#### PR Dependency Tree
* **PR #14620** 👈
This tree was auto-generated by
[Charcoal](https://github.com/danerwilliams/charcoal)
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Native LLM workflows: structured outputs, embeddings, and reranking
plus richer multimodal attachments (images, audio, files) and improved
remote-attachment inlining.
* **Refactor**
* Tooling API unified behind a local tool-definition helper;
provider/adapters reorganized to route through native dispatch paths.
* **Chores**
* Dependency updates, removed legacy Google SDK integrations, and
increased front memory allocation.
* **Tests**
* Expanded end-to-end and streaming tests exercising native provider
flows, attachments, and rerank/structured scenarios.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
- New Features
- Added GPT-5 family and made GPT-5/-mini the new defaults for Copilot
scenarios and prompts.
- Bug Fixes
- Improved streaming chunk formats and reasoning/text semantics,
consistent attachment mediaType handling, and more reliable reranking
via log-prob handling.
- Refactor
- Unified maxOutputTokens usage; removed per-call step caps and migrated
several tools to a unified inputSchema shape.
- Chores
- Upgraded AI SDK dependencies and bumped an internal dependency
version.
- Tests
- Updated mocks and tests to reference GPT-5 variants and new stream
formats.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
fix AI-404
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Introduced scenario-based configuration for copilot, allowing default
model assignments for various AI use cases.
* Added a new image generation model to the available options.
* **Improvements**
* Refined copilot provider settings by removing deprecated fallback
options and standardizing base URL configuration.
* Enhanced prompt management to support scenario-driven updates and
improved configuration handling.
* Updated admin and settings interfaces to support new scenario
configurations.
* **Bug Fixes**
* Removed deprecated or unused prompts and related references across
platforms for consistency.
* **Other**
* Improved test coverage and updated test assets to reflect prompt and
scenario changes.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
fix AI-398
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Added support for specifying fallback models for multiple AI
providers, enhancing reliability when primary models are unavailable.
* Providers can now fetch and update their list of available models
dynamically from external APIs.
* Configuration options expanded to allow custom base URLs for certain
providers.
* **Bug Fixes**
* Improved model selection logic to use fallback models if the requested
model is not available online.
* **Chores**
* Updated backend dependencies to include authentication support for
Google services.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **New Features**
- Improved input validation and error reporting for chat messages, attachments, and embeddings, with clearer error messages for invalid inputs.
- Enhanced support for multimodal messages, including attachments such as images or audio.
- **Refactor**
- Unified and streamlined parameter validation across AI providers, resulting in more consistent behavior and error handling.
- Centralized parameter checks into a common provider layer, removing duplicate validation code from individual AI providers.
- **Tests**
- Simplified and consolidated audio transcription test stubs for better maintainability.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
fix AI-4
fix AI-18
better provider/model choose to allow fallback to similar models (e.g., self-hosted) when the provider is not fully configured
split functions of different output types
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **Bug Fixes**
- Improved handling of messages without attachments, ensuring a placeholder is shown when content is empty and attachments are omitted.
- **New Features**
- Added the ability to selectively include or exclude attachments in message processing.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
