merge: merge origin/gamma/refactor and origin/feature/teamhoa/r05-r06 into feature/delta-team/epic-R04
This commit is contained in:
+11
-1
@@ -1 +1,11 @@
|
||||
"""domain/ — Quy tắc nghiệp vụ thuần. KHÔNG import PySide6, không chạm đĩa/mạng."""
|
||||
"""Domain layer - pure Python entities, value objects and events.
|
||||
|
||||
The innermost layer of the 4-tier architecture (see
|
||||
``docs/architecture/ADR-001-layered-architecture.md``). Modules here describe
|
||||
WHAT the application is about - a turn of conversation, a model candidate, an
|
||||
agent event - and depend on nothing but the standard library.
|
||||
|
||||
Hard rule (ADR-001 I1/I2, enforced by ``scripts/check_imports.py``): no imports
|
||||
of PySide6/PyQt, and no imports from ``application/``, ``infrastructure/``,
|
||||
``presentation/`` or the legacy ``core/``/``ui/`` packages.
|
||||
"""
|
||||
|
||||
@@ -1 +1,51 @@
|
||||
"""Domain agents package: turn requests, agent events, and role definitions."""
|
||||
|
||||
from .agent_event import (
|
||||
NOTICE_INFO,
|
||||
NOTICE_PROGRESS,
|
||||
NOTICE_WARNING,
|
||||
AgentEvent,
|
||||
AssistantMessageCompletedEvent,
|
||||
ErrorEvent,
|
||||
HistoryReadyEvent,
|
||||
NoticeEvent,
|
||||
OutputsAddedEvent,
|
||||
OutputsRemovedEvent,
|
||||
PlanStep,
|
||||
PlanUpdatedEvent,
|
||||
ReasoningChunkEvent,
|
||||
TextChunkEvent,
|
||||
ToolCallFinishedEvent,
|
||||
ToolCallStartedEvent,
|
||||
ToolOutputChunkEvent,
|
||||
ToolPreview,
|
||||
TurnCompletedEvent,
|
||||
)
|
||||
from .conversation_execution_request import (
|
||||
PREFIX_SEPARATOR,
|
||||
ConversationExecutionRequest,
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
"NOTICE_INFO",
|
||||
"NOTICE_PROGRESS",
|
||||
"NOTICE_WARNING",
|
||||
"PREFIX_SEPARATOR",
|
||||
"AgentEvent",
|
||||
"AssistantMessageCompletedEvent",
|
||||
"ConversationExecutionRequest",
|
||||
"ErrorEvent",
|
||||
"HistoryReadyEvent",
|
||||
"NoticeEvent",
|
||||
"OutputsAddedEvent",
|
||||
"OutputsRemovedEvent",
|
||||
"PlanStep",
|
||||
"PlanUpdatedEvent",
|
||||
"ReasoningChunkEvent",
|
||||
"TextChunkEvent",
|
||||
"ToolCallFinishedEvent",
|
||||
"ToolCallStartedEvent",
|
||||
"ToolOutputChunkEvent",
|
||||
"ToolPreview",
|
||||
"TurnCompletedEvent",
|
||||
]
|
||||
|
||||
@@ -1 +1,13 @@
|
||||
"""Domain models package: provider descriptors, model pricing, and routing metadata."""
|
||||
|
||||
from .provider_descriptor import (
|
||||
AuthKind,
|
||||
ProviderDescriptor,
|
||||
WireProtocol,
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
"AuthKind",
|
||||
"ProviderDescriptor",
|
||||
"WireProtocol",
|
||||
]
|
||||
|
||||
@@ -1 +1,18 @@
|
||||
"""Domain tools package: tool descriptors, capability scopes, and registry interfaces."""
|
||||
"""Domain entities for tool risk classification and lookup (EPIC R05)."""
|
||||
|
||||
from .tool_descriptor import ToolCapability, ToolDescriptor
|
||||
from .tool_registry import (
|
||||
BUILT_IN_CAPABILITIES,
|
||||
UNKNOWN_SOURCE_CAPABILITIES,
|
||||
ToolRegistry,
|
||||
default_registry,
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
"ToolCapability",
|
||||
"ToolDescriptor",
|
||||
"ToolRegistry",
|
||||
"BUILT_IN_CAPABILITIES",
|
||||
"UNKNOWN_SOURCE_CAPABILITIES",
|
||||
"default_registry",
|
||||
]
|
||||
|
||||
@@ -0,0 +1,86 @@
|
||||
"""ToolCapability / ToolDescriptor - the risk-tagged catalogue entry for one
|
||||
tool the agent loop can call (R05-T01).
|
||||
|
||||
Today a tool is just a name inside ``core/tools.py::TOOL_SPECS`` (a
|
||||
``providers.base.ToolSpec`` — name/description/JSON-schema parameters, with
|
||||
no notion of risk) plus a hand-written membership test wherever gating is
|
||||
needed: ``core/tools.py::WRITE_TOOLS``, ``core/code_agent.py``'s
|
||||
``WRITE_TOOLS | MS365_WRITE_TOOLS``, and ``core/chat_agent.py``'s literal
|
||||
``name in ("run_command", "install_package")``. Three call sites, three
|
||||
independently-maintained lists, and a new tool (or an MCP/connector tool,
|
||||
which has no list membership at all - see ``core/mcp_client.py``) is gated
|
||||
only if someone remembers to add it everywhere.
|
||||
|
||||
``ToolDescriptor`` makes the risk an attribute of the tool itself, declared
|
||||
once, so ``application/conversations/tool_policy_gateway.py`` (R05-T03) can
|
||||
decide ALLOW/CONFIRM/DENY from data instead of a growing set of literal
|
||||
tuples.
|
||||
|
||||
Pure domain code: stdlib only, no Qt, no I/O. ``to_spec``/``from_spec`` are
|
||||
the only place this module touches something outside domain/, and that
|
||||
something (``providers.base.ToolSpec``) is itself a plain dataclass with no
|
||||
further dependencies.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass, field
|
||||
from enum import Flag, auto
|
||||
from typing import Any, Dict
|
||||
|
||||
from cowork_local.providers.base import ToolSpec
|
||||
|
||||
|
||||
class ToolCapability(Flag):
|
||||
"""What calling a tool can do to the machine or the network.
|
||||
|
||||
A ``Flag`` (not a plain ``Enum``) because a single tool can combine risks
|
||||
- ``install_package`` writes to the environment, runs pip as a
|
||||
subprocess, AND needs network access. Composing three separate booleans
|
||||
per call site is exactly the duplication this type replaces.
|
||||
"""
|
||||
|
||||
NONE = 0
|
||||
READ = auto()
|
||||
WRITE = auto()
|
||||
EXECUTE = auto()
|
||||
NETWORK = auto()
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ToolDescriptor:
|
||||
"""An immutable description of one callable tool.
|
||||
|
||||
Attributes:
|
||||
name: the identifier the model calls (``ToolSpec.name``).
|
||||
description: shown to the model, unchanged from ``ToolSpec``.
|
||||
parameters: JSON-Schema object for the call's arguments.
|
||||
capabilities: the risk this tool carries - see :class:`ToolCapability`.
|
||||
"""
|
||||
|
||||
name: str
|
||||
description: str
|
||||
parameters: Dict[str, Any] = field(default_factory=dict)
|
||||
capabilities: ToolCapability = ToolCapability.NONE
|
||||
|
||||
def has(self, capability: ToolCapability) -> bool:
|
||||
"""True when this tool carries (any bit of) ``capability``."""
|
||||
return bool(self.capabilities & capability)
|
||||
|
||||
def to_spec(self) -> ToolSpec:
|
||||
"""Project back to the ``ToolSpec`` shape the model-facing catalogue
|
||||
and the provider call actually use - risk tagging is metadata the
|
||||
wire format has no room for."""
|
||||
return ToolSpec(name=self.name, description=self.description,
|
||||
parameters=self.parameters)
|
||||
|
||||
@classmethod
|
||||
def from_spec(cls, spec: ToolSpec,
|
||||
capabilities: ToolCapability = ToolCapability.NONE) -> "ToolDescriptor":
|
||||
"""Wrap an existing ``ToolSpec`` (built-in, MCP, or connector) with a
|
||||
capability tag. The one place callers attach risk to a spec they did
|
||||
not author themselves."""
|
||||
return cls(name=spec.name, description=spec.description,
|
||||
parameters=spec.parameters, capabilities=capabilities)
|
||||
|
||||
|
||||
__all__ = ["ToolCapability", "ToolDescriptor"]
|
||||
@@ -0,0 +1,125 @@
|
||||
"""ToolRegistry - the centralised catalogue every tool source registers into
|
||||
(R05-T01).
|
||||
|
||||
Built-in file/command/fetch tools (``core/tools.py``), MCP server tools
|
||||
(``core/mcp_client.py``) and unified connectors (``core/ext_connectors.py``)
|
||||
each produce their own ``List[ToolSpec]`` today, concatenated ad-hoc by
|
||||
``core/tools.py::combine_tool_sources``. None of that concatenation carries
|
||||
risk information, which is exactly why an MCP tool call reaches
|
||||
``core/chat_agent.py`` with no ``ToolDescriptor`` to consult and skips the
|
||||
permission gate entirely (the gap R05-T04 closes).
|
||||
|
||||
``ToolRegistry`` is the one place a :class:`~domain.tools.tool_descriptor.ToolDescriptor`
|
||||
is looked up by name, so a policy gateway - or anything else that needs to ask
|
||||
"what can this tool do" - has a single source of truth instead of re-deriving
|
||||
it from a spec list.
|
||||
|
||||
Pure domain code: stdlib only, no Qt, no I/O.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Dict, Iterable, List, Optional
|
||||
|
||||
from cowork_local.providers.base import ToolSpec
|
||||
|
||||
from .tool_descriptor import ToolCapability, ToolDescriptor
|
||||
|
||||
|
||||
class ToolRegistry:
|
||||
"""An in-memory, name-keyed catalogue of :class:`ToolDescriptor`.
|
||||
|
||||
Deliberately mutable and unordered-by-name-only: a turn builds one
|
||||
registry from whichever tool sources it has (built-ins + whatever MCP
|
||||
servers/connectors are enabled), so re-registering the same name simply
|
||||
replaces the previous descriptor rather than raising - the same
|
||||
"last one wins" behaviour ``combine_tool_sources`` already has for
|
||||
duplicate tool names across sources.
|
||||
"""
|
||||
|
||||
def __init__(self, descriptors: Optional[Iterable[ToolDescriptor]] = None) -> None:
|
||||
self._by_name: Dict[str, ToolDescriptor] = {}
|
||||
for descriptor in descriptors or ():
|
||||
self.register(descriptor)
|
||||
|
||||
def register(self, descriptor: ToolDescriptor) -> None:
|
||||
self._by_name[descriptor.name] = descriptor
|
||||
|
||||
def get(self, name: str) -> Optional[ToolDescriptor]:
|
||||
return self._by_name.get(name)
|
||||
|
||||
def all(self) -> List[ToolDescriptor]:
|
||||
return list(self._by_name.values())
|
||||
|
||||
def specs(self) -> List[ToolSpec]:
|
||||
"""Every registered descriptor, projected back to ``ToolSpec`` - the
|
||||
shape the provider call and the model-facing catalogue need."""
|
||||
return [d.to_spec() for d in self._by_name.values()]
|
||||
|
||||
def capabilities_for(self, name: str) -> ToolCapability:
|
||||
"""The capability set for ``name``, or ``NONE`` for an unknown tool.
|
||||
|
||||
Returning ``NONE`` rather than raising lets a policy gateway treat an
|
||||
unregistered tool the same way as one with no declared risk - the
|
||||
gateway's DENY-on-unknown-name rule is a deliberate, separate check,
|
||||
not something this lookup should pre-empt.
|
||||
"""
|
||||
descriptor = self._by_name.get(name)
|
||||
return descriptor.capabilities if descriptor is not None else ToolCapability.NONE
|
||||
|
||||
def __contains__(self, name: str) -> bool:
|
||||
return name in self._by_name
|
||||
|
||||
def __len__(self) -> int:
|
||||
return len(self._by_name)
|
||||
|
||||
|
||||
# --------------------------------------------------------------------------- #
|
||||
# Default capability map for this app's built-in tools (core/tools.py).
|
||||
# Kept here, next to the registry, rather than inside core/tools.py itself -
|
||||
# core/ is the legacy engine layer being strangled, not where new domain facts
|
||||
# should accumulate.
|
||||
# --------------------------------------------------------------------------- #
|
||||
_CAP = ToolCapability
|
||||
BUILT_IN_CAPABILITIES: Dict[str, ToolCapability] = {
|
||||
"read_file": _CAP.READ,
|
||||
"list_dir": _CAP.READ,
|
||||
"write_file": _CAP.WRITE,
|
||||
"edit_file": _CAP.WRITE,
|
||||
"run_command": _CAP.EXECUTE,
|
||||
"install_package": _CAP.WRITE | _CAP.EXECUTE | _CAP.NETWORK,
|
||||
"fetch_url": _CAP.NETWORK,
|
||||
"jira_search": _CAP.NETWORK,
|
||||
"jira_get_issue": _CAP.NETWORK,
|
||||
# Advertised by every engine but has no filesystem/process/network effect
|
||||
# of its own - it only drives the Plan panel (see core/chat_agent.py).
|
||||
"update_plan": _CAP.NONE,
|
||||
"save_file": _CAP.WRITE,
|
||||
}
|
||||
|
||||
# Tools with no standard, self-declared risk metadata (every MCP server tool,
|
||||
# every unified connector) are tagged with this conservative default - see
|
||||
# R05-T04. Better to over-gate an unknown remote tool than to silently let it
|
||||
# through as READ-only.
|
||||
UNKNOWN_SOURCE_CAPABILITIES: ToolCapability = _CAP.WRITE | _CAP.EXECUTE | _CAP.NETWORK
|
||||
|
||||
|
||||
def default_registry(specs: Iterable[ToolSpec]) -> ToolRegistry:
|
||||
"""Build a registry from ``core/tools.py``'s own ``TOOL_SPECS`` (plus
|
||||
``save_file``/``update_plan``, which the engines add separately), using
|
||||
:data:`BUILT_IN_CAPABILITIES`. A spec with no entry in that map falls back
|
||||
to :data:`UNKNOWN_SOURCE_CAPABILITIES` - the same conservative default
|
||||
applied to MCP/connector tools, so a built-in nobody has classified yet
|
||||
fails safe instead of silently ungated."""
|
||||
registry = ToolRegistry()
|
||||
for spec in specs:
|
||||
capability = BUILT_IN_CAPABILITIES.get(spec.name, UNKNOWN_SOURCE_CAPABILITIES)
|
||||
registry.register(ToolDescriptor.from_spec(spec, capability))
|
||||
return registry
|
||||
|
||||
|
||||
__all__ = [
|
||||
"ToolRegistry",
|
||||
"BUILT_IN_CAPABILITIES",
|
||||
"UNKNOWN_SOURCE_CAPABILITIES",
|
||||
"default_registry",
|
||||
]
|
||||
@@ -1 +1,5 @@
|
||||
"""Domain workspaces package: immutable WorkspaceSession definitions."""
|
||||
"""Domain entities for workspace/project isolation (EPIC R06)."""
|
||||
|
||||
from .workspace_session import WorkspaceSession
|
||||
|
||||
__all__ = ["WorkspaceSession"]
|
||||
|
||||
@@ -0,0 +1,96 @@
|
||||
"""WorkspaceSession - an immutable snapshot of which project a turn belongs
|
||||
to and where it may touch the filesystem (R06-T01).
|
||||
|
||||
``state.py::AppContext.active_project_id`` is a single mutable field read by
|
||||
every background worker thread. ``ui/workspace_tab.py::_load_current`` writes
|
||||
it (and the related ``config._project_history_dir``) on the UI thread the
|
||||
moment the user switches projects - while a turn already running on a
|
||||
worker thread may read either field mid-switch and end up acting on the
|
||||
OTHER project's workspace/history for the rest of its run (the race
|
||||
R06-T04 fixes).
|
||||
|
||||
The fix, same shape as R04's ``ConversationExecutionRequest``: capture the
|
||||
workspace facts a turn needs ONCE, on the thread that knows which project is
|
||||
selected, into one frozen object. Whatever the user does to the UI afterwards,
|
||||
the turn keeps using the workspace it was handed at submit time.
|
||||
|
||||
Pure domain code: stdlib only, no Qt, no network. It does touch ``Path`` (not
|
||||
plain strings, unlike ``ConversationExecutionRequest``) because its whole job
|
||||
is path-containment checking - a snapshot with no room to answer "is this
|
||||
path mine" would not replace what ``ToolContext.resolve`` currently does
|
||||
inline.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass, field
|
||||
from pathlib import Path
|
||||
from typing import Tuple
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class WorkspaceSession:
|
||||
"""Everything a turn needs to know about ITS workspace, fixed at the
|
||||
moment it was submitted.
|
||||
|
||||
Attributes:
|
||||
project_id: the project this turn belongs to (``""`` when no project
|
||||
is selected - e.g. the Code tab, which has no project concept).
|
||||
workspace_root: the project's sandbox root (``Project.workspace_dir()``).
|
||||
sandbox_dir: the ``.scratch`` subtree inside ``workspace_root`` used for
|
||||
generator/helper scripts, never a final deliverable (see
|
||||
``infrastructure/filesystem/file_tools.py::_flatten_rel``).
|
||||
allowed_paths: every root a tool call may read/write under. Almost
|
||||
always just ``(workspace_root,)``; a project with a custom
|
||||
``output_dir`` outside the managed workspace tree still resolves
|
||||
to exactly one root - the tuple exists so a future caller (e.g. a
|
||||
step scoped to a shared input folder) can widen it without a
|
||||
shape change.
|
||||
"""
|
||||
|
||||
project_id: str
|
||||
workspace_root: Path
|
||||
sandbox_dir: Path
|
||||
allowed_paths: Tuple[Path, ...] = field(default_factory=tuple)
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
if not self.allowed_paths:
|
||||
object.__setattr__(self, "allowed_paths", (self.workspace_root,))
|
||||
|
||||
@classmethod
|
||||
def from_project(cls, project) -> "WorkspaceSession":
|
||||
"""Build a session from a ``core.projects.Project``. ``project`` is
|
||||
typed loosely (not imported) so this module has no dependency on
|
||||
``core/`` - the caller (``core/projects.py`` itself, or
|
||||
``application/conversations``) already has the Project in hand."""
|
||||
root = Path(project.workspace_dir())
|
||||
return cls(project_id=project.project_id, workspace_root=root,
|
||||
sandbox_dir=root / ".scratch", allowed_paths=(root,))
|
||||
|
||||
@classmethod
|
||||
def unscoped(cls, workspace_root: Path) -> "WorkspaceSession":
|
||||
"""A session for callers with no project concept (e.g. the Code tab,
|
||||
which sandboxes to a plain folder rather than a ``Project``)."""
|
||||
root = Path(workspace_root)
|
||||
return cls(project_id="", workspace_root=root, sandbox_dir=root / ".scratch")
|
||||
|
||||
def is_allowed(self, path: Path) -> bool:
|
||||
"""True when ``path`` resolves inside one of :attr:`allowed_paths`.
|
||||
|
||||
Same containment rule as ``ToolContext.resolve`` (an exact root match
|
||||
or a real descendant), but side-effect-free: it reports the answer
|
||||
instead of raising, so a caller (``FileWorkspaceService``, R06-T05)
|
||||
can decide what "not allowed" means for its own UI instead of
|
||||
catching a ``ToolError``.
|
||||
"""
|
||||
try:
|
||||
resolved = Path(path).expanduser().resolve()
|
||||
except OSError:
|
||||
return False
|
||||
for allowed in self.allowed_paths:
|
||||
root = Path(allowed).resolve()
|
||||
if resolved == root or root in resolved.parents:
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
__all__ = ["WorkspaceSession"]
|
||||
Reference in New Issue
Block a user