<!-- CURSOR_SUMMARY -->
> [!NOTE]
> Refactors code highlighting to use react-shiki/core with a singleton
highlighter and preloaded langs/themes, adds a fallback renderer, bumps
react-shiki, and adds tests for message summarization.
>
> - **Frontend**
> - **CodeHighlight** (`src/components/chat/CodeHighlight.tsx`): Replace
`useShikiHighlighter` with `ShikiHighlighter` from `react-shiki/core`
using a singleton `createHighlighterCore` and JS regex engine; preload
common languages and GitHub light/dark themes; add `<pre><code>`
fallback while loading.
> - **Tests**
> - Add/expand Vitest suite for `formatMessagesForSummary`
(`src/__tests__/formatMessagesForSummary.test.ts`): covers truncation,
ordering, special chars, undefined content, and edge cases.
> - **Dependencies**
> - Upgrade `react-shiki` to `^0.9.0` in `package.json`.
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
b32d224cd21d3c76e77799f2995905e523406bf9. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
<!-- This is an auto-generated description by cubic. -->
---
## Summary by cubic
Preloaded a specific set of Shiki languages and themes using react-shiki
core, and updated CodeHighlight to use a singleton highlighter. This
reduces bundle size and stabilizes code rendering with a simple fallback
while loading.
- **Refactors**
- Switched to react-shiki/core with ShikiHighlighter and a singleton
highlighter.
- Preloaded common languages
(js/ts/jsx/tsx/html/css/json/markdown/python/etc.) and GitHub light/dark
themes.
- Used the JavaScript regex engine and added a plain <pre><code>
fallback until the highlighter is ready.
- **Dependencies**
- Upgraded react-shiki to ^0.9.0.
<sup>Written for commit b32d224cd21d3c76e77799f2995905e523406bf9.
Summary will update automatically on new commits.</sup>
<!-- End of auto-generated description by cubic. -->
<!-- This is an auto-generated description by cubic. -->
---
## Summary by cubic
Prototype visual editing mode for the preview app. Toggle the mode, pick
elements (single or multiple), and edit margin, padding, border,
background, static text, and text styles with live updates, then save
changes back to code.
- **New Features**
- Pen tool button to enable/disable visual editing in the preview and
toggle single/multi select; pro-only.
- Inline toolbar anchored to the selected element for Margin (X/Y),
Padding (X/Y), Border (width/radius/color), Background color, Edit Text
(when static), and Text Style (font size/weight/color/font family).
- Reads computed styles from the iframe and applies changes in real
time; auto-appends px; overlay updates on scroll/resize.
- Save/Discard dialog batches edits and writes Tailwind classes to
source files via IPC; uses AST/recast to update className and text,
replacing conflicting classes by prefix; supports multiple components.
- New visual editor worker to get/apply styles and enable inline text
editing via postMessage; selector client updated for coordinates
streaming and highlight/deselect.
- Proxy injects the visual editor client; new atoms track selected
component, coordinates, and pending changes; component analysis flags
dynamic styling and static text.
- Uses runtimeId to correctly target and edit duplicate components.
- **Dependencies**
- Added @babel/parser for AST-based text updates.
- Added recast for safer code transformations.
<sup>Written for commit cdd50d33387a29103864f4743ae7570d64d61e93.
Summary will update automatically on new commits.</sup>
<!-- End of auto-generated description by cubic. -->
<!-- CURSOR_SUMMARY -->
> [!NOTE]
> Adds a context-limit banner with one-click “summarize into new chat,”
refactors token counting with react-query, and persists per-message max
token usage.
>
> - **Chat UX**
> - **Context limit banner** (`ContextLimitBanner.tsx`,
`MessagesList.tsx`): shows when within 40k tokens of `contextWindow`,
with tooltip and action to summarize into a new chat.
> - **Summarize flow**: extracted to `useSummarizeInNewChat` and used in
chat input and banner; new summarize system prompt
(`summarize_chat_system_prompt.ts`).
> - **Token usage & counting**
> - **Persist max tokens used per assistant message**: DB migration
(`messages.max_tokens_used`), schema updates, and saving usage during
streaming (`chat_stream_handlers.ts`).
> - **Token counting refactor** (`useCountTokens.ts`): react-query with
debounce; returns `estimatedTotalTokens` and `actualMaxTokens`;
invalidated on model change and stream end; `TokenBar` updated.
> - **Surfacing usage**: tooltip on latest assistant message shows total
tokens (`ChatMessage.tsx`).
> - **Model/config tweaks**
> - Set `auto` model `contextWindow` to `200_000`
(`language_model_constants.ts`).
> - Improve chat auto-scroll dependency (`ChatPanel.tsx`).
> - Fix app path validation regex (`app_handlers.ts`).
> - **Testing & dev server**
> - E2E tests for banner and summarize
(`e2e-tests/context_limit_banner.spec.ts` + fixtures/snapshot).
> - Fake LLM server streams usage to simulate high token scenarios
(`testing/fake-llm-server/*`).
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
2ae16a14d50699cc772407426419192c2fdf2ec3. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
<!-- This is an auto-generated description by cubic. -->
---
## Summary by cubic
Adds a “Summarize into new chat” trigger and a context limit banner to
help keep conversations focused and avoid hitting model limits. Also
tracks and surfaces actual token usage per assistant message, with a
token counting refactor for reliability.
- **New Features**
- Summarize into new chat from the input or banner; improved system
prompt with clear output format.
- Context limit banner shows when within 40k tokens of the model’s
context window and offers a one-click summarize action.
- Tooltip on the latest assistant message shows total tokens used.
- **Refactors**
- Token counting now uses react-query and returns estimatedTotalTokens
and actualMaxTokens; counts are invalidated on model change and when
streaming settles.
- Persist per-message max_tokens_used in the messages table; backend
aggregates model usage during streaming and saves it.
- Adjusted default “Auto” model contextWindow to 200k for more realistic
limits.
- Improved chat scrolling while streaming; fixed app path validation
regex.
<sup>Written for commit 2ae16a14d50699cc772407426419192c2fdf2ec3.
Summary will update automatically on new commits.</sup>
<!-- End of auto-generated description by cubic. -->
closes#1688
<!-- This is an auto-generated description by cubic. -->
---
## Summary by cubic
Add a “Fix All Errors” button to the chat that collects all error
messages and sends a single request to resolve them. This helps users
fix multiple errors in one step.
- New Features
- Parse dyad-output type=error messages and track count/last index in
DyadMarkdownParser.
- Show FixAllErrorsButton after the last error when there are 2+ errors,
not streaming, and chatId is present.
- Button streams a prompt listing all errors, shows a loading state, and
displays the error count.
<sup>Written for commit b9762955d3b9cecd3b00c9efb478ce599f60e32d.
Summary will update automatically on new commits.</sup>
<!-- 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>
Fixes#1037
<!-- This is an auto-generated description by cubic. -->
---
## Summary by cubic
Enable JSON file support in codebase scanning so common configs and data
(e.g., package.json, vercel.json, translations) are included. Adds .json
to the allowed extensions and removes special-casing for
package.json/vercel.json.
<!-- End of auto-generated description by cubic. -->
Test cases:
- [x] create-ts-errors
- [x] with auto-fix
- [x] without auto-fix
- [x] create-unfixable-ts-errors
- [x] manually edit file & click recheck
- [x] fix all
- [x] delete and rename case
THINGS
- [x] error handling for checkProblems isn't working as expected
- [x] make sure it works for both default templates (add tests)
- [x] fix bad animation
- [x] change file context (prompt/files)
IF everything passes in Windows AND defensive try catch... then enable
by default
- [x] enable auto-fix by default
- [x] add e2e test - happy case (make sure it clears selection and next
prompt is empty, and preview is cleared); de-selection case
- [x] shim - old & new file
- [x] upgrade path
- [x] add docs
- [x] add try-catch to parser script
- [x] make it work for next.js
- [x] extract npm package
- [x] make sure plugin doesn't apply in prod
