Conversation
…atures and externalized selenium llm engine
…ayload handling in plugin instance
…e handling with enqueue_and_wait functionality
…gation for plugins and engines
…tachment normalization
…tions and update tests
feat(plugin_instance): enhance image attachment handling and extraction logic feat(webui): include iris components in summary and error handling test(iris): update tests for register_instance to validate capabilities test(webui): add tests for extracting image data and multimodal attachments
…on handling, and add Ollama server response validation
…nAICompatAdapter feat(plugin_instance): improve Iris plugin attachment handling and logging feat(webui): refine attachments directory management and logging feat(init-db): enable vision support and increase response timeout for selenium-llm-engine fix(debrief_action_intent): extend timeout for LLM generation test(webui): add tests for attachments directory and message forwarding
- Updated the Iris plugin to use a model override for vision analysis, allowing for more flexible model selection. - Introduced a new configuration variable `IRIS_DEFAULT_MODEL` to set a default model for Iris requests. - Enhanced the web UI to include a model selection dropdown for the active Iris engine. - Modified the handling of incoming messages to ensure the user's text is not passed as a prompt to Iris. - Improved logging for better traceability of Iris processing steps. - Added tests to verify the correct model is used during image description requests. - Cleaned up code formatting and improved readability across multiple files.
… and improve model parameter passing
…ve media processing
…c_Heart into Scarlet-Raine-feat/iris # Conflicts: # core/plugin_instance.py # tests/test_iris.py
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds the new Iris vision subsystem to Synthetic Heart, enabling image/video analysis through a dedicated, engine-agnostic media pipeline and exposing a selectable Iris engine in the WebUI.
What changed
IrisResultandIrisEngineBase.describe_image(...).ACTIVE_IRIS_ENGINEin init-db.sql and provider metadata updates.Testing
Notes
The implementation preserves the project’s engine-agnostic design: Iris-specific logic is isolated to the new registry/plugin/adapter layer, and core logic does not hardcode any concrete engine.Continuato con Autopilot