mirror of
https://github.com/NCBM/plyngent.git
synced 2026-11-07 23:47:54 +08:00
cli: notify the model when a session resumes after a restart
This commit is contained in:
@@ -167,7 +167,8 @@ async def _bind_session(
|
|||||||
) -> None:
|
) -> None:
|
||||||
if session_id is not None:
|
if session_id is not None:
|
||||||
try:
|
try:
|
||||||
await state.resume_session(session_id)
|
# Startup resume: this process did not run the session's last turn.
|
||||||
|
await state.resume_session(session_id, restarted=True)
|
||||||
except ValueError as exc:
|
except ValueError as exc:
|
||||||
raise click.ClickException(str(exc)) from exc
|
raise click.ClickException(str(exc)) from exc
|
||||||
if not quiet and not oneshot:
|
if not quiet and not oneshot:
|
||||||
@@ -184,7 +185,7 @@ async def _bind_session(
|
|||||||
err=True,
|
err=True,
|
||||||
)
|
)
|
||||||
return
|
return
|
||||||
mode = await state.resume_latest_or_new()
|
mode = await state.resume_latest_or_new(restarted=True)
|
||||||
if quiet:
|
if quiet:
|
||||||
return
|
return
|
||||||
if mode == "resume":
|
if mode == "resume":
|
||||||
@@ -324,6 +325,7 @@ async def _run_chat( # noqa: C901, PLR0912, PLR0915 — chat orchestration
|
|||||||
interactive_limits=interactive,
|
interactive_limits=interactive,
|
||||||
auto_continue_limits=auto_effective,
|
auto_continue_limits=auto_effective,
|
||||||
yolo=yolo,
|
yolo=yolo,
|
||||||
|
quiet=quiet,
|
||||||
mcp_manager=mcp_manager,
|
mcp_manager=mcp_manager,
|
||||||
)
|
)
|
||||||
# Path denylist and policy confirm live on instance.workspace (no process bag).
|
# Path denylist and policy confirm live on instance.workspace (no process bag).
|
||||||
|
|||||||
@@ -27,7 +27,7 @@ from plyngent.lmproto.openai_compatible.model import AssistantFunctionToolCall
|
|||||||
if TYPE_CHECKING:
|
if TYPE_CHECKING:
|
||||||
from collections.abc import AsyncIterator, Callable
|
from collections.abc import AsyncIterator, Callable
|
||||||
|
|
||||||
from plyngent.agent import AgentEvent
|
from plyngent.agent import AgentEvent, Notice
|
||||||
|
|
||||||
_TOOL_RESULT_PREVIEW = 120
|
_TOOL_RESULT_PREVIEW = 120
|
||||||
_TOOL_ARGS_PREVIEW = 80
|
_TOOL_ARGS_PREVIEW = 80
|
||||||
@@ -72,6 +72,12 @@ def markdown_render_available() -> bool:
|
|||||||
return interactive_terminal()
|
return interactive_terminal()
|
||||||
|
|
||||||
|
|
||||||
|
def echo_notice(notice: Notice, *, err: bool = False) -> None:
|
||||||
|
"""Show a host notice to the user; the model gets the full body."""
|
||||||
|
text = f"[notice] {notice.kind}: {notice.summary}" if notice.summary else f"[notice] {notice.kind}"
|
||||||
|
click.secho(text, fg="yellow", err=err)
|
||||||
|
|
||||||
|
|
||||||
def _preview(text: str, limit: int) -> str:
|
def _preview(text: str, limit: int) -> str:
|
||||||
if len(text) <= limit:
|
if len(text) <= limit:
|
||||||
return text
|
return text
|
||||||
|
|||||||
@@ -11,6 +11,8 @@ from plyngent.agent.loop import DEFAULT_MAX_ROUNDS
|
|||||||
from plyngent.agent.todo_stack import TodoStack
|
from plyngent.agent.todo_stack import TodoStack
|
||||||
|
|
||||||
if TYPE_CHECKING:
|
if TYPE_CHECKING:
|
||||||
|
from datetime import datetime
|
||||||
|
|
||||||
from plyngent.agent.types import AnyLLMClient
|
from plyngent.agent.types import AnyLLMClient
|
||||||
from plyngent.cli.models_source import (
|
from plyngent.cli.models_source import (
|
||||||
DEFAULT_MODELS_CACHE_TTL,
|
DEFAULT_MODELS_CACHE_TTL,
|
||||||
@@ -65,6 +67,8 @@ class ReplState:
|
|||||||
max_rounds: int = DEFAULT_MAX_ROUNDS
|
max_rounds: int = DEFAULT_MAX_ROUNDS
|
||||||
stream_enabled: bool = True
|
stream_enabled: bool = True
|
||||||
verbose: bool = False
|
verbose: bool = False
|
||||||
|
# Less status on stderr (--quiet); host notices are still pushed to the model.
|
||||||
|
quiet: bool = False
|
||||||
# End-of-turn Rich markdown for assistant text (TTY only).
|
# End-of-turn Rich markdown for assistant text (TTY only).
|
||||||
markdown_enabled: bool = True
|
markdown_enabled: bool = True
|
||||||
# One-shot / scripts: never prompt to raise tool-loop limits.
|
# One-shot / scripts: never prompt to raise tool-loop limits.
|
||||||
@@ -704,8 +708,12 @@ class ReplState:
|
|||||||
await self.new_session()
|
await self.new_session()
|
||||||
return was_current
|
return was_current
|
||||||
|
|
||||||
async def resume_session(self, session_id: int) -> None:
|
async def resume_session(self, session_id: int, *, restarted: bool = False) -> None:
|
||||||
"""Load a session; on workspace mismatch, prompt keep / rebind / abort."""
|
"""Load a session; on workspace mismatch, prompt keep / rebind / abort.
|
||||||
|
|
||||||
|
With *restarted* (a session resumed by a freshly started process) the
|
||||||
|
model gets a notice about the process-scoped state that a restart drops.
|
||||||
|
"""
|
||||||
from plyngent.cli.limits import prompt_workspace_mismatch
|
from plyngent.cli.limits import prompt_workspace_mismatch
|
||||||
|
|
||||||
self._reset_limit_auto_continue()
|
self._reset_limit_auto_continue()
|
||||||
@@ -743,9 +751,15 @@ class ReplState:
|
|||||||
await self.agent.load_history()
|
await self.agent.load_history()
|
||||||
await self.load_todo_stack()
|
await self.load_todo_stack()
|
||||||
await self.load_access_grants()
|
await self.load_access_grants()
|
||||||
|
if restarted:
|
||||||
|
await self._notice_restart(last_active=row.updated_at)
|
||||||
|
|
||||||
async def resume_latest_or_new(self, name: str = "chat") -> str:
|
async def resume_latest_or_new(self, name: str = "chat", *, restarted: bool = False) -> str:
|
||||||
"""Resume most recently updated session for this workspace, or create one."""
|
"""Resume most recently updated session for this workspace, or create one.
|
||||||
|
|
||||||
|
With *restarted* the resumed session gets the new-process notice; a
|
||||||
|
freshly created session has nothing to explain, so it gets none.
|
||||||
|
"""
|
||||||
self._reset_limit_auto_continue()
|
self._reset_limit_auto_continue()
|
||||||
latest = await self.memory.get_latest_session(workspace=self.workspace)
|
latest = await self.memory.get_latest_session(workspace=self.workspace)
|
||||||
if latest is None:
|
if latest is None:
|
||||||
@@ -760,9 +774,22 @@ class ReplState:
|
|||||||
await self.agent.load_history()
|
await self.agent.load_history()
|
||||||
await self.load_todo_stack()
|
await self.load_todo_stack()
|
||||||
await self.load_access_grants()
|
await self.load_access_grants()
|
||||||
|
if restarted:
|
||||||
|
# Before touch_session: the stamp should be the previous run's activity.
|
||||||
|
await self._notice_restart(last_active=latest.updated_at)
|
||||||
_ = await self.memory.touch_session(latest.sid)
|
_ = await self.memory.touch_session(latest.sid)
|
||||||
return "resume"
|
return "resume"
|
||||||
|
|
||||||
|
async def _notice_restart(self, *, last_active: datetime | None) -> None:
|
||||||
|
"""Tell the model — and the user — that this session outlived a restart."""
|
||||||
|
from plyngent.agent import resume_notice
|
||||||
|
from plyngent.cli.display import echo_notice
|
||||||
|
|
||||||
|
notice = resume_notice(last_active=last_active)
|
||||||
|
_ = await self.agent.push_notice(notice)
|
||||||
|
if not self.quiet:
|
||||||
|
echo_notice(notice, err=True)
|
||||||
|
|
||||||
async def compact_to_new_session(self, *, name: str | None = None) -> tuple[int, int, str]:
|
async def compact_to_new_session(self, *, name: str | None = None) -> tuple[int, int, str]:
|
||||||
"""Soft-compact + model-summarize current history into a new workspace session.
|
"""Soft-compact + model-summarize current history into a new workspace session.
|
||||||
|
|
||||||
|
|||||||
@@ -0,0 +1,152 @@
|
|||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
from typing import TYPE_CHECKING, Literal, overload
|
||||||
|
|
||||||
|
import pytest
|
||||||
|
import tomlkit
|
||||||
|
|
||||||
|
from plyngent.agent import ChatAgent
|
||||||
|
from plyngent.cli.app import _bind_session
|
||||||
|
from plyngent.cli.state import ReplState
|
||||||
|
from plyngent.config.models import DatabaseConfig, OpenAIProvider
|
||||||
|
from plyngent.config.store import ConfigStore
|
||||||
|
from plyngent.lmproto.openai_compatible.model import (
|
||||||
|
AssistantChatMessage,
|
||||||
|
ChatCompletionChunk,
|
||||||
|
ChatCompletionResponse,
|
||||||
|
ChatCompletionsParam,
|
||||||
|
DeveloperChatMessage,
|
||||||
|
UserChatMessage,
|
||||||
|
)
|
||||||
|
from plyngent.memory import MemoryStore
|
||||||
|
|
||||||
|
if TYPE_CHECKING:
|
||||||
|
from collections.abc import AsyncIterator
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
|
||||||
|
class DummyClient:
|
||||||
|
"""Client stub: these tests never run a model turn."""
|
||||||
|
|
||||||
|
@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]:
|
||||||
|
del param, stream
|
||||||
|
msg = "no model call expected"
|
||||||
|
raise AssertionError(msg)
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.fixture
|
||||||
|
async def state(tmp_path: Path) -> AsyncIterator[ReplState]:
|
||||||
|
memory = await MemoryStore.open(DatabaseConfig())
|
||||||
|
provider = OpenAIProvider(access_key_or_token="sk-test")
|
||||||
|
config = ConfigStore(path=tmp_path / "plyngent.toml", document=tomlkit.document())
|
||||||
|
config.providers = {"local": provider}
|
||||||
|
st = ReplState(
|
||||||
|
config=config,
|
||||||
|
memory=memory,
|
||||||
|
workspace=tmp_path,
|
||||||
|
provider_name="local",
|
||||||
|
provider=provider,
|
||||||
|
model="gpt-test",
|
||||||
|
tools_enabled=False,
|
||||||
|
)
|
||||||
|
st.client = DummyClient()
|
||||||
|
st.agent = ChatAgent(st.client, model=st.model, memory=st.memory, session_id=None)
|
||||||
|
yield st
|
||||||
|
await memory.close()
|
||||||
|
|
||||||
|
|
||||||
|
async def _seed_finished_turn(state: ReplState) -> int:
|
||||||
|
"""Start a session and give it one finished exchange; return its id."""
|
||||||
|
await state.new_session("t")
|
||||||
|
sid = state.session_id
|
||||||
|
assert sid is not None
|
||||||
|
_ = await state.memory.append_message(sid, UserChatMessage(content="hello"))
|
||||||
|
_ = await state.memory.append_message(sid, AssistantChatMessage(content="hi there"))
|
||||||
|
return sid
|
||||||
|
|
||||||
|
|
||||||
|
async def test_startup_resume_notifies_model_and_user(
|
||||||
|
state: ReplState,
|
||||||
|
capsys: pytest.CaptureFixture[str],
|
||||||
|
) -> None:
|
||||||
|
sid = await _seed_finished_turn(state)
|
||||||
|
|
||||||
|
await _bind_session(state, session_id=sid, new_session=False, oneshot=False, quiet=False)
|
||||||
|
|
||||||
|
rows = await state.memory.list_messages(sid)
|
||||||
|
tail = rows[-1]
|
||||||
|
assert isinstance(tail, DeveloperChatMessage)
|
||||||
|
assert tail.content.startswith("[plyngent notice: resume]")
|
||||||
|
assert "resumed in a new plyngent process" in tail.content
|
||||||
|
assert "grants were restored" in tail.content
|
||||||
|
# The live agent holds the same notice after loading history.
|
||||||
|
assert state.agent.messages[-1].content == tail.content
|
||||||
|
captured = capsys.readouterr()
|
||||||
|
assert "[notice] resume:" in captured.err
|
||||||
|
assert "resumed session" in captured.err
|
||||||
|
|
||||||
|
|
||||||
|
async def test_quiet_startup_resume_still_notifies_model(
|
||||||
|
state: ReplState,
|
||||||
|
capsys: pytest.CaptureFixture[str],
|
||||||
|
) -> None:
|
||||||
|
state.quiet = True
|
||||||
|
sid = await _seed_finished_turn(state)
|
||||||
|
|
||||||
|
await _bind_session(state, session_id=sid, new_session=False, oneshot=False, quiet=True)
|
||||||
|
|
||||||
|
rows = await state.memory.list_messages(sid)
|
||||||
|
assert isinstance(rows[-1], DeveloperChatMessage)
|
||||||
|
assert "[notice]" not in capsys.readouterr().err
|
||||||
|
|
||||||
|
|
||||||
|
async def test_mid_process_resume_has_no_restart_notice(
|
||||||
|
state: ReplState,
|
||||||
|
capsys: pytest.CaptureFixture[str],
|
||||||
|
) -> None:
|
||||||
|
"""``/resume`` in a live process loses nothing, so nothing is announced."""
|
||||||
|
sid = await _seed_finished_turn(state)
|
||||||
|
before = len(await state.memory.list_messages(sid))
|
||||||
|
|
||||||
|
await state.resume_session(sid)
|
||||||
|
|
||||||
|
assert len(await state.memory.list_messages(sid)) == before
|
||||||
|
assert "[notice]" not in capsys.readouterr().err
|
||||||
|
|
||||||
|
|
||||||
|
async def test_fresh_session_gets_no_restart_notice(state: ReplState) -> None:
|
||||||
|
mode = await state.resume_latest_or_new(restarted=True)
|
||||||
|
|
||||||
|
assert mode == "new"
|
||||||
|
sid = state.session_id
|
||||||
|
assert sid is not None
|
||||||
|
assert await state.memory.list_messages(sid) == []
|
||||||
|
|
||||||
|
|
||||||
|
async def test_latest_resume_stamps_previous_activity(
|
||||||
|
state: ReplState,
|
||||||
|
capsys: pytest.CaptureFixture[str],
|
||||||
|
) -> None:
|
||||||
|
sid = await _seed_finished_turn(state)
|
||||||
|
|
||||||
|
mode = await state.resume_latest_or_new(restarted=True)
|
||||||
|
|
||||||
|
assert mode == "resume"
|
||||||
|
rows = await state.memory.list_messages(sid)
|
||||||
|
tail = rows[-1]
|
||||||
|
assert isinstance(tail, DeveloperChatMessage)
|
||||||
|
# touch_session must not overwrite the stamp with the resume time.
|
||||||
|
assert "previous run's last activity: unknown" not in tail.content
|
||||||
|
assert "[notice] resume:" in capsys.readouterr().err
|
||||||
Reference in New Issue
Block a user