core/agent: suppress end-of-turn todo nag on retry when turn-start pair survived

src/plyngent/agent/chat.py

@@ -437,6 +437,12 @@ class ChatAgent:
             # have survived rollback (it looks like a committed tool batch).
             # Skip fresh injection — refresh_synthetic_todo_nags already updated
             # the content of the surviving pair above.
+            _turn_nag_skipped = (
+                self.todo_stack is not None
+                and not self.todo_stack.is_empty()
+                and _turn_nag_strategy == "synthetic_tool"
+                and _synthetic_todo_pair_after(self.messages, user_index)
+            )
             if (
                 self.todo_stack is not None
                 and not self.todo_stack.is_empty()
@@ -467,6 +473,7 @@ class ChatAgent:
                 max_context_tokens=self.max_context_tokens,
                 todo_stack=self.todo_stack,
                 todo_nag_strategy=_turn_nag_strategy,
+                turn_start_nag_skipped=_turn_nag_skipped,
                 directive_reminder_tokens=self.directive_reminder_tokens,
                 directive_reminder_text=self.directive_reminder_text,
                 reminder_last_band=self.reminder_last_band,

src/plyngent/agent/loop.py

@@ -360,6 +360,7 @@ async def run_chat_loop(  # noqa: C901, PLR0912 — multi-phase tool loop
     max_context_tokens: int = DEFAULT_CONTEXT_MAX_TOKENS,
     todo_stack: TodoStack | None = None,
     todo_nag_strategy: TodoNagStrategy = DEFAULT_TODO_NAG_STRATEGY,
+    turn_start_nag_skipped: bool = False,
     directive_reminder_tokens: int = DEFAULT_DIRECTIVE_REMINDER_TOKENS,
     directive_reminder_text: str | None = None,
     reminder_last_band: int = 0,
@@ -453,6 +454,13 @@ async def run_chat_loop(  # noqa: C901, PLR0912 — multi-phase tool loop
             if not has_tools:
                 if todo_stack is not None and todo_stack.needs_review() and not todo_review_injected:
                     todo_review_injected = True
+                    # On retry, the turn-start nag was skipped (pair survived
+                    # rollback).  The model already has the stack reminder
+                    # in-history — skip the end-of-turn duplicate.
+                    if turn_start_nag_skipped:
+                        injected = False
+                        nag_events: list[AgentEvent] = []
+                    else:
                         injected, nag_events = inject_todo_nag_for_stack_with_events(
                             messages,
                             todo_stack,

tests/test_agent/test_retry_nag_integration.py

@@ -0,0 +1,267 @@
+"""Integration tests: full run→fail→retry flow, synthetic_tool nag detection.
+
+Uses mock clients to simulate model responses across retries, covering:
+- Turn-start nag skipped on retry (pair survived rollback)
+- End-of-turn nag NOT injected on retry (turn-start pair covers it)
+- No duplicate synthetic pairs accumulate in history
+"""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Literal, overload
+
+import pytest
+from msgspec import UNSET
+
+from plyngent.agent import ChatAgent
+from plyngent.agent.todo_nag import (
+    is_synthetic_todo_nag_call_id,
+)
+from plyngent.agent.todo_stack import TodoStack
+from plyngent.config.models import DatabaseConfig
+from plyngent.lmproto.openai_compatible.model import (
+    AnyChatMessage,
+    AssistantChatMessage,
+    AssistantFunctionToolCall,
+    ChatCompletionChoice,
+    ChatCompletionChunk,
+    ChatCompletionResponse,
+    ChatCompletionsParam,
+    ChunkChoice,
+    DeltaMessage,
+    ToolChatMessage,
+)
+from plyngent.memory import MemoryStore
+
+if TYPE_CHECKING:
+    from collections.abc import AsyncIterator
+
+
+def _response(message: AssistantChatMessage) -> ChatCompletionResponse:
+    return ChatCompletionResponse(
+        id="r",
+        object="chat.completion",
+        created=0,
+        model="m",
+        choices=[
+            ChatCompletionChoice(
+                index=0,
+                message=message,
+                logprobs={},
+                finish_reason="stop",
+            )
+        ],
+        system_fingerprint="",
+        usage={},
+    )
+
+
+def _chunks_from_text(text: str) -> list[ChatCompletionChunk]:
+    chunks: list[ChatCompletionChunk] = []
+    if text:
+        chunks.append(
+            ChatCompletionChunk(
+                id="c",
+                object="chat.completion.chunk",
+                created=0,
+                model="m",
+                choices=[
+                    ChunkChoice(
+                        index=0,
+                        delta=DeltaMessage(content=text),
+                        finish_reason=None,
+                    )
+                ],
+            )
+        )
+    chunks.append(
+        ChatCompletionChunk(
+            id="c",
+            object="chat.completion.chunk",
+            created=0,
+            model="m",
+            choices=[
+                ChunkChoice(
+                    index=0,
+                    delta=DeltaMessage(),
+                    finish_reason="stop",
+                )
+            ],
+        )
+    )
+    return chunks
+
+
+def count_synthetic_pairs(messages: list[AnyChatMessage]) -> int:
+    """Count complete synthetic todo nag pairs in messages."""
+    count = 0
+    for i, m in enumerate(messages):
+        if not isinstance(m, AssistantChatMessage):
+            continue
+        tc = m.tool_calls
+        if tc is UNSET or not tc:
+            continue
+        if not all(isinstance(c, AssistantFunctionToolCall) and is_synthetic_todo_nag_call_id(c.id) for c in tc):
+            continue
+        if i + 1 < len(messages) and isinstance(messages[i + 1], ToolChatMessage):
+            count += 1
+    return count
+
+
+class FailTwiceThenTextClient:
+    """First 2 stream calls fail; 3rd returns text (no tools)."""
+
+    def __init__(self) -> None:
+        self.stream_calls = 0
+        self.non_stream_calls = 0
+
+    @overload
+    async def chat_completions(
+        self, param: ChatCompletionsParam, *, stream: Literal[False] = False
+    ) -> ChatCompletionResponse: ...
+
+    @overload
+    async def chat_completions(
+        self, param: ChatCompletionsParam, *, stream: Literal[True]
+    ) -> AsyncIterator[ChatCompletionChunk]: ...
+
+    async def chat_completions(
+        self, param: ChatCompletionsParam, *, stream: bool = False
+    ) -> ChatCompletionResponse | AsyncIterator[ChatCompletionChunk]:
+        if stream:
+            self.stream_calls += 1
+            if self.stream_calls <= 2:
+                msg = f"stream fail #{self.stream_calls}"
+                raise RuntimeError(msg)
+            return self._stream_ok()
+        self.non_stream_calls += 1
+        return _response(AssistantChatMessage(content="ok"))
+
+    async def _stream_ok(self) -> AsyncIterator[ChatCompletionChunk]:
+        for chunk in _chunks_from_text("final answer"):
+            yield chunk
+
+    async def __aenter__(self):
+        return self
+
+    async def __aexit__(self, *exc: object) -> None:
+        return None
+
+
+@pytest.mark.asyncio
+async def test_retry_twice_no_extra_pairs() -> None:
+    """After two failed streams + one success, only 1 synthetic pair exists."""
+    store = await MemoryStore.open(DatabaseConfig())
+    session = await store.create_session(name="t")
+
+    stack = TodoStack()
+    _ = stack.push("task A")
+
+    client = FailTwiceThenTextClient()
+    agent = ChatAgent(
+        client,
+        model="m",
+        memory=store,
+        session_id=session.sid,
+        todo_stack=stack,
+        todo_nag_strategy="synthetic_tool",
+    )
+
+    # First run fails
+    with pytest.raises(RuntimeError, match="stream fail"):
+        async for _ in agent.run("hi"):
+            pass
+
+    assert count_synthetic_pairs(agent.messages) == 1, "1 pair after first run failure"
+
+    # First retry fails
+    with pytest.raises(RuntimeError, match="stream fail"):
+        async for _ in agent.retry():
+            pass
+
+    assert count_synthetic_pairs(agent.messages) == 1, "Still 1 pair after first retry failure — no duplicate injection"
+
+    # Second retry succeeds
+    async for _ in agent.retry():
+        pass
+
+    assert count_synthetic_pairs(agent.messages) == 1, "Still 1 pair after successful retry"
+
+    await store.close()
+
+
+@pytest.mark.asyncio
+async def test_retry_after_tool_round_completed() -> None:
+    """Tool calls executed + retry on next round produces no duplicate nag."""
+    store = await MemoryStore.open(DatabaseConfig())
+    session = await store.create_session(name="t")
+
+    stack = TodoStack()
+    _ = stack.push("task B")
+    registry = None  # no tools, so model always returns text
+
+    call_count = 0
+
+    class ToolThenStreamFailClient:
+        @overload
+        async def chat_completions(
+            self, param: ChatCompletionsParam, *, stream: Literal[False] = False
+        ) -> ChatCompletionResponse: ...
+
+        @overload
+        async def chat_completions(
+            self, param: ChatCompletionsParam, *, stream: Literal[True]
+        ) -> AsyncIterator[ChatCompletionChunk]: ...
+
+        async def chat_completions(
+            self, param: ChatCompletionsParam, *, stream: bool = False
+        ) -> ChatCompletionResponse | AsyncIterator[ChatCompletionChunk]:
+            nonlocal call_count
+            call_count += 1
+            if stream:
+                if call_count >= 3:
+                    return _stream_ok()
+                msg = f"stream fail #{call_count}"
+                raise RuntimeError(msg)
+            return _response(AssistantChatMessage(content="ok"))
+
+        async def __aenter__(self):
+            return self
+
+        async def __aexit__(self, *exc: object) -> None:
+            return None
+
+    async def _stream_ok() -> AsyncIterator[ChatCompletionChunk]:
+        for chunk in _chunks_from_text("done"):
+            yield chunk
+
+    client = ToolThenStreamFailClient()
+    agent = ChatAgent(
+        client,
+        model="m",
+        memory=store,
+        session_id=session.sid,
+        todo_stack=stack,
+        todo_nag_strategy="synthetic_tool",
+        tools=registry,
+    )
+
+    # First run fails
+    with pytest.raises(RuntimeError, match="stream fail"):
+        async for _ in agent.run("hi"):
+            pass
+
+    # Retry fails again
+    with pytest.raises(RuntimeError, match="stream fail"):
+        async for _ in agent.retry():
+            pass
+
+    assert count_synthetic_pairs(agent.messages) == 1, "Only 1 pair after 2 failures"
+
+    # Final retry succeeds
+    async for _ in agent.retry():
+        pass
+
+    assert count_synthetic_pairs(agent.messages) == 1, "1 pair after final success — no extra nag pair"
+
+    await store.close()