1 files changed, 9 insertions, 1 deletions
diff --git a/libpanto/src/provider_openai_chat.zig b/libpanto/src/provider_openai_chat.zig
index d70eb30..c454679 100644
--- a/libpanto/src/provider_openai_chat.zig
+++ b/libpanto/src/provider_openai_chat.zig
@@ -137,6 +137,14 @@ pub const OpenAIChatRequest = struct {
                 @intFromEnum(response.head.status),
                 err_buf.items,
             });
+            // Detect a context-overflow rejection so the caller can
+            // compact and retry rather than treating it as a hard error.
+            // OpenAI-compatible APIs return HTTP 400 with a
+            // `context_length_exceeded` code / "maximum context length"
+            // message on the input side.
+            if (@intFromEnum(response.head.status) == 400 and provider_mod.isContextOverflowBody(err_buf.items)) {
+                return error.ContextOverflow;
+            }
             return error.HttpError;
         }
 
@@ -524,7 +532,7 @@ const StreamState = struct {
         const moved_blocks = try self.blocks.toOwnedSlice(self.allocator);
         defer self.allocator.free(moved_blocks);
 
-        try conv.addAssistantMessage(moved_blocks);
+        try conv.addAssistantMessageWithUsage(moved_blocks, self.usage);
 
         const msg = conv.messages.items[conv.messages.items.len - 1];
         try receiver.onMessageComplete(msg, self.usage);