Log the prompt token count of every LLM round

Asks llama-server for usage in the stream, so the log shows how full
the model's context is; history, tool definitions and tool results all
count.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

1 files changed, 7 insertions, 1 deletions

diff --git a/assistant.py b/assistant.py
index 4ea8113..4dc11db 100644
--- a/assistant.py
+++ b/assistant.py
@@ -253,6 +253,7 @@ def llm_model():
 def ask(messages, calls, tools=None):
     # Yields reply text as it streams; tool-call fragments go into calls.
     body = {"model": llm_model(), "messages": messages, "stream": True,
+            "stream_options": {"include_usage": True},
             "chat_template_kwargs": {"enable_thinking": False}}
     if tools:
         body["tools"] = tools
@@ -262,7 +263,12 @@ def ask(messages, calls, tools=None):
         for line in r:
             if not line.startswith(b"data: ") or line.strip() == b"data: [DONE]":
                 continue
-            choices = json.loads(line[6:])["choices"]
+            chunk = json.loads(line[6:])
+            if chunk.get("usage"):
+                # How full the model's context is: history, tool results and
+                # tool definitions all count.
+                log(f"context: {chunk['usage']['prompt_tokens']} prompt tokens")
+            choices = chunk["choices"]
             if not choices:
                 continue
             delta = choices[0]["delta"]