<!-- CURSOR_SUMMARY -->
> [!NOTE]
> Default Smart Files context to deep and align UI and stream handler
logic so any non-balanced option uses deep when Pro mode is enabled.
>
> - **Smart Context behavior**
> - UI (`src/components/ProModeSelector.tsx`): default
`getCurrentValue()` to `"deep"` when Pro Smart Files mode is enabled
without an explicit option.
> - Engine (`src/ipc/handlers/chat_stream_handlers.ts`):
`isDeepContextEnabled` now requires `enableProSmartFilesContextMode` and
treats any option other than `"balanced"` as deep; `smartContextMode`
set accordingly and `versioned_files` used when deep.
> - **Snapshots**
> - Update e2e snapshots to reflect `smart_context_mode: "deep"` and new
`dyad_options.versioned_files` structure.
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
7426890467d60b671a7a9712f7544a35ed922981. 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
Default smart files context to deep and align the UI and stream handler
so anything not “balanced” uses deep when Pro Smart Files mode is on.
This prevents mismatches and makes deep context the default.
- **Bug Fixes**
- ProModeSelector: default to deep when no option is set.
- chat_stream_handlers: isDeepContextEnabled requires Pro Smart Files
mode and treats non-“balanced” as deep; smartContextMode set to deep
accordingly.
- Engine payload: use versioned_files; update e2e snapshots.
<sup>Written for commit 7426890467d60b671a7a9712f7544a35ed922981.
Summary will update automatically on new commits.</sup>
<!-- End of auto-generated description by cubic. -->
Fixes#1405
<!-- This is an auto-generated description by cubic. -->
## Summary by cubic
Adds GPT-5 Codex (OpenAI and Azure) and Claude 4.5 Sonnet to the model
options to enable newer coding models and larger contexts. Also
increases Claude 4 Sonnet max output tokens to 32k.
<!-- End of auto-generated description by cubic. -->
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> Adds GPT‑5 Codex (OpenAI/Azure) and Claude 4.5 Sonnet, and increases
Claude 4 Sonnet max output tokens to 32k across providers and tests.
>
> - **Models**:
> - **OpenAI**: add `gpt-5-codex` (400k context, default temp 1).
> - **Anthropic**:
> - add `claude-sonnet-4-5-20250929` (1M context, `maxOutputTokens:
32_000`).
> - update `claude-sonnet-4-20250514` `maxOutputTokens` from `16_000` to
`32_000`.
> - **Azure**: add `gpt-5-codex` (400k context, `maxOutputTokens:
128_000`).
> - **Bedrock**:
> - add `us.anthropic.claude-sonnet-4-5-20250929-v1:0` (1M context,
`maxOutputTokens: 32_000`).
> - update `us.anthropic.claude-sonnet-4-20250514-v1:0`
`maxOutputTokens` to `32_000`.
> - **E2E tests**:
> - Update snapshots to reflect `max_tokens` increased to `32000` for
`anthropic/claude-sonnet-4-20250514` in engine and gateway tests.
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
73298d2da0c833468f957bb436f1e33400307483. 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
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#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. -->
Fixes#554#1049
<!-- This is an auto-generated description by cubic. -->
---
## Summary by cubic
Stop mutating package.json when reading files. readFileWithCache now
returns raw content so all fields are preserved (e.g., packageManager).
Fixes#554 and #1049.
- **Bug Fixes**
- Removed package.json "cleaning" logic and the cleanContent helper.
- Return and cache unmodified file content from both fs and
virtualFileSystem.
<!-- 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.
