Add GPT 5 Codex and Sonnet 4.5 (#1398)

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 -->

e2e-tests/snapshots/engine.spec.ts_send-message-to-engine---anthropic-claude-sonnet-4-1.txt

@@ -1,7 +1,7 @@
 {
   "body": {
     "model": "anthropic/claude-sonnet-4-20250514",
-    "max_tokens": 16000,
+    "max_tokens": 32000,
     "temperature": 0,
     "messages": [
       {

e2e-tests/snapshots/gateway.spec.ts_claude-4-sonnet-1.txt

@@ -1,7 +1,7 @@
 {
   "body": {
     "model": "anthropic/claude-sonnet-4-20250514",
-    "max_tokens": 16000,
+    "max_tokens": 32000,
     "temperature": 0,
     "messages": [
       {

src/ipc/shared/language_model_constants.ts

@@ -20,6 +20,18 @@ export interface ModelOption {
 
 export const MODEL_OPTIONS: Record<string, ModelOption[]> = {
   openai: [
+    // https://platform.openai.com/docs/models/gpt-5-codex
+    {
+      name: "gpt-5-codex",
+      displayName: "GPT 5 Codex",
+      description: "OpenAI's flagship model optimized for coding",
+      // Technically it's 128k but OpenAI errors if you set max_tokens instead of max_completion_tokens
+      maxOutputTokens: undefined,
+      contextWindow: 400_000,
+      // Requires temperature to be default value (1)
+      temperature: 1,
+      dollarSigns: 3,
+    },
     // https://platform.openai.com/docs/models/gpt-5
     {
       name: "gpt-5",
@@ -72,12 +84,23 @@ export const MODEL_OPTIONS: Record<string, ModelOption[]> = {
   ],
   // https://docs.anthropic.com/en/docs/about-claude/models/all-models#model-comparison-table
   anthropic: [
+    {
+      name: "claude-sonnet-4-5-20250929",
+      displayName: "Claude 4.5 Sonnet",
+      description:
+        "Anthropic's best model for coding (note: >200k tokens is very expensive!)",
+      // Set to 32k since context window is 1M tokens
+      maxOutputTokens: 32_000,
+      contextWindow: 1_000_000,
+      temperature: 0,
+      dollarSigns: 5,
+    },
     {
       name: "claude-sonnet-4-20250514",
       displayName: "Claude 4 Sonnet",
       description: "Excellent coder (note: >200k tokens is very expensive!)",
-      // See comment below for Claude 3.7 Sonnet for why we set this to 16k
+      // Set to 32k since context window is 1M tokens
-      maxOutputTokens: 16_000,
+      maxOutputTokens: 32_000,
       contextWindow: 1_000_000,
       temperature: 0,
       dollarSigns: 5,
@@ -265,37 +288,50 @@ export const MODEL_OPTIONS: Record<string, ModelOption[]> = {
     },
   ],
   azure: [
+    {
+      name: "gpt-5-codex",
+      displayName: "GPT-5 Codex",
+      description: "Azure OpenAI GPT-5 Codex model",
+      // See OpenAI comment above
+      // maxOutputTokens: 128_000,
+      contextWindow: 400_000,
+      temperature: 1,
+    },
     {
       name: "gpt-5",
       displayName: "GPT-5",
       description: "Azure OpenAI GPT-5 model with reasoning capabilities",
-      maxOutputTokens: 128_000,
+      // See OpenAI comment above
+      // maxOutputTokens: 128_000,
       contextWindow: 400_000,
-      temperature: 0,
+      temperature: 1,
     },
     {
       name: "gpt-5-mini",
       displayName: "GPT-5 Mini",
       description: "Azure OpenAI GPT-5 Mini model",
-      maxOutputTokens: 128_000,
+      // See OpenAI comment above
+      // maxOutputTokens: 128_000,
       contextWindow: 400_000,
-      temperature: 0,
+      temperature: 1,
     },
     {
       name: "gpt-5-nano",
       displayName: "GPT-5 Nano",
       description: "Azure OpenAI GPT-5 Nano model",
-      maxOutputTokens: 128_000,
+      // See OpenAI comment above
+      // maxOutputTokens: 128_000,
       contextWindow: 400_000,
-      temperature: 0,
+      temperature: 1,
     },
     {
       name: "gpt-5-chat",
       displayName: "GPT-5 Chat",
       description: "Azure OpenAI GPT-5 Chat model",
-      maxOutputTokens: 16_384,
+      // See OpenAI comment above
+      // maxOutputTokens: 16_384,
       contextWindow: 128_000,
-      temperature: 0,
+      temperature: 1,
     },
   ],
   xai: [
@@ -329,11 +365,20 @@ export const MODEL_OPTIONS: Record<string, ModelOption[]> = {
     },
   ],
   bedrock: [
+    {
+      name: "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
+      displayName: "Claude 4.5 Sonnet",
+      description:
+        "Anthropic's best model for coding (note: >200k tokens is very expensive!)",
+      maxOutputTokens: 32_000,
+      contextWindow: 1_000_000,
+      temperature: 0,
+    },
     {
       name: "us.anthropic.claude-sonnet-4-20250514-v1:0",
       displayName: "Claude 4 Sonnet",
       description: "Excellent coder (note: >200k tokens is very expensive!)",
-      maxOutputTokens: 16_000,
+      maxOutputTokens: 32_000,
       contextWindow: 1_000_000,
       temperature: 0,
     },