fix(ai): clean up openai-codex models and token limits

- Remove model aliases (gpt-5, gpt-5-mini, gpt-5-nano, codex-mini-latest, gpt-5-codex, gpt-5.1-codex, gpt-5.1-chat-latest)
- Fix context window from 400k to 272k tokens to match Codex CLI defaults
- Keep maxTokens at 128k (original value)
- Simplify reasoning effort clamping

closes #536

packages/ai/CHANGELOG.md

@@ -2,9 +2,13 @@
 
 ## [Unreleased]
 
+### Breaking Changes
+
+- Removed OpenAI Codex model aliases (`gpt-5`, `gpt-5-mini`, `gpt-5-nano`, `codex-mini-latest`, `gpt-5-codex`, `gpt-5.1-codex`, `gpt-5.1-chat-latest`). Use canonical model IDs: `gpt-5.1`, `gpt-5.1-codex-max`, `gpt-5.1-codex-mini`, `gpt-5.2`, `gpt-5.2-codex`. ([#536](https://github.com/badlogic/pi-mono/pull/536) by [@ghoulr](https://github.com/ghoulr))
+
 ### Fixed
 
-- Fixed OpenAI Codex OAuth model list (removed aliases), aligned context window/maxTokens with observed backend limits, and refined reasoning effort clamping.
+- Fixed OpenAI Codex context window from 400,000 to 272,000 tokens to match Codex CLI defaults and prevent 400 errors. ([#536](https://github.com/badlogic/pi-mono/pull/536) by [@ghoulr](https://github.com/ghoulr))
 
 ## [0.37.8] - 2026-01-07
 

packages/ai/scripts/generate-models.ts

@@ -447,8 +447,7 @@ async function generateModels() {
 	// Context window is based on observed server limits (400s above ~272k), not marketing numbers.
 	const CODEX_BASE_URL = "https://chatgpt.com/backend-api";
 	const CODEX_CONTEXT = 272000;
-	// Use the same max output token budget as Codex CLI.
+	const CODEX_MAX_TOKENS = 128000;
-	const CODEX_MAX_TOKENS = 10000;
 	const codexModels: Model<"openai-codex-responses">[] = [
 		{
 			id: "gpt-5.1",

packages/ai/src/models.generated.ts

@@ -2806,7 +2806,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 272000,
-			maxTokens: 10000,
+			maxTokens: 128000,
 		} satisfies Model<"openai-codex-responses">,
 		"gpt-5.1-codex-max": {
 			id: "gpt-5.1-codex-max",
@@ -2823,7 +2823,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 272000,
-			maxTokens: 10000,
+			maxTokens: 128000,
 		} satisfies Model<"openai-codex-responses">,
 		"gpt-5.1-codex-mini": {
 			id: "gpt-5.1-codex-mini",
@@ -2840,7 +2840,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 272000,
-			maxTokens: 10000,
+			maxTokens: 128000,
 		} satisfies Model<"openai-codex-responses">,
 		"gpt-5.2": {
 			id: "gpt-5.2",
@@ -2857,7 +2857,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 272000,
-			maxTokens: 10000,
+			maxTokens: 128000,
 		} satisfies Model<"openai-codex-responses">,
 		"gpt-5.2-codex": {
 			id: "gpt-5.2-codex",
@@ -2874,7 +2874,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 272000,
-			maxTokens: 10000,
+			maxTokens: 128000,
 		} satisfies Model<"openai-codex-responses">,
 	},
 	"openrouter": {