fix(session): remove message time replay prefixes

This commit is contained in:
chengyongru
2026-06-27 11:04:36 +08:00
committed by Xubin Ren
parent 8656549129
commit 9b45fc1172
6 changed files with 21 additions and 53 deletions
-2
View File
@@ -1183,7 +1183,6 @@ class AgentLoop:
_hist_kwargs: dict[str, Any] = {
"max_messages": self._max_messages,
"max_tokens": self._replay_token_budget(),
"include_timestamps": True,
"extend_to_user": is_subagent,
}
history = session.get_history(**_hist_kwargs)
@@ -1462,7 +1461,6 @@ class AgentLoop:
_hist_kwargs: dict[str, Any] = {
"max_messages": self._max_messages,
"max_tokens": self._replay_token_budget(),
"include_timestamps": True,
"extend_to_user": False,
}
ctx.history = ctx.session.get_history(**_hist_kwargs)
+2 -7
View File
@@ -712,17 +712,12 @@ class Consolidator:
@staticmethod
def _full_unconsolidated_history(
session: Session,
*,
include_timestamps: bool = False,
) -> list[dict[str, Any]]:
"""Return the whole unconsolidated tail for consolidation decisions."""
unconsolidated_count = len(session.messages) - session.last_consolidated
if unconsolidated_count <= 0:
return []
return session.get_history(
max_messages=unconsolidated_count,
include_timestamps=include_timestamps,
)
return session.get_history(max_messages=unconsolidated_count)
@staticmethod
def _replay_overflow_boundary(
@@ -797,7 +792,7 @@ class Consolidator:
session: Session,
) -> tuple[int, str]:
"""Estimate prompt size from the full unconsolidated session tail."""
history = self._full_unconsolidated_history(session, include_timestamps=True)
history = self._full_unconsolidated_history(session)
channel, chat_id = (session.key.split(":", 1) if ":" in session.key else (None, None))
# Include archived summary in estimation so the budget accounts for it.
meta = session.metadata.get("_last_summary")
-22
View File
@@ -118,25 +118,6 @@ class Session:
):
self.last_consolidated = 0
@staticmethod
def _annotate_message_time(message: dict[str, Any], content: Any) -> Any:
"""Expose persisted turn timestamps to the model for relative-date reasoning.
Annotating *every* assistant turn trains the model (via in-context
demonstrations) to start its own replies with the same
``[Message Time: ...]`` prefix, which leaks metadata back to the user.
We therefore only annotate user turns. User-side stamps are enough to
pin adjacent assistant replies for relative-time reasoning, including
proactive messages the user replies to later.
"""
timestamp = message.get("timestamp")
if not timestamp or not isinstance(content, str):
return content
role = message.get("role")
if role != "user":
return content
return f"[Message Time: {timestamp}]\n{content}"
def add_message(self, role: str, content: str, **kwargs: Any) -> None:
"""Add a message to the session."""
msg = {
@@ -153,7 +134,6 @@ class Session:
max_messages: int = 120,
*,
max_tokens: int = 0,
include_timestamps: bool = False,
extend_to_user: bool = False,
) -> list[dict[str, Any]]:
"""Return unconsolidated messages for LLM input.
@@ -243,8 +223,6 @@ class Session:
if mcp_lines:
breadcrumbs = "\n".join(mcp_lines)
content = f"{content}\n{breadcrumbs}" if content else breadcrumbs
if include_timestamps:
content = self._annotate_message_time(message, content)
if role == "assistant" and isinstance(content, str) and not content.strip():
if not any(key in message for key in ("tool_calls", "reasoning_content", "thinking_blocks")):
continue
+1 -1
View File
@@ -223,7 +223,7 @@ class TestAgentLoopTTLParam:
kwargs = session.get_history.call_args.kwargs
assert isinstance(kwargs.get("max_tokens"), int)
assert kwargs["max_tokens"] > 0
assert kwargs["include_timestamps"] is True
assert set(kwargs) == {"max_messages", "max_tokens", "extend_to_user"}
@pytest.mark.asyncio
async def test_session_file_cap_archives_and_trims_old_messages(self, tmp_path):
+3 -5
View File
@@ -1222,11 +1222,9 @@ async def test_system_subagent_followup_is_persisted_before_prompt_assembly(tmp_
non_system = [m for m in seen["initial_messages"] if m.get("role") != "system"]
assert "question" in non_system[0]["content"]
assert "working" in non_system[1]["content"]
# User turns carry the timestamp prefix so the model can reason about
# relative time. Assistant turns do NOT, otherwise the model treats those
# past replies as in-context examples and starts its own outputs with
# ``[Message Time: ...]`` (which then leaks back to the user).
assert "[Message Time:" in non_system[0]["content"]
# Persisted timestamps stay in session records, but replay content is not
# rewritten with volatile ``[Message Time: ...]`` prefixes.
assert "[Message Time:" not in non_system[0]["content"]
assert "[Message Time:" not in non_system[1]["content"]
assert non_system[2]["content"].count("subagent result") == 1
assert "Current Time:" in non_system[2]["content"]
+15 -16
View File
@@ -266,13 +266,8 @@ def test_get_history_preserves_reasoning_content():
]
def test_get_history_annotates_user_turns_but_not_assistant_turns():
"""Only user turns carry the timestamp prefix.
Annotating assistant turns trains the model (via in-context examples) to
start its own replies with ``[Message Time: ...]``. User-side stamps are
enough to pin adjacent assistant replies for relative-time reasoning.
"""
def test_get_history_does_not_inject_persisted_timestamps_into_replay_content():
"""Persisted timestamps are session metadata, not prompt content."""
session = Session(key="test:timestamps")
session.messages.append({
"role": "user",
@@ -285,12 +280,14 @@ def test_get_history_annotates_user_turns_but_not_assistant_turns():
"timestamp": "2026-04-26T22:00:05",
})
history = session.get_history(max_messages=500, include_timestamps=True)
history = session.get_history(max_messages=500)
assert session.messages[0]["timestamp"] == "2026-04-26T22:00:00"
assert session.messages[1]["timestamp"] == "2026-04-26T22:00:05"
assert history == [
{
"role": "user",
"content": "[Message Time: 2026-04-26T22:00:00]\n10 点提醒是昨天发生的",
"content": "10 点提醒是昨天发生的",
},
{
"role": "assistant",
@@ -299,8 +296,8 @@ def test_get_history_annotates_user_turns_but_not_assistant_turns():
]
def test_get_history_does_not_annotate_proactive_assistant_deliveries_with_timestamps():
"""Assistant-side timestamp examples can leak back into future replies."""
def test_get_history_keeps_proactive_delivery_timestamps_out_of_replay_content():
"""Timestamp metadata remains persisted without becoming prompt text."""
session = Session(key="test:proactive-timestamps")
session.messages.append({
"role": "assistant",
@@ -314,8 +311,10 @@ def test_get_history_does_not_annotate_proactive_assistant_deliveries_with_times
"timestamp": "2026-04-26T18:00:00",
})
history = session.get_history(max_messages=500, include_timestamps=True)
history = session.get_history(max_messages=500)
assert session.messages[0]["timestamp"] == "2026-04-26T15:00:00"
assert session.messages[1]["timestamp"] == "2026-04-26T18:00:00"
assert history == [
{
"role": "assistant",
@@ -323,18 +322,18 @@ def test_get_history_does_not_annotate_proactive_assistant_deliveries_with_times
},
{
"role": "user",
"content": "[Message Time: 2026-04-26T18:00:00]\n",
"content": "",
},
]
def test_get_history_does_not_annotate_tool_results_with_timestamps():
def test_get_history_does_not_inject_tool_result_timestamps():
session = Session(key="test:tool-timestamps")
session.messages.append({"role": "user", "content": "run tool"})
session.messages.extend(_tool_turn("ts", 0))
session.messages[-1]["timestamp"] = "2026-04-26T22:00:10"
history = session.get_history(max_messages=500, include_timestamps=True)
history = session.get_history(max_messages=500)
tool_result = history[-1]
assert tool_result["role"] == "tool"
@@ -555,7 +554,7 @@ def test_get_history_sanitizes_existing_assistant_replay_artifacts():
}
)
history = session.get_history(max_messages=500, include_timestamps=True)
history = session.get_history(max_messages=500)
assert history == [{"role": "assistant", "content": "来了 🎨"}]