fix: retry transient 'thinking blocks cannot be modified' 400s from Bedrock

strix/llm/llm.py

@@ -159,12 +159,36 @@ async def generate(
         messages = self._prepare_messages(conversation_history)
         max_retries = int(Config.get("strix_llm_max_retries") or "5")
 
+        transient_thinking_retries = 0
+        max_transient_thinking_retries = 6
+
         for attempt in range(max_retries + 1):
             try:
                 async for response in self._stream(messages):
                     yield response
                 return  # noqa: TRY300
             except Exception as e:  # noqa: BLE001
+                # Bedrock occasionally returns a 400 claiming the assistant's thinking
+                # blocks have been modified — even when the payload is structurally
+                # valid and the same payload succeeds on replay. Observed on
+                # claude-sonnet-4-6 with adaptive thinking. Retry with exponential
+                # backoff (5s, 10s, 20s, 40s, 80s, 160s — ~5 min total budget), using
+                # an inner loop so the transient retry counter does not share slots
+                # with the outer max_retries budget. Once the inner budget is
+                # exhausted (or a non-transient error is raised), fall through to the
+                # generic retry path below.
+                while (
+                    self._is_transient_thinking_error(e)
+                    and transient_thinking_retries < max_transient_thinking_retries
+                ):
+                    transient_thinking_retries += 1
+                    await asyncio.sleep(min(240, 5 * (2 ** (transient_thinking_retries - 1))))
+                    try:
+                        async for response in self._stream(messages):
+                            yield response
+                        return  # noqa: TRY300
+                    except Exception as e2:  # noqa: BLE001
+                        e = e2
                 if attempt >= max_retries or not self._should_retry(e):
                     self._raise_error(e)
                 wait = min(90, 2 * (2**attempt))
@@ -323,6 +347,22 @@ def _extract_cost(self, response: Any) -> float:
         except Exception:  # noqa: BLE001
             return 0.0
 
+    @staticmethod
+    def _is_transient_thinking_error(e: Exception) -> bool:
+        """Detect Bedrock's transient 'thinking blocks cannot be modified' 400.
+
+        Observed on claude-sonnet-4-6 with adaptive thinking: Bedrock occasionally
+        rejects a well-formed payload with this error, and the identical payload
+        succeeds on replay. Treat it as transient rather than a structural issue.
+        """
+        code = getattr(e, "status_code", None) or getattr(
+            getattr(e, "response", None), "status_code", None
+        )
+        if code != 400:
+            return False
+        message = str(e).lower()
+        return "thinking" in message and "cannot be modified" in message
+
     def _should_retry(self, e: Exception) -> bool:
         code = getattr(e, "status_code", None) or getattr(
             getattr(e, "response", None), "status_code", None