<!-- This is an auto-generated description by cubic. -->
## Summary by cubic
Adds web search to Dyad Pro chats with a new UI, tag parsing, and a Pro
Mode toggle that wires through to the engine.
- **New Features**
- Pro Mode toggle: “Web Search” (settings.enableProWebSearch).
- New custom tags: dyad-web-search, dyad-web-search-result, dyad-read.
- Collapsible Web Search Result UI with in-progress badge and markdown
rendering.
- Engine integration: passes enable_web_search and activates DyadEngine
when web search is on.
<!-- End of auto-generated description by cubic. -->
<!-- This is an auto-generated description by cubic. -->
## Summary by cubic
Adds “Dyad Turbo” models for Pro users and centralizes model/provider
constants. Pro users can pick fast, cost‑effective models directly from
the ModelPicker, with clearer labels and gating.
- **New Features**
- Added Dyad Turbo provider in ModelPicker with Qwen3 Coder and Kimi K2
(Pro only).
- Turbo options are hidden for non‑Pro users; “Pro only” badge shown
where applicable.
- “Smart Auto” label now applies only to the Auto model to avoid
confusion.
- **Refactors**
- Moved all model/provider constants into language_model_constants.ts
and updated imports (helpers, client, thinking utils).
<!-- End of auto-generated description by cubic. -->
<!-- This is an auto-generated description by cubic. -->
## Summary by cubic
Adds support for free OpenRouter models and a new “Free (OpenRouter)”
auto option that fails over across free models for reliability. Improves
setup flow and UI with provider cards, a “Free” price badge, and an
OpenRouter setup prompt in chat.
- **New Features**
- Added OpenRouter free models: Qwen3 Coder (free), DeepSeek v3 (free),
DeepSeek v3.1 (free), marked with dollarSigns=0 and a “Free” badge.
- New auto model: “Free (OpenRouter)” that uses a fallback client to
cycle through free models with smart retry on transient errors.
- New SetupProviderCard component and updated SetupBanner with dedicated
Google and OpenRouter setup cards.
- Chat shows an OpenRouter setup prompt when “Free (OpenRouter)” is
selected and OpenRouter isn’t configured.
- New PriceBadge component in ModelPicker to display “Free” or price
tier.
- E2E: added setup flow test and option to show the setup screen in
tests.
- Model updates: added DeepSeek v3.1, updated Kimi K2 to kimi-k2-0905,
migrated providers to LanguageModelV2.
<!-- End of auto-generated description by cubic. -->
# Add xAI (Grok) Provider Support
## Overview
This PR adds support for xAI's Grok models as an AI provider, focusing
on coding-optimized models.
## Changes Made
### Provider Configuration (`language_model_helpers.ts`)
- Added xAI to `MODEL_OPTIONS` with 3 coding-focused models:
- `grok-code-fast-1`: Fast, economical coding model (256k context)
- `grok-4`: Most capable flagship model (256k context)
- `grok-3`: Powerful coding model (131k context)
<img width="805" height="592" alt="image"
src="https://github.com/user-attachments/assets/a99b9495-e90e-40f3-a772-be9807b24501"
/>
<img width="805" height="653" alt="image"
src="https://github.com/user-attachments/assets/aad7b333-ee74-457a-b5b7-5d20bd54d7e0"
/>
## Dependencies
- Requires `@ai-sdk/xai` package (already imported)
- Uses existing provider pattern and infrastructure
## Why xAI for Coding?
xAI's Grok models have shown impressive results in coding benchmarks:
- Trained on high-quality programming datasets reflecting real-world
tasks
- Excels at agentic coding workflows with fast reasoning capabilities
- Strong performance across multiple programming languages (TypeScript,
Python, Java, Rust, C++, Go)
- Achieved 70.8% on SWE-Bench-Verified using internal evaluation
- Optimized for rapid iteration in development environments
<!-- This is an auto-generated description by cubic. -->
---
## Summary by cubic
Adds xAI (Grok) as a provider so users can pick Grok coding models in
the app. Integrates provider config, client wiring, and schema updates.
- **New Features**
- Added xAI provider with env var mapping (XAI_API_KEY) and provider
metadata.
- Exposed models: grok-code-fast-1 (256k), grok-4 (256k), grok-3 (131k).
- Hooked up get_model_client to use @ai-sdk/xai (createXai).
- Included "xai" in validation schemas and model options.
- **Migration**
- Set XAI_API_KEY to enable xAI.
<!-- End of auto-generated description by cubic. -->
---------
Co-authored-by: Will Chen <willchen90@gmail.com>
- follows existing patterns for AI SDK to provide Bedrock integration
- Uses Bedrock's API token feature for authentication which provides a
standard experience
- bedrock provided models match the Anthropic provided models (for now)
**Disclaimer**: The contributing docs are extremely sparse. I don't
actually know how to build this and get this running in Electron
## Testing
- AWS Bedrock provider is available for selection
<img width="994" height="496" alt="image"
src="https://github.com/user-attachments/assets/3cb21fed-9826-40e5-8019-b2b5df5e873b"
/>
- The provider settings also show the right models and offer the right
env variable to use
<img width="949" height="862" alt="image"
src="https://github.com/user-attachments/assets/8c23d5c8-d84d-4bf7-856a-8dc8d9d6c4b4"
/>
<!-- This is an auto-generated description by cubic. -->
---
## Summary by cubic
Adds AWS Bedrock as a provider so users can run Claude models via
Bedrock with API token authentication. The settings now list Bedrock
with supported models and a new env var.
- New Features
- New provider: bedrock using @ai-sdk/amazon-bedrock, wired into model
client and schemas.
- Models: Claude 4 Sonnet, Claude 3.7 Sonnet, Claude 3.5 Sonnet (Bedrock
model IDs).
- Settings: shows AWS Bedrock with correct models and env var
AWS_BEARER_TOKEN_BEDROCK.
- Default region: us-east-1.
- Migration
- Set AWS_BEARER_TOKEN_BEDROCK with your Bedrock API token.
- Select AWS Bedrock in settings and pick a model.
<!-- End of auto-generated description by cubic. -->
Co-authored-by: Samrat Jha <samratj@amazon.com>
Co-authored-by: Will Chen <willchen90@gmail.com>
<!-- This is an auto-generated description by cubic. -->
## Summary by cubic
Set “balanced” as the default smart context mode. Users now get balanced
when Smart Files Context is enabled and no mode is set; “conservative”
must be explicitly selected.
- **Refactors**
- Default fallback to balanced in UI and engine (proSmartContextOption
undefined -> "balanced").
- ProModeSelector saves "conservative" explicitly; selector reads
undefined as balanced.
- Updated schema and types to allow "balanced" | "conservative".
- Engine payload now includes smart_context_mode with "balanced" by
default; e2e tests and snapshots updated.
- **Migration**
- No action needed. Existing users without an explicit mode will use
balanced by default; selecting conservative persists.
<!-- End of auto-generated description by cubic. -->
Fixes#710
This PR implements comprehensive Azure OpenAI integration for Dyad,
enabling users to leverage Azure
OpenAI models through proper environment variable configuration. The
implementation adds Azure as a
supported provider with full integration into the existing language
model architecture, including support
for GPT-5 models. Key features include environment-based
configuration using `AZURE_API_KEY` and `AZURE_RESOURCE_NAME`,
specialized UI components that provide clear
setup instructions and status indicators, and seamless integration with
Dyad's existing provider system.
The Azure provider leverages the @ai-sdk/azure package (v1.3.25) for
compatibility with the current
TypeScript language model interfaces.
The implementation includes robust error handling for missing
configuration, comprehensive test coverage
with 9 new unit tests covering critical functionality like model client
creation and error scenarios, and
an E2E test for the Azure-specific settings UI.
<img width="1510" height="908" alt="Screenshot 2025-08-18 at 9 14 32 PM"
src="https://github.com/user-attachments/assets/04aa99e1-1590-4bb0-86c9-a67b97bc7500"
/>
---------
Co-authored-by: graphite-app[bot] <96075541+graphite-app[bot]@users.noreply.github.com>
Co-authored-by: Will Chen <willchen90@gmail.com>
<!-- This is an auto-generated description by cubic. -->
## Summary by cubic
Adds Smart Context v3 with selectable modes (Off, Conservative,
Balanced) and surfaces token savings in chat. Also improves token
estimation by counting per-file tokens when Smart Context is enabled.
- **New Features**
- Smart Context selector in Pro settings with three options.
Conservative is the default when enabled without an explicit choice.
- New setting: proSmartContextOption ("balanced"); undefined implies
Conservative.
- Engine now receives enable_smart_files_context and smart_context_mode.
- Chat shows a DyadTokenSavings card when the message contains
token-savings?original-tokens=...&smart-context-tokens=..., with percent
saved and a tooltip for exact tokens.
- Token estimation uses extracted file contents for accuracy when Pro +
Smart Context is on; otherwise falls back to formatted codebase output.
<!-- End of auto-generated description by cubic. -->
This uses Gemini's native [thinking
summaries](https://cloud.google.com/vertex-ai/generative-ai/docs/thinking#thought-summaries)
which were recently added to the API.
Why? The grafted thinking would sometimes cause weird issues where the
model, especially Gemini 2.5 Flash, got confused and put dyad tags like
`<dyad-write>` inside the `<think>` tags.
This also improves the UX because you can see the native thoughts rather
than having the Gemini response load for a while without any feedback.
I tried adding Anthropic extended thinking, however it requires temp to
be set at 1, which isn't ideal for Dyad's use case where we need precise
syntax following.
This code was quite complex and hairy and resulted in very opaque errors
(for both free and pro users). There's not much benefit to budget saver
because Google removed 2.5 Pro free quota a while ago (after it
graduated the model from experimental to preview). Dyad Pro users can
still use 2.5 Flash free quota by disabling Dyad Pro by clicking on the
Dyad Pro button at the top.
* Do not make API key input (password) - hurts usability
* Support LLM gateway (and add GPT 4.1 mini model)
* Show Dyad Pro button
* Fix to use auto (not dyad) for detecting dyad pro
* Fix description of gpt 4.1-mini
