From 830314177fd75adb8a513a53b2837ca3fd93f4b3 Mon Sep 17 00:00:00 2001
From: Jeevan Babu Gotru <114808955+jeevan1098@users.noreply.github.com>
Date: Tue, 27 Oct 2026 10:20:41 -0500
Subject: [PATCH] fix(github_copilot): surface copilot_usage token_details as
 cache token counts

---
 .../litellm_core_utils/streaming_handler.py   | 26 +++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/litellm/litellm_core_utils/streaming_handler.py b/litellm/litellm_core_utils/streaming_handler.py
index 2df470edc59..7c3d56b0245 100644
--- a/litellm/litellm_core_utils/streaming_handler.py
+++ b/litellm/litellm_core_utils/streaming_handler.py
@@ -2757,10 +2757,36 @@ def calculate_total_usage(chunks: Sequence[ModelResponse | ModelResponseStream])
         )
         if latest_cost is not None:
             returned_usage_chunk.cost = latest_cost
+        _apply_copilot_cache_counts(returned_usage_chunk, latest_usage_chunk)
 
     return returned_usage_chunk
 
 
+def _apply_copilot_cache_counts(returned_usage: Usage, latest_usage_chunk: Usage | Mapping[str, int]) -> None:
+    from litellm.llms.github_copilot.chat.transformation import copilot_cache_token_counts
+
+    copilot_usage: Final = (
+        latest_usage_chunk.get("copilot_usage")
+        if isinstance(latest_usage_chunk, Mapping)
+        else getattr(latest_usage_chunk, "copilot_usage", None)
+    )
+    if not isinstance(copilot_usage, Mapping):
+        return
+    cache_read, cache_write = copilot_cache_token_counts({"copilot_usage": copilot_usage})
+    if not cache_read and not cache_write:
+        return
+    details: Final = returned_usage.prompt_tokens_details or PromptTokensDetailsWrapper()
+    if cache_read and not getattr(details, "cached_tokens", None):
+        details.cached_tokens = cache_read
+    if cache_write and not getattr(details, "cache_write_tokens", None):
+        details.cache_write_tokens = cache_write
+    returned_usage.prompt_tokens_details = details  # rebind-ok: attaches copilot cache counts to the aggregated usage
+    if cache_read and getattr(returned_usage, "cache_read_input_tokens", None) is None:
+        returned_usage.cache_read_input_tokens = cache_read
+    if cache_write and getattr(returned_usage, "cache_creation_input_tokens", None) is None:
+        returned_usage.cache_creation_input_tokens = cache_write
+
+
 def generic_chunk_has_all_required_fields(chunk: dict) -> bool:
     """
     Checks if the provided chunk dictionary contains all required fields for GenericStreamingChunk.