Switch back to upstream async-openai

Once async-openai v0.31.0 gets released as a final version, we'll be able top pull it from crates.io. This does not quite compile yet, because of https://github.com/64bit/async-openai/issues/465
2025-11-08 13:33:46 +02:00
62 changed files with 1734 additions and 2325 deletions
--- a/.github/workflows/workflow.yml
+++ b/.github/workflows/workflow.yml
@@ -16,8 +16,8 @@ jobs:
    name: Unit testing and linting
    runs-on: ubuntu-latest
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
-      - uses: dtolnay/rust-toolchain@1.93.0
+      - 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
@@ -30,7 +30,7 @@ jobs:
    steps:
      - name: Extract metadata (tags, labels) for Docker
        id: meta
-        uses: docker/metadata-action@v6
+        uses: docker/metadata-action@v5
        with:
          images: |
            ghcr.io/${{ github.repository }}
@@ -56,16 +56,16 @@ jobs:
    steps:
      - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
      - name: Log in to the GitHub Container registry
-        uses: docker/login-action@v4
+        uses: docker/login-action@v3
        with:
          registry: ghcr.io
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}
      - name: Extract metadata (tags, labels) for Docker
        id: meta
-        uses: docker/metadata-action@v6
+        uses: docker/metadata-action@v5
        with:
          tags: |
            type=raw,value=latest,enable=${{ github.ref_name == 'main' }}
@@ -77,7 +77,7 @@ jobs:
            ghcr.io/${{ github.repository }}
      - name: Build and push Docker images
-        uses: docker/build-push-action@v7
+        uses: docker/build-push-action@v6
        with:
          push: true
          tags: ${{ steps.meta.outputs.tags }}
@@ -95,7 +95,7 @@ jobs:
    steps:
      - name: Log in to the GitHub Container registry
-        uses: docker/login-action@v4
+        uses: docker/login-action@v3
        with:
          registry: ghcr.io
          username: ${{ github.actor }}
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -1,36 +0,0 @@
 repos:
  # Fast built-in hooks (Rust-native, no dependencies)
  - repo: builtin
    hooks:
      - id: trailing-whitespace
      - id: end-of-file-fixer
      - id: check-yaml
      - id: check-merge-conflict
      - id: check-added-large-files
        args: ['--maxkb=1024']
  # Local hooks that run project-specific tools
  - repo: local
    hooks:
      - id: cargo-fmt-check
        name: Cargo Format Check
        entry: cargo fmt --all -- --check
        language: system
        files: '\.rs$'
        pass_filenames: false
      - id: cargo-clippy
        name: Cargo Clippy
        entry: cargo clippy -- -D warnings
        language: system
        files: '\.rs$'
        pass_filenames: false
        priority: 100
      - id: test-unit
        name: Unit Tests
        entry: just test
        language: system
        files: '\.rs$'
        pass_filenames: false
        priority: 100
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,95 +1,3 @@
 # (2026-03-07) Version 1.15.0
 - (**Feature**) Add support for authentication via access tokens (for [Matrix Authentication Service](https://github.com/element-hq/matrix-authentication-service)/OIDC-enabled homeservers) as an alternative to password authentication. See [🔐 Authentication](./docs/configuration/authentication.md) for setup details. Thanks to [Taylor Southwick](https://github.com/twsouthwick) for the contribution in [#83](https://github.com/etkecc/baibot/pull/83)!
 - (**Internal Improvement**) Pin the Rust toolchain to `1.93.0` in both CI and local development to avoid `matrix-sdk` build failures on newer stable toolchains.
 - (**Internal Improvement**) Documentation updates.
 - (**Internal Improvement**) Dependency updates.
 # (2026-02-18) Version 1.14.3
 - (**Internal Improvement**) Add [Renovate](https://docs.renovatebot.com/) configuration for automated dependency updates
 - (**Internal Improvement**) Dependency updates
 # (2026-02-18) Version 1.14.2
 - (**Internal Improvement**) Dependency updates
 - (**Internal Improvement**) Reorganize the development environment to support [Continuwuity](https://continuwuity.org/) as a homeserver choice (in addition to [Synapse](https://github.com/element-hq/synapse)). Continuwuity is now the default for its lighter footprint (no external database required). See [development docs](./docs/development.md) for details.
 # (2026-02-10) Version 1.14.1
 - (**Security**) Dependency updates to fix security vulnerabilities ([time](https://crates.io/crates/time) stack exhaustion DoS, [bytes](https://crates.io/crates/bytes) integer overflow), via [mxlink](https://crates.io/crates/mxlink) 1.12.0
 - (**Internal Improvement**) Switch from deprecated [serde_yaml](https://crates.io/crates/serde_yaml) to its maintained fork [serde_yaml_ng](https://crates.io/crates/serde_yaml_ng)
 - (**Internal Improvement**) Add [prek](https://github.com/nicholasgasior/prek) pre-commit hooks via [mise](https://mise.jdx.dev/) for automated code quality checks (formatting, clippy, tests)
 - (**Internal Improvement**) Fix clippy warnings and formatting issues
 # (2026-02-04) Version 1.14.0
 - (**Feature**) The `openai` provider now uses OpenAI's [Responses API](https://platform.openai.com/docs/api-reference/responses) (instead of the older Chat Completions API), adding support for [🛠️ built-in tools](./docs/features.md#️-built-in-tools-openai-only) (`web_search` and `code_interpreter`). These tools are **disabled by default** and can be enabled via the `text_generation.tools` configuration (see the [sample configuration](https://github.com/etkecc/baibot/blob/c70387b0c38d8d0f30bba2179a2a21a3710dbeaf/docs/sample-provider-configs/openai.yml#L12-L15)). To enable tools on an existing agent, you need to [update the agent](./docs/agents.md#updating-agents) to re-create it with the `text_generation.tools` section added and enable the tools you need. Thanks to [Layla Manley](https://github.com/yeslayla) for the contribution in [#62](https://github.com/etkecc/baibot/pull/62)!
 - (**Bugfix**) Fix sticker generation for newer GPT image models (`gpt-image-1`, `gpt-image-1-mini`, `gpt-image-1.5`) which don't support the previously hardcoded `256x256` size (minimum is `1024x1024`)
 - (**Internal Improvement**) Dependency updates
 # (2026-01-23) Version 1.13.0
 - (**Improvement**) Extend auto-switching to support cheaper models (`gpt-image-1-mini`) for `gpt-image-1` and `gpt-image-1.5` when generating stickers ([e0b4a40](https://github.com/etkecc/baibot/commit/e0b4a40))
 - (**Internal Improvement**) Upgrade Rust compiler (1.92.0 -> 1.93.0) ([691aeeb](https://github.com/etkecc/baibot/commit/691aeeb))
 - (**Internal Improvement**) Dependency updates
 # (2025-12-21) Version 1.12.0
 - (**Improvement**) Upgrade [async-openai](https://crates.io/crates/async-openai) (0.31.1 -> 0.32.2) and add support for OpenAI's `gpt-image-1.5` model ([08c689a](https://github.com/etkecc/baibot/commit/08c689a), [f7bf3d7](https://github.com/etkecc/baibot/commit/f7bf3d7))
 - (**Internal Improvement**) Dependency updates
 # (2025-12-15) Version 1.11.0
 - (**Feature**) Add support for custom avatars via file path and for keeping the already-set avatar (for those who wish to manage it by themselves via other means). See the [sample config](./etc/app/config.yml.dist) for details. ([062fbbb](https://github.com/etkecc/baibot/commit/062fbbb8ef9ad600db483a431c5c782402191023))
 - (**Internal Improvement**) Dependency updates ([99bde53](https://github.com/etkecc/baibot/commit/99bde53ef648a5a9086a96778fde4a9dbc1ede58))
 - (**Internal Improvement**) Documentation updates ([b3fd8e5](https://github.com/etkecc/baibot/commit/b3fd8e548f83fe46398ced4760d7e2bb7588c24d))
 - (**Internal Improvement**) Upgrade Rust compiler (1.91.1 -> 1.92.0) ([22906aa](https://github.com/etkecc/baibot/commit/22906aa2d3cae51815fad2560a545eaa69c247b6))
 # (2025-12-06) Version 1.10.0
 - (**Internal Improvement**) Dependency updates. This version is based on [mxlink](https://crates.io/crates/mxlink)@1.11.0 (which is based on the newly released [matrix-sdk](https://crates.io/crates/matrix-sdk)@[0.16.0](https://github.com/matrix-org/matrix-rust-sdk/releases/tag/matrix-sdk-0.16.0).
 # (2025-11-30) Version 1.9.0
 - (**Internal Improvement**) Upgrade [async-openai](https://crates.io/crates/async-openai) from our own etkecc fork (0.28.1-patched) to the official upstream version 0.31.1. This upgrade required some code adaptations to the new module structure, etc. While tested, regressions are possible.
 # (2025-11-28) Version 1.8.3
 - (**Improvement**) Add support for the `BAIBOT_PERSISTENCE_SESSION_ENCRYPTION_KEY` environment variable for configuring `persistence.session_encryption_key`
 - (**Improvement**) Add support for the `BAIBOT_USER_ENCRYPTION_RECOVERY_RESET_ALLOWED` environment variable for configuring `user.encryption.recovery_reset_allowed`
 - (**Internal Improvement**) Dependency updates.
 # (2025-11-20) Version 1.8.2
 - (**Internal Improvement**) Dependency and compiler updates (Rust 1.89.0 -> 1.91.1).
 # (2025-09-12) Version 1.8.1
 - (**Internal Improvement**) Dependency updates.
--- a/Cargo.lock
+++ b/Cargo.lock
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -7,7 +7,7 @@ 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 = "1.15.0"
+version = "1.8.1"
 edition = "2024"
 [lib]
@@ -17,24 +17,23 @@ path = "src/lib.rs"
 [dependencies]
 anthropic = { git = "https://github.com/etkecc/anthropic-rs.git", branch = "fix-content-block-image" }
 anyhow = "1.0.*"
-async-openai = { version = "0.33.0", features = ["audio", "chat-completion", "image", "responses"] }
+async-openai = { git = "https://github.com/64bit/async-openai", branch = "main" }
 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.
 # We add the `native-tls` feature, because of https://github.com/etkecc/rust-mxlink/issues/1
-matrix-sdk = { version = "0.16.0", default-features = false, features = ["native-tls"] }
+matrix-sdk = { version = "0.14.0", default-features = false, features = ["native-tls"] }
 mime_guess = "2.0.*"
 mxidwc = "1.0.*"
-mxlink = ">=1.13.0"
+mxlink = ">=1.10.0"
 etke_openai_api_rust = "0.1.*"
 quick_cache = "0.6.*"
-regex = "1.12.*"
+regex = "1.11.*"
 serde = { version = "1.0.*", features = ["derive"], default-features = false }
 serde_json = "1.0.*"
-serde_yaml_ng = "0.10.*"
+serde_yaml = "0.9.*"
-tempfile = "3.26.*"
+tempfile = "3.21.*"
-tiktoken-rs = { version = "0.9.*", default-features = false }
+tiktoken-rs = { version = "0.7.*", default-features = false }
-tokio = { version = "1.50.*", features = ["rt", "rt-multi-thread", "macros"] }
+tokio = { version = "1.47.*", features = ["rt", "rt-multi-thread", "macros"] }
 tracing = "0.1.*"
 tracing-subscriber = { version = "0.3.*", features = ["env-filter"] }
 url = "2.5.*"
--- a/2
+++ b/2
@@ -4,7 +4,7 @@
 #                                     #
 #######################################
-FROM docker.io/rust:1.93.1-slim-trixie AS build
+FROM docker.io/rust:1.90.0-slim-trixie AS build
 RUN apt-get update && apt-get install -y build-essential pkg-config libssl-dev libsqlite3-dev
--- a/Dockerfile.ci
+++ b/Dockerfile.ci
@@ -4,7 +4,7 @@
 #                                     #
 #######################################
-FROM docker.io/rust:1.93.1-slim-trixie AS build
+FROM docker.io/rust:1.90.0-slim-trixie AS build
 RUN apt-get update && apt-get install -y build-essential pkg-config libssl-dev libsqlite3-dev
--- a/README.md
+++ b/README.md
@@ -17,7 +17,7 @@ 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 (though certain models may "see" images as well). The [OpenAI provider](./docs/providers.md#openai) also supports [🛠️ built-in tools](./docs/features.md#️-built-in-tools-openai-only) (web search, code interpreter)
+  - [💬 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#image-generation): creating and editing images based on instructions
--- a/docs/access.md
+++ b/docs/access.md
@@ -43,8 +43,7 @@ Administrators cannot be changed without adjusting the bot's configuration on th
 Room-local agent managers are users privileged to **create their own [agents](./agents.md)** (see `!bai agent`) in rooms.
-> [!WARNING]
+**⚠️ WARNING**: Letting regular users create agents which contact arbitrary network services **may be a security issue**.
 > Letting regular users create agents which contact arbitrary network services **may be a security issue**.
 The following commands are available:
 - **Show** the currently allowed users: `!bai access room-local-agent-managers`
--- a/docs/configuration/README.md
+++ b/docs/configuration/README.md
@@ -12,17 +12,12 @@ This file is created from the template found in [etc/app/config.yml.dist](../../
 Certain keys can be left unset, in which case [📝 hardcoded defaults](../../src/entity/cfg/defaults.rs) would be used.
-Some configuration keys found in the YAML configuration can be overridden by setting an environment variable (dots should be replaced with `_`). Example:
+Each configuration key found in the YAML configuration can be overridden by setting an environment variable (dots should be replaced with `_`). Example:
 - to override `command_prefix`, set an environment variable `BAIBOT_COMMAND_PREFIX`
 - to override `homeserver.server_name`, set an environment variable `BAIBOT_HOMESERVER_SERVER_NAME`
-You can see the list of supported environment variables in the [🦀 src/entity/cfg/env.rs](../../src/entity/cfg/env.rs) file.
+The static configuration contains an `initial_global_config` key, which is used to populate the bot's global configuration (stored as [dynamic configuration](#dynamic-configuration)) the first time the bot starts. Modifying this subsequently will not have any effect. After initial global configuration creation, it's expected to be managed dynamically via chat commands.
 > [!WARNING]
 > The static configuration contains an `initial_global_config` key, which is used to populate the bot's global configuration (stored as [dynamic configuration](#dynamic-configuration)) the first time the bot starts. Modifying this subsequently will not have any effect. After initial global configuration creation, it's expected to be managed dynamically via chat commands.
 For Matrix-account authentication setup, see [🔐 Authentication](./authentication.md).
 ### Dynamic configuration
--- a/docs/configuration/authentication.md
+++ b/docs/configuration/authentication.md
@@ -1,23 +0,0 @@
 ## 🔐 Authentication
 baibot supports 2 authentication modes for the Matrix account (`user.*` keys in config).
 Set **exactly one** mode. If both are set (or neither is set), startup validation fails.
 ### Password authentication
 - Config key: `user.password`
 - Environment variable: `BAIBOT_USER_PASSWORD`
 ### Access token authentication
 - Config keys: `user.access_token` + `user.device_id`
 - Environment variables: `BAIBOT_USER_ACCESS_TOKEN` + `BAIBOT_USER_DEVICE_ID`
 Access-token authentication is useful for OIDC-enabled homeservers (e.g. those using [Matrix Authentication Service](https://github.com/element-hq/matrix-authentication-service)).
 Example token-generation command:
 ```sh
 mas-cli manage issue-compatibility-token <username> [device_id]
 ```
--- a/docs/development.md
+++ b/docs/development.md
@@ -18,27 +18,6 @@ For local development, we run all dependency services in [🐋 Docker](https://w
 - (Optional) an API key for some Large Language Model [☁️ provider](./providers.md) (e.g. [OpenAI](./providers.md#openai)), though we recommend using [LocalAI](#localai) or [Ollama](#ollama) for local development
 ### Choosing a homeserver
 The development environment supports two homeserver implementations:
 - **[Continuwuity](https://continuwuity.org/)** (default) — lightweight, no external database required. Good for most development needs.
 - **[Synapse](https://github.com/element-hq/synapse)** — the reference implementation, bundled with Postgres. Use this if you need Synapse-specific behavior.
 To choose a homeserver (optional — defaults to Continuwuity if skipped):
 ```sh
 just homeserver-init continuwuity  # or: just homeserver-init synapse
 ```
 The choice is stored in `var/homeserver` and affects all subsequent commands.
 > **Note:** If you switch homeservers after initial setup, you will need to:
 > - Delete `var/app/local/` and/or `var/app/container/` (app config and data)
 > - Delete `var/services/element-web/` (to regenerate its config)
 > - Re-run the prepare and user registration steps
 ### Getting started guide
 Developing [locally](#running-locally) is possible, but requires a [Rust](https://www.rust-lang.org/) toolchain.
@@ -49,12 +28,11 @@ In any case, you will need [🐋 Docker](https://www.docker.com/) as [dependency
 #### Running locally
-1. (Optional) Choose a homeserver: `just homeserver-init continuwuity` (or `synapse`). Default is `continuwuity`.
+1. Start the core dependency services (Postgres, Synapse, Element Web): `just services-start`
-2. Start the homeserver and Element Web: `just services-start`
+2. (Only the first time around) Prepare initial app configuration in `var/app/local/config.yml`: `just app-local-prepare`
-3. (Only the first time around) Prepare initial app configuration in `var/app/local/config.yml`: `just app-local-prepare`
+3. (Only the first time around) [Prepare your configuration file](#prepare-your-configuration-file)
-4. (Only the first time around) [Prepare your configuration file](#prepare-your-configuration-file)
+4. (Only the first time around) Prepare initial default Matrix user accounts (`admin` and `baibot`): `just users-prepare`
-5. (Only the first time around) Prepare initial default Matrix user accounts (`admin` and `baibot`): `just users-prepare`
+5. (Optional) Start additional services depending on which [agent provider you've chosen](#choosing-an-agent-provider):
 6. (Optional) Start additional services depending on which [agent provider you've chosen](#choosing-an-agent-provider):
  - for [LocalAI](#localai):
    - Start services: `just localai-start`
 	- Wait a while for LocalAI to start up. It has a lot of models to download. Monitor progress using `just localai-tail-logs`
@@ -62,12 +40,12 @@ In any case, you will need [🐋 Docker](https://www.docker.com/) as [dependency
  - for [Ollama](#ollama):
    - Start services: `just ollama-start`
    - (Only the first time around) Pull the model configured in `agents.static_definitions` in the configuration file: `just ollama-pull-model gemma2:2b`
-7. Start the bot: `just run-locally`
+6. Start the bot: `just run-locally`
-8. Go to http://element.127.0.0.1.nip.io:42025/ and login with `admin` / `admin`
+7. Go to http://element.127.0.0.1.nip.io:42025/ and login with `admin` / `admin`
-9. Create a new room and invite `@baibot:continuwuity.127.0.0.1.nip.io` (or `@baibot:synapse.127.0.0.1.nip.io` if using Synapse)
+8. Create a new room and invite `@baibot:synapse.127.0.0.1.nip.io`
-10. When done, stop the bot (`Ctrl` + `C`)
+9. When done, stop the bot (`Ctrl` + `C`)
-11. Stop the services: `just services-stop`
+10. Stop the core dependency services: `just services-stop`
-12. (Optional) Stop additional services:
+11. (Optional) Stop additional services:
  - for [LocalAI](#localai): `just localai-stop`
  - for [Ollama](#ollama): `just ollama-stop`
@@ -76,12 +54,11 @@ In any case, you will need [🐋 Docker](https://www.docker.com/) as [dependency
 You can avoid having a [Rust](https://www.rust-lang.org/) toolchain installed locally and build/run this in a container.
-1. (Optional) Choose a homeserver: `just homeserver-init continuwuity` (or `synapse`). Default is `continuwuity`.
+1. Start the core dependency services (Postgres, Synapse, Element Web): `just services-start`
-2. Start the homeserver and Element Web: `just services-start`
+2. (Only the first time around) Prepare initial app configuration in `var/app/container/config.yml`: `just app-container-prepare`
-3. (Only the first time around) Prepare initial app configuration in `var/app/container/config.yml`: `just app-container-prepare`
+3. (Only the first time around) [Prepare your configuration file](#prepare-your-configuration-file)
-4. (Only the first time around) [Prepare your configuration file](#prepare-your-configuration-file)
+4. (Only the first time around) Prepare initial default Matrix user accounts (`admin` and `baibot`): `just users-prepare`
-5. (Only the first time around) Prepare initial default Matrix user accounts (`admin` and `baibot`): `just users-prepare`
+5. (Optional) Start additional services depending on which [agent provider you've chosen](#choosing-an-agent-provider):
 6. (Optional) Start additional services depending on which [agent provider you've chosen](#choosing-an-agent-provider):
  - for [LocalAI](#localai):
    - Start services: `just localai-start`
 	- Wait a while for LocalAI to start up. It has a lot of models to download. Monitor progress using `just localai-tail-logs`
@@ -89,12 +66,12 @@ You can avoid having a [Rust](https://www.rust-lang.org/) toolchain installed lo
  - for [Ollama](#ollama):
    - Start services: `just ollama-start`
    - (Only the first time around) Pull the model configured in `agents.static_definitions` in the configuration file: `just ollama-pull-model gemma2:2b`
-7. Start the bot: `just run-in-container`
+6. Start the bot: `just run-in-container`
-8. Go to http://element.127.0.0.1.nip.io:42025/ and login with `admin` / `admin`
+7. Go to http://element.127.0.0.1.nip.io:42025/ and login with `admin` / `admin`
-9. Create a new room and invite `@baibot:continuwuity.127.0.0.1.nip.io` (or `@baibot:synapse.127.0.0.1.nip.io` if using Synapse)
+8. Create a new room and invite `@baibot:synapse.127.0.0.1.nip.io`
-10. When done, stop the bot (`Ctrl` + `C`)
+9. When done, stop the bot (`Ctrl` + `C`)
-11. Stop the services: `just services-stop`
+10. Stop the dependency services: `just services-stop`
-12. (Optional) Stop additional services:
+11. (Optional) Stop additional services:
  - for [LocalAI](#localai): `just localai-stop`
  - for [Ollama](#ollama): `just ollama-stop`
--- a/docs/features.md
+++ b/docs/features.md
@@ -40,23 +40,6 @@ You may also wish to see:
 - [📖 Usage / 💬 Text Generation](./usage.md#-text-generation) section for more details on how to use the bot for Text Generation in a room
 #### 🛠️ Built-in Tools (OpenAI only)
 The [OpenAI provider](./providers.md#openai) supports built-in tools that extend the model's capabilities:
 - [🔍 Web Search](https://platform.openai.com/docs/guides/tools-web-search) (`web_search`): allows the model to search the web for up-to-date information. [🖼️ Screenshot](./screenshots/text-generation-tools-web-search.webp)
 - [💻 Code Interpreter](https://platform.openai.com/docs/guides/tools-code-interpreter) (`code_interpreter`): allows the model to write and execute Python code in a sandbox
 These tools are **disabled by default** and need to be explicitly enabled in the agent's `text_generation.tools` configuration. See the [OpenAI sample configuration](https://github.com/etkecc/baibot/blob/c70387b0c38d8d0f30bba2179a2a21a3710dbeaf/docs/sample-provider-configs/openai.yml#L12-L15) for reference.
 To enable tools on an existing dynamically-created agent, you need to [update the agent](./agents.md#updating-agents) to re-create it with the `text_generation.tools` section added and enable the tools you need
 💡 **Note**: These tools run on OpenAI's infrastructure and may incur additional costs. Web search results include citations that are incorporated into the response.
 #### On-demand involvement
 In the following 2 cases, it's useful to involve the bot in conversations on-demand:
--- 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) (incl. vision, incl. [🛠️ tools](./features.md#️-built-in-tools-openai-only)), [🖌️ 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) (incl. vision, no tools)
+- 🌟 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) (no vision, no tools), [🦻 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) (no vision, no tools), [🗣️ 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) (no vision, no tools)
+- 🌟 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) (no vision, no tools)
+- 🌟 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`
@@ -120,12 +120,15 @@ 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-creation), [💬 text-generation](./features.md#-text-generation) (incl. vision, incl. [🛠️ tools](./features.md#️-built-in-tools-openai-only)), [🗣️ 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 looks [like this](./sample-provider-configs/openai.yml).
+💡 When creating an agent, the bot will show you an up-to-date sample configuration for this provider which:
 - in the general case looks [like this](./sample-provider-configs/openai.yml)
 - for the [o1](https://platform.openai.com/docs/models/o1) models needs to look [like this](./sample-provider-configs/openai-o1.yml)
 ### OpenAI Compatible
@@ -137,7 +140,7 @@ 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-creation), [💬 text-generation](./features.md#-text-generation) (no vision, no tools), [🗣️ 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`
@@ -151,7 +154,7 @@ 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) (no vision, no tools)
+- 🌟 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`
@@ -165,7 +168,7 @@ 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) (no vision, no tools)
+- 🌟 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/openai-o1.yml
+++ b/docs/sample-provider-configs/openai-o1.yml
@@ -0,0 +1,24 @@
 base_url: https://api.openai.com/v1
 api_key: YOUR_API_KEY_HERE
 text_generation:
  model_id: o1-mini
  # o1 models do not support a system prompt
  prompt: null
  temperature: 1.0
  # o1 models do not support max_response_tokens.
  # They use `max_completion_tokens` as an alternative
  max_response_tokens: null
  max_completion_tokens: 16384
  max_context_tokens: 128000
 speech_to_text:
  model_id: whisper-1
 text_to_speech:
  model_id: tts-1-hd
  voice: onyx
  speed: 1.0
  response_format: opus
 image_generation:
  model_id: gpt-image-1
  style: null
  size: null
  quality: null
--- a/docs/sample-provider-configs/openai.yml
+++ b/docs/sample-provider-configs/openai.yml
@@ -1,18 +1,11 @@
 base_url: https://api.openai.com/v1
 api_key: YOUR_API_KEY_HERE
 text_generation:
-  model_id: gpt-5.2
+  model_id: gpt-5
  prompt: "You are a brief, but helpful bot called {{ baibot_name }} powered by the {{ baibot_model_id }} model. The date/time of this conversation's start is: {{ baibot_conversation_start_time_utc }}."
  temperature: 1.0
-  # Reasoning models need to use `max_completion_tokens` instead of `max_response_tokens`.
+  max_response_tokens: 16384
-  # If you're dealing with a non-reasoning model, specify `max_response_tokens` and unset `max_completion_tokens`.
+  max_context_tokens: 128000
  max_response_tokens: null
  max_completion_tokens: 128000
  max_context_tokens: 400000
  # Built-in tools
  tools:
    web_search: false
    code_interpreter: false
 speech_to_text:
  model_id: whisper-1
 text_to_speech:
@@ -21,7 +14,7 @@ text_to_speech:
  speed: 1.0
  response_format: opus
 image_generation:
-  model_id: gpt-image-1.5
+  model_id: gpt-image-1
  style: null
  size: null
  quality: null
--- a/docs/screenshots/text-generation-tools-web-search.webp
+++ b/docs/screenshots/text-generation-tools-web-search.webp
--- a/etc/app/config.yml.dist
+++ b/etc/app/config.yml.dist
@@ -1,31 +1,16 @@
 homeserver:
  # The canonical homeserver domain name
-  server_name: __HOMESERVER_SERVER_NAME__
+  server_name: synapse.127.0.0.1.nip.io
-  url: __HOMESERVER_URL__
+  url: http://synapse.127.0.0.1.nip.io:42020
 user:
  mxid_localpart: baibot
  # Authentication: set EITHER password OR access_token + device_id.
  #
  # Password-based login (traditional homeservers):
  password: baibot
  # Access token login (for Matrix Authentication Service/OIDC-enabled homeservers):
  # Generate a token via: mas-cli manage issue-compatibility-token <username> [device_id]
  # access_token: null
  # device_id: null
  # The name the bot uses as a display name and when it refers to itself.
  # Leave empty to use the default (baibot).
  name: baibot
  # An optional path to an image file to be used as a custom avatar image.
  # - null or empty string: use the default avatar
  # - "keep": don't touch the avatar, keep whatever is already set
  # - any other value: path to a custom avatar image file
  avatar: null
  encryption:
    # An optional passphrase to use for backing up and recovering the bot's encryption keys.
    # You can use any string here.
@@ -54,7 +39,7 @@ room:
 access:
  # Space-separated list of MXID patterns which specify who is an admin.
  admin_patterns:
-    - "@admin:__HOMESERVER_SERVER_NAME__"
+    - "@admin:synapse.127.0.0.1.nip.io"
 persistence:
  # This is unset here, because we expect the configuration to come from an environment variable (BAIBOT_PERSISTENCE_DATA_DIR_PATH).
@@ -91,18 +76,13 @@ agents:
    #     base_url: https://api.openai.com/v1
    #     api_key: ""
    #     text_generation:
-    #       model_id: gpt-5.2
+    #       model_id: gpt-5
    #       prompt: "You are a brief, but helpful bot called {{ baibot_name }} powered by the {{ baibot_model_id }} model. The date/time of this conversation's start is: {{ baibot_conversation_start_time_utc }}."
    #       temperature: 1.0
    #       max_response_tokens: ~
    #       # Reasoning models need to use `max_completion_tokens` instead of `max_response_tokens`.
    #       # If you're dealing with a non-reasoning model, specify `max_response_tokens` and unset `max_completion_tokens`.
    #       max_response_tokens: null
    #       max_completion_tokens: 128000
    #       max_context_tokens: 400000
    #       # Built-in tools
    #       tools:
    #         web_search: false
    #         code_interpreter: false
    #     speech_to_text:
    #       model_id: whisper-1
    #     text_to_speech:
@@ -111,7 +91,7 @@ agents:
    #       speed: 1.0
    #       response_format: opus
    #     image_generation:
-    #       model_id: gpt-image-1.5
+    #       model_id: gpt-image-1
    #       style: null
    #       size: null
    #       quality: null
@@ -166,7 +146,7 @@ initial_global_config:
  # Space-separated list of MXID patterns which specify who can use the bot.
  # By default, we let anyone on the homeserver use the bot.
  user_patterns:
-    - "@*:__HOMESERVER_SERVER_NAME__"
+    - "@*:synapse.127.0.0.1.nip.io"
 # Controls logging.
 #
--- a/etc/services/continuwuity/compose.yml
+++ b/etc/services/continuwuity/compose.yml
@@ -1,23 +0,0 @@
 services:
  continuwuity:
    image: forgejo.ellis.link/continuwuation/continuwuity:v0.5.6
    user: "${UID}:${GID}"
    restart: unless-stopped
    cap_drop:
      - ALL
    read_only: true
    environment:
      CONDUWUIT_CONFIG: /etc/continuwuity/continuwuity.toml
      CONDUWUIT_DATABASE_PATH: /var/lib/continuwuity
    ports:
      - "${SERVICE_CONTINUWUITY_BIND_PORT_CLIENT_API}:6167"
    volumes:
      - ../../etc/services/continuwuity/config:/etc/continuwuity:ro
      - ./continuwuity/data:/var/lib/continuwuity
    tmpfs:
      - /tmp:rw,noexec,nosuid,size=500m
 networks:
  default:
    name: ${NETWORK_NAME}
    external: true
--- a/etc/services/continuwuity/config/continuwuity.toml
+++ b/etc/services/continuwuity/config/continuwuity.toml
@@ -1,19 +0,0 @@
 [global]
 server_name = "continuwuity.127.0.0.1.nip.io"
 address = "0.0.0.0"
 port = 6167
 database_path = "/var/lib/continuwuity"
 allow_registration = true
 yes_i_am_very_very_sure_i_want_an_open_registration_server_prone_to_abuse = true
 new_user_displayname_suffix = ""
 max_request_size = 20_000_000
 allow_federation = false
 trusted_servers = ["matrix.org"]
 log = "info,state_res=warn,rocket=off,_=off,sled=off"
--- a/etc/services/continuwuity/register-user.sh
+++ b/etc/services/continuwuity/register-user.sh
@@ -1,48 +0,0 @@
 #!/bin/sh
 set -eu
 if [ $# -ne 3 ]; then
 	echo "Usage: $0 <env-file> <username> <password>"
 	exit 1
 fi
 ENV_FILE="$1"
 USERNAME="$2"
 PASSWORD="$3"
 SERVER="http://$(grep '^SERVICE_CONTINUWUITY_BIND_PORT_CLIENT_API=' "${ENV_FILE}" | cut -d= -f2)"
 REGISTER_URL="${SERVER}/_matrix/client/v3/register"
 echo "Registering user '${USERNAME}' on ${SERVER}..."
 SESSION_RESPONSE=$(curl -s -X POST "${REGISTER_URL}" \
 	-H 'Content-Type: application/json' \
 	-d "{\"username\": \"${USERNAME}\", \"password\": \"${PASSWORD}\"}")
 SESSION_ID=$(echo "${SESSION_RESPONSE}" | grep -o '"session":"[^"]*"' | head -1 | cut -d'"' -f4)
 if [ -z "${SESSION_ID}" ]; then
 	echo "Error: Could not get session ID. Response: ${SESSION_RESPONSE}"
 	exit 1
 fi
 # Determine the required auth flow from the server response.
 # The first user requires m.login.registration_token (bootstrap token from logs).
 # Subsequent users use m.login.dummy (open registration).
 if echo "${SESSION_RESPONSE}" | grep -q 'm.login.registration_token'; then
 	CONTAINER_ID=$(docker ps -q --filter name=baibot-continuwuity-continuwuity)
 	REG_TOKEN=$(docker logs "${CONTAINER_ID}" 2>&1 | sed 's/\x1b\[[0-9;]*m//g' | grep 'using the registration token' | grep -oP 'registration token \K[A-Za-z0-9]+' | head -1)
 	AUTH_BODY="{\"type\": \"m.login.registration_token\", \"token\": \"${REG_TOKEN}\", \"session\": \"${SESSION_ID}\"}"
 else
 	AUTH_BODY="{\"type\": \"m.login.dummy\", \"session\": \"${SESSION_ID}\"}"
 fi
 RESULT=$(curl -s -X POST "${REGISTER_URL}" \
 	-H 'Content-Type: application/json' \
 	-d "{\"username\": \"${USERNAME}\", \"password\": \"${PASSWORD}\", \"auth\": ${AUTH_BODY}}")
 if echo "${RESULT}" | grep -q '"user_id"'; then
 	echo "Successfully registered user: $(echo "${RESULT}" | grep -o '"user_id":"[^"]*"' | cut -d'"' -f4)"
 else
 	echo "Registration failed. Response: ${RESULT}"
 	exit 1
 fi
--- a/etc/services/synapse/compose.yml
+++ b/etc/services/synapse/compose.yml
@@ -1,6 +1,6 @@
 services:
  postgres:
-    image: docker.io/postgres:18.3-alpine
+    image: docker.io/postgres:18.0-alpine
    user: ${UID}:${GID}
    restart: unless-stopped
    environment:
@@ -14,7 +14,7 @@ services:
    - /etc/passwd:/etc/passwd:ro
  synapse:
-    image: ghcr.io/element-hq/synapse:v1.148.0
+    image: ghcr.io/element-hq/synapse:v1.140.0
    user: "${UID}:${GID}"
    restart: unless-stopped
    entrypoint: python
@@ -23,9 +23,25 @@ services:
    - "${SERVICE_SYNAPSE_BIND_PORT_CLIENT_API}:8008"
    - "${SERVICE_SYNAPSE_BIND_PORT_FEDERATION_API}:8008"
    volumes:
-    - ../../etc/services/synapse/config:/config:ro
+    - ../../etc/services/core/synapse/config:/config:ro
    - ./synapse/media-store:/media-store
  element-web:
    image: ghcr.io/element-hq/element-web:v1.12.2
    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/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:
    name: ${NETWORK_NAME}
--- a/etc/services/core/element-web/config.json
+++ b/etc/services/core/element-web/config.json
@@ -1,5 +1,5 @@
 {
-    "default_hs_url": "__HOMESERVER_CLIENT_URL__",
+    "default_hs_url": "http://synapse.127.0.0.1.nip.io:42020",
    "default_is_url": "https://vector.im",
    "integrations_ui_url": "https://scalar.vector.im/",
    "integrations_rest_url": "https://scalar.vector.im/api",
--- a/etc/services/core/synapse/config/homeserver.yaml
+++ b/etc/services/core/synapse/config/homeserver.yaml
--- a/etc/services/core/synapse/config/synapse.127.0.0.1.nip.io.log.config
+++ b/etc/services/core/synapse/config/synapse.127.0.0.1.nip.io.log.config
--- a/etc/services/core/synapse/config/synapse.127.0.0.1.nip.io.signing.key
+++ b/etc/services/core/synapse/config/synapse.127.0.0.1.nip.io.signing.key
--- a/etc/services/element-web/compose.yml
+++ b/etc/services/element-web/compose.yml
@@ -1,21 +0,0 @@
 services:
  element-web:
    image: ghcr.io/element-hq/element-web:v1.12.11
    user: "${UID}:${GID}"
    restart: unless-stopped
    environment:
      ELEMENT_WEB_PORT: 8080
    ports:
      - "${SERVICE_ELEMENT_WEB_BIND_PORT_HTTP}:8080"
    volumes:
    - ./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:
    name: ${NETWORK_NAME}
    external: true
--- a/etc/services/env.dist
+++ b/etc/services/env.dist
@@ -3,8 +3,6 @@ SERVICE_SYNAPSE_BIND_PORT_FEDERATION_API=127.0.0.1:42028
 SERVICE_ELEMENT_WEB_BIND_PORT_HTTP=127.0.0.1:42025
 SERVICE_CONTINUWUITY_BIND_PORT_CLIENT_API=127.0.0.1:42030
 SERVICE_OLLAMA_BIND_PORT_HTTP=127.0.0.1:42026
 # See https://localai.io/basics/container/#all-in-one-images for the list of available images
--- a/etc/services/ollama/compose.yml
+++ b/etc/services/ollama/compose.yml
@@ -1,6 +1,6 @@
 services:
  ollama:
-    image: docker.io/ollama/ollama:0.17.7
+    image: docker.io/ollama/ollama:0.12.6
    restart: unless-stopped
    ports:
      - "${SERVICE_OLLAMA_BIND_PORT_HTTP}:11434"
--- a/212
+++ b/212
@@ -2,33 +2,10 @@ project_name := "baibot"
 container_image_name := "localhost/baibot"
 project_container_network := "baibot"
 admin_username := "admin"
 admin_password := "admin"
 bot_username := "baibot"
 bot_password := "baibot"
 homeserver := `cat var/homeserver 2>/dev/null || echo continuwuity`
 mise_data_dir := env("MISE_DATA_DIR", justfile_directory() / "var/mise")
 mise_trusted_config_paths := justfile_directory() / "mise.toml"
 # Show help by default
 default:
 	@just --list --justfile {{ justfile() }}
 # Selects which homeserver implementation to use (continuwuity or synapse)
 homeserver-init value:
 	#!/bin/sh
 	mkdir -p {{ justfile_directory() }}/var
 	echo {{ value }} > {{ justfile_directory() }}/var/homeserver
 	echo ""
 	echo "⚠️  If you had already prepared your app configuration (var/app/local/config.yml or var/app/container/config.yml),"
 	echo "    you will need to update it manually or delete it and re-run the prepare step."
 	echo "    You should also delete var/app/local/data and/or var/app/container/data,"
 	echo "    as old application state is not compatible across homeserver implementations."
 	echo ""
 	echo "⚠️  If Element Web was already prepared, delete var/services/element-web/ to regenerate its config."
 # Builds and runs a development binary
 run-locally *extra_args: app-local-prepare
 	RUST_BACKTRACE=1 \
@@ -88,13 +65,9 @@ docker-compose services_type *extra_args:
 	-p {{ project_name }}-{{ services_type }} \
 	{{ extra_args }}
-# Runs a docker-compose command against the synapse services
+# Runs a docker-compose command against the core services
-docker-compose-synapse *extra_args:
+docker-compose-core *extra_args:
-	just docker-compose synapse {{ extra_args }}
+	just docker-compose core {{ extra_args }}
 # Runs a docker-compose command against the element-web services
 docker-compose-element-web *extra_args:
 	just docker-compose element-web {{ extra_args }}
 # Runs a docker-compose command against the localai services
 docker-compose-localai *extra_args:
@@ -104,52 +77,17 @@ docker-compose-localai *extra_args:
 docker-compose-ollama *extra_args:
 	just docker-compose ollama {{ extra_args }}
-# Runs a docker-compose command against the continuwuity services
+# Runs all core dependency components (in the background)
-docker-compose-continuwuity *extra_args:
+services-start: services-prepare (docker-compose-core "up" "-d")
 	just docker-compose continuwuity {{ extra_args }}
-# Runs the homeserver and Element Web (in the background)
+# Stops all core dependency components
-services-start: services-prepare
+services-stop: (docker-compose-core "down")
 	just -f {{ justfile_directory() }}/justfile {{ homeserver }}-start
 	just -f {{ justfile_directory() }}/justfile element-web-start
-# Stops Element Web and the homeserver
+# Tails the logs for all running core services
-services-stop:
+services-tail-logs: (docker-compose-core "logs" "-f")
 	just -f {{ justfile_directory() }}/justfile element-web-stop
 	just -f {{ justfile_directory() }}/justfile {{ homeserver }}-stop
-# Tails the logs for the homeserver and Element Web
+# Prepares the core services for running
-services-tail-logs:
+services-prepare: _prepare-var-services-env _prepare-var-services-postgres _prepare-var-services-synapse _prepare-container-network
 	just -f {{ justfile_directory() }}/justfile {{ homeserver }}-tail-logs
 # Prepares the homeserver and Element Web for running
 services-prepare:
 	just -f {{ justfile_directory() }}/justfile {{ homeserver }}-prepare
 	just -f {{ justfile_directory() }}/justfile element-web-prepare
 # Runs Synapse (in the background)
 synapse-start: synapse-prepare (docker-compose-synapse "up" "-d")
 # Stops Synapse
 synapse-stop: (docker-compose-synapse "down")
 # Tails the logs for Synapse
 synapse-tail-logs: (docker-compose-synapse "logs" "-f")
 # Prepares Synapse for running
 synapse-prepare: _prepare-var-services-env _prepare-var-services-postgres _prepare-var-services-synapse _prepare-container-network
 # Runs Element Web (in the background)
 element-web-start: element-web-prepare (docker-compose-element-web "up" "-d")
 # Stops Element Web
 element-web-stop: (docker-compose-element-web "down")
 # Tails the logs for Element Web
 element-web-tail-logs: (docker-compose-element-web "logs" "-f")
 # Prepares Element Web for running
 element-web-prepare: _prepare-var-services-env _prepare-var-services-element-web _prepare-container-network
 # Runs LocalAI (in the background)
 localai-start: localai-prepare (docker-compose-localai "up" "-d")
@@ -175,27 +113,6 @@ ollama-tail-logs: (docker-compose-ollama "logs" "-f")
 # Prepares Ollama for running
 ollama-prepare: _prepare-var-services-env _prepare-var-services-ollama _prepare-container-network
 # Runs Continuwuity (in the background)
 continuwuity-start: continuwuity-prepare (docker-compose-continuwuity "up" "-d")
 # Stops Continuwuity
 continuwuity-stop: (docker-compose-continuwuity "down")
 # Tails the logs for Continuwuity
 continuwuity-tail-logs: (docker-compose-continuwuity "logs" "-f")
 # Prepares Continuwuity for running
 continuwuity-prepare: _prepare-var-services-env _prepare-var-services-continuwuity _prepare-container-network
 # Registers a user on Continuwuity via the Matrix Client-Server API
 continuwuity-register-user username password:
 	{{ justfile_directory() }}/etc/services/continuwuity/register-user.sh {{ justfile_directory() }}/var/services/env {{ username }} {{ password }}
 # Prepares the Continuwuity user accounts
 continuwuity-users-prepare: continuwuity-prepare
 	just -f {{ justfile_directory() }}/justfile continuwuity-register-user "{{ admin_username }}" "{{ admin_password }}"
 	just -f {{ justfile_directory() }}/justfile continuwuity-register-user "{{ bot_username }}" "{{ bot_password }}"
 # Pulls an Ollama model
 ollama-pull-model model_id:
 	just -f {{ justfile_directory() }}/justfile docker-compose-ollama \
@@ -209,20 +126,16 @@ app-local-prepare: _prepare-var-app-local-config_yml _prepare-var-app-local-data
 app-container-prepare: _prepare-var-app-container-config_yml _prepare-var-app-container-data
 # Prepares the user accounts
-users-prepare:
+users-prepare: services-prepare
-	just -f {{ justfile_directory() }}/justfile {{ homeserver }}-users-prepare
+	just -f {{ justfile_directory() }}/justfile synapse-register-admin-user "admin" "admin"
-
+	just -f {{ justfile_directory() }}/justfile synapse-register-regular-user "baibot" "baibot"
 # Prepares the Synapse user accounts
 synapse-users-prepare: synapse-prepare
 	just -f {{ justfile_directory() }}/justfile synapse-register-admin-user "{{ admin_username }}" "{{ admin_password }}"
 	just -f {{ justfile_directory() }}/justfile synapse-register-regular-user "{{ bot_username }}" "{{ bot_password }}"
 # Starts a Postgres CLI (psql)
-postgres-cli: synapse-prepare (docker-compose-synapse "exec" "postgres" "/bin/sh" "-c" "'PGUSER=synapse PGPASSWORD=synapse-password PGDATABASE=homeserver psql -h postgres'")
+postgres-cli: services-prepare (docker-compose-core "exec" "postgres" "/bin/sh" "-c" "'PGUSER=synapse PGPASSWORD=synapse-password PGDATABASE=homeserver psql -h postgres'")
-# Creates an administrator user on Synapse
+# Creates an administrator user
-synapse-register-admin-user username password: synapse-prepare
+synapse-register-admin-user username password: services-prepare
-	just -f {{ justfile_directory() }}/justfile docker-compose-synapse \
+	just -f {{ justfile_directory() }}/justfile docker-compose-core \
 		exec synapse \
 		register_new_matrix_user \
 		--admin \
@@ -231,9 +144,9 @@ synapse-register-admin-user username password: synapse-prepare
 		-c /config/homeserver.yaml \
 		http://localhost:8008
-# Creates a regular user on Synapse
+# Create a regular user
-synapse-register-regular-user username password: synapse-prepare
+synapse-register-regular-user username password: services-prepare
-	just -f {{ justfile_directory() }}/justfile docker-compose-synapse \
+	just -f {{ justfile_directory() }}/justfile docker-compose-core \
 		exec synapse \
 		register_new_matrix_user \
 		--no-admin \
@@ -246,44 +159,6 @@ synapse-register-regular-user username password: synapse-prepare
 clippy *extra_args:
 	cargo clippy {{ extra_args }}
 # Checks that the code compiles without building
 check:
 	cargo check
 # Invokes mise with the project-local data directory
 mise *args: _ensure_mise_data_directory
 	#!/bin/sh
 	export MISE_DATA_DIR="{{ mise_data_dir }}"
 	export MISE_TRUSTED_CONFIG_PATHS="{{ mise_trusted_config_paths }}"
 	mise {{ args }}
 # Runs prek (pre-commit hooks manager) with the given arguments
 prek *args: _ensure_mise_tools_installed
 	@just --justfile {{ justfile() }} mise exec -- prek {{ args }}
 # Runs pre-commit hooks on staged files
 prek-run-on-staged *args: _ensure_mise_tools_installed
 	@just --justfile {{ justfile() }} mise exec -- prek run {{ args }}
 # Runs pre-commit hooks on all files
 prek-run-on-all *args: _ensure_mise_tools_installed
 	@just --justfile {{ justfile() }} mise exec -- prek run --all-files {{ args }}
 # Installs the git pre-commit hook (runs prek automatically before each commit)
 prek-install-git-pre-commit-hook: _ensure_mise_tools_installed
 	@just --justfile {{ justfile() }} mise exec -- prek install
 # Internal - ensures var/mise directory exists
 _ensure_mise_data_directory:
 	#!/bin/sh
 	if [ ! -d "{{ mise_data_dir }}" ]; then
 		mkdir -p "{{ mise_data_dir }}"
 	fi
 # Internal - ensures mise tools are installed
 _ensure_mise_tools_installed: _ensure_mise_data_directory
 	@just --justfile {{ justfile() }} mise install --quiet
 _prepare-var-services-env:
 	#!/bin/sh
 	cd {{ justfile_directory() }};
@@ -313,22 +188,6 @@ _prepare-var-services-synapse:
 		mkdir -p var/services/synapse/media-store
 	fi
 _prepare-var-services-element-web:
 	#!/bin/sh
 	cd {{ justfile_directory() }};
 	if [ ! -f var/services/element-web/config.json ]; then
 		mkdir -p var/services/element-web
 		cp {{ justfile_directory() }}/etc/services/element-web/config.json.dist var/services/element-web/config.json
 		homeserver="{{ homeserver }}"
 		if [ "$homeserver" = "continuwuity" ]; then
 			sed --in-place 's|__HOMESERVER_CLIENT_URL__|http://continuwuity.127.0.0.1.nip.io:42030|g' var/services/element-web/config.json
 		elif [ "$homeserver" = "synapse" ]; then
 			sed --in-place 's|__HOMESERVER_CLIENT_URL__|http://synapse.127.0.0.1.nip.io:42020|g' var/services/element-web/config.json
 		fi
 	fi
 _prepare-var-services-ollama:
 	#!/bin/sh
 	cd {{ justfile_directory() }};
@@ -337,14 +196,6 @@ _prepare-var-services-ollama:
 		mkdir -p var/services/ollama
 	fi
 _prepare-var-services-continuwuity:
 	#!/bin/sh
 	cd {{ justfile_directory() }};
 	if [ ! -f var/services/continuwuity ]; then
 		mkdir -p var/services/continuwuity/data
 	fi
 _prepare-var-services-localai:
 	#!/bin/sh
 	cd {{ justfile_directory() }};
@@ -368,15 +219,6 @@ _prepare-var-app-local-config_yml:
 	if [ ! -f var/app/local/config.yml ]; then
 		mkdir -p var/app/local
 		cp {{ justfile_directory() }}/etc/app/config.yml.dist var/app/local/config.yml
 		homeserver="{{ homeserver }}"
 		if [ "$homeserver" = "continuwuity" ]; then
 			sed --in-place 's/__HOMESERVER_SERVER_NAME__/continuwuity.127.0.0.1.nip.io/g' var/app/local/config.yml
 			sed --in-place 's|__HOMESERVER_URL__|http://continuwuity.127.0.0.1.nip.io:42030|g' var/app/local/config.yml
 		elif [ "$homeserver" = "synapse" ]; then
 			sed --in-place 's/__HOMESERVER_SERVER_NAME__/synapse.127.0.0.1.nip.io/g' var/app/local/config.yml
 			sed --in-place 's|__HOMESERVER_URL__|http://synapse.127.0.0.1.nip.io:42020|g' var/app/local/config.yml
 		fi
 	fi
 _prepare-var-app-local-data:
@@ -394,18 +236,7 @@ _prepare-var-app-container-config_yml:
 	if [ ! -f var/app/container/config.yml ]; then
 		mkdir -p var/app/container
 		cp {{ justfile_directory() }}/etc/app/config.yml.dist var/app/container/config.yml
 		homeserver="{{ homeserver }}"
 		if [ "$homeserver" = "continuwuity" ]; then
 			sed --in-place 's/__HOMESERVER_SERVER_NAME__/continuwuity.127.0.0.1.nip.io/g' var/app/container/config.yml
 			sed --in-place 's|__HOMESERVER_URL__|http://continuwuity.127.0.0.1.nip.io:42030|g' var/app/container/config.yml
 			sed --in-place 's/continuwuity.127.0.0.1.nip.io:42030/continuwuity:6167/g' var/app/container/config.yml
 		elif [ "$homeserver" = "synapse" ]; then
 			sed --in-place 's/__HOMESERVER_SERVER_NAME__/synapse.127.0.0.1.nip.io/g' var/app/container/config.yml
 			sed --in-place 's|__HOMESERVER_URL__|http://synapse.127.0.0.1.nip.io:42020|g' var/app/container/config.yml
 		sed --in-place 's/synapse.127.0.0.1.nip.io:42020/synapse:8008/g' var/app/container/config.yml
 		fi
 		sed --in-place 's/127.0.0.1:42026/ollama:11434/g' var/app/container/config.yml
 		sed --in-place 's/127.0.0.1:42027/localai:8080/g' var/app/container/config.yml
 	fi
@@ -417,3 +248,4 @@ _prepare-var-app-container-data:
 	if [ ! -f var/app/container/data ]; then
 		mkdir -p var/app/container/data
 	fi
--- a/mise.toml
+++ b/mise.toml
@@ -1,6 +0,0 @@
 [tools]
 prek = "0.3.2"
 [settings]
 # Disable automatic trust prompts - we trust this config
 yes = true
--- a/renovate.json
+++ b/renovate.json
@@ -1,9 +0,0 @@
 {
 	"$schema": "https://docs.renovatebot.com/renovate-schema.json",
 	"extends": [
 		"config:recommended"
 	],
 	"labels": [
 		"dependencies"
 	]
 }
--- a/rust-toolchain.toml
+++ b/rust-toolchain.toml
@@ -1,4 +0,0 @@
 [toolchain]
 channel = "1.93.0"
 components = ["rustfmt", "clippy"]
 profile = "default"
--- a/src/agent/definition.rs
+++ b/src/agent/definition.rs
@@ -33,11 +33,11 @@ pub struct AgentDefinition {
    )]
    pub provider: AgentProvider,
-    pub config: serde_yaml_ng::Value,
+    pub config: serde_yaml::Value,
 }
 impl AgentDefinition {
-    pub fn new(id: String, provider: AgentProvider, config: serde_yaml_ng::Value) -> Self {
+    pub fn new(id: String, provider: AgentProvider, config: serde_yaml::Value) -> Self {
        Self {
            id,
            provider,
--- a/src/agent/instantiation.rs
+++ b/src/agent/instantiation.rs
@@ -15,7 +15,7 @@ pub enum Error {
    // Contains the error from the constructor function
    ConstructionFailed(anyhow::Error),
    // Contains the error from the YAML deserialization function
-    Yaml(serde_yaml_ng::Error),
+    Yaml(serde_yaml::Error),
 }
 pub type Result<T> = std::result::Result<T, Error>;
@@ -69,7 +69,7 @@ pub(super) fn create(
 pub fn create_from_provider_and_yaml_value_config(
    provider: &AgentProvider,
    identifier: &PublicIdentifier,
-    config: serde_yaml_ng::Value,
+    config: serde_yaml::Value,
 ) -> Result<AgentInstance> {
    let definition = AgentDefinition::new(identifier.prefixless(), provider.to_owned(), config);
@@ -79,7 +79,7 @@ pub fn create_from_provider_and_yaml_value_config(
 fn create_controller_from_provider_and_json_value_config(
    agent_id: &str,
    provider: &AgentProvider,
-    config: serde_yaml_ng::Value,
+    config: serde_yaml::Value,
 ) -> Result<ControllerType> {
    match provider {
        AgentProvider::Anthropic => {
@@ -112,43 +112,43 @@ fn create_controller_from_provider_and_json_value_config(
    }
 }
-pub fn default_config_for_provider(provider: &AgentProvider) -> serde_yaml_ng::Value {
+pub fn default_config_for_provider(provider: &AgentProvider) -> serde_yaml::Value {
    match provider {
        AgentProvider::Anthropic => {
            let config = super::provider::anthropic::default_config();
-            serde_yaml_ng::to_value(config).expect("Failed to serialize config")
+            serde_yaml::to_value(config).expect("Failed to serialize config")
        }
        AgentProvider::Groq => {
            let config = super::provider::groq::default_config();
-            serde_yaml_ng::to_value(config).expect("Failed to serialize config")
+            serde_yaml::to_value(config).expect("Failed to serialize config")
        }
        AgentProvider::LocalAI => {
            let config = super::provider::localai::default_config();
-            serde_yaml_ng::to_value(config).expect("Failed to serialize config")
+            serde_yaml::to_value(config).expect("Failed to serialize config")
        }
        AgentProvider::Mistral => {
            let config = super::provider::mistral::default_config();
-            serde_yaml_ng::to_value(config).expect("Failed to serialize config")
+            serde_yaml::to_value(config).expect("Failed to serialize config")
        }
        AgentProvider::Ollama => {
            let config = super::provider::ollama::default_config();
-            serde_yaml_ng::to_value(config).expect("Failed to serialize config")
+            serde_yaml::to_value(config).expect("Failed to serialize config")
        }
        AgentProvider::OpenAI => {
            let config = super::provider::openai::default_config();
-            serde_yaml_ng::to_value(config).expect("Failed to serialize config")
+            serde_yaml::to_value(config).expect("Failed to serialize config")
        }
        AgentProvider::OpenAICompat => {
            let config = super::provider::openai_compat::default_config();
-            serde_yaml_ng::to_value(config).expect("Failed to serialize config")
+            serde_yaml::to_value(config).expect("Failed to serialize config")
        }
        AgentProvider::OpenRouter => {
            let config = super::provider::openrouter::default_config();
-            serde_yaml_ng::to_value(config).expect("Failed to serialize config")
+            serde_yaml::to_value(config).expect("Failed to serialize config")
        }
        AgentProvider::TogetherAI => {
            let config = super::provider::togetherai::default_config();
-            serde_yaml_ng::to_value(config).expect("Failed to serialize config")
+            serde_yaml::to_value(config).expect("Failed to serialize config")
        }
    }
 }
--- a/src/agent/provider/anthropic/controller.rs
+++ b/src/agent/provider/anthropic/controller.rs
@@ -146,11 +146,11 @@ impl ControllerTrait for Controller {
            .temperature_override
            .unwrap_or(text_generation_config.temperature);
-        if let Some(prompt_message) = prompt_message
+        if let Some(prompt_message) = prompt_message {
-            && let LLMMessageContent::Text(text) = &prompt_message.content
+            if let LLMMessageContent::Text(text) = &prompt_message.content {
        {
                request.system = text.clone();
            }
        }
        request.model = text_generation_config.model_id.clone();
        request.temperature = Some(temperature as f64);
--- a/src/agent/provider/anthropic/mod.rs
+++ b/src/agent/provider/anthropic/mod.rs
@@ -12,12 +12,12 @@ use super::controller::ControllerType;
 pub fn create_controller_from_yaml_value_config(
    agent_id: &str,
-    config: serde_yaml_ng::Value,
+    config: serde_yaml::Value,
 ) -> AgentInstantiationResult<ControllerType> {
    let config = match &config {
-        serde_yaml_ng::Value::Mapping(_) => {
+        serde_yaml::Value::Mapping(_) => {
            let config: Config =
-                serde_yaml_ng::from_value(config).map_err(AgentInstantiationError::Yaml)?;
+                serde_yaml::from_value(config).map_err(AgentInstantiationError::Yaml)?;
            config
                .validate()
--- a/src/agent/provider/entity/agent_provider.rs
+++ b/src/agent/provider/entity/agent_provider.rs
@@ -69,7 +69,6 @@ impl AgentProvider {
                models_list_url: Some("https://docs.anthropic.com/en/docs/about-claude/models"),
                supported_purposes: vec![AgentPurpose::TextGeneration],
                text_generation_supports_vision: true,
                text_generation_supports_tools: false,
            },
            Self::Groq => AgentProviderInfo {
                id: Self::Groq.to_static_str(),
@@ -81,12 +80,11 @@ impl AgentProvider {
                models_list_url: Some("https://console.groq.com/docs/models"),
                supported_purposes: vec![AgentPurpose::TextGeneration, AgentPurpose::SpeechToText],
                text_generation_supports_vision: false,
                text_generation_supports_tools: false,
            },
            Self::LocalAI => AgentProviderInfo {
                id: Self::LocalAI.to_static_str(),
                name: "LocalAI",
-                description: "LocalAI is the free, Open Source OpenAI alternative. LocalAI act as a drop-in replacement REST API that's compatible with OpenAI API specifications for local inferencing. It allows you to run LLMs, generate images, audio (and not only) locally or on-prem with consumer grade hardware, supporting multiple model families and architectures.",
+                description: "LocalAI is the free, Open Source OpenAI alternative. LocalAI act as a drop-in replacement REST API that’s compatible with OpenAI API specifications for local inferencing. It allows you to run LLMs, generate images, audio (and not only) locally or on-prem with consumer grade hardware, supporting multiple model families and architectures.",
                homepage_url: Some("https://localai.io/"),
                wiki_url: None,
                sign_up_url: None,
@@ -97,7 +95,6 @@ impl AgentProvider {
                    AgentPurpose::SpeechToText,
                ],
                text_generation_supports_vision: false,
                text_generation_supports_tools: false,
            },
            Self::Mistral => AgentProviderInfo {
                id: Self::Mistral.to_static_str(),
@@ -109,7 +106,6 @@ impl AgentProvider {
                models_list_url: Some("https://docs.mistral.ai/getting-started/models/"),
                supported_purposes: vec![AgentPurpose::TextGeneration],
                text_generation_supports_vision: false,
                text_generation_supports_tools: false,
            },
            Self::Ollama => AgentProviderInfo {
                id: Self::Ollama.to_static_str(),
@@ -121,7 +117,6 @@ impl AgentProvider {
                models_list_url: Some("https://ollama.com/library"),
                supported_purposes: vec![AgentPurpose::TextGeneration],
                text_generation_supports_vision: false,
                text_generation_supports_tools: false,
            },
            Self::OpenAI => AgentProviderInfo {
                id: Self::OpenAI.to_static_str(),
@@ -138,7 +133,6 @@ impl AgentProvider {
                    AgentPurpose::SpeechToText,
                ],
                text_generation_supports_vision: true,
                text_generation_supports_tools: true,
            },
            Self::OpenAICompat => AgentProviderInfo {
                id: Self::OpenAICompat.to_static_str(),
@@ -155,7 +149,6 @@ impl AgentProvider {
                    AgentPurpose::SpeechToText,
                ],
                text_generation_supports_vision: false,
                text_generation_supports_tools: false,
            },
            Self::OpenRouter => AgentProviderInfo {
                id: Self::OpenRouter.to_static_str(),
@@ -167,7 +160,6 @@ impl AgentProvider {
                models_list_url: Some("https://openrouter.ai/models"),
                supported_purposes: vec![AgentPurpose::TextGeneration],
                text_generation_supports_vision: false,
                text_generation_supports_tools: false,
            },
            Self::TogetherAI => AgentProviderInfo {
                id: Self::TogetherAI.to_static_str(),
@@ -179,7 +171,6 @@ impl AgentProvider {
                models_list_url: Some("https://api.together.xyz/models"),
                supported_purposes: vec![AgentPurpose::TextGeneration],
                text_generation_supports_vision: false,
                text_generation_supports_tools: false,
            },
        }
    }
@@ -201,5 +192,4 @@ pub struct AgentProviderInfo {
    pub models_list_url: Option<&'static str>,
    pub supported_purposes: Vec<AgentPurpose>,
    pub text_generation_supports_vision: bool,
    pub text_generation_supports_tools: bool,
 }
--- a/src/agent/provider/entity/image.rs
+++ b/src/agent/provider/entity/image.rs
@@ -2,7 +2,7 @@ use mxlink::mime;
 #[derive(Default)]
 pub struct ImageGenerationParams {
-    pub smallest_size_possible: bool,
+    pub size_override: Option<String>,
    pub cheaper_model_switching_allowed: bool,
@@ -10,8 +10,8 @@ pub struct ImageGenerationParams {
 }
 impl ImageGenerationParams {
-    pub fn with_smallest_size_possible(mut self, value: bool) -> Self {
+    pub fn with_size_override(mut self, value: Option<String>) -> Self {
-        self.smallest_size_possible = value;
+        self.size_override = value;
        self
    }
@@ -56,8 +56,8 @@ impl ImageSource {
    }
 }
-impl From<ImageSource> for async_openai::types::images::ImageInput {
+impl From<ImageSource> for async_openai::types::ImageInput {
    fn from(value: ImageSource) -> Self {
-        async_openai::types::images::ImageInput::from_vec_u8(value.filename, value.bytes)
+        async_openai::types::ImageInput::from_vec_u8(value.filename, value.bytes)
    }
 }
--- a/src/agent/provider/openai/config.rs
+++ b/src/agent/provider/openai/config.rs
@@ -1,6 +1,6 @@
 use serde::{Deserialize, Serialize};
-use super::OPENAI_IMAGE_MODEL_GPT_IMAGE_1_DOT_5;
+use super::OPENAI_IMAGE_MODEL_GPT_IMAGE_1;
 use crate::agent::{default_prompt, provider::ConfigTrait};
 #[derive(Debug, Clone, Serialize, Deserialize)]
@@ -64,9 +64,6 @@ pub struct TextGenerationConfig {
    #[serde(default)]
    pub max_context_tokens: u32,
    #[serde(default)]
    pub tools: ToolsConfig,
 }
 impl Default for TextGenerationConfig {
@@ -78,22 +75,12 @@ impl Default for TextGenerationConfig {
            max_response_tokens: None,
            max_completion_tokens: Some(128_000),
            max_context_tokens: 400_000,
            tools: ToolsConfig::default(),
        }
    }
 }
 fn default_text_model_id() -> String {
-    "gpt-5.2".to_owned()
+    "gpt-5".to_owned()
 }
 #[derive(Debug, Clone, Serialize, Deserialize, Default)]
 pub struct ToolsConfig {
    #[serde(default)]
    pub web_search: bool,
    #[serde(default)]
    pub code_interpreter: bool,
 }
 #[derive(Debug, Clone, Serialize, Deserialize)]
@@ -163,19 +150,19 @@ pub struct ImageGenerationConfig {
    pub model_id: String,
    #[serde(default = "default_image_style")]
-    pub style: Option<async_openai::types::images::ImageStyle>,
+    pub style: Option<async_openai::types::ImageStyle>,
    #[serde(default = "default_image_size")]
-    pub size: Option<async_openai::types::images::ImageSize>,
+    pub size: Option<async_openai::types::ImageSize>,
    #[serde(default = "default_image_quality")]
-    pub quality: Option<async_openai::types::images::ImageQuality>,
+    pub quality: Option<async_openai::types::ImageQuality>,
 }
 impl Default for ImageGenerationConfig {
    fn default() -> Self {
        Self {
-            model_id: OPENAI_IMAGE_MODEL_GPT_IMAGE_1_DOT_5.to_owned(),
+            model_id: OPENAI_IMAGE_MODEL_GPT_IMAGE_1.to_owned(),
            style: default_image_style(),
            size: default_image_size(),
            quality: default_image_quality(),
@@ -186,28 +173,23 @@ impl Default for ImageGenerationConfig {
 impl ImageGenerationConfig {
    pub fn model_id_as_openai_image_model(
        &self,
-    ) -> Result<async_openai::types::images::ImageModel, String> {
+    ) -> Result<async_openai::types::ImageModel, String> {
        match self.model_id.as_str() {
-            "dall-e-2" => Ok(async_openai::types::images::ImageModel::DallE2),
+            "dall-e-2" => Ok(async_openai::types::ImageModel::DallE2),
-            "dall-e-3" => Ok(async_openai::types::images::ImageModel::DallE3),
+            "dall-e-3" => Ok(async_openai::types::ImageModel::DallE3),
-            "gpt-image-1" => Ok(async_openai::types::images::ImageModel::GptImage1),
+            other => Ok(async_openai::types::ImageModel::Other(other.to_owned())),
            "gpt-image-1.5" => Ok(async_openai::types::images::ImageModel::GptImage1dot5),
            "gpt-image-1-mini" => Ok(async_openai::types::images::ImageModel::GptImage1Mini),
            other => Ok(async_openai::types::images::ImageModel::Other(
                other.to_owned(),
            )),
        }
    }
 }
-fn default_image_style() -> Option<async_openai::types::images::ImageStyle> {
+fn default_image_style() -> Option<async_openai::types::ImageStyle> {
    None
 }
-fn default_image_size() -> Option<async_openai::types::images::ImageSize> {
+fn default_image_size() -> Option<async_openai::types::ImageSize> {
    None
 }
-fn default_image_quality() -> Option<async_openai::types::images::ImageQuality> {
+fn default_image_quality() -> Option<async_openai::types::ImageQuality> {
    None
 }
--- a/src/agent/provider/openai/controller.rs
+++ b/src/agent/provider/openai/controller.rs
@@ -4,15 +4,10 @@ use async_openai::{
    Client as OpenAIClient,
    config::OpenAIConfig,
    types::{
        ChatCompletionRequestMessage, CreateChatCompletionRequestArgs, CreateImageEditRequestArgs,
        CreateImageRequestArgs,
        DallE2ImageSize, Image, ImageModel, ImageResponseFormat,
        audio::{AudioInput, CreateSpeechRequestArgs, CreateTranscriptionRequestArgs},
        images::{
            CreateImageEditRequestArgs, CreateImageRequestArgs, Image, ImageInput, ImageModel,
            ImageResponseFormat,
        },
        responses::{
            CodeInterpreterContainerAuto, CodeInterpreterTool, CodeInterpreterToolContainer,
            CreateResponseArgs, OutputItem, OutputMessageContent, Tool, WebSearchTool,
        },
    },
 };
@@ -31,9 +26,12 @@ use crate::{
 use crate::{
    agent::{
        AgentPurpose,
-        provider::entity::{
+        provider::{
-            ImageEditResult, ImageGenerationResult, ImageSource, PingResult, TextToSpeechParams,
+            entity::{
-            TextToSpeechResult,
+                ImageEditResult, ImageGenerationResult, ImageSource, PingResult,
                TextToSpeechParams, TextToSpeechResult,
            },
            openai::utils::convert_string_to_enum,
        },
    },
    strings,
@@ -41,6 +39,8 @@ use crate::{
 use super::config::Config;
 use super::OPENAI_IMAGE_MODEL_GPT_IMAGE_1;
 #[derive(Debug, Clone)]
 pub struct Controller {
    config: Config,
@@ -129,45 +129,28 @@ impl ControllerTrait for Controller {
            conversation_messages.insert(0, prompt_message);
        }
-        let input =
+        let openai_conversation_messages: Vec<ChatCompletionRequestMessage> =
-            super::utils::convert_llm_messages_to_openai_response_input(conversation_messages);
+            super::utils::convert_llm_messages_to_openai_messages(conversation_messages);
-        let messages_count = match &input {
+        let messages_count = openai_conversation_messages.len();
            async_openai::types::responses::InputParam::Items(items) => items.len(),
            _ => 1,
        };
        let temperature = params
            .temperature_override
            .unwrap_or(text_generation_config.temperature);
-        let mut request_builder = CreateResponseArgs::default();
+        let mut request_builder = CreateChatCompletionRequestArgs::default();
        request_builder
            .model(&text_generation_config.model_id)
            .temperature(temperature)
-            .input(input);
+            .messages(openai_conversation_messages);
        let mut tools = Vec::new();
        if text_generation_config.tools.web_search {
            tools.push(Tool::WebSearch(WebSearchTool::default()));
        }
        if text_generation_config.tools.code_interpreter {
            tools.push(Tool::CodeInterpreter(CodeInterpreterTool {
                container: CodeInterpreterToolContainer::Auto(
                    CodeInterpreterContainerAuto::default(),
                ),
            }));
        }
        if !tools.is_empty() {
            request_builder.tools(tools);
        }
        if let Some(max_response_tokens) = text_generation_config.max_response_tokens {
-            request_builder.max_output_tokens(max_response_tokens);
+            request_builder.max_tokens(max_response_tokens);
-        } else if let Some(max_completion_tokens) = text_generation_config.max_completion_tokens {
+        }
-            request_builder.max_output_tokens(max_completion_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()?;
@@ -177,28 +160,33 @@ impl ControllerTrait for Controller {
                model = format!("{:?}", request.model),
                ?messages_count,
                request = request_as_json,
-                "Sending OpenAI response API request"
+                "Sending OpenAI chat completion API request"
            );
        }
-        let response = self.client.responses().create(request).await?;
+        let response = self.client.chat().create(request).await?;
-        tracing::trace!(?response, "Got response from the OpenAI response API");
+        tracing::trace!(
            ?response,
            "Got response from the OpenAI chat completion API"
        );
-        for item in response.output {
+        // We only request 1 result, so there should only be 1 choice.
-            if let OutputItem::Message(message) = item {
+        if let Some(choice) = response.choices.into_iter().next() {
-                for content in message.content {
+            match choice.message.content {
-                    if let OutputMessageContent::OutputText(text_content) = content {
+                Some(text) => {
-                        return Ok(TextGenerationResult {
+                    return Ok(TextGenerationResult { text });
                            text: text_content.text,
                        });
                }
                None => {
                    return Err(anyhow::anyhow!(
                        "No content was found in the response choice from the OpenAI chat completion API"
                    ));
                }
            }
        }
        Err(anyhow::anyhow!(
-            "No response messages choices were returned from the OpenAI response API"
+            "No response messages choices were returned from the OpenAI chat completion API"
        ))
    }
@@ -264,12 +252,11 @@ impl ControllerTrait for Controller {
        let model = if params.cheaper_model_switching_allowed {
            // Switch to a cheaper model
            match original_model {
-                ImageModel::DallE2 => ImageModel::DallE2,
+                async_openai::types::ImageModel::DallE2 => async_openai::types::ImageModel::DallE2,
-                ImageModel::DallE3 => ImageModel::DallE2,
+                async_openai::types::ImageModel::DallE3 => async_openai::types::ImageModel::DallE2,
-                ImageModel::GptImage1 => ImageModel::GptImage1Mini,
+                async_openai::types::ImageModel::Other(_) => {
-                ImageModel::GptImage1dot5 => ImageModel::GptImage1Mini,
+                    async_openai::types::ImageModel::DallE2
-                ImageModel::GptImage1Mini => ImageModel::GptImage1Mini,
+                }
                ImageModel::Other(_) => ImageModel::DallE2,
            }
        } else {
            original_model
@@ -279,24 +266,24 @@ impl ControllerTrait for Controller {
            // Switch to a cheaper quality
            match &image_generation_config.quality {
                Some(quality) => match quality {
-                    async_openai::types::images::ImageQuality::Standard => {
+                    async_openai::types::ImageQuality::Standard => {
-                        Some(async_openai::types::images::ImageQuality::Standard)
+                        Some(async_openai::types::ImageQuality::Standard)
                    }
-                    async_openai::types::images::ImageQuality::HD => {
+                    async_openai::types::ImageQuality::HD => {
-                        Some(async_openai::types::images::ImageQuality::Standard)
+                        Some(async_openai::types::ImageQuality::Standard)
                    }
                    // New quality levels - keep as-is or downgrade to Standard
-                    async_openai::types::images::ImageQuality::High => {
+                    async_openai::types::ImageQuality::High => {
-                        Some(async_openai::types::images::ImageQuality::Standard)
+                        Some(async_openai::types::ImageQuality::Standard)
                    }
-                    async_openai::types::images::ImageQuality::Medium => {
+                    async_openai::types::ImageQuality::Medium => {
-                        Some(async_openai::types::images::ImageQuality::Medium)
+                        Some(async_openai::types::ImageQuality::Medium)
                    }
-                    async_openai::types::images::ImageQuality::Low => {
+                    async_openai::types::ImageQuality::Low => {
-                        Some(async_openai::types::images::ImageQuality::Low)
+                        Some(async_openai::types::ImageQuality::Low)
                    }
-                    async_openai::types::images::ImageQuality::Auto => {
+                    async_openai::types::ImageQuality::Auto => {
-                        Some(async_openai::types::images::ImageQuality::Auto)
+                        Some(async_openai::types::ImageQuality::Auto)
                    }
                },
                None => None,
@@ -305,21 +292,20 @@ impl ControllerTrait for Controller {
            image_generation_config.quality.clone()
        };
-        let size = if params.smallest_size_possible {
+        let size = params
-            Some(get_sticker_size(&model))
+            .size_override
-        } else {
+            .map(|s| convert_string_to_enum::<async_openai::types::ImageSize>(&s).unwrap())
-            image_generation_config.size
+            .or(image_generation_config.size);
        };
        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.
-            ImageModel::GptImage1 => None,
+                OPENAI_IMAGE_MODEL_GPT_IMAGE_1 => None,
-            ImageModel::GptImage1Mini => None,
+                _ => Some(ImageResponseFormat::B64Json),
-            ImageModel::GptImage1dot5 => None,
+            },
            ImageModel::Other(_) => Some(ImageResponseFormat::B64Json),
        };
        let mut request_builder = CreateImageRequestArgs::default();
@@ -353,15 +339,15 @@ impl ControllerTrait for Controller {
            "Sending OpenAI image generation API request"
        );
-        let response = self.client.images().generate(request).await?;
+        let response = self.client.images().create(request).await?;
        if let Some(image) = response.data.into_iter().next() {
            match image.deref() {
-                Image::B64Json {
+                async_openai::types::Image::B64Json {
                    b64_json,
                    revised_prompt,
                } => {
-                    let bytes = base64_decode(b64_json.as_ref())?;
+                    let bytes = base64_decode(b64_json)?;
                    return Ok(ImageGenerationResult {
                        bytes,
@@ -398,21 +384,15 @@ impl ControllerTrait for Controller {
            return Err(anyhow::anyhow!("No image sources provided"));
        }
-        let mut image_inputs: Vec<ImageInput> = Vec::new();
+        let mut image_inputs = Vec::new();
        for image in images {
            image_inputs.push(image.into());
        }
        let dalle2_size = match image_generation_config.size {
-            Some(async_openai::types::images::ImageSize::S256x256) => {
+            Some(async_openai::types::ImageSize::S256x256) => Some(DallE2ImageSize::S256x256),
-                Some(async_openai::types::images::ImageSize::S256x256)
+            Some(async_openai::types::ImageSize::S512x512) => Some(DallE2ImageSize::S512x512),
-            }
+            Some(async_openai::types::ImageSize::S1024x1024) => Some(DallE2ImageSize::S1024x1024),
            Some(async_openai::types::images::ImageSize::S512x512) => {
                Some(async_openai::types::images::ImageSize::S512x512)
            }
            Some(async_openai::types::images::ImageSize::S1024x1024) => {
                Some(async_openai::types::images::ImageSize::S1024x1024)
            }
            _ => None,
        };
@@ -421,14 +401,16 @@ impl ControllerTrait for Controller {
            .map_err(|err| anyhow::anyhow!(err))?;
        let response_format = match model.clone() {
-            ImageModel::DallE2 => Some(ImageResponseFormat::B64Json),
+            async_openai::types::ImageModel::DallE2 => {
-            ImageModel::DallE3 => Some(ImageResponseFormat::B64Json),
+                Some(async_openai::types::ImageResponseFormat::B64Json)
-            // gpt-image-1 only outputs base64 and we don't need to specify the response format.
+            }
-            // In fact, specifying the response format results in an error.
+            async_openai::types::ImageModel::DallE3 => {
-            ImageModel::GptImage1 => None,
+                Some(async_openai::types::ImageResponseFormat::B64Json)
-            ImageModel::GptImage1Mini => None,
+            }
-            ImageModel::GptImage1dot5 => None,
+            async_openai::types::ImageModel::Other(model_str) => match model_str.as_str() {
-            ImageModel::Other(_) => Some(ImageResponseFormat::B64Json),
+                OPENAI_IMAGE_MODEL_GPT_IMAGE_1 => None,
                _ => Some(async_openai::types::ImageResponseFormat::B64Json),
            },
        };
        let mut request_builder = CreateImageEditRequestArgs::default();
@@ -457,12 +439,12 @@ impl ControllerTrait for Controller {
            "Sending OpenAI image edit API request"
        );
-        let response = self.client.images().edit(request).await?;
+        let response = self.client.images().create_edit(request).await?;
        if let Some(image_data) = response.data.into_iter().next() {
            match image_data.deref() {
                Image::B64Json { b64_json, .. } => {
-                    let bytes = base64_decode(b64_json.as_ref())?;
+                    let bytes = base64_decode(b64_json)?;
                    return Ok(ImageEditResult {
                        bytes,
                        mime_type: mxlink::mime::IMAGE_PNG,
@@ -634,17 +616,3 @@ fn audio_mime_type_to_file_name(mime_type: &mxlink::mime::Mime) -> Option<String
    Some(format!("audio.{}", file_extension))
 }
 /// Returns the smallest supported size for stickers based on what the image model supports.
 fn get_sticker_size(model: &ImageModel) -> async_openai::types::images::ImageSize {
    use async_openai::types::images::ImageSize;
    match model {
        ImageModel::DallE2 => ImageSize::S256x256,
        ImageModel::DallE3 => ImageSize::S1024x1024,
        ImageModel::GptImage1 => ImageSize::S1024x1024,
        ImageModel::GptImage1Mini => ImageSize::S1024x1024,
        ImageModel::GptImage1dot5 => ImageSize::S1024x1024,
        ImageModel::Other(_) => ImageSize::S1024x1024,
    }
 }
--- a/src/agent/provider/openai/mod.rs
+++ b/src/agent/provider/openai/mod.rs
@@ -16,16 +16,16 @@ use super::super::AgentInstantiationResult;
 use super::ConfigTrait;
 use super::controller::ControllerType;
-pub const OPENAI_IMAGE_MODEL_GPT_IMAGE_1_DOT_5: &str = "gpt-image-1.5";
+pub const OPENAI_IMAGE_MODEL_GPT_IMAGE_1: &str = "gpt-image-1";
 pub fn create_controller_from_yaml_value_config(
    agent_id: &str,
-    config: serde_yaml_ng::Value,
+    config: serde_yaml::Value,
 ) -> AgentInstantiationResult<ControllerType> {
    let config = match &config {
-        serde_yaml_ng::Value::Mapping(_) => {
+        serde_yaml::Value::Mapping(_) => {
            let config: Config =
-                serde_yaml_ng::from_value(config).map_err(AgentInstantiationError::Yaml)?;
+                serde_yaml::from_value(config).map_err(AgentInstantiationError::Yaml)?;
            config
                .validate()
--- a/src/agent/provider/openai/utils.rs
+++ b/src/agent/provider/openai/utils.rs
@@ -1,6 +1,8 @@
-use async_openai::types::responses::{
+use async_openai::types::{
-    EasyInputContent, EasyInputMessage, ImageDetail, InputContent, InputImageContent, InputItem,
+    ChatCompletionRequestAssistantMessageArgs, ChatCompletionRequestMessage,
-    InputParam, MessageType, Role,
+    ChatCompletionRequestMessageContentPartImage, ChatCompletionRequestSystemMessageArgs,
    ChatCompletionRequestUserMessageArgs, ChatCompletionRequestUserMessageContent,
    ChatCompletionRequestUserMessageContentPart, ImageUrlArgs,
 };
 use crate::conversation::llm::{
@@ -8,20 +10,43 @@ use crate::conversation::llm::{
 };
 use crate::utils::base64::base64_encode;
-pub fn convert_llm_messages_to_openai_response_input(
+pub fn convert_llm_messages_to_openai_messages(
    conversation_messages: Vec<LLMMessage>,
-) -> InputParam {
+) -> Vec<ChatCompletionRequestMessage> {
-    let mut items = Vec::with_capacity(conversation_messages.len());
+    let mut openai_conversation_messages: Vec<ChatCompletionRequestMessage> =
        Vec::with_capacity(conversation_messages.len());
    for message in conversation_messages {
-        let role = match message.author {
+        let openai_message = convert_llm_message_to_openai_message(message);
-            LLMAuthor::Prompt => Role::System,
+        if let Some(openai_message) = openai_message {
-            LLMAuthor::Assistant => Role::Assistant,
+            openai_conversation_messages.push(openai_message);
-            LLMAuthor::User => Role::User,
+        }
-        };
+    }
-        let content = match message.content {
+    openai_conversation_messages
-            LLMMessageContent::Text(text) => EasyInputContent::Text(text),
+}
 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(text.clone())
                .build()
                .expect("Failed building OpenAI system message")
                .into(),
            LLMAuthor::Assistant => ChatCompletionRequestAssistantMessageArgs::default()
                .content(text.clone())
                .build()
                .expect("Failed building OpenAI assistant message")
                .into(),
            LLMAuthor::User => ChatCompletionRequestUserMessageArgs::default()
                .content(text.clone())
                .build()
                .expect("Failed building OpenAI user message")
                .into(),
        }),
        LLMMessageContent::Image(image_details) => {
            let image_url = format!(
                "data:{};base64,{}",
@@ -29,20 +54,49 @@ pub fn convert_llm_messages_to_openai_response_input(
                base64_encode(&image_details.data)
            );
-                EasyInputContent::ContentList(vec![InputContent::InputImage(InputImageContent {
+            let part = ChatCompletionRequestUserMessageContentPart::ImageUrl(
-                    image_url: Some(image_url),
+                ChatCompletionRequestMessageContentPartImage {
-                    detail: ImageDetail::Auto,
+                    image_url: ImageUrlArgs::default()
-                    file_id: None,
+                        .url(image_url)
-                })])
+                        .build()
-            }
+                        .expect("Failed building OpenAI image url"),
-        };
+                },
            );
-        items.push(InputItem::EasyMessage(EasyInputMessage {
+            let message_content = ChatCompletionRequestUserMessageContent::Array(vec![part]);
            r#type: MessageType::Message,
            role,
            content,
        }));
    }
-    InputParam::Items(items)
+            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
                }
            }
        }
    }
 }
 pub(super) fn convert_string_to_enum<T>(value: &str) -> Result<T, String>
 where
    T: serde::de::DeserializeOwned,
 {
    // This is a hacky way to construct an enum from the string we have.
    let enum_result: serde_json::Result<T> = serde_json::from_str(&format!("\"{}\"", value));
    match enum_result {
        Ok(enum_result) => Ok(enum_result),
        Err(err) => {
            tracing::debug!(?err, "Failed to parse into enum");
            Err(format!("The value ({}) is not supported.", value))
        }
    }
 }
--- a/src/agent/provider/openai_compat/config.rs
+++ b/src/agent/provider/openai_compat/config.rs
@@ -95,7 +95,6 @@ impl TryInto<OpenAITextGenerationConfig> for TextGenerationConfig {
            max_response_tokens: self.max_response_tokens,
            max_completion_tokens: None,
            max_context_tokens: self.max_context_tokens,
            tools: Default::default(),
        })
    }
 }
@@ -162,14 +161,13 @@ impl TryInto<OpenAITextToSpeechConfig> for TextToSpeechConfig {
    type Error = String;
    fn try_into(self) -> Result<OpenAITextToSpeechConfig, Self::Error> {
-        let model_id =
+        let model_id = convert_string_to_enum::<async_openai::types::audio::SpeechModel>(&self.model_id)?;
            convert_string_to_enum::<async_openai::types::audio::SpeechModel>(&self.model_id)?;
        let voice = convert_string_to_enum::<async_openai::types::audio::Voice>(&self.voice)?;
-        let response_format = convert_string_to_enum::<
+        let response_format = convert_string_to_enum::<async_openai::types::audio::SpeechResponseFormat>(
-            async_openai::types::audio::SpeechResponseFormat,
+            &self.response_format,
-        >(&self.response_format)?;
+        )?;
        Ok(OpenAITextToSpeechConfig {
            model_id,
@@ -226,25 +224,25 @@ impl TryInto<OpenAIImageGenerationConfig> for ImageGenerationConfig {
    fn try_into(self) -> Result<OpenAIImageGenerationConfig, Self::Error> {
        let size = if let Some(size) = &self.size {
-            Some(convert_string_to_enum::<
+            Some(convert_string_to_enum::<async_openai::types::ImageSize>(
-                async_openai::types::images::ImageSize,
+                size,
-            >(size)?)
+            )?)
        } else {
            None
        };
        let style = if let Some(style) = &self.style {
-            Some(convert_string_to_enum::<
+            Some(convert_string_to_enum::<async_openai::types::ImageStyle>(
-                async_openai::types::images::ImageStyle,
+                style,
-            >(style)?)
+            )?)
        } else {
            None
        };
        let quality = if let Some(quality) = &self.quality {
-            Some(convert_string_to_enum::<
+            Some(convert_string_to_enum::<async_openai::types::ImageQuality>(
-                async_openai::types::images::ImageQuality,
+                quality,
-            >(quality)?)
+            )?)
        } else {
            None
        };
--- a/src/agent/provider/openai_compat/controller.rs
+++ b/src/agent/provider/openai_compat/controller.rs
@@ -3,8 +3,6 @@ use etke_openai_api_rust::chat::{ChatApi, ChatBody};
 use etke_openai_api_rust::images::{ImagesApi, ImagesBody};
 use etke_openai_api_rust::{Auth, Message, OpenAI};
 const SMALLEST_IMAGE_SIZE: &str = "256x256";
 use super::super::ControllerTrait;
 use crate::utils::base64::base64_decode;
 use crate::{
@@ -305,11 +303,9 @@ impl ControllerTrait for Controller {
        // when they span multiple lines.
        let prompt = prompt.replace("\n", " ");
-        let size: Option<String> = if params.smallest_size_possible {
+        let size: Option<String> = params
-            Some(SMALLEST_IMAGE_SIZE.to_owned())
+            .size_override
-        } else {
+            .or_else(|| image_generation_config.size.clone());
            image_generation_config.size.clone()
        };
        let request = ImagesBody {
            model: Some(image_generation_config.model_id.to_owned()),
--- a/src/agent/provider/openai_compat/mod.rs
+++ b/src/agent/provider/openai_compat/mod.rs
@@ -26,12 +26,12 @@ use super::controller::ControllerType;
 pub fn create_controller_from_yaml_value_config(
    agent_id: &str,
-    config: serde_yaml_ng::Value,
+    config: serde_yaml::Value,
 ) -> AgentInstantiationResult<ControllerType> {
    let config = match &config {
-        serde_yaml_ng::Value::Mapping(_) => {
+        serde_yaml::Value::Mapping(_) => {
            let config: Config =
-                serde_yaml_ng::from_value(config).map_err(AgentInstantiationError::Yaml)?;
+                serde_yaml::from_value(config).map_err(AgentInstantiationError::Yaml)?;
            config
                .validate()
--- a/src/bot/implementation.rs
+++ b/src/bot/implementation.rs
@@ -1,13 +1,12 @@
 use std::fs;
 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::api::client::profile::{AvatarUrl, DisplayName};
 use mxlink::matrix_sdk::ruma::{
    MilliSecondsSinceUnixEpoch, OwnedUserId, events::room::MediaSource,
 };
 use mxlink::matrix_sdk::ruma::api::client::profile::{AvatarUrl, DisplayName};
 use mxlink::{
    InitConfig, LoginConfig, LoginCredentials, LoginEncryption, MatrixLink, PersistenceConfig,
@@ -19,13 +18,12 @@ use mxlink::helpers::account_data_config::{
    RoomConfigManager as AccountDataRoomConfigManager,
 };
 use mxlink::helpers::encryption::Manager as EncryptionManager;
 use mxlink::mime::Mime;
 use crate::agent::Manager as AgentManager;
 use crate::entity::catch_up_marker::{
    CatchUpMarker, CatchUpMarkerManager, DelayedCatchUpMarkerManager,
 };
-use crate::entity::cfg::{Avatar, Config, ConfigUserAuth};
+use crate::entity::cfg::Config;
 use crate::entity::globalconfig::{GlobalConfig, GlobalConfigurationManager};
 use crate::entity::roomconfig::{RoomConfig, RoomConfigurationManager};
@@ -318,35 +316,8 @@ impl Bot {
            }
        }
        let desired_avatar: Option<(Vec<u8>, Mime)> = match &self.inner.config.user.avatar {
            Avatar::Keep => {
                tracing::info!("Avatar configured to keep current, skipping avatar management");
                None
            }
            Avatar::Default => {
                tracing::info!("Avatar configured to use default");
                Some((
                    LOGO_BYTES.to_vec(),
                    LOGO_MIME_TYPE
                        .parse()
                        .expect("Failed parsing mime type for logo"),
                ))
            }
            Avatar::Custom(avatar_path) => {
                tracing::info!(?avatar_path, "Avatar configured to use custom path");
                let bytes = fs::read(avatar_path).map_err(|e| {
                    anyhow::anyhow!("Failed reading avatar from {:?}: {:?}", avatar_path, e)
                })?;
                let mime = mime_guess::from_path(avatar_path).first_or_octet_stream();
                tracing::debug!(?mime, bytes_len = bytes.len(), "Loaded custom avatar");
                Some((bytes, mime))
            }
        };
        if let Some((desired_bytes, mime_type)) = desired_avatar {
        let should_update_avatar = match &current_avatar_url {
            Some(avatar_url) => {
                    tracing::debug!(?avatar_url, "Fetching current avatar to compare");
                let request = MediaRequestParameters {
                    source: MediaSource::Plain(avatar_url.to_owned()),
                    format: MediaFormat::File,
@@ -357,33 +328,22 @@ impl Bot {
                    .await
                    .map_err(|e| anyhow::anyhow!("Failed fetching existing avatar: {:?}", e))?;
-                    let needs_update = content.as_slice() != desired_bytes;
+                content.as_slice() != LOGO_BYTES
                    tracing::debug!(
                        current_bytes_len = content.len(),
                        desired_bytes_len = desired_bytes.len(),
                        ?needs_update,
                        "Compared current and desired avatar"
                    );
                    needs_update
                }
                None => {
                    tracing::debug!("No current avatar set, will upload");
                    true
            }
            None => true,
        };
        if should_update_avatar {
            tracing::info!("Updating avatar..");
            let mime_type = LOGO_MIME_TYPE
                .parse()
                .expect("Failed parsing mime type for logo");
            account
-                    .upload_avatar(&mime_type, desired_bytes)
+                .upload_avatar(&mime_type, LOGO_BYTES.to_vec())
                .await
                .map_err(|e| anyhow::anyhow!("Failed uploading avatar: {:?}", e))?;
                tracing::info!("Avatar updated successfully");
            } else {
                tracing::debug!("Avatar already up to date, skipping upload");
            }
        }
        Ok(())
@@ -395,22 +355,10 @@ async fn create_matrix_link(config: &Config) -> anyhow::Result<MatrixLink> {
    let session_encryption_key = config.persistence.session_encryption_key()?;
    let db_dir_path: std::path::PathBuf = config.persistence.db_dir_path()?;
-    let user_auth = config.user.auth_config(&config.homeserver.server_name)?;
+    let login_creds = LoginCredentials::UserPassword(
-
+        config.user.mxid_localpart.to_owned(),
-    let login_creds = match user_auth {
+        config.user.password.to_owned(),
-        ConfigUserAuth::UserPassword { username, password } => {
+    );
            LoginCredentials::UserPassword(username, password)
        }
        ConfigUserAuth::AccessToken {
            user_id,
            device_id,
            access_token,
        } => LoginCredentials::AccessToken {
            user_id,
            device_id,
            access_token,
        },
    };
    let login_encryption = LoginEncryption::new(
        config.user.encryption.recovery_passphrase.clone(),
--- 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::{Avatar, Config, defaults as cfg_defaults, env as cfg_env};
+pub use crate::entity::cfg::{Config, defaults as cfg_defaults, env as cfg_env};
 pub fn load() -> anyhow::Result<Config> {
    let config_file_path = env::var(cfg_env::BAIBOT_CONFIG_FILE_PATH)
@@ -21,7 +21,7 @@ pub fn load() -> anyhow::Result<Config> {
    }
    let config_str = std::fs::read_to_string(config_file_path)?;
-    let mut config: Config = serde_yaml_ng::from_str(&config_str)?;
+    let mut config: Config = serde_yaml::from_str(&config_str)?;
    // Allow environment variables to override some configuration keys
    for (key, value) in env::vars() {
@@ -29,25 +29,11 @@ pub fn load() -> anyhow::Result<Config> {
            cfg_env::BAIBOT_HOMESERVER_SERVER_NAME => config.homeserver.server_name = value,
            cfg_env::BAIBOT_HOMESERVER_URL => config.homeserver.url = value,
            cfg_env::BAIBOT_USER_MXID_LOCALPART => config.user.mxid_localpart = value,
-            cfg_env::BAIBOT_USER_PASSWORD => {
+            cfg_env::BAIBOT_USER_PASSWORD => config.user.password = value,
                config.user.password = optional_non_empty(value);
            }
            cfg_env::BAIBOT_USER_ACCESS_TOKEN => {
                config.user.access_token = optional_non_empty(value);
            }
            cfg_env::BAIBOT_USER_DEVICE_ID => {
                config.user.device_id = optional_non_empty(value);
            }
            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_USER_AVATAR => {
                config.user.avatar = Avatar::from_string(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>()?;
@@ -65,9 +51,6 @@ 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);
            }
@@ -128,7 +111,3 @@ pub fn load() -> anyhow::Result<Config> {
    Ok(config)
 }
 fn optional_non_empty(value: String) -> Option<String> {
    if value.is_empty() { None } else { Some(value) }
 }
--- a/src/controller/access/room_local_agent_managers.rs
+++ b/src/controller/access/room_local_agent_managers.rs
@@ -28,9 +28,8 @@ pub async fn handle_set(
    message_context: &MessageContext,
    patterns: &Option<Vec<String>>,
 ) -> anyhow::Result<()> {
-    if let Some(patterns) = patterns
+    if let Some(patterns) = patterns {
-        && let Err(err) = mxidwc::parse_patterns_vector(patterns)
+        if let Err(err) = mxidwc::parse_patterns_vector(patterns) {
    {
            bot.messaging()
                .send_error_markdown_no_fail(
                    message_context.room(),
@@ -41,6 +40,7 @@ pub async fn handle_set(
            return Ok(());
        }
    }
    let mut global_config_manager_guard = bot.global_config_manager().lock().await;
--- a/src/controller/access/users.rs
+++ b/src/controller/access/users.rs
@@ -24,9 +24,8 @@ pub async fn handle_set(
    message_context: &MessageContext,
    patterns: &Option<Vec<String>>,
 ) -> anyhow::Result<()> {
-    if let Some(patterns) = patterns
+    if let Some(patterns) = patterns {
-        && let Err(err) = mxidwc::parse_patterns_vector(patterns)
+        if let Err(err) = mxidwc::parse_patterns_vector(patterns) {
    {
            bot.messaging()
                .send_error_markdown_no_fail(
                    message_context.room(),
@@ -37,6 +36,7 @@ pub async fn handle_set(
            return Ok(());
        }
    }
    let mut global_config_manager_guard = bot.global_config_manager().lock().await;
--- a/src/controller/agent/create/mod.rs
+++ b/src/controller/agent/create/mod.rs
@@ -15,7 +15,7 @@ use crate::{Bot, entity::MessageContext};
 struct ParsedAgentConfig {
    agent: AgentInstance,
-    config: serde_yaml_ng::Value,
+    config: serde_yaml::Value,
 }
 pub async fn handle_room_local(
@@ -250,7 +250,7 @@ async fn send_guide(
    provider: &AgentProvider,
 ) -> anyhow::Result<()> {
    let sample_config = crate::agent::default_config_for_provider(provider);
-    let sample_config_pretty_yaml = serde_yaml_ng::to_string(&sample_config)?;
+    let sample_config_pretty_yaml = serde_yaml::to_string(&sample_config)?;
    bot.messaging()
        .send_text_markdown_no_fail(
@@ -263,7 +263,7 @@ async fn send_guide(
    Ok(())
 }
-fn parse_from_message_to_yaml_value(text: &str) -> Result<serde_yaml_ng::Value, String> {
+fn parse_from_message_to_yaml_value(text: &str) -> Result<serde_yaml::Value, String> {
    let mut text = text.trim();
    if text.starts_with("```") {
@@ -274,10 +274,10 @@ fn parse_from_message_to_yaml_value(text: &str) -> Result<serde_yaml_ng::Value,
        text = text.trim_end_matches("```");
    }
-    let config: serde_yaml_ng::Value = serde_yaml_ng::from_str(text).map_err(|e| e.to_string())?;
+    let config: serde_yaml::Value = serde_yaml::from_str(text).map_err(|e| e.to_string())?;
    match config {
-        serde_yaml_ng::Value::Mapping(_) => {}
+        serde_yaml::Value::Mapping(_) => {}
        _ => {
            return Err("Not a valid YAML hashmap".to_owned());
        }
--- a/src/controller/agent/create/tests.rs
+++ b/src/controller/agent/create/tests.rs
@@ -2,12 +2,12 @@
 fn agent_config_parsing_works() {
    struct TestCase {
        input: String,
-        expected: Option<serde_yaml_ng::Value>,
+        expected: Option<serde_yaml::Value>,
    }
    let provider = crate::agent::AgentProvider::OpenAI;
    let sample_config = crate::agent::default_config_for_provider(&provider);
-    let sample_config_pretty_yaml = serde_yaml_ng::to_string(&sample_config).unwrap();
+    let sample_config_pretty_yaml = serde_yaml::to_string(&sample_config).unwrap();
    let test_cases = vec![
        // Invalid input
--- a/src/controller/agent/details/mod.rs
+++ b/src/controller/agent/details/mod.rs
@@ -64,7 +64,7 @@ pub async fn handle(
        PublicIdentifier::Static(_) => {}
    };
-    let config_yaml_pretty = serde_yaml_ng::to_string(&agent.definition().config)?;
+    let config_yaml_pretty = serde_yaml::to_string(&agent.definition().config)?;
    bot.messaging()
        .send_text_markdown_no_fail(
--- a/src/controller/cfg/dispatching/mod.rs
+++ b/src/controller/cfg/dispatching/mod.rs
@@ -39,9 +39,8 @@ async fn dispatch_config_related_handler(
    message_context: &MessageContext,
    bot: &Bot,
 ) -> anyhow::Result<()> {
-    if let SettingsStorageSource::Global = config_type
+    if let SettingsStorageSource::Global = config_type {
-        && !message_context.sender_can_manage_global_config()
+        if !message_context.sender_can_manage_global_config() {
    {
            bot.messaging()
                .send_error_markdown_no_fail(
                    message_context.room(),
@@ -51,6 +50,7 @@ async fn dispatch_config_related_handler(
                .await;
            return Ok(());
        }
    };
    let room_settings = match config_type {
        SettingsStorageSource::Room => &message_context.room_config().settings,
--- a/src/controller/image/generation.rs
+++ b/src/controller/image/generation.rs
@@ -12,6 +12,9 @@ use crate::strings;
 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";
 pub async fn handle_image(
    bot: &Bot,
    matrix_link: MatrixLink,
@@ -174,7 +177,7 @@ pub async fn handle_sticker(
    );
    let params = ImageGenerationParams::default()
-        .with_smallest_size_possible(true)
+        .with_size_override(Some(STICKER_SIZE.to_owned()))
        .with_cheaper_model_switching_allowed(true)
        .with_cheaper_quality_switching_allowed(true);
--- a/src/conversation/matrix/utils/mod.rs
+++ b/src/conversation/matrix/utils/mod.rs
@@ -154,10 +154,8 @@ pub async fn process_matrix_messages(
        let mut message = message.clone();
-        if i == 0
+        if i == 0 && !params.first_message_prefixes_to_strip.is_empty() {
-            && !params.first_message_prefixes_to_strip.is_empty()
+            if let MatrixMessageContent::Text(message_text) = &message.content {
            && let MatrixMessageContent::Text(message_text) = &message.content
        {
                let mut message_text = message_text.clone();
                for prefix in &params.first_message_prefixes_to_strip {
@@ -168,12 +166,13 @@ pub async fn process_matrix_messages(
                message.content = MatrixMessageContent::Text(message_text.trim().to_owned());
            }
        }
        // We only strip `bot_user_prefixes_to_strip`-defined prefixes from messages that mention the bot user.
        if !params.bot_user_prefixes_to_strip.is_empty()
            && message.mentioned_users.contains(&params.bot_user_id)
            && let MatrixMessageContent::Text(message_text) = &message.content
        {
            if let MatrixMessageContent::Text(message_text) = &message.content {
                let mut message_text = message_text.clone();
                for prefix in &params.bot_user_prefixes_to_strip {
@@ -184,6 +183,7 @@ pub async fn process_matrix_messages(
                message.content = MatrixMessageContent::Text(message_text.trim().to_owned());
            }
        }
        messages_filtered.push(message);
    }
--- a/src/entity/cfg/config.rs
+++ b/src/entity/cfg/config.rs
@@ -1,8 +1,7 @@
 use std::path::PathBuf;
 use mxlink::helpers::encryption::EncryptionKey;
-use mxlink::matrix_sdk::ruma::{OwnedDeviceId, OwnedUserId};
+use serde::{Deserialize, Serialize};
 use serde::{Deserialize, Deserializer, Serialize};
 use crate::{
    agent::{AgentDefinition, AgentPurpose, PublicIdentifier},
@@ -39,7 +38,7 @@ pub struct Config {
 impl Config {
    pub fn validate(&self) -> anyhow::Result<()> {
        self.homeserver.validate()?;
-        self.user.validate(&self.homeserver.server_name)?;
+        self.user.validate()?;
        self.persistence.validate()?;
        self.room.validate()?;
        self.access.validate()?;
@@ -58,19 +57,6 @@ impl Config {
    }
 }
 #[derive(Debug)]
 pub enum ConfigUserAuth {
    UserPassword {
        username: String,
        password: String,
    },
    AccessToken {
        user_id: OwnedUserId,
        device_id: OwnedDeviceId,
        access_token: String,
    },
 }
 #[derive(Debug, Serialize, Deserialize)]
 pub struct ConfigHomeserver {
    pub server_name: String,
@@ -97,72 +83,20 @@ impl ConfigHomeserver {
    }
 }
 /// Configuration for the bot's avatar.
 ///
 /// - `Default`: Use the built-in default avatar (null, empty string, or missing in config)
 /// - `Keep`: Don't touch the avatar, keep whatever is already set ("keep" in config)
 /// - `Custom(String)`: Use a custom avatar from the specified file path
 #[derive(Debug, Clone, Default, PartialEq, Serialize)]
 pub enum Avatar {
    /// Use the built-in default avatar
    #[default]
    Default,
    /// Keep the current avatar, don't change it
    Keep,
    /// Use a custom avatar from the specified file path
    Custom(String),
 }
 impl<'de> Deserialize<'de> for Avatar {
    fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>
    where
        D: Deserializer<'de>,
    {
        let value: Option<String> = Option::deserialize(deserializer)?;
        Ok(match value {
            None => Avatar::Default,
            Some(s) => Avatar::from_string(s),
        })
    }
 }
 impl Avatar {
    pub fn from_string(value: String) -> Self {
        if value.is_empty() {
            Avatar::Default
        } else if value.eq_ignore_ascii_case("keep") {
            Avatar::Keep
        } else {
            Avatar::Custom(value)
        }
    }
 }
 #[derive(Debug, Serialize, Deserialize)]
 pub struct ConfigUser {
    pub mxid_localpart: String,
-
+    pub password: String,
    #[serde(default)]
    pub password: Option<String>,
    #[serde(default)]
    pub access_token: Option<String>,
    #[serde(default)]
    pub device_id: Option<String>,
    #[serde(default = "super::defaults::name")]
    pub name: String,
    #[serde(default)]
    pub encryption: ConfigUserEncryption,
    #[serde(default)]
    pub avatar: Avatar,
 }
 impl ConfigUser {
-    pub fn validate(&self, homeserver_server_name: &str) -> anyhow::Result<()> {
+    pub fn validate(&self) -> anyhow::Result<()> {
        if self.mxid_localpart.is_empty() {
            return Err(anyhow::anyhow!(
                "The user.mxid_localpart ({}) configuration must be set",
@@ -170,7 +104,12 @@ impl ConfigUser {
            ));
        }
-        self.auth_config(homeserver_server_name)?;
+        if self.password.is_empty() {
            return Err(anyhow::anyhow!(
                "The user.password ({}) configuration must be set",
                super::env::BAIBOT_USER_PASSWORD
            ));
        }
        if self.name.is_empty() {
            return Err(anyhow::anyhow!(
@@ -183,57 +122,6 @@ impl ConfigUser {
        Ok(())
    }
    pub fn auth_config(&self, homeserver_server_name: &str) -> anyhow::Result<ConfigUserAuth> {
        let password = self.password.as_deref().filter(|value| !value.is_empty());
        let access_token = self
            .access_token
            .as_deref()
            .filter(|value| !value.is_empty());
        match (password, access_token) {
            (Some(_), Some(_)) => Err(anyhow::anyhow!(
                "Set exactly one authentication method: either user.password ({}) OR user.access_token ({}) + user.device_id ({})",
                super::env::BAIBOT_USER_PASSWORD,
                super::env::BAIBOT_USER_ACCESS_TOKEN,
                super::env::BAIBOT_USER_DEVICE_ID
            )),
            (None, None) => Err(anyhow::anyhow!(
                "Set one authentication method: either user.password ({}) OR user.access_token ({}) + user.device_id ({})",
                super::env::BAIBOT_USER_PASSWORD,
                super::env::BAIBOT_USER_ACCESS_TOKEN,
                super::env::BAIBOT_USER_DEVICE_ID
            )),
            (Some(password), None) => Ok(ConfigUserAuth::UserPassword {
                username: self.mxid_localpart.to_owned(),
                password: password.to_owned(),
            }),
            (None, Some(access_token)) => {
                let device_id = self
                    .device_id
                    .as_deref()
                    .filter(|value| !value.is_empty())
                    .ok_or_else(|| {
                        anyhow::anyhow!(
                            "user.device_id ({}) must be set when using access token authentication",
                            super::env::BAIBOT_USER_DEVICE_ID
                        )
                    })?;
                let user_id = OwnedUserId::try_from(format!(
                    "@{}:{}",
                    self.mxid_localpart, homeserver_server_name
                ))
                .map_err(|e| anyhow::anyhow!("Invalid user ID: {e}"))?;
                Ok(ConfigUserAuth::AccessToken {
                    user_id,
                    device_id: OwnedDeviceId::from(device_id),
                    access_token: access_token.to_owned(),
                })
            }
        }
    }
 }
 #[derive(Debug, Default, Serialize, Deserialize)]
@@ -244,14 +132,14 @@ pub struct ConfigUserEncryption {
 impl ConfigUserEncryption {
    pub fn validate(&self) -> anyhow::Result<()> {
-        if let Some(passphrase) = &self.recovery_passphrase
+        if let Some(passphrase) = &self.recovery_passphrase {
-            && passphrase.is_empty()
+            if passphrase.is_empty() {
        {
                return Err(anyhow::anyhow!(
                    "The user.encryption.recovery_passphrase ({}) configuration must either be null or set to a non-empty passphrase",
                    super::env::BAIBOT_USER_ENCRYPTION_RECOVERY_PASSPHRASE
                ));
            }
        }
        Ok(())
    }
@@ -536,7 +424,3 @@ impl TryInto<GlobalConfig> for ConfigInitialGlobalConfig {
        Ok(entity)
    }
 }
 #[cfg(test)]
 #[path = "config_tests.rs"]
 mod config_tests;
--- a/src/entity/cfg/config_tests.rs
+++ b/src/entity/cfg/config_tests.rs
@@ -1,117 +0,0 @@
 use super::{Avatar, ConfigUser, ConfigUserAuth, ConfigUserEncryption};
 use crate::entity::cfg::env;
 fn base_user() -> ConfigUser {
    ConfigUser {
        mxid_localpart: "baibot".to_owned(),
        password: None,
        access_token: None,
        device_id: None,
        name: "baibot".to_owned(),
        encryption: ConfigUserEncryption {
            recovery_passphrase: None,
            recovery_reset_allowed: false,
        },
        avatar: Avatar::Default,
    }
 }
 #[test]
 fn auth_config_uses_password_mode() {
    let mut user = base_user();
    user.password = Some("secret".to_owned());
    let auth = user
        .auth_config("example.com")
        .expect("password auth should be valid");
    match auth {
        ConfigUserAuth::UserPassword { username, password } => {
            assert_eq!(username, "baibot");
            assert_eq!(password, "secret");
        }
        ConfigUserAuth::AccessToken { .. } => {
            panic!("expected password auth mode");
        }
    }
 }
 #[test]
 fn auth_config_uses_access_token_mode() {
    let mut user = base_user();
    user.access_token = Some("token123".to_owned());
    user.device_id = Some("DEVICE1".to_owned());
    let auth = user
        .auth_config("example.com")
        .expect("access token auth should be valid");
    match auth {
        ConfigUserAuth::AccessToken {
            user_id,
            device_id,
            access_token,
        } => {
            assert_eq!(user_id.as_str(), "@baibot:example.com");
            assert_eq!(device_id.as_str(), "DEVICE1");
            assert_eq!(access_token, "token123");
        }
        ConfigUserAuth::UserPassword { .. } => {
            panic!("expected access token auth mode");
        }
    }
 }
 #[test]
 fn auth_config_rejects_both_auth_methods() {
    let mut user = base_user();
    user.password = Some("secret".to_owned());
    user.access_token = Some("token123".to_owned());
    user.device_id = Some("DEVICE1".to_owned());
    let err = user
        .auth_config("example.com")
        .expect_err("both auth methods should be rejected");
    assert!(
        err.to_string()
            .contains("exactly one authentication method")
    );
 }
 #[test]
 fn auth_config_rejects_missing_auth() {
    let user = base_user();
    let err = user
        .auth_config("example.com")
        .expect_err("missing auth should be rejected");
    assert!(err.to_string().contains("Set one authentication method"));
 }
 #[test]
 fn auth_config_rejects_access_token_without_device_id() {
    let mut user = base_user();
    user.access_token = Some("token123".to_owned());
    let err = user
        .auth_config("example.com")
        .expect_err("access token mode without device_id should be rejected");
    assert!(err.to_string().contains(env::BAIBOT_USER_DEVICE_ID));
 }
 #[test]
 fn auth_config_treats_empty_strings_as_unset() {
    let mut user = base_user();
    user.password = Some(String::new());
    user.access_token = Some(String::new());
    user.device_id = Some(String::new());
    let err = user
        .auth_config("example.com")
        .expect_err("empty auth values should be treated as unset");
    assert!(err.to_string().contains("Set one authentication method"));
 }
--- a/src/entity/cfg/env.rs
+++ b/src/entity/cfg/env.rs
@@ -5,14 +5,9 @@ pub const BAIBOT_HOMESERVER_URL: &str = "BAIBOT_HOMESERVER_URL";
 pub const BAIBOT_USER_MXID_LOCALPART: &str = "BAIBOT_USER_MXID_LOCALPART";
 pub const BAIBOT_USER_PASSWORD: &str = "BAIBOT_USER_PASSWORD";
 pub const BAIBOT_USER_ACCESS_TOKEN: &str = "BAIBOT_USER_ACCESS_TOKEN";
 pub const BAIBOT_USER_DEVICE_ID: &str = "BAIBOT_USER_DEVICE_ID";
 pub const BAIBOT_USER_NAME: &str = "BAIBOT_USER_NAME";
 pub const BAIBOT_USER_AVATAR: &str = "BAIBOT_USER_AVATAR";
 pub const BAIBOT_USER_ENCRYPTION_RECOVERY_PASSPHRASE: &str =
    "BAIBOT_USER_ENCRYPTION_RECOVERY_PASSPHRASE";
 pub const BAIBOT_USER_ENCRYPTION_RECOVERY_RESET_ALLOWED: &str =
    "BAIBOT_USER_ENCRYPTION_RECOVERY_RESET_ALLOWED";
 pub const BAIBOT_COMMAND_PREFIX: &str = "BAIBOT_COMMAND_PREFIX";
--- a/src/entity/cfg/mod.rs
+++ b/src/entity/cfg/mod.rs
@@ -2,4 +2,4 @@ mod config;
 pub mod defaults;
 pub mod env;
-pub use config::{Avatar, Config, ConfigUserAuth};
+pub use config::Config;
--- a/src/strings/provider.rs
+++ b/src/strings/provider.rs
@@ -109,21 +109,11 @@ pub fn help_provider_details(id: &str, info: &AgentProviderInfo) -> String {
        let mut purpose_line = format!("{} {}", purpose.emoji(), purpose.as_str());
        if let AgentPurpose::TextGeneration = purpose {
            let mut extras = vec![];
            if info.text_generation_supports_vision {
-                extras.push("incl. vision");
+                purpose_line = format!("{} ({})", purpose_line, "incl. vision");
            } else {
-                extras.push("no vision");
+                purpose_line = format!("{} ({})", purpose_line, "no vision");
            }
            if info.text_generation_supports_tools {
                extras.push("incl. tools");
            } else {
                extras.push("no tools");
            }
            purpose_line = format!("{} ({})", purpose_line, extras.join(", "));
        }
        capabilities.push(purpose_line);
--- a/src/strings/usage.rs
+++ b/src/strings/usage.rs
@@ -64,7 +64,7 @@ To create a sticker, send a command like `%command_prefix% sticker A huge bowl o
 The difference from **creating images** is that the bot will:
- create a smaller-resolution image (as small as the model allows) - smaller/quicker, but still good enough for a sticker
+- create a smaller-resolution image (`256x256`) - smaller/quicker, but still good enough for a sticker
 - potentially switch to a different (cheaper or otherwise more suitable) model, if available
 - post the image directly to the room (as a reply to your message), without starting a threaded conversation
 "#;