core/agent: derive pending_retry_text from trailing user message

Drop stored pending field; incomplete turns are just history ending in
UserChatMessage. Compact seeds use an assistant summary so they are not
mistaken for retryable orphans.
This commit is contained in:
2026-07-15 11:27:29 +08:00
parent 00a8ed3a9c
commit 6e9e034de4
7 changed files with 29 additions and 51 deletions
+19 -41
View File
@@ -43,7 +43,6 @@ class ChatAgent:
parallel_tools: bool
max_context_tokens: int
messages: list[AnyChatMessage]
pending_retry_text: str | None
session_usage: TokenUsage
last_turn_usage: TokenUsage
last_request_usage: TokenUsage
@@ -81,13 +80,22 @@ class ChatAgent:
self.parallel_tools = parallel_tools
self.max_context_tokens = max_context_tokens
self.messages = list(messages) if messages is not None else []
self.pending_retry_text = None
self.session_usage = TokenUsage()
self.last_turn_usage = TokenUsage()
self.last_request_usage = TokenUsage()
self.last_turn_rounds = 0
self._ensure_system_prompt()
self._sync_pending_from_orphan_user()
@property
def pending_retry_text(self) -> str | None:
"""Text of an incomplete last user turn, if any.
Derived only: history ending with a user message means that turn never
completed (failure, cancel, or resume of an orphan user in DB).
"""
if self.messages and isinstance(self.messages[-1], UserChatMessage):
return self.messages[-1].content
return None
@property
def context_tokens(self) -> int:
@@ -116,13 +124,6 @@ class ChatAgent:
return
self.messages.insert(0, SystemChatMessage(content=self.system_prompt))
def _sync_pending_from_orphan_user(self) -> None:
"""If history ends with a user message, that turn is incomplete → retryable."""
if self.messages and isinstance(self.messages[-1], UserChatMessage):
self.pending_retry_text = self.messages[-1].content
else:
self.pending_retry_text = None
async def load_history(self) -> None:
"""Replace in-memory messages from the bound memory session."""
if self.memory is None or self.session_id is None:
@@ -130,7 +131,6 @@ class ChatAgent:
raise RuntimeError(msg)
self.messages = await self.memory.list_messages(self.session_id)
self._ensure_system_prompt()
self._sync_pending_from_orphan_user()
async def bind_session(self, session_id: int, *, load: bool = True) -> None:
"""Attach a memory session id; optionally load existing messages."""
@@ -149,7 +149,6 @@ class ChatAgent:
for i in range(len(self.messages) - 1, -1, -1):
if self.messages[i] is user_msg:
return i
# Fallback: last matching content user message
for i in range(len(self.messages) - 1, -1, -1):
msg = self.messages[i]
if isinstance(msg, UserChatMessage) and msg.content == user_msg.content:
@@ -157,17 +156,16 @@ class ChatAgent:
msg = "user message not found in history"
raise RuntimeError(msg)
def _rollback_partial(self, user_index: int, user_text: str) -> None:
def _rollback_partial(self, user_index: int) -> None:
"""Drop assistant/tool messages after the user; keep user for retry/DB."""
del self.messages[user_index + 1 :]
self.pending_retry_text = user_text
async def _run_from_user_message(self, user_msg: UserChatMessage) -> AsyncIterator[AgentEvent]:
"""Run the tool loop for an already-appended user message.
On success, persists assistant/tool messages produced after the user.
On failure, keeps the user message (already in memory/DB) and sets
``pending_retry_text`` so ``retry()`` can re-run without duplicating it.
On failure, keeps the trailing user message so :meth:`retry` can re-run
without duplicating it (see :attr:`pending_retry_text`).
"""
user_index = self._user_index(user_msg)
@@ -190,7 +188,6 @@ class ChatAgent:
max_context_tokens=self.max_context_tokens,
):
if isinstance(event, UsageEvent):
# Each tool-loop round re-sends history; sum is billing, not context size.
turn_rounds += 1
last_request = event.usage
turn_usage = turn_usage.add(event.usage)
@@ -199,7 +196,7 @@ class ChatAgent:
completed = True
except BaseException:
if not completed:
self._rollback_partial(user_index, user_msg.content)
self._rollback_partial(user_index)
raise
self.last_turn_usage = turn_usage
@@ -207,7 +204,6 @@ class ChatAgent:
self.last_turn_rounds = turn_rounds
for message in self.messages[user_index + 1 :]:
await self._persist(message)
self.pending_retry_text = None
async def run(self, user_text: str) -> AsyncIterator[AgentEvent]:
"""Append a user message (persist immediately), run the tool loop, yield events."""
@@ -221,31 +217,13 @@ class ChatAgent:
async def retry(self) -> AsyncIterator[AgentEvent]:
"""Re-run the incomplete last user turn without appending a new user message.
Useful after a failed/cancelled turn (user already in memory/DB) or after
``load_history`` when the session ends with an orphan user message.
Requires history to end with a :class:`UserChatMessage` (failed/cancelled
turn or resumed orphan user in the session DB).
"""
text = self.pending_retry_text
if text is None:
self._sync_pending_from_orphan_user()
text = self.pending_retry_text
if text is None:
if not self.messages or not isinstance(self.messages[-1], UserChatMessage):
msg = "nothing to retry"
raise RuntimeError(msg)
user_msg = self.messages[-1]
self._ensure_system_prompt()
if self.messages and isinstance(self.messages[-1], UserChatMessage):
user_msg = self.messages[-1]
if user_msg.content != text:
# Pending text out of sync: replace trailing user
user_msg = UserChatMessage(content=text)
self.messages[-1] = user_msg
else:
user_msg = UserChatMessage(content=text)
self.messages.append(user_msg)
# Already persisted on the original run when memory is bound; only
# persist if this is a reconstructed orphan without DB (no memory).
if self.memory is None or self.session_id is None:
await self._persist(user_msg)
async for event in self._run_from_user_message(user_msg):
yield event