crates/gateway/src/v1/openrouter.rs

@@ -102,7 +102,21 @@ pub async fn chat(
     let latency_ms = t0.elapsed().as_millis();
     let choice = parsed.choices.into_iter().next()
         .ok_or_else(|| "openrouter returned no choices".to_string())?;
-    let text = choice.message.content;
+    let reasoning_only = choice.message.content.is_none() && choice.message.reasoning.is_some();
+    let text = choice.message.content.unwrap_or_default();
+    if reasoning_only {
+        // The model spent its whole budget thinking. Return well-formed empty
+        // content (callers' schema validation + retry budgets handle it
+        // deterministically) rather than a decode error that reads as a
+        // gateway fault — and never pass thinking-text off as an answer.
+        tracing::warn!(
+            target: "v1.chat",
+            provider = "openrouter",
+            model = %model,
+            finish = %choice.finish_reason.as_deref().unwrap_or("?"),
+            "reasoning-only response (content null) — raise max_tokens or use a non-reasoning model",
+        );
+    }
 
     let prompt_tokens = parsed.usage.as_ref().map(|u| u.prompt_tokens).unwrap_or_else(|| {
         let chars: usize = req.messages.iter().map(|m| m.text().chars().count()).sum();
@@ -169,7 +183,18 @@ struct ORChoice {
 }
 
 #[derive(Deserialize)]
-struct ORMessageResp { content: String }
+struct ORMessageResp {
+    // Reasoning models (GLM-5.x, deepseek-v4-pro) return `content: null` plus a
+    // `reasoning` field when they exhaust max_tokens mid-thought. A bare String
+    // here made serde reject the whole body ("invalid openrouter response",
+    // 2026-08-28) — which took down every reasoning model on the lane,
+    // including phase2's configured glm-5.2. Content stays the only text we
+    // ever return; reasoning is observability, never an answer.
+    #[serde(default)]
+    content: Option<String>,
+    #[serde(default)]
+    reasoning: Option<String>,
+}
 
 #[derive(Deserialize)]
 struct ORUsage { prompt_tokens: u32, completion_tokens: u32 }
@@ -178,6 +203,21 @@ struct ORUsage { prompt_tokens: u32, completion_tokens: u32 }
 mod tests {
     use super::*;
 
+    #[test]
+    fn reasoning_model_null_content_parses() {
+        // GLM-5.x / deepseek-v4-pro shape: content null + reasoning present
+        // (the 2026-08-28 decode failure). Must parse, not error.
+        let body = r#"{"choices":[{"message":{"role":"assistant","content":null,"reasoning":"thinking…"},"finish_reason":"length"}],"usage":{"prompt_tokens":5,"completion_tokens":10}}"#;
+        let parsed: ORChatResponse = serde_json::from_str(body).expect("null content must parse");
+        let choice = &parsed.choices[0];
+        assert!(choice.message.content.is_none());
+        assert_eq!(choice.message.reasoning.as_deref(), Some("thinking…"));
+        // And the normal shape still parses with reasoning absent.
+        let normal = r#"{"choices":[{"message":{"role":"assistant","content":"OK"},"finish_reason":"stop"}]}"#;
+        let parsed: ORChatResponse = serde_json::from_str(normal).expect("normal shape");
+        assert_eq!(parsed.choices[0].message.content.as_deref(), Some("OK"));
+    }
+
     #[test]
     fn resolve_openrouter_key_does_not_panic() {
         // Smoke test — all three sources may or may not be set depending