diff --git a/packages/ai/CHANGELOG.md b/packages/ai/CHANGELOG.md
index fe1954ea..71135a2e 100644
--- a/packages/ai/CHANGELOG.md
+++ b/packages/ai/CHANGELOG.md
@@ -6,6 +6,8 @@
 
 - Stopped sending `tools: []` on OpenAI-compatible, Anthropic, OpenAI Responses, OpenAI Codex Responses, and Azure OpenAI Responses requests when no tools are active (e.g. `pi --no-tools`). DashScope/Aliyun Qwen (OpenAI-compatible) rejects empty tools arrays with `"[] is too short - 'tools'"` (HTTP 400); the field is now omitted unless the conversation has tool history (the existing LiteLLM/Anthropic-proxy workaround).
 - Fixed `supportsXhigh()` to recognize DeepSeek V4 Pro, preserving `xhigh` reasoning requests so they map to DeepSeek's `max` effort ([#3662](https://github.com/badlogic/pi-mono/issues/3662))
+- Fixed OpenAI-compatible DeepSeek V4 model replay to include empty `reasoning_content` on assistant messages when needed, preventing OpenRouter DeepSeek V4 sessions from failing after responses without reasoning deltas ([#3668](https://github.com/badlogic/pi-mono/issues/3668))
+
 ## [0.70.2] - 2026-04-24
 
 ### Fixed
diff --git a/packages/ai/scripts/generate-models.ts b/packages/ai/scripts/generate-models.ts
index 3c0f7e6d..f572b864 100644
--- a/packages/ai/scripts/generate-models.ts
+++ b/packages/ai/scripts/generate-models.ts
@@ -1063,6 +1063,15 @@ async function generateModels() {
 	];
 	allModels.push(...deepseekV4Models);
 
+	for (const candidate of allModels) {
+		if (candidate.api === "openai-completions" && candidate.id.includes("deepseek-v4")) {
+			candidate.compat = {
+				...candidate.compat,
+				requiresReasoningContentOnAssistantMessages: true,
+			};
+		}
+	}
+
 	const minimaxDirectSupportedIds = new Set(["MiniMax-M2.7", "MiniMax-M2.7-highspeed"]);
 
 	for (const candidate of allModels) {
diff --git a/packages/ai/src/models.generated.ts b/packages/ai/src/models.generated.ts
index 9706242c..6f2fe25c 100644
--- a/packages/ai/src/models.generated.ts
+++ b/packages/ai/src/models.generated.ts
@@ -8240,6 +8240,7 @@ export const MODELS = {
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
+			compat: {"requiresReasoningContentOnAssistantMessages":true},
 			reasoning: true,
 			input: ["text"],
 			cost: {
@@ -8257,6 +8258,7 @@ export const MODELS = {
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
+			compat: {"requiresReasoningContentOnAssistantMessages":true},
 			reasoning: true,
 			input: ["text"],
 			cost: {