fix(ai): disable OpenCode long cache retention for rejecting routes

closes #5702

packages/ai/CHANGELOG.md

@@ -2,6 +2,10 @@
 
 ## [Unreleased]
 
+### Fixed
+
+- Fixed OpenCode/OpenCode Go completion models that reject `prompt_cache_retention` to omit long-retention cache fields when `cacheRetention` is `long` ([#5702](https://github.com/earendil-works/pi/issues/5702)).
+
 ## [0.79.3] - 2026-06-13
 
 ### Fixed

packages/ai/scripts/generate-models.ts

@@ -187,6 +187,15 @@ const OPENAI_RESPONSES_NONE_REASONING_MODELS = new Set([
 	"gpt-5.5",
 ]);
 
+const OPENCODE_OPENAI_COMPLETIONS_LONG_CACHE_RETENTION_UNSUPPORTED_MODELS = new Set([
+	"opencode:deepseek-v4-flash",
+	"opencode:deepseek-v4-pro",
+	"opencode:kimi-k2.5",
+	"opencode:kimi-k2.6",
+	"opencode:minimax-m2.7",
+	"opencode-go:kimi-k2.6",
+]);
+
 function mergeThinkingLevelMap(model: Model<any>, map: NonNullable<Model<any>["thinkingLevelMap"]>): void {
 	model.thinkingLevelMap = { ...model.thinkingLevelMap, ...map };
 }
@@ -1070,6 +1079,13 @@ async function loadModelsDevData(): Promise<Model<any>[]> {
 
 				if (api === "openai-completions") {
 					compat = { ...(compat ?? {}), maxTokensField: "max_tokens" };
+					if (
+						OPENCODE_OPENAI_COMPLETIONS_LONG_CACHE_RETENTION_UNSUPPORTED_MODELS.has(
+							`${variant.provider}:${modelId}`,
+						)
+					) {
+						compat = { ...compat, supportsLongCacheRetention: false };
+					}
 				}
 
 				models.push({

packages/ai/src/models.generated.ts

@@ -7889,7 +7889,7 @@ export const MODELS = {
 			api: "openai-completions",
 			provider: "opencode",
 			baseUrl: "https://opencode.ai/zen/v1",
-			compat: {"maxTokensField":"max_tokens","requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
+			compat: {"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
 			reasoning: true,
 			thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max"},
 			input: ["text"],
@@ -7927,7 +7927,7 @@ export const MODELS = {
 			api: "openai-completions",
 			provider: "opencode",
 			baseUrl: "https://opencode.ai/zen/v1",
-			compat: {"maxTokensField":"max_tokens","requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
+			compat: {"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
 			reasoning: true,
 			thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max"},
 			input: ["text"],
@@ -8343,7 +8343,7 @@ export const MODELS = {
 			api: "openai-completions",
 			provider: "opencode",
 			baseUrl: "https://opencode.ai/zen/v1",
-			compat: {"maxTokensField":"max_tokens"},
+			compat: {"maxTokensField":"max_tokens","supportsLongCacheRetention":false},
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
@@ -8361,7 +8361,7 @@ export const MODELS = {
 			api: "openai-completions",
 			provider: "opencode",
 			baseUrl: "https://opencode.ai/zen/v1",
-			compat: {"thinkingFormat":"deepseek","supportsReasoningEffort":false,"maxTokensField":"max_tokens"},
+			compat: {"thinkingFormat":"deepseek","supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false},
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
@@ -8415,7 +8415,7 @@ export const MODELS = {
 			api: "openai-completions",
 			provider: "opencode",
 			baseUrl: "https://opencode.ai/zen/v1",
-			compat: {"maxTokensField":"max_tokens"},
+			compat: {"maxTokensField":"max_tokens","supportsLongCacheRetention":false},
 			reasoning: true,
 			input: ["text"],
 			cost: {
@@ -8579,7 +8579,7 @@ export const MODELS = {
 			api: "openai-completions",
 			provider: "opencode-go",
 			baseUrl: "https://opencode.ai/zen/go/v1",
-			compat: {"thinkingFormat":"deepseek","supportsReasoningEffort":false,"maxTokensField":"max_tokens"},
+			compat: {"thinkingFormat":"deepseek","supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false},
 			reasoning: true,
 			thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
 			input: ["text", "image"],
@@ -10473,13 +10473,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0.95,
+				input: 0.75,
-				output: 4,
+				output: 3.5,
-				cacheRead: 0.19,
+				cacheRead: 0.16,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
-			maxTokens: 4096,
+			maxTokens: 262144,
 		} satisfies Model<"openai-completions">,
 		"nex-agi/nex-n2-pro:free": {
 			id: "nex-agi/nex-n2-pro:free",
@@ -16823,6 +16823,24 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
+		"glm-5.2": {
+			id: "glm-5.2",
+			name: "GLM-5.2",
+			api: "openai-completions",
+			provider: "zai",
+			baseUrl: "https://api.z.ai/api/coding/paas/v4",
+			compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai","zaiToolStream":true},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1000000,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
 		"glm-5v-turbo": {
 			id: "glm-5v-turbo",
 			name: "GLM-5V-Turbo",
@@ -16915,6 +16933,24 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
+		"glm-5.2": {
+			id: "glm-5.2",
+			name: "GLM-5.2",
+			api: "openai-completions",
+			provider: "zai-coding-cn",
+			baseUrl: "https://open.bigmodel.cn/api/coding/paas/v4",
+			compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai","zaiToolStream":true},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1000000,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
 		"glm-5v-turbo": {
 			id: "glm-5v-turbo",
 			name: "GLM-5V-Turbo",

packages/ai/test/cache-retention.test.ts

@@ -1,4 +1,5 @@
 import { afterEach, beforeEach, describe, expect, it } from "vitest";
+import { MODELS } from "../src/models.generated.ts";
 import { getModel } from "../src/models.ts";
 import { streamAnthropic } from "../src/providers/anthropic.ts";
 import { streamOpenAICompletions } from "../src/providers/openai-completions.ts";
@@ -13,6 +14,11 @@ class PayloadCaptured extends Error {
 	}
 }
 
+interface OpenAICompletionsCachePayload {
+	prompt_cache_key?: string;
+	prompt_cache_retention?: string;
+}
+
 function stopAfterPayload<TPayload>(capture: (payload: TPayload) => void): (payload: unknown) => never {
 	return (payload: unknown): never => {
 		capture(payload as TPayload);
@@ -455,5 +461,39 @@ describe("Cache Retention (PI_CACHE_RETENTION)", () => {
 			expect(capturedPayload.prompt_cache_key).toBeUndefined();
 			expect(capturedPayload.prompt_cache_retention).toBeUndefined();
 		});
+
+		it.each([
+			MODELS.opencode["deepseek-v4-flash"],
+			MODELS.opencode["deepseek-v4-pro"],
+			MODELS.opencode["kimi-k2.5"],
+			MODELS.opencode["kimi-k2.6"],
+			MODELS.opencode["minimax-m2.7"],
+			MODELS["opencode-go"]["kimi-k2.6"],
+		] as const)("should omit long cache retention for $provider/$id", async (metadata) => {
+			const model = metadata as Model<"openai-completions">;
+			let capturedPayload: OpenAICompletionsCachePayload | undefined;
+
+			try {
+				const s = streamOpenAICompletions(model, context, {
+					apiKey: "fake-key",
+					cacheRetention: "long",
+					sessionId: "session-opencode-long-cache-unsupported",
+					onPayload: stopAfterPayload<OpenAICompletionsCachePayload>((payload) => {
+						capturedPayload = payload;
+					}),
+				});
+
+				for await (const event of s) {
+					if (event.type === "error") break;
+				}
+			} catch {
+				// Expected to fail
+			}
+
+			expect(model.compat?.supportsLongCacheRetention).toBe(false);
+			expect(capturedPayload).toBeDefined();
+			expect(capturedPayload?.prompt_cache_key).toBeUndefined();
+			expect(capturedPayload?.prompt_cache_retention).toBeUndefined();
+		});
 	});
 });

packages/coding-agent/CHANGELOG.md

@@ -4,6 +4,7 @@
 
 ### Fixed
 
+- Fixed inherited OpenCode/OpenCode Go completion model metadata to omit long-retention cache fields for routes that reject `prompt_cache_retention` ([#5702](https://github.com/earendil-works/pi/issues/5702)).
 - Fixed custom provider config so plain uppercase API key and header values remain literals instead of being treated as legacy environment references; use explicit `$ENV_VAR` syntax for environment variables ([#5661](https://github.com/earendil-works/pi/issues/5661)).
 
 ## [0.79.3] - 2026-06-13