<!-- CURSOR_SUMMARY -->
> [!NOTE]
> Adds `gemini-3-pro-preview` to Google model options with 1,048,576
context window and 65,535 max output tokens.
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
6aefc4449908e862476f61c0bcb2a625111256a3. 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
Added Gemini 3 Pro (Preview) to the Google model list so users can
select it in the app. Sets a 1,048,576-token context window and a safe
max output of 65,535 tokens, with temperature 1.0.
<sup>Written for commit 6aefc4449908e862476f61c0bcb2a625111256a3.
Summary will update automatically on new commits.</sup>
<!-- End of auto-generated description by cubic. -->
Added to OpenAI and Azure
GPT-5.1: adaptive reasoning
GPT-5.1-codex: advanced coding workflows
GPT-5.1-codex-mini: compact and efficient
<!-- This is an auto-generated description by cubic. -->
---
## Summary by cubic
Added support for OpenAI and Azure GPT-5.1, including GPT-5.1 Codex and
Codex Mini, for smarter conversations and better coding tasks. All
models use a 400k context window, require temperature 1, and leave max
output tokens unspecified to align with API behavior.
<sup>Written for commit 9788541c88732aa7d522fc70bfb20f22c3544982.
Summary will update automatically on new commits.</sup>
<!-- End of auto-generated description by cubic. -->
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> Adds GPT-5.1, GPT-5.1 Codex, and Codex Mini to OpenAI and Azure model
catalogs with 400k context and temperature 1 (max output tokens
unspecified).
>
> - **Model registry updates
(`src/ipc/shared/language_model_constants.ts`)**:
> - **OpenAI**:
> - Add `gpt-5.1`, `gpt-5.1-codex`, `gpt-5.1-codex-mini` (400k
`contextWindow`, `temperature: 1`, `maxOutputTokens: undefined`).
> - Keep existing `gpt-5`, `gpt-5-codex`, `gpt-5-mini`, `gpt-5-nano`,
`o4-mini`.
> - **Azure**:
> - Add `gpt-5.1`, `gpt-5.1-codex`, `gpt-5.1-codex-mini` with matching
settings (400k `contextWindow`, `temperature: 1`).
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
9788541c88732aa7d522fc70bfb20f22c3544982. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
---------
Co-authored-by: Will Chen <willchen90@gmail.com>
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 -->
<!-- CURSOR_SUMMARY -->
> [!NOTE]
> Introduces a new `auto` model `value` (Super Value Pro), adds
configurable tag colors across model types, and updates Model Picker
filtering and badges.
>
> - **Models and Types**:
> - Add new auto model `value` ("Super Value (Pro)") with `tag: Budget`
and `tagColor`.
> - Enhance `turbo` auto model with `tag: Fast` and `tagColor`.
> - Extend `LanguageModel` and `ModelOption` with optional `tagColor`.
> - **Model Picker UI**:
> - Render model tags with configurable colors via `tagColor` and `cn`
utility.
> - Update "Pro only" badge logic (hide when display name already
includes "(Pro)"); adjust badge text size.
> - Refine auto model visibility: non‑Pro hides `turbo` and `value`; Pro
hides `free`.
> - Minor styling/labeling tweaks in tag and badge rendering.
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
4485fddad502237d4bceb43732043d3eaa60eaa0. 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 “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. -->
