core/agent: keep executed tool results when a failed turn is rolled back

A tool batch counted as committed only once every call had its result, so a
batch cut short was dropped whole and the retry ran tools that had already
had effects. Keep the calls that did report a result: their assistant row
stays as the pairing carrier (a request must answer every tool_calls id),
without the text of the unfinished turn, and the calls without a result are
absent so the retry re-issues them instead of assuming they ran. The kept
rows go to the store right away, and a failed rollback write is not allowed
to mask the failure being rolled back.

tests/test_agent/test_loop.py

@@ -639,6 +639,77 @@ async def test_chat_agent_failed_turn_keeps_user_in_db() -> None:
     await store.close()
 
 
+async def test_rollback_keeps_executed_tool_result_in_store() -> None:
+    """Rolling back a cut-short batch keeps its executed result, in memory and on disk."""
+    store = await MemoryStore.open(DatabaseConfig())
+    session = await store.create_session(name="t")
+    ran: list[str] = []
+
+    @tool(register=False)
+    def first() -> str:
+        ran.append("first")
+        return "first ran"
+
+    client = ScriptedClient([_response(AssistantChatMessage(content="finished"))])
+    agent = ChatAgent(
+        client,
+        model="m",
+        tools=ToolRegistry([first]),
+        memory=store,
+        session_id=session.sid,
+        stream=False,
+    )
+    user = UserChatMessage(content="do both")
+    await store.append_message(session.sid, user)
+    agent.replace_messages(
+        [
+            user,
+            AssistantChatMessage(
+                content="running both",
+                tool_calls=[
+                    AssistantFunctionToolCall(
+                        id="call_1", function=AssistantFunctionTool(name="first", arguments="{}")
+                    ),
+                    AssistantFunctionToolCall(
+                        id="call_2", function=AssistantFunctionTool(name="other", arguments="{}")
+                    ),
+                ],
+            ),
+            ToolChatMessage(tool_call_id="call_1", content="first ran"),
+        ],
+        persist_from=1,
+    )
+
+    await agent._rollback_uncommitted(0)  # the failure path itself
+
+    kept = [message for message in agent.messages if isinstance(message, ToolChatMessage)]
+    assert [message.content for message in kept] == ["first ran"]
+    assert agent.pending_retry_text == "do both"
+    # What the model continues from is on disk too, or a restart re-runs it.
+    assert agent.persist_from == len(agent.messages)
+
+    stored = await store.list_messages(session.sid)
+    assert [type(message).__name__ for message in stored] == [
+        "UserChatMessage",
+        "AssistantChatMessage",
+        "ToolChatMessage",
+    ]
+    record = stored[1]
+    assert isinstance(record, AssistantChatMessage)
+    assert record.content is UNSET
+    calls = record.tool_calls
+    assert calls is not UNSET
+    assert [call.id for call in calls] == ["call_1"]
+
+    # The retry answers from the stored result instead of running the tool again.
+    events = [event async for event in agent.retry()]
+    assert ran == []
+    assert any(isinstance(event, TextDeltaEvent) and event.content == "finished" for event in events)
+    sent = client.calls[-1].messages
+    assert any(isinstance(message, ToolChatMessage) and message.content == "first ran" for message in sent)
+    await store.close()
+
+
 async def test_chat_agent_retry_after_failure() -> None:
     store = await MemoryStore.open(DatabaseConfig())
     session = await store.create_session(name="t")

tests/test_agent/test_rollback.py

@@ -0,0 +1,99 @@
+"""Rollback of a failed turn keeps the tool work that already ran.
+
+``committed_prefix_end`` commits a batch only once every call has its result, so
+``rollback_tail`` keeps the executed part of a batch that was cut short: the
+retry then continues from real results instead of running those tools again.
+"""
+
+from __future__ import annotations
+
+from msgspec import UNSET
+
+from plyngent.agent.chat import rollback_tail
+from plyngent.lmproto.openai_compatible.model import (
+    AnyChatMessage,
+    AssistantChatMessage,
+    AssistantFunctionTool,
+    AssistantFunctionToolCall,
+    DeveloperChatMessage,
+    ToolChatMessage,
+    UserChatMessage,
+)
+
+
+def _call(call_id: str, name: str = "some_tool") -> AssistantFunctionToolCall:
+    return AssistantFunctionToolCall(id=call_id, function=AssistantFunctionTool(name=name, arguments="{}"))
+
+
+def test_rollback_tail_keeps_the_executed_call_of_a_cut_short_batch() -> None:
+    messages: list[AnyChatMessage] = [
+        UserChatMessage(content="do both"),
+        AssistantChatMessage(content="first, then the other", tool_calls=[_call("call_a"), _call("call_b")]),
+        ToolChatMessage(tool_call_id="call_a", content="a ran"),
+    ]
+
+    tail = rollback_tail(messages, 1)
+
+    assert len(tail) == 2
+    record, result = tail
+    assert isinstance(record, AssistantChatMessage)
+    # The assistant row survives only as the carrier of the pairing.
+    assert record.content is UNSET
+    assert record.reasoning_content is UNSET
+    calls = record.tool_calls
+    assert calls is not UNSET
+    assert [call.id for call in calls] == ["call_a"]
+    assert isinstance(result, ToolChatMessage)
+    assert result.content == "a ran"
+
+
+def test_rollback_tail_drops_a_batch_that_reported_nothing() -> None:
+    messages: list[AnyChatMessage] = [
+        UserChatMessage(content="go"),
+        AssistantChatMessage(content="about to call", tool_calls=[_call("call_a")]),
+    ]
+
+    assert rollback_tail(messages, 1) == []
+
+
+def test_rollback_tail_drops_unfinished_text_and_keeps_developer_rows() -> None:
+    messages: list[AnyChatMessage] = [
+        UserChatMessage(content="go"),
+        AssistantChatMessage(content=UNSET, tool_calls=[_call("call_a")]),
+        ToolChatMessage(tool_call_id="call_a", content="a ran"),
+        DeveloperChatMessage(content="checkpoint"),
+        AssistantChatMessage(content="half-written answer"),
+    ]
+
+    tail = rollback_tail(messages, 1)
+
+    assert [type(message) for message in tail] == [AssistantChatMessage, ToolChatMessage, DeveloperChatMessage]
+
+
+def test_rollback_tail_pairs_a_repeated_call_id_once() -> None:
+    messages: list[AnyChatMessage] = [
+        UserChatMessage(content="go"),
+        AssistantChatMessage(content=UNSET, tool_calls=[_call("call_a"), _call("call_a")]),
+        ToolChatMessage(tool_call_id="call_a", content="only once"),
+    ]
+
+    tail = rollback_tail(messages, 1)
+
+    assert len(tail) == 2
+    record, result = tail
+    assert isinstance(record, AssistantChatMessage)
+    calls = record.tool_calls
+    assert calls is not UNSET
+    assert [call.id for call in calls] == ["call_a"]
+    assert isinstance(result, ToolChatMessage)
+    assert result.content == "only once"
+
+
+def test_rollback_tail_ignores_rows_before_start() -> None:
+    messages: list[AnyChatMessage] = [
+        UserChatMessage(content="go"),
+        AssistantChatMessage(content=UNSET, tool_calls=[_call("call_a")]),
+        ToolChatMessage(tool_call_id="call_a", content="a ran"),
+    ]
+
+    assert rollback_tail(messages, len(messages)) == []