Keep tool calls in history, with placeholder results

History kept only what was said, so after a few factual answers the
model saw no tool behind them and invented the next one: asked for
pending updates it made up counts without calling the tool (1/10 on a
replayed session). Keeping each turn's tool calls brings it back to
10/10. Their results are replaced by a placeholder, which scores the
same and keeps the context close to what it was; a follow-up on an old
result calls the tool again. The window is now the last 10 whole turns.

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

1 files changed, 13 insertions, 5 deletions

diff --git a/assistant.py b/assistant.py
index 991dfa0..2a84cd6 100644
--- a/assistant.py
+++ b/assistant.py
@@ -548,15 +548,17 @@ def reply(history, q, mine):
     log(f"you ({lang}, {time.perf_counter() - t:.2f}s): {text}")
     emit({"type": "state", "state": "thinking"})
     question = {"role": "user", "content": text}
-    # ponytail: last 20 messages, summarise if long sessions need memory
     # The model has no clock: without the date it makes one up for tools.
     # Also stamped on the question itself, which history does not keep: with
     # the time only in the system prompt, "what time is it?" asked again an
     # hour later copied the old answer from history. Stamping every message
     # in history fixed that but lost tool arguments (account filter 0/6).
     now = time.strftime("%A %d %B %Y, %H:%M")
-    msgs = ([{"role": "system", "content": f"{CFG['system']} It is {now}."}] + history[-20:]
+    # ponytail: last 10 turns, summarise if long sessions need memory
+    msgs = ([{"role": "system", "content": f"{CFG['system']} It is {now}."}]
+            + [m for past in history[-10:] for m in past]
             + [{"role": "user", "content": f"[{now}] {text}"}])
+    first = len(msgs)                            # this turn's tool messages start here
     t, said, voice, announced = time.perf_counter(), [], lang, False
 
     def say(s):
@@ -607,9 +609,15 @@ def reply(history, q, mine):
         log("interrupted")
         return
     q.put((mine, None))
-    # Tool calls stay inside the turn: history keeps only what was said. A cut
-    # off exchange is dropped whole, so user and assistant still alternate.
-    history += [question, {"role": "assistant", "content": " ".join(said)}]
+    # History keeps the tool calls: with only what was said, the model saw
+    # facts answered without tools and invented the next ones (no tool call
+    # 9/10 on a replayed session, 0/10 with the calls kept). Results are
+    # replaced by a placeholder, for context: same 10/10, and a follow-up on
+    # an old result calls the tool again (10/10). A cut off exchange is
+    # dropped whole, so user and assistant still alternate.
+    past = [{**m, "content": "(shown to the user at the time)"} if m["role"] == "tool" else m
+            for m in msgs[first:]]
+    history.append([question] + past + [{"role": "assistant", "content": " ".join(said)}])
     log("assistant:", " ".join(said))