refactor(cli): simplify ChatGPT subscription detection to zero-cost heuristic

Co-authored-by: kiloconnect[bot] <240665456+kiloconnect[bot]@users.noreply.github.com>

packages/opencode/src/provider/transform.ts

@@ -329,14 +329,12 @@ function normalizeMessages(
 }
 
 // kilocode_change start - explicit prompt cache breakpoints for GPT-5.6+ (excluding ChatGPT subscriptions)
-function isChatGPTSubscription(model: Provider.Model): boolean {
-  if (model.providerID === "openai" && model.cost?.input === 0 && model.cost?.output === 0) return true
-  if (typeof model.api.url === "string" && model.api.url.includes("chatgpt.com")) return true
-  return false
+function isLikelyChatGPTSubscription(model: Provider.Model): boolean {
+  return model.providerID === "openai" && model.cost?.input === 0 && model.cost?.output === 0
 }
 
 function supportsPromptCacheBreakpoint(model: Provider.Model): boolean {
-  if (isChatGPTSubscription(model)) return false
+  if (isLikelyChatGPTSubscription(model)) return false
   const match = model.api.id.match(/gpt-(\d+)\.(\d+)/)
   if (match) {
     const major = Number(match[1])

packages/opencode/test/provider/transform.test.ts

@@ -3163,7 +3163,7 @@ describe("ProviderTransform.message - cache control on gateway", () => {
     })
   })
 
-  test("openai gpt-5.6 with ChatGPT subscription (zero cost) does not apply promptCacheBreakpoint", () => {
+  test("openai gpt-5.6 with ChatGPT subscription (zero cost heuristic) does not apply promptCacheBreakpoint", () => {
     const model = createModel({
       providerID: "openai",
       api: {
@@ -3194,38 +3194,6 @@ describe("ProviderTransform.message - cache control on gateway", () => {
     expect(result[0].providerOptions?.openai?.promptCacheBreakpoint).toBeUndefined()
     expect(result[1].providerOptions?.openai?.promptCacheBreakpoint).toBeUndefined()
   })
-
-  test("openai gpt-5.6 with ChatGPT backend endpoint does not apply promptCacheBreakpoint", () => {
-    const model = createModel({
-      providerID: "openai",
-      api: {
-        id: "gpt-5.6",
-        url: "https://chatgpt.com/backend-api/codex/responses",
-        npm: "@ai-sdk/openai",
-      },
-      id: "gpt-5.6",
-      cost: {
-        input: 0.002,
-        output: 0.008,
-        cache: { read: 0.0005, write: 0.002 },
-      },
-    })
-    const msgs = [
-      {
-        role: "system",
-        content: "You are a helpful assistant",
-      },
-      {
-        role: "user",
-        content: "Hello",
-      },
-    ] as any[]
-
-    const result = ProviderTransform.message(msgs, model, {}) as any[]
-
-    expect(result[0].providerOptions?.openai?.promptCacheBreakpoint).toBeUndefined()
-    expect(result[1].providerOptions?.openai?.promptCacheBreakpoint).toBeUndefined()
-  })
   // kilocode_change end
 })