt-5` -> `gpt-5.1`)	2025-11-20 05:25:20 +02:00
Slavi Pantaleev	b430fe0189	Update sample OpenAI config (for `gpt-5`) misleading users into using `max_response_tokens` & remove `openai-o1.yml` sample config No need to have both sample configs now. Fixes https://github.com/etkecc/baibot/issues/57	2025-11-20 05:25:20 +02:00
Slavi Pantaleev	f03126a9e1	Upgrade Rust (1.89.0 -> 1.90.0)	2025-10-26 09:00:01 +02:00
Slavi Pantaleev	7d46b926c1	Update services	2025-10-26 08:30:42 +02:00
Slavi Pantaleev	6f3c048195	Release 1.8.1	2025-09-12 16:54:11 +03:00
Slavi Pantaleev	b47cf598b5	Update dependencies	2025-09-12 16:53:35 +03:00
Slavi Pantaleev	265ad7e1cb	Release 1.8.0	2025-09-08 15:19:06 +03:00
Slavi Pantaleev	a159f67e45	Upgrade Rust (1.88.0 -> 1.89.0) and Debian base (12/bookworm -> 13/trixie) in Dockerfiles	2025-09-08 15:01:25 +03:00
Slavi Pantaleev	624b9de35b	Upgrade mxlink (1.9.0 -> 1.10.0) and matrix-sdk (0.13.0 -> 0.14.0)	2025-09-08 14:26:37 +03:00
Slavi Pantaleev	941bf7ca42	Update sample configs for OpenAI (gpt-5) to specify `max_completion_tokens`, not `max_response_tokens` Fixup for `b43f61f5ff`	2025-09-08 10:37:00 +03:00
Slavi Pantaleev	ef0f1671da	Update services	2025-09-08 10:04:48 +03:00
Slavi Pantaleev	b43f61f5ff	Change default OpenAI model (`gpt-4.1` -> `gpt-5`) Ref: https://openai.com/index/introducing-gpt-5/	2025-08-08 07:22:19 +03:00
Slavi Pantaleev	1967d2b34c	Release 1.7.6	2025-07-11 16:43:34 +03:00
Slavi Pantaleev	bb3734ad24	Upgrade mxlink (1.8.1 -> 1.9.0) and matrix-sdk (0.12.0 -> 0.13.0)	2025-07-11 16:41:46 +03:00
Slavi Pantaleev	eb6db34177	Update dependencies	2025-07-11 16:23:58 +03:00
Slavi Pantaleev	6e845caa2e	Release 1.7.5	2025-06-27 16:40:08 +03:00
Slavi Pantaleev	1004966785	Update Cargo.lock-pinned dependencies	2025-06-27 16:15:53 +03:00
Slavi Pantaleev	7ae1864c2e	Upgrade Rust (1.86.0 -> 1.88.0) Ref: https://releases.rs/docs/1.88.0/	2025-06-27 16:09:12 +03:00
Slavi Pantaleev	68a2fb161f	Release 1.7.4	2025-06-10 16:38:03 +03:00
Slavi Pantaleev	3a3eb58d7b	Update Cargo.lock-pinned dependencies	2025-06-10 16:37:13 +03:00
Slavi Pantaleev	74d988e650	Update mxlink (1.8.0 -> 1.8.1)	2025-06-10 16:33:44 +03:00
Slavi Pantaleev	ed8bedcd7e	Release 1.7.3	2025-06-10 15:28:56 +03:00
Slavi Pantaleev	2842632969	Disable `async-openai` feature of tiktoken-rs crate We don't make use of this feature, so it's not necessary. Ref: `af52be12fa/tiktoken-rs/Cargo.toml (L21)`	2025-06-10 15:26:25 +03:00
Slavi Pantaleev	10a5bd2abb	Update OpenAI model in sample config (gpt-4o -> gpt-4.1)	2025-06-10 15:20:00 +03:00
Slavi Pantaleev	5308b75f52	Update dependencies	2025-06-10 15:18:58 +03:00
Slavi Pantaleev	dad61e1270	Adjust `docker run` command on installation instructions to ensure `/tmp` is writable Ref: https://github.com/etkecc/baibot/issues/43	2025-06-09 10:54:11 +03:00
Slavi Pantaleev	91986a129c	Release 1.7.2	2025-05-11 23:20:58 +03:00
Slavi Pantaleev	264f683d6a	Allow `image_generation.size` to be `null` for OpenAI and default it to that The API spec for image creation and image editing says "string or null", so we're allowing `null` now to trigger automatic selection.	2025-05-11 23:20:07 +03:00
Slavi Pantaleev	62f0f4fa0d	Release 1.7.1	2025-05-11 22:20:26 +03:00
Slavi Pantaleev	69627abd74	Add image-editing feature documentation to the `!bai usage` command and adjust texts a bit	2025-05-11 22:19:15 +03:00
Slavi Pantaleev	d2660be33c	Update sample config for OpenAI to use `gpt-image-1`, not `dall-e-3`	2025-05-10 12:30:16 +03:00
Slavi Pantaleev	ce81fe69bd	Release 1.7.0	2025-05-10 12:22:58 +03:00
Slavi Pantaleev	1162636b88	Upgrade Rust (1.85.1 -> 1.86.0)	2025-05-10 12:22:46 +03:00
Slavi Pantaleev	8c90e13a79	Upgrade services	2025-05-10 12:11:08 +03:00
Slavi Pantaleev	274b614d25	Update dependencies	2025-05-10 11:58:06 +03:00
Slavi Pantaleev	7bd46821dc	Update README to mention the images editing feature	2025-05-10 11:49:43 +03:00
Slavi Pantaleev	a84135ff32	fmt	2025-05-10 11:47:50 +03:00
Slavi Pantaleev	231528a0d8	Document which providers support vision	2025-05-10 11:47:00 +03:00
Slavi Pantaleev	d8e47b0578	Document vision support for text-generation	2025-05-10 11:39:33 +03:00
Slavi Pantaleev	96c1542f4a	Add an image-editing screenshot that demos multiple image support	2025-05-10 11:36:14 +03:00
Slavi Pantaleev	2f9c3dfce0	Use patched `anthropic-rs` library to add Vision support to text conversations Related to: https://github.com/AbdelStark/anthropic-rs/pull/11	2025-05-10 10:25:15 +03:00
Slavi Pantaleev	de958208b2	Use patched `async-openai` library to work around a few upstream issues Related to: - CreateImageEditRequest forces an application/octet-stream content type for images (https://github.com/64bit/async-openai/issues/364) - CreateImageEditRequest only deals with a single image (https://github.com/64bit/async-openai/issues/363) This is a continuation of `8f86289373` and fixes the Image Editing feature for OpenAI.	2025-05-10 10:00:36 +03:00
Slavi Pantaleev	ac4f2080ce	Make some improvements as suggested by clippy	2025-05-10 09:33:44 +03:00
Slavi Pantaleev	3ffa50b7b9	Use `ImageInput\|AudioInput::from_vec_u8` helper	2025-05-10 09:29:06 +03:00
Slavi Pantaleev	8f86289373	Initial work on Vision support in text conversations and Image Editing 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)	2025-05-10 09:18:01 +03:00
Slavi Pantaleev	e0dcc39a72	Default OpenAI image-generation model to `gpt-image-1` (previously `dall-e-3`)	2025-05-03 09:42:46 +03:00
Slavi Pantaleev	c94376109c	Avoid passing `response_format` to OpenAI's image generation API for the `gpt-image-1` model The API reference for `response_format` says: > This parameter isn't supported for gpt-image-1 which will always return base64-encoded images. Related to https://github.com/etkecc/baibot/issues/40	2025-05-03 09:42:44 +03:00
Slavi Pantaleev	256ed05662	Make `style`, `quality` and internal `response_format` image generation parameters optional Some OpenAI models (like `gpt-image-1`) either don't support these or only support specific other values. Related to https://github.com/etkecc/baibot/issues/40	2025-05-03 09:42:39 +03:00
Slavi Pantaleev	8222681e27	Default OpenAI text-generation model to `gpt-4.1` (previously `gpt-4o`)	2025-05-03 09:42:37 +03:00
Slavi Pantaleev	f304b93c68	Improve in-room error reporting details when image generation fails What previously was a generic error message like: > ⚠️ Error: An error occurred while processing your message. Please try again. .. now becomes a much more helpful error message like: > ⚠️ Error: There was a problem performing image-generation via the room-local/my-openai-agent agent: > > invalid_request_error: Invalid value: 'standard'. Supported values are: 'low', 'medium', 'high', and 'auto'. (param: quality) (code: invalid_value) Related to https://github.com/etkecc/baibot/issues/40	2025-05-03 09:42:28 +03:00
Slavi Pantaleev	889d8a1d04	Upgrade Synapse (v1.127.1 -> v1.128.0) and Element Web (v1.11.96 -> v1.11.99)	2025-05-03 08:50:00 +03:00
Slavi Pantaleev	6082bfaf56	Release 1.6.0	2025-04-12 08:04:23 +03:00
Slavi Pantaleev	1d629e0859	Update dependencies	2025-04-12 07:57:12 +03:00
Slavi Pantaleev	49471c1df0	Upgrade mxlink (1.6.0 -> 1.7.0) and matrix-sdk (0.10.0 -> 0.11.0)	2025-04-12 07:49:26 +03:00
Slavi Pantaleev	8f956d2329	Release 1.5.1	2025-03-31 14:37:23 +03:00
Slavi Pantaleev	ba4aa35987	Upgrade Rust compiler in container image (1.85.0 -> 1.85.1)	2025-03-31 14:33:49 +03:00
Slavi Pantaleev	06d699a17d	Update dependencies	2025-03-31 14:33:49 +03:00
Slavi Pantaleev	77d41fb7eb	Update services	2025-03-31 14:33:49 +03:00
Slavi Pantaleev	aaf283dde3	Upgrade Element Web (v1.11.93 -> v1.11.96) and adapt to its own way of running as a non-privileged user	2025-03-31 14:33:49 +03:00
Slavi Pantaleev	17eafa86af	Release 1.5.0	2025-02-27 11:29:26 +02:00
Slavi Pantaleev	4704934b06	Run amd64 builds on a self-hosted runner	2025-02-27 11:06:18 +02:00
Slavi Pantaleev	6719538530	Switch to using native ARM64 builders The workflow code is inspired by https://github.com/matrix-org/matrix-hookshot/pull/1007 Ref: https://github.blog/news-insights/product-news/arm64-on-github-actions-powering-faster-more-efficient-build-systems/ This decreases build times from ~40 minutes (on powerful self-hosted runners) to ~8 minutes (on public runners).	2025-02-27 10:31:23 +02:00
Slavi Pantaleev	59e2746578	Remove explicit lifetime to fix clippy-reported warning	2025-02-27 09:58:58 +02:00
Slavi Pantaleev	47d8edea70	Add support for configuring `max_completion_tokens` for OpenAI Related to `db9422740c`	2025-02-27 09:58:58 +02:00
Slavi Pantaleev	692d61b239	Replace Anthropic library (`anthropic-rs` -> `anthropic`) and switch default recommended model (`claude-3-5-sonnet-20240620` -> `claude-3-7-sonnet-20250219`) Fixes https://github.com/etkecc/baibot/issues/22 Ultimate related to `anthropic-rs` hardcoding models as enumeration variants in the code and not updating them. See: - https://github.com/roushou/mesh/issues/1 - https://github.com/roushou/mesh/pull/2 https://github.com/cortesi/misanthropy was also considered as an alternative, but it did not allow configuring the base API URL like our old Anthropic library (`anthropic-rs`) and like our new choice (`anthropic`). We'd rather not lose support for this, so we're going with the `anthropic` library.	2025-02-27 09:44:49 +02:00
Slavi Pantaleev	05902f4c17	Add `fmt` justfile recipe	2025-02-27 09:31:26 +02:00
Slavi Pantaleev	7e66068b16	Update dependencies	2025-02-27 07:48:10 +02:00
Slavi Pantaleev	406141cd7d	fmt	2025-02-27 07:46:16 +02:00
Slavi Pantaleev	c051da2f4a	Add config setting controlling if a self-introduction message is posted after joining a room Fixes https://github.com/etkecc/baibot/issues/32	2025-02-26 20:51:24 +02:00
Slavi Pantaleev	1ff7e8cf79	Switch Rust edition (2021 -> 2024)	2025-02-26 20:51:24 +02:00
Slavi Pantaleev	b3bca98e84	Upgrade Rust compiler in container image (1.82.0 -> 1.85.0)	2025-02-26 20:51:24 +02:00
Slavi Pantaleev	c07b712318	Upgrade mxlink (1.5.0 -> 1.6.0) and matrix-sdk (0.9.0 -> 0.10.0)	2025-02-26 20:51:24 +02:00
Slavi Pantaleev	6741483056	Update dependencies	2025-02-26 20:51:24 +02:00
Slavi Pantaleev	06b2b6d776	Use progress indicator emoji (⏳), not 🦻 to indicate that speech-to-text is happening 🦻 is used for another purpose - to denote that a message is one coming from speech-to-text, by: - having the bot react to its own speech-to-text transcription message with the 🦻 emoji when it's posted in a non-thread - having the bot prefix its speech-to-text transcription messages with `> 🦻` when it's posted in a thread ⏳ is already used as a progress indicator for other features, so it makes sense to use it for indicating that speech-to-text is happening for a given audio message as well. While 🦻 was an even more descriptive illustration of what's actually happening to the audio message ("it's being heard by the bot"), us using the 🦻 emoji for different things didn't seem good.	2025-02-26 20:51:24 +02:00
Slavi Pantaleev	a1bd292752	Add support for making Text-To-Speech send regular text messages instead of notices 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	2025-02-26 20:51:08 +02:00
Slavi Pantaleev	e4e1fe0e7b	Upgrade some components	2025-02-26 09:39:48 +02:00
Slavi Pantaleev	45a2d96029	Enable necessary feature for matrix-sdk which affects us if used as a library Fixes https://github.com/etkecc/rust-mxlink/issues/1	2025-02-02 07:51:25 +02:00
Slavi Pantaleev	ec1879d212	Populate image/audio attachment `body` with a filename, not with text Various clients (including newer versions of Element Web), do not like it when the `body` field of the attachment is not a file name. For images, a preview may not be shown and downloading the attachment may suggest that the whole long text is used as a filename (which is odd). There is value (improved accessibility, etc.) in adding better descriptions (especially to generated images), but given that it's currently problematic, I'm getting rid of it. It's better and safer if we stick to using filenames.	2025-01-24 11:35:08 +02:00
Slavi Pantaleev	5e6a600895	Update dependencies	2025-01-24 10:55:12 +02:00
Slavi Pantaleev	3db924b124	Upgrade services	2025-01-24 10:01:50 +02:00
Slavi Pantaleev	ff7a5ef7af	Install SQLite 3 for test-and-clippy CI job	2024-12-12 12:25:56 +02:00
Slavi Pantaleev	cd7d9137e8	Fix broken commit link in changelog entry	2024-12-12 12:03:25 +02:00
Slavi Pantaleev	0d509b2d0e	Release 1.4.1	2024-12-12 12:01:22 +02:00
Slavi Pantaleev	3c47d40781	Upgrade `mxlink` to fix incorrect on-being-last-member determination Related to `ec69da79ff`	2024-12-12 12:00:47 +02:00
Slavi Pantaleev	78893247e7	Mention Matrix authenticated media support for the 1.4.0 release Related to https://github.com/etkecc/baibot/issues/12	2024-11-20 07:41:05 +02:00
Slavi Pantaleev	4847bd8ba8	Enable authenticated media for the local Synapse service This is now supported thanks to us upgrading mxlink/matrix-sdk in `39a184e5d0`.	2024-11-20 07:40:08 +02:00