imio.omnia.assistant 1.0

Registry settings

Stored under the prefix imio.omnia.assistant.browser.controlpanel.IOmniaAssistantSettings:

Widget loading

Two Plone resource bundles are registered by the default GenericSetup profile:

• omnia-assistant-preact — Preact UMD (loaded first as a global).

• omnia-assistant — the assistant UI library (depends on the preact bundle).

An OmniaAssistantConfigViewlet registered in plone.htmlhead renders a <script> tag that:

1. Sets window.omnia_assistant_settings with configuration from the Plone registry (model, selectors, dimensions, etc.).

2. Waits for the OmniaAssistantUI global to be available (exported by the bundle).

3. Calls OmniaAssistantUI.mount('omnia-assistant-root', window.omnia_assistant_settings) to mount the Preact widget into a <div id="omnia-assistant-root"> that the viewlet template appends to the page body.

The widget is not rendered when the enabled setting is False. More generally, page-level availability and server-side prompt composition are exposed through the IOmniaAssistantAdapter multi-adapter. The default implementation reads enabled and base_prompt from the registry.

Streaming chat

Chat messages are sent as POST requests to <portal_url>/@@omnia-assistant-api/chat/completions with stream: true. The assistant proxy inherits from the shared imio.omnia.core.browser.proxy.OmniaOpenAIProxyView implementation, keeps the shared auth/streaming behavior, and forwards the request to the configured OpenAI-compatible gateway in real time.

Authentication uses an HMAC Bearer token generated server-side by the viewlet (imio.omnia.core.tokens.generate_token()). Tokens are signed with the Plone site keyring and expire after 2 hours. By default, the caller must also have the imio.omnia.core: Access Omnia OpenAI proxy permission, which imio.omnia.core grants to Authenticated users.

Projects that need anonymous access can override that permission mapping in their own GenericSetup rolemap.xml.

The request payload follows the OpenAI Chat Completions format:

{
  "model": "<configured model>",
  "messages": [
    { "role": "system", "content": "<page content>" },
    { "role": "user",   "content": "<user message>" }
  ],
  "stream": true
}

If base_prompt is configured, the assistant proxy prepends it server-side as the first system message before dispatching upstream. The prompt is no longer exposed in window.omnia_assistant_settings. Projects can override that behavior with a more specific IOmniaAssistantAdapter that changes availability rules or returns a custom system prompt for the current context/request.

Conversation length limit

When max_messages_per_session is greater than 0, the assistant counts user prompts in the current thread. Assistant replies do not consume the limit.

Once the limit is reached:

• the composer is disabled for the current thread,

• the UI tells the user to start a new conversation,

• the backend proxy also rejects any request whose payload contains more user messages than the configured limit.

Starting a new conversation from the panel header resets the counter because the limit is applied per thread, not across the whole browser session.

Page content injection

When include_page_content is True, the widget extracts DOM content using the CSS selector(s) in page_content_selector (a single selector string, or a JSON array of selectors). Each matching element contributes either its innerHTML or innerText (controlled by page_content_clean), joined by blank lines.

If the extracted content exceeds max_context_chars characters, the widget displays a warning banner and invites the user to select a specific text excerpt on the page. The selected text replaces the full page content as context for that turn.

Uninstall

The uninstall handler disables both Plone bundles (omnia-assistant and omnia-assistant-preact) by setting their enabled registry flag to False.

1.0 (2026-08-03)

• OIA-241: Follow imio.omnia.core’s httpx -> httpx2 migration in test mocks; drop unused httpx dependency. [duchenean]

• OIA-241: Bundle the UI from the published npm package @imiobe/omnia-assistant-ui (0.3.2) instead of a git submodule. [duchenean]

1.0a4 (2026-04-03)

• Load imio.omnia.core ZCML. [aduchene]

1.0a3 (2026-04-03)

• Re-release because ZCML files were lacking (2). [aduchene]

1.0a2 (2026-04-03)

• Re-release because ZCML files were lacking. [aduchene]

1.0a1 (2026-04-03)

• Initial release. [duchenean]

• Added floating/fixed AI chat assistant widget built with Vite + Preact and @assistant-ui/react. [duchenean]

• Added real-time SSE streaming of chat completions from the OpenAI-compatible Omnia gateway. [duchenean]

• Added server-side API proxy (@@omnia-assistant-api) so upstream credentials are never exposed to the browser. [duchenean]

• Added HMAC-signed bearer token authentication (2-hour expiration) for proxy requests, signed with the Plone site keyring. [duchenean]

• Added automatic page content injection as conversation context, with configurable CSS selectors, HTML or plain-text mode, and character limit. [duchenean]

• Added server-side system prompt (base_prompt) injection — no longer exposed to the frontend. [duchenean]

• Added control panel tab (@@omnia-assistant-settings) in the shared Omnia settings UI: enable/disable, model selection, display mode (floating/fixed), dimensions, disclaimer, and conversation limits. [duchenean]

• Added IOmniaAssistantAdapter extension point for context-specific availability, system prompt composition, and frontend config overrides. [duchenean]

• Added dynamic model vocabulary fetched from the IOmniaOpenAIService. [duchenean]

• Added max_messages_per_session enforced both client and server-side. [duchenean]

• Added keyboard shortcut (Alt+I) to toggle the assistant panel. [duchenean]

• Added i18n support (en, fr). [duchenean]