application/conversations/conversation_application_service.py

@@ -0,0 +1,322 @@
+"""The turn lifecycle, once, in pure Python (R04-T03).
+
+Extracted from ``core/chat_agent.py::run_cowork``, whose 260-line body mixed the
+lifecycle (compose the prompt, call the model, dispatch tools, respect the step
+ceiling, tidy the sandbox) with the concrete machinery that does each of those
+things. The lifecycle is the part with rules worth testing — and the part that
+was untestable, because reaching it meant standing up a Qt widget and a worker
+thread.
+
+Here it is a plain object driven through the seams in :mod:`turn_runtime`, so a
+test states a rule ("the guard runs before the model", "a rejected command never
+executes") in three lines. ``core/chat_agent.py`` keeps its signature and
+delegates, and the presentation layer keeps receiving the same events via the
+legacy codec, so nothing downstream had to change with it.
+
+Behavioural contract: this is a faithful port, not an improvement pass. Where
+the original had a quirk (the step-ceiling note only merges into the answer when
+the last message is the assistant's), the quirk is preserved and commented —
+changing what a user sees belongs in its own change, not smuggled into a move.
+"""
+
+from __future__ import annotations
+
+import logging
+from typing import Any, Dict, List, Optional, Tuple
+
+from ...domain.agents.agent_event import (
+    AssistantMessageCompletedEvent,
+    ErrorEvent,
+    OutputsAddedEvent,
+    OutputsRemovedEvent,
+    PlanStep,
+    PlanUpdatedEvent,
+    ReasoningChunkEvent,
+    TextChunkEvent,
+    ToolCallFinishedEvent,
+    ToolCallStartedEvent,
+    ToolOutputChunkEvent,
+)
+from ...domain.agents.agent_result import AgentResult
+from ...domain.agents.conversation_execution_request import ConversationExecutionRequest
+from .turn_runtime import (
+    BUDGET_NOTE_TEMPLATE,
+    GATED_TOOLS,
+    PLAN_TOOL,
+    REASONING_ONLY_NOTE,
+    REJECTED_OUTPUT,
+    AttachmentReader,
+    CancelFn,
+    CommandGuard,
+    ContextCompactor,
+    EventSink,
+    ModelCallPort,
+    PermissionRequest,
+    PromptGuard,
+    PromptPreparer,
+    ToolRuntimePort,
+)
+
+logger = logging.getLogger("cowork_local.application.conversations")
+
+
+class ConversationApplicationService:
+    """Runs one :class:`ConversationExecutionRequest` to completion."""
+
+    def __init__(
+        self,
+        model: ModelCallPort,
+        tools: ToolRuntimePort,
+        *,
+        prepare_prompt: Optional[PromptPreparer] = None,
+        prompt_guard: Optional[PromptGuard] = None,
+        command_guard: Optional[CommandGuard] = None,
+        compact: Optional[ContextCompactor] = None,
+        permission_request: Optional[PermissionRequest] = None,
+        attachment_reader: Optional[AttachmentReader] = None,
+    ) -> None:
+        self._model = model
+        self._tools = tools
+        # Every hook is optional so the service degrades to a plain chat turn.
+        # That is not only a test convenience: a headless caller legitimately has
+        # no guards (``security_config=None`` today) and no permission dialog.
+        self._prepare_prompt = prepare_prompt
+        self._prompt_guard = prompt_guard
+        self._command_guard = command_guard
+        self._compact = compact
+        self._permission_request = permission_request
+        self._attachment_reader = attachment_reader
+
+    # -- public API ------------------------------------------------------ #
+    def execute(self, request: ConversationExecutionRequest, sink: EventSink,
+                cancel: Optional[CancelFn] = None,
+                messages: Optional[List[Dict[str, Any]]] = None) -> AgentResult:
+        """Run the turn, streaming events to ``sink``, and report the outcome.
+
+        ``messages``, when given, is a working list the caller already built —
+        it MUST already end with this turn's user message, and the service
+        appends into that very object instead of composing its own. The Cowork
+        widget needs this: it hands out the same list to
+        ``_reattach_running_turn``, which replays the steps done so far while the
+        worker is still appending, and to ``_finalize_turn``, which slices it by
+        the pre-turn snapshot length. A private list would break both silently.
+        Passing ``None`` (every headless caller) lets the service compose the
+        list from the request, which is the mode the rest of this class assumes.
+
+        Raises whatever the runtime raises (a blocked prompt, a dead gateway):
+        the caller already has a failure path for that — ``AgentWorker.failed``
+        in the UI, the artifact writer in Schedule Task — and swallowing the
+        exception here would silently turn a failed turn into an empty answer.
+        An :class:`ErrorEvent` is emitted first so subscribers see the failure
+        on the same stream as everything else.
+        """
+        cancel = cancel or (lambda: False)
+
+        # -- pre-flight. Runs BEFORE the output snapshot, so a turn refused here
+        #    leaves the output folder completely untouched (tidying is not a
+        #    read-only operation — see ToolRuntimePort.finalize).
+        try:
+            # The caller's list is used by reference on purpose (see above); only
+            # the self-composed path may build a fresh one.
+            working = messages if messages is not None else self._compose_messages(request)
+            tools = list(self._tools.specs(request.allowed_tools))
+            if self._prepare_prompt is not None:
+                self._prepare_prompt(working, tuple(getattr(t, "name", "") for t in tools))
+            if request.enforce_rules and self._prompt_guard is not None:
+                self._prompt_guard(working)
+        except Exception as exc:  # noqa: BLE001 — reported, then re-raised as-is
+            sink(ErrorEvent(message=str(exc)))
+            raise
+
+        before = self._tools.snapshot()
+        steps_used = 0
+        plan_steps: Tuple[PlanStep, ...] = ()
+        completed_naturally = False
+        try:
+            for _ in range(request.effective_max_steps):
+                if cancel():
+                    break
+                # Auto-compress when nearing the model's context budget; a no-op
+                # when off or when the conversation is still short.
+                if self._compact is not None:
+                    self._compact(working, cancel)
+
+                assistant = self._model.call(
+                    working, tools,
+                    on_text=lambda piece: sink(TextChunkEvent(delta=piece)),
+                    on_reasoning=lambda piece: sink(ReasoningChunkEvent(delta=piece)),
+                    cancel=cancel,
+                )
+                working.append(assistant)
+                steps_used += 1
+                tool_calls = assistant.get("tool_calls") or []
+
+                if not tool_calls and not (assistant.get("content") or "").strip():
+                    # Written into the message, not just emitted, so the stored
+                    # conversation never ends on a blank assistant turn.
+                    assistant["content"] = REASONING_ONLY_NOTE
+                    sink(TextChunkEvent(delta=REASONING_ONLY_NOTE))
+                sink(AssistantMessageCompletedEvent(content=assistant.get("content", "")))
+
+                if not tool_calls:
+                    completed_naturally = True
+                    break
+
+                for call in tool_calls:
+                    if cancel():
+                        break
+                    tool_message, steps = self._dispatch(request, call, sink, cancel)
+                    working.append(tool_message)
+                    if steps is not None:
+                        plan_steps = steps
+
+            if not completed_naturally and not cancel():
+                self._announce_budget_exhausted(request, working, sink)
+        except Exception as exc:  # noqa: BLE001 — reported, then re-raised as-is
+            sink(ErrorEvent(message=str(exc)))
+            raise
+        finally:
+            # Always tidy: the sandbox and generator scripts must not survive a
+            # turn that stopped abruptly. Runs on success, cancel and failure.
+            self._finalize_outputs(before, sink, cancelled=cancel())
+
+        result = AgentResult(
+            messages=working, steps_used=steps_used, cancelled=cancel(),
+            budget_exhausted=not completed_naturally and not cancel(),
+            plan_steps=plan_steps,
+        )
+        sink(result.to_turn_completed_event())
+        return result
+
+    # -- internals ------------------------------------------------------- #
+    def _compose_messages(self, request: ConversationExecutionRequest) -> List[Dict[str, Any]]:
+        """History snapshot plus this turn's user message.
+
+        The attachment text is read HERE rather than when the request was built,
+        because extraction is slow enough to freeze the UI thread; the request
+        deliberately carries paths only.
+        """
+        body = request.prompt
+        if self._attachment_reader is not None:
+            body = self._attachment_reader(request.prompt, request.attachments)
+        messages = [dict(m) for m in request.messages]
+        messages.append({"role": "user", "content": request.user_content(body)})
+        return messages
+
+    def _dispatch(self, request: ConversationExecutionRequest, call: Dict[str, Any],
+                  sink: EventSink, cancel: CancelFn
+                  ) -> Tuple[Dict[str, Any], Optional[Tuple[PlanStep, ...]]]:
+        """Run one tool call.
+
+        Returns ``(tool_message, plan_steps)`` — the message to append to the
+        conversation, and the new checklist when this call was the plan tool
+        (``None`` otherwise, so the caller can tell "no change" from "empty
+        plan").
+        """
+        call_id = str(call.get("id", ""))
+        name = str(call.get("name", ""))
+        args = call.get("arguments") or {}
+
+        # The plan tool is invisible in the transcript: it updates the Plan panel
+        # and nothing else, so it skips preview, guard and gate entirely.
+        if name == PLAN_TOOL:
+            outcome = self._tools.execute(name, args, on_output=None, cancel=cancel)
+            steps = tuple(outcome.get("plan_steps") or ())
+            sink(PlanUpdatedEvent(steps=steps))
+            return self._tool_message(call_id, name, outcome.get("output", "")), steps
+
+        # Announce first: the user sees the code/command about to run before the
+        # guard or the approval dialog interrupts them, which is the whole point
+        # of showing the step CLI-style.
+        preview = self._tools.preview(name, args)
+        sink(ToolCallStartedEvent(call_id=call_id, name=name, arguments=dict(args),
+                                  preview=preview))
+
+        if request.enforce_rules and self._command_guard is not None:
+            self._command_guard(name, args)
+
+        if not self._approved(request, name, args, preview, sink, call_id):
+            return self._tool_message(call_id, name, REJECTED_OUTPUT), None
+
+        outcome = self._tools.execute(
+            name, args,
+            on_output=lambda piece: sink(ToolOutputChunkEvent(
+                call_id=call_id, name=name, delta=piece)),
+            cancel=cancel,
+        )
+        sink(ToolCallFinishedEvent(
+            call_id=call_id, name=name, ok=bool(outcome.get("ok", False)),
+            output=str(outcome.get("output", "")), path=str(outcome.get("path", "") or ""),
+            produced=outcome.get("produced") or (),
+        ))
+        return self._tool_message(call_id, name, outcome.get("output", "")), None
+
+    def _approved(self, request: ConversationExecutionRequest, name: str,
+                  args: Dict[str, Any], preview: Any, sink: EventSink,
+                  call_id: str) -> bool:
+        """Whether this call may run.
+
+        Only command-shaped tools are gated, and only when the workspace asked
+        to confirm them: file writes stay inside the turn's own sandbox, so
+        prompting for those would be noise. A rejection is reported as a failed
+        tool result — the model needs to read back that it was refused, or it
+        will simply try the same call again.
+        """
+        if not request.requires_permission_gate or name not in GATED_TOOLS:
+            return True
+        if self._permission_request is None:
+            # Confirm mode with nobody to ask: refusing is the safe direction,
+            # since auto-running is exactly what confirm mode exists to prevent.
+            logger.warning("turn: confirm mode without a permission callback — refusing %r", name)
+            approved = False
+        else:
+            approved = bool(self._permission_request({
+                "name": name, "args": args,
+                "preview": preview.to_dict() if preview is not None else {},
+            }))
+        if not approved:
+            sink(ToolCallFinishedEvent(call_id=call_id, name=name, ok=False,
+                                       output=REJECTED_OUTPUT))
+        return approved
+
+    @staticmethod
+    def _tool_message(call_id: str, name: str, output: Any) -> Dict[str, Any]:
+        """The canonical ``role: tool`` message the model reads back."""
+        return {"role": "tool", "tool_call_id": call_id, "name": name,
+                "content": str(output or "")}
+
+    @staticmethod
+    def _announce_budget_exhausted(request: ConversationExecutionRequest,
+                                   messages: List[Dict[str, Any]], sink: EventSink) -> None:
+        """Report being cut off by the step ceiling.
+
+        The note always reaches the transcript. It is merged into the stored
+        answer only when the last message is the assistant's — which, when the
+        ceiling is hit, it never is (the turn ends on a tool result). The branch
+        is kept because it is what the current runtime does, and because it is
+        the correct behaviour the day a caller ends the loop differently.
+        """
+        note = BUDGET_NOTE_TEMPLATE.format(steps=request.effective_max_steps)
+        sink(TextChunkEvent(delta=note))
+        if messages and messages[-1].get("role") == "assistant":
+            messages[-1]["content"] = (messages[-1].get("content") or "") + note
+
+    def _finalize_outputs(self, before: Any, sink: EventSink, cancelled: bool) -> None:
+        """Tidy the output folder and report what moved.
+
+        Failures are logged, never raised: this runs in a ``finally``, so an
+        exception here would replace the turn's real error (or its success) with
+        a housekeeping one.
+        """
+        try:
+            removed, added = self._tools.finalize(before, cancelled=cancelled)
+        except Exception:  # noqa: BLE001
+            logger.exception("turn: tidying the output folder failed")
+            return
+        if removed:
+            sink(OutputsRemovedEvent(paths=tuple(removed)))
+        if added:
+            sink(OutputsAddedEvent(paths=tuple(added)))
+
+
+__all__ = ["ConversationApplicationService"]

application/conversations/core_runtime_adapter.py

@@ -0,0 +1,325 @@
+"""Wires :class:`ConversationApplicationService` to the existing runtime (R04-T03).
+
+The service is written against the narrow seams in :mod:`turn_runtime` so it can
+be tested with plain fakes. This module supplies the real implementations — the
+provider call with its recovery pass, the tool/sandbox runtime, the security
+guards, context compaction — and is therefore the ONLY file in
+``application/conversations/`` that knows ``core/*`` exists. Same shape (and
+same reason) as ``application/model_routing/core_routing_adapter.py`` in R03.
+
+Every ``core`` import is deferred into a method body: importing the tool runtime
+pulls in ``requests``, ``psutil`` and the sandbox stack, and code that merely
+*builds* a service must not pay for that.
+
+Faithfulness notes — two places where this reproduces a quirk of the current
+runtime rather than the behaviour one would design fresh. Both are marked
+inline: the MS365 system-prompt paragraph keys off the CONFIGURED extra tools
+(not the advertised subset), and the ``tool_result`` path falls back to the
+call's own ``path`` argument resolved against the workdir.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any, Callable, Dict, List, Optional, Sequence, Tuple
+
+from ...domain.agents.agent_event import PlanStep, ToolPreview
+from .conversation_application_service import ConversationApplicationService
+from .turn_runtime import PLAN_TOOL, EventSink
+
+# Legacy emit: the dict-based callback every current caller already owns.
+LegacyEmit = Callable[[Dict[str, Any]], None]
+
+
+def legacy_event_sink(emit: LegacyEmit) -> EventSink:
+    """Adapt a typed :class:`EventSink` onto the legacy dict ``emit``.
+
+    This is what lets R04 land without touching the presentation layer: the
+    service thinks in typed events, ``ui/chat_panel.py::_on_event`` keeps
+    receiving exactly the dicts it already dispatches on. Deleted in R08 once
+    the widget consumes events directly.
+    """
+    return lambda event: emit(event.to_legacy_dict())
+
+
+class CoreModelCall:
+    """:class:`ModelCallPort` over ``code_agent._call_provider_with_recovery``.
+
+    Not ``provider.chat`` directly: the recovery wrapper adds the one bounded
+    retry that hides a dropped connection or a momentarily unreachable gateway,
+    and losing it would be a visible regression on flaky corporate networks.
+    """
+
+    def __init__(self, provider: Any) -> None:
+        self._provider = provider
+
+    def call(self, messages, tools, on_text=None, on_reasoning=None, cancel=None):
+        from ...core.code_agent import _call_provider_with_recovery
+
+        return _call_provider_with_recovery(self._provider, messages, tools, on_text,
+                                            cancel, on_reasoning)
+
+
+class CoreToolRuntime:
+    """:class:`ToolRuntimePort` over ``core/tools.py`` + Cowork's file tools."""
+
+    def __init__(self, output_dir: Path, *, title: str = "",
+                 extra_tools: Optional[Sequence[Any]] = None, extra_executor=None,
+                 security_config: Any = None, agent_role: str = "") -> None:
+        self._output_dir = Path(output_dir)
+        self._title = title
+        self._extra_tools = list(extra_tools or ())
+        self._extra_names = {getattr(t, "name", "") for t in self._extra_tools}
+        # The connector executor MCP/REST tools are routed to; None when the
+        # turn has no connectors enabled.
+        self._extra_executor = extra_executor
+        self._security_config = security_config
+        self._agent_role = agent_role
+        self._ctx: Any = None          # built on first use (see _tool_context)
+
+    # -- the configured extra tools, for the system-prompt hints ---------- #
+    @property
+    def extra_names(self) -> frozenset:
+        return frozenset(self._extra_names)
+
+    def _tool_context(self):
+        """The sandboxed ``ToolContext`` every built-in tool call runs inside.
+
+        Built once per turn and cached: it carries the resource limits and the
+        network policy, so re-deriving it mid-turn could let a Settings change
+        take effect halfway through work already in flight.
+        """
+        if self._ctx is None:
+            from ...core import agent_security
+            from ...core.tools import ToolContext
+
+            limits, block_network = agent_security.sandbox_settings(self._security_config)
+            self._ctx = ToolContext(
+                self._output_dir, flatten_writes=True,   # keep every file in the Output root
+                resource_limits=limits, block_network=block_network,
+                allow_url_fetch=agent_security.url_fetch_allowed(self._security_config),
+                jira=(self._security_config.data.get("jira") if self._security_config else None),
+            )
+        return self._ctx
+
+    # -- ToolRuntimePort -------------------------------------------------- #
+    def specs(self, allowed_tools: Optional[Sequence[str]] = None) -> List[Any]:
+        """Advertised tools: Cowork's own two, the enabled built-ins, then MCP.
+
+        ``allowed_tools`` restricts the list so a read-only step literally cannot
+        write. ``update_plan`` and the connector tools always survive the filter:
+        the plan tool has no side effects, and connectors are opted into
+        explicitly rather than governed by the built-in capability scope.
+        """
+        from ...core.chat_agent import SAVE_FILE_SPEC
+        from ...core.plan import UPDATE_PLAN_SPEC
+        from ...core.tools import enabled_tool_specs
+
+        specs = ([SAVE_FILE_SPEC, UPDATE_PLAN_SPEC]
+                 + list(enabled_tool_specs(self._security_config))
+                 + self._extra_tools)
+        if allowed_tools is None:
+            return specs
+        allow = set(allowed_tools) | {PLAN_TOOL} | self._extra_names
+        return [t for t in specs if getattr(t, "name", "") in allow]
+
+    def preview(self, name: str, args: Dict[str, Any]) -> Optional[ToolPreview]:
+        """What the user sees before the call runs."""
+        # A connector call has no local diff to show, so it renders as the plain
+        # argument dump the runtime already used.
+        if name in self._extra_names:
+            return ToolPreview(kind="info", title=name, text=str(args))
+        if name == "save_file":
+            return self._save_file_preview(args)
+        from ...core.tools import describe_action
+
+        raw = describe_action(self._tool_context(), name, args)
+        return ToolPreview.from_dict(raw)
+
+    def _save_file_preview(self, args: Dict[str, Any]) -> ToolPreview:
+        """A before/after diff for the file the agent is about to write.
+
+        A brand-new file renders all-green (before is empty); an overwrite shows
+        the real change, so saving a file reads like editing one.
+        """
+        import difflib
+
+        from ...core.chat_agent import _structure_summary, _titled_filename
+
+        fname = _titled_filename(self._title, args.get("filename", "output.txt"))
+        content = str(args.get("content", ""))
+        summary = _structure_summary(fname, content)
+        old = ""
+        existing = self._output_dir / fname
+        if existing.exists():
+            try:
+                old = existing.read_text(encoding="utf-8", errors="replace")
+            except OSError:
+                pass   # unreadable existing file: show it as a fresh write
+        diff = "".join(difflib.unified_diff(
+            old.splitlines(keepends=True), content.splitlines(keepends=True),
+            fromfile=f"a/{fname}", tofile=f"b/{fname}",
+        )) or content[:4000]
+        return ToolPreview(kind="diff", title=f"Save {fname}",
+                           text=f"{summary}\n\n{diff[:4000]}")
+
+    def execute(self, name: str, args: Dict[str, Any], on_output=None,
+                cancel=None) -> Dict[str, Any]:
+        """Run one tool call and return the runtime's result mapping."""
+        if name == PLAN_TOOL:
+            return self._execute_plan(args)
+        if name in self._extra_names and self._extra_executor is not None:
+            # Connector results carry no local file, so no path/produced keys —
+            # matching what the runtime reports for an MCP call today.
+            result = self._extra_executor(name, args) or {}
+            return {"ok": bool(result.get("ok", False)), "output": result.get("output", "")}
+        if name == "save_file":
+            from ...core.chat_agent import _do_save_file
+
+            return dict(_do_save_file(self._output_dir, self._title, args))
+
+        from ...core.tools import execute_tool
+
+        ctx = self._tool_context()
+        result = dict(execute_tool(ctx, name, args, cancel=cancel, on_output=on_output,
+                                   agent_role=self._agent_role))
+        # Quirk preserved: a tool that wrote the file named in its OWN arguments
+        # (write_file/edit_file) does not report a path, so the runtime derives
+        # one from the argument. Dropping this would empty the Output list.
+        if not result.get("path") and isinstance(args, dict) and args.get("path"):
+            result["path"] = str(ctx.workdir / str(args["path"]))
+        return result
+
+    def _execute_plan(self, args: Dict[str, Any]) -> Dict[str, Any]:
+        """Apply an ``update_plan`` call: validate the steps and audit them.
+
+        Produces no file and no chat bubble; the service turns the returned
+        steps into a single plan event.
+        """
+        from ...core import agent_roles, audit_log
+        from ...core.plan import normalize_plan_steps
+
+        steps = normalize_plan_steps(args.get("steps"))
+        audit_log.record("tool_call", PLAN_TOOL, True, f"{len(steps)} step(s)",
+                         agent_role=agent_roles.PLANNER)
+        return {"ok": True, "output": "Plan updated.",
+                "plan_steps": [PlanStep(title=s["title"], status=s["status"]) for s in steps]}
+
+    def snapshot(self) -> Any:
+        from ...core.tools import _snapshot
+
+        return _snapshot(self._output_dir)
+
+    def finalize(self, before: Any, cancelled: bool = False
+                 ) -> Tuple[List[str], List[str]]:
+        """Drop the scratch sandbox and flatten deliverables into the root.
+
+        Returns ``(gone, arrived)``: a file that MOVED counts as both, because
+        the Output list keys entries by path and must drop the old one.
+        """
+        from ...core.chat_agent import _cleanup_cowork_intermediates
+
+        removed, moved = _cleanup_cowork_intermediates(self._output_dir, before,
+                                                       cancelled=cancelled)
+        gone = list(removed) + [old for old, _new in moved]
+        arrived = [new for _old, new in moved]
+        return gone, arrived
+
+
+def build_cowork_conversation_service(
+    provider: Any,
+    output_dir: Path,
+    emit: LegacyEmit,
+    *,
+    title: str = "",
+    project_context: str = "",
+    extra_tools: Optional[Sequence[Any]] = None,
+    extra_executor=None,
+    security_config: Any = None,
+    gate: Any = None,
+    agent_role: str = "",
+) -> ConversationApplicationService:
+    """A service wired to the real runtime, ready to execute a Cowork turn.
+
+    ``emit`` is the legacy dict callback: the guards and the compactor publish
+    their own notices through it directly (exactly as they do now), while the
+    service's typed events reach it via :func:`legacy_event_sink`.
+
+    ``gate`` present means the workspace asked to confirm commands; pass the
+    request with ``gate_mode="confirm"`` so the two agree. A gate of ``None``
+    keeps the pre-existing auto-run behaviour.
+    """
+    from ...core import agent_roles
+
+    tools = CoreToolRuntime(
+        output_dir, title=title, extra_tools=extra_tools, extra_executor=extra_executor,
+        security_config=security_config, agent_role=agent_role or agent_roles.COWORK,
+    )
+
+    def prepare_prompt(messages: List[Dict[str, Any]], advertised: Tuple[str, ...]) -> None:
+        """Insert the system prompt, then fold in skills, rules and project text.
+
+        ``advertised`` is unused on purpose: the runtime decides the MS365
+        paragraph from the CONFIGURED connector tools, not from the subset a
+        capability scope left advertised. Changing that changes the prompt the
+        model sees, so it stays as-is here and belongs to R05's tool-policy work.
+        """
+        from ...core.chat_agent import (
+            COWORK_TOOL_PROMPT,
+            OPENDATALOADER_PDF_PROMPT,
+            _apply_project_context,
+            _apply_security_rules,
+            _apply_skills,
+        )
+        from ...core.deps import _can_pip
+        from ...core.java_runtime import find_java
+        from ...core.security_rules import load_rules
+        from ...core.skills import active_skills_text
+
+        if not messages or messages[0].get("role") != "system":
+            system = COWORK_TOOL_PROMPT
+            if any(n.startswith("ms365_") for n in tools.extra_names):
+                system += ("\nThe user has signed in to Microsoft 365 and enabled some ms365__* "
+                           "tools (Outlook / Teams / OneDrive / SharePoint / meeting transcripts, "
+                           "via the built-in MS365 MCP server). Use them whenever the request "
+                           "involves that data — don't say you can't access it.")
+            if find_java() is not None and _can_pip():
+                # Only advertise the Java-backed PDF extractor when BOTH the JVM
+                # and pip are available, so the agent is never steered into a
+                # command that cannot work on this machine.
+                system += "\n\n" + OPENDATALOADER_PDF_PROMPT
+            messages.insert(0, {"role": "system", "content": system})
+        _apply_skills(messages, active_skills_text())
+        _apply_security_rules(messages, load_rules())
+        _apply_project_context(messages, project_context)
+
+    def prompt_guard(messages: List[Dict[str, Any]]) -> None:
+        from ...core import agent_security
+
+        agent_security.enforce_prompt(provider, messages, security_config, emit)
+
+    def command_guard(name: str, args: Dict[str, Any]) -> None:
+        from ...core import agent_security
+
+        agent_security.enforce_command(provider, name, args, security_config, emit)
+
+    def compact(messages: List[Dict[str, Any]], cancel) -> None:
+        from ...core import context_budget
+
+        context_budget.maybe_compact(provider, messages, security_config,
+                                     emit=emit, cancel=cancel)
+
+    return ConversationApplicationService(
+        CoreModelCall(provider), tools,
+        prepare_prompt=prepare_prompt,
+        prompt_guard=prompt_guard,
+        command_guard=command_guard,
+        compact=compact,
+        permission_request=(gate.request if gate is not None else None),
+    )
+
+
+__all__ = [
+    "LegacyEmit", "legacy_event_sink", "CoreModelCall", "CoreToolRuntime",
+    "build_cowork_conversation_service",
+]

application/conversations/cowork_turn_request.py

@@ -0,0 +1,77 @@
+"""Turn the Cowork widget's captured state into a request (R04-T04).
+
+``ui/cowork_tab.py::build_job`` reads a dozen values off the widget on the UI
+thread and has to translate three of them before a turn can run: which message
+is this turn's prompt, which messages are its history, and whether the workspace
+wants commands confirmed. Those rules lived inline in the widget, where no test
+could reach them — and each fails silently when wrong (a duplicated user message,
+or a command that quietly stops asking for approval).
+
+They live here instead, as the mapping step the migration map assigns to the
+application layer. The widget keeps only what is genuinely widget-specific:
+reading its own state and building the provider.
+
+Layer rules (``docs/architecture/ADR-001-layered-architecture.md``): pure Python.
+Everything arrives as a plain value, so this module never sees a widget.
+"""
+
+from __future__ import annotations
+
+from typing import Any, Dict, Optional, Sequence
+
+from ...domain.agents.conversation_execution_request import ConversationExecutionRequest
+
+
+def build_cowork_turn_request(
+    *,
+    turn_id: str,
+    session_id: str,
+    messages: Sequence[Dict[str, Any]],
+    surface: str = "cowork",
+    project_id: str = "",
+    title: str = "",
+    provider_id: str = "",
+    model: str = "",
+    instructions: str = "",
+    output_dir: Optional[Any] = None,
+    home_output_root: Optional[Any] = None,
+    confirm_commands: bool = False,
+    agent_role: str = "cowork",
+) -> ConversationExecutionRequest:
+    """Build one Cowork turn's immutable request.
+
+    ``messages`` is the widget's working list, which ALREADY ends with this
+    turn's user message (the chat panel composes it — prefix, attachments,
+    session notes — before the job starts). So the prompt is that last message
+    and the history is everything before it. The request records both; the
+    service is handed the same working list and appends into it.
+
+    Keyword-only on purpose: a dozen positional strings in a call site is exactly
+    how a title ends up in the project-id slot.
+    """
+    history = list(messages or ())
+    # ``pop`` rather than ``[-1]``/``[:-1]`` so the empty-list case needs no
+    # special branch: a turn with nothing in it yields an empty prompt instead of
+    # raising IndexError deep inside a worker thread.
+    last = history.pop() if history else {}
+    return ConversationExecutionRequest(
+        turn_id=turn_id,
+        session_id=session_id,
+        surface=surface,
+        project_id=project_id,
+        title=title,
+        prompt=str(last.get("content") or ""),
+        messages=history,
+        provider_id=provider_id,
+        model=model,
+        project_context=instructions,
+        output_dir=output_dir,
+        home_output_root=home_output_root,
+        # The workspace's Auto-run override (or the global setting) decides
+        # whether run_command/install_package must be approved first.
+        gate_mode="confirm" if confirm_commands else "auto",
+        agent_role=agent_role,
+    )
+
+
+__all__ = ["build_cowork_turn_request"]

application/conversations/turn_runtime.py

@@ -0,0 +1,177 @@
+"""The seams :mod:`conversation_application_service` runs a turn through (R04-T03).
+
+Two Protocols and six callables — chosen deliberately, not by reflex. The
+refactor plan forbids giving every class an interface, so a contract exists here
+only where there is both a real ``core/*`` implementation AND a test double:
+
+* :class:`ModelCallPort` — one provider round-trip *including* the app's
+  existing context-overflow recovery, which is why the raw ``Provider.chat``
+  signature is not enough.
+* :class:`ToolRuntimePort` — the tool + output-folder runtime, kept as one
+  cohesive object because every method operates on the same sandbox.
+
+Everything else is a single function, so it is expressed as a callable type
+rather than a class with one method (the same choice R03 made for
+``ConfirmationCallback``). All of them are optional: a service built with none
+of them still runs a plain chat turn, which is what keeps the unit tests short.
+
+Layer rules (``docs/architecture/ADR-001-layered-architecture.md``): application
+layer — pure Python. Nothing here imports PySide6, ``core.*``, ``providers.*``
+or ``ui.*``; the concrete wiring lives in :mod:`core_runtime_adapter`.
+"""
+
+from __future__ import annotations
+
+from typing import (
+    Any,
+    Callable,
+    Dict,
+    List,
+    Optional,
+    Protocol,
+    Sequence,
+    Tuple,
+    runtime_checkable,
+)
+
+from ...domain.agents.agent_event import AgentEvent, ToolPreview
+
+# The plan tool is special-cased by the loop: it drives the Plan panel and
+# produces no chat bubble and no file. Named here so the check is not a bare
+# string literal in the middle of the dispatch.
+PLAN_TOOL = "update_plan"
+
+# Tools that need approval before they run when the workspace is in confirm
+# mode. R05 replaces this tuple with a real ``ToolPolicyGateway`` keyed on
+# ToolCapability; until then it mirrors exactly what the runtime gates today.
+GATED_TOOLS = ("run_command", "install_package")
+
+# Shown when the user (or the workspace policy) rejects a proposed command. The
+# exact string also becomes the tool message the model reads back, so it must
+# stay stable.
+REJECTED_OUTPUT = "Rejected by user."
+
+# A reasoning model can answer with thinking only. The note is written into the
+# assistant message itself, not merely emitted, so an unattended run does not
+# read back an empty answer and report "(no output)".
+REASONING_ONLY_NOTE = "*(model returned only its reasoning — try rephrasing)*"
+
+# Emitted when the turn is stopped by its own safety ceiling rather than by the
+# model finishing. Never silent: being cut off looks exactly like being done.
+BUDGET_NOTE_TEMPLATE = (
+    "\n\n⚠️ Reached the {steps}-step safety limit before the task signalled "
+    "completion — stopping here. Re-run to continue if more work remains."
+)
+
+
+def combine_instructions(*blocks: Optional[str]) -> str:
+    """Join the standing-instruction blocks of a turn, skipping the absent ones.
+
+    A turn's instructions arrive as several independent blocks — the project's
+    shared context, an Admin agent's persona, a skill's rules, the
+    "this runs unattended" reminder — and each caller was joining them inline
+    with its own ``f"{a}\\n\\n{b}" if a else b`` expression. Two call sites now
+    need the same rule (the Cowork widget in R04-T04 and the task runner in
+    R04-T05), which is the point at which it stops being an expression.
+
+    Whitespace-only blocks count as absent: they would otherwise open the system
+    prompt with a stray blank line.
+    """
+    return "\n\n".join(b.strip() for b in blocks if b and b.strip())
+
+
+# --------------------------------------------------------------------------- #
+# Callables.
+# --------------------------------------------------------------------------- #
+# Receives every typed event the turn produces. The caller decides what that
+# means — render it, forward it as a legacy dict, autosave on it.
+EventSink = Callable[[AgentEvent], None]
+
+# True once the user has asked to stop. Polled between steps and between tool
+# calls, the same cadence the current runtime uses.
+CancelFn = Callable[[], bool]
+
+# ``(prompt, attachment_paths) -> body``. Runs on the worker thread because
+# extracting a .docx may pip-install a parser or call LibreOffice.
+AttachmentReader = Callable[[str, Tuple[str, ...]], str]
+
+# ``(messages, advertised_tool_names) -> None`` — inserts the system prompt and
+# folds in skills, security rules and project instructions, in place. It needs
+# the tool names because the system prompt gains an MS365 paragraph only when
+# ms365 tools are actually present.
+PromptPreparer = Callable[[List[Dict[str, Any]], Tuple[str, ...]], None]
+
+# Reviews the assembled request; raises to refuse the turn outright.
+PromptGuard = Callable[[List[Dict[str, Any]]], None]
+
+# Reviews one proposed tool call; raises to refuse it.
+CommandGuard = Callable[[str, Dict[str, Any]], None]
+
+# ``(messages, cancel) -> None``. Summarises old turns in place when the
+# conversation nears the model's context budget; a no-op when compaction is off
+# or the conversation is short. It takes the cancel signal because compacting
+# calls the model itself, so Stop has to reach it too.
+ContextCompactor = Callable[[List[Dict[str, Any]], "CancelFn"], None]
+
+# ``(action) -> approved``. Blocks the worker thread while a human decides.
+PermissionRequest = Callable[[Dict[str, Any]], bool]
+
+
+# --------------------------------------------------------------------------- #
+# Ports.
+# --------------------------------------------------------------------------- #
+@runtime_checkable
+class ModelCallPort(Protocol):
+    """One call to the model, with the app's retry/recovery behaviour applied."""
+
+    def call(self, messages: List[Dict[str, Any]], tools: Sequence[Any],
+             on_text: Optional[Callable[[str], None]] = None,
+             on_reasoning: Optional[Callable[[str], None]] = None,
+             cancel: Optional[CancelFn] = None) -> Dict[str, Any]:
+        """Return the canonical assistant message (content plus tool calls)."""
+
+
+@runtime_checkable
+class ToolRuntimePort(Protocol):
+    """The tools a turn may call, and the folder its files land in."""
+
+    def specs(self, allowed_tools: Optional[Sequence[str]] = None) -> Sequence[Any]:
+        """Tool specs to advertise to the model, already filtered.
+
+        Returns opaque objects (the provider layer's ``ToolSpec``); the service
+        only ever reads ``.name`` off them, which is what keeps this layer free
+        of a provider import.
+        """
+
+    def preview(self, name: str, args: Dict[str, Any]) -> Optional[ToolPreview]:
+        """Human-readable description of a call that is about to run."""
+
+    def execute(self, name: str, args: Dict[str, Any],
+                on_output: Optional[Callable[[str], None]] = None,
+                cancel: Optional[CancelFn] = None) -> Dict[str, Any]:
+        """Run one tool call.
+
+        Returns the runtime's own result mapping: ``ok``, ``output``, optionally
+        ``path``/``produced`` for files it created, and ``plan_steps`` for the
+        plan tool.
+        """
+
+    def snapshot(self) -> Any:
+        """Opaque record of the output folder before the turn started."""
+
+    def finalize(self, before: Any, cancelled: bool = False
+                 ) -> Tuple[Sequence[str], Sequence[str]]:
+        """Tidy the output folder; return ``(removed_paths, added_paths)``.
+
+        Not read-only — it deletes the scratch sandbox and flattens sub-folders —
+        so the service only calls it for a turn that actually started.
+        """
+
+
+__all__ = [
+    "PLAN_TOOL", "GATED_TOOLS", "REJECTED_OUTPUT", "REASONING_ONLY_NOTE",
+    "BUDGET_NOTE_TEMPLATE", "combine_instructions",
+    "EventSink", "CancelFn", "AttachmentReader", "PromptPreparer", "PromptGuard",
+    "CommandGuard", "ContextCompactor", "PermissionRequest",
+    "ModelCallPort", "ToolRuntimePort",
+]

core/task_executors.py

@@ -2,7 +2,9 @@
 
 ``execute_task`` dispatches by ``task_type`` to the app's existing engines:
 
-- ``cowork``     → ``chat_agent.run_cowork``  (documents/answers, real files)
+- ``cowork``     → ``ConversationApplicationService`` (documents/answers, real
+                   files) — the same turn engine the interactive Cowork chat
+                   runs on since R04-T05
 - ``co4e_code``  → ``code_agent.run_code``    (code agent with file/command tools)
 - ``script``     → local subprocess with a timeout
 - ``flow``       → the task's own simple step list, run sequentially, each
@@ -162,6 +164,30 @@ _TIMEOUT_NOTICE_TMPL = (
 )
 
 
+_UNATTENDED_PREFIX = (
+    "This runs unattended (Schedule Task) — no one is watching live. Use "
+    "update_plan to track your steps and keep it accurate: mark a step "
+    "'error' (not silently skip it) if it genuinely can't be completed."
+)
+
+
+def _unattended_prompt(prompt: str, *, skill_text: str = "",
+                       agent_instructions: str = "") -> str:
+    """Assemble the user message an unattended run sends.
+
+    The order is load-bearing and used to be encoded as three successive
+    rebindings of ``prompt``, each prepending its own block: the plan reminder
+    must lead (it is the instruction that keeps a run without a human watching
+    honest), then the chosen skill's rules, then the Admin agent's persona, and
+    the task's own words last. Routing it through ``combine_instructions`` keeps
+    that order in one readable expression and drops the absent blocks instead of
+    leaving blank lines behind.
+    """
+    from ..application.conversations.turn_runtime import combine_instructions
+
+    return combine_instructions(_UNATTENDED_PREFIX, skill_text, agent_instructions, prompt)
+
+
 def _cancel_with_timeout(cancel: CancelFn, timeout_sec: Optional[int]) -> Tuple[CancelFn, Callable[[], bool]]:
     """Wrap ``cancel`` so it also fires once ``timeout_sec`` of wall-clock time
     elapses. ``timed_out()`` tells the caller whether THAT is why it stopped
@@ -218,36 +244,29 @@ def _run_agent(ctx, task_type: str, prompt: str, out_dir: Path,
     # default, see state.build_provider_for). A legacy Admin-agent preset
     # (task.admin_agent_id), if still set on an older task, keeps working and
     # takes precedence — it pins the provider/model AND prepends instructions.
+    agent_instructions = ""
     if admin_agent is not None:
         from .admin_agents import build_agent_provider
 
         provider = build_agent_provider(ctx, admin_agent)
         agent_instructions = admin_agent.effective_prompt()
-        if agent_instructions:
-            prompt = f"{agent_instructions}\n\n{prompt}"
     elif provider_name or model:
         # An explicit per-task provider/model override.
         provider = ctx.build_provider_for(provider_name or None, model or None)
     else:
         # Neither overridden → the machine's own Settings default, exactly as before.
         provider = ctx.build_active_provider()
-    # A chosen skill's instructions are prepended so this unattended run follows
+    # A chosen skill's instructions are applied so this unattended run follows
     # them, mirroring how the interactive chat applies /skill.
+    skill_text = ""
     if skill_slug:
         from .skills import skill_prefix_for
 
         skill_text = skill_prefix_for(skill_slug)
-        if skill_text:
-            prompt = f"{skill_text}\n\n{prompt}"
-    # This is an UNATTENDED run (no human watching to catch a half-finished
-    # job) — push the agent to actually use the Plan checklist so completion
-    # can be verified afterward, instead of just trusting "no exception".
-    prompt = (
-        "This runs unattended (Schedule Task) — no one is watching live. Use "
-        "update_plan to track your steps and keep it accurate: mark a step "
-        "'error' (not silently skip it) if it genuinely can't be completed.\n\n"
-        f"{prompt}"
-    )
+    # Assemble reminder + skill + persona + the task's own words in one place
+    # (see _unattended_prompt for why that order matters).
+    prompt = _unattended_prompt(prompt, skill_text=skill_text,
+                                agent_instructions=agent_instructions)
     messages = [{"role": "user", "content": prompt}]
     session_id = new_session_id()
     project_id = project.project_id if project is not None else ""
@@ -273,10 +292,41 @@ def _run_agent(ctx, task_type: str, prompt: str, out_dir: Path,
     watched_cancel, timed_out = _cancel_with_timeout(cancel, timeout_sec)
     try:
         if task_type == "cowork":
-            from .chat_agent import run_cowork
-            run_cowork(provider, messages, out_dir, emit_and_autosave, watched_cancel,
-                      security_config=ctx.config, agent_role=agent_roles.TASK,
-                      project_context=project_context)
+            # R04-T05: the unattended run shares the interactive turn engine
+            # instead of calling run_cowork itself, so there is exactly one place
+            # where a turn's lifecycle is defined. Everything unattended-specific
+            # stays here (the plan reminder above, the History autosave in
+            # emit_and_autosave, the timeout notice below).
+            from ..application.conversations.core_runtime_adapter import (
+                build_cowork_conversation_service,
+                legacy_event_sink,
+            )
+            from ..domain.agents.conversation_execution_request import (
+                ConversationExecutionRequest,
+            )
+
+            # No extra_tools/extra_executor and no permission gate: a scheduled
+            # run gets no MCP connectors and nobody is there to approve a
+            # command, which is exactly what run_cowork was called with.
+            service = build_cowork_conversation_service(
+                provider, out_dir, emit_and_autosave, title=title,
+                project_context=project_context, security_config=ctx.config,
+                agent_role=agent_roles.TASK,
+            )
+            request = ConversationExecutionRequest(
+                # The artifact folder is named by the run id, which identifies
+                # this attempt in the audit log.
+                turn_id=out_dir.name or session_id, session_id=session_id,
+                surface="task", title=title, project_id=project_id,
+                prompt=prompt, output_dir=out_dir,
+                agent_role=agent_roles.TASK, unattended=True,
+                timeout_sec=timeout_sec,
+            )
+            # ``messages`` is handed over so the History autosave in
+            # emit_and_autosave (and the final save in the finally block below)
+            # keep reading the live conversation as it grows.
+            service.execute(request, legacy_event_sink(emit_and_autosave),
+                            cancel=watched_cancel, messages=messages)
         else:
             from .code_agent import run_code
             limits, block_network = agent_security.sandbox_settings(ctx.config)

docs/refactor/Refactoring_Checklist.md

@@ -135,16 +135,22 @@
 * **Team chịu trách nhiệm**: 🔵 **Team Duy** (Chủ trì)
 * **Mục tiêu**: Đóng gói input turn chat thành `ConversationExecutionRequest` bất biến, điều phối vòng đời qua `ConversationApplicationService` và phát sinh sự kiện `AgentEvent` có định kiểu.
 
-- [ ] **R04-T01 (Team Duy)**: Định nghĩa immutable dataclass `ConversationExecutionRequest` ➔ `domain/agents/conversation_execution_request.py`  
-  *Start: `____-__-__ __:__` | End: `____-__-__ __:__`*
-- [ ] **R04-T02 (Team Duy)**: Chuẩn hóa các sự kiện `AgentEvent` (TextChunk, ToolCallStarted, ToolCallResult, Error) ➔ `domain/agents/agent_event.py`  
-  *Start: `____-__-__ __:__` | End: `____-__-__ __:__`*
-- [ ] **R04-T03 (Team Duy)**: Xây dựng `ConversationApplicationService` điều phối thực thi từ `core/chat_agent.py` ➔ `application/conversations/conversation_application_service.py`  
-  *Start: `____-__-__ __:__` | End: `____-__-__ __:__`*
-- [ ] **R04-T04 (Team Duy)**: Di chuyển `ui/cowork_tab.py::build_job` sang sử dụng `ConversationExecutionRequest`  
-  *Start: `____-__-__ __:__` | End: `____-__-__ __:__`*
-- [ ] **R04-T05 (Team Duy)**: Di chuyển `core/task_executors.py` sang dùng chung `ConversationApplicationService`  
-  *Start: `____-__-__ __:__` | End: `____-__-__ __:__`*
+- [x] **R04-T01 (Team Duy)**: Định nghĩa immutable dataclass `ConversationExecutionRequest` ➔ `domain/agents/conversation_execution_request.py`  
+  *Start: `2026-08-23 00:56` | End: `2026-08-23 01:00`*
+- [x] **R04-T02 (Team Duy)**: Chuẩn hóa các sự kiện `AgentEvent` (TextChunk, ToolCallStarted, ToolCallResult, Error) ➔ `domain/agents/agent_event.py` (+ `domain/agents/agent_event_codec.py` — shim dịch legacy dict, tách riêng để giữ LOC < 400 và để xoá gọn sau R08)  
+  *Start: `2026-08-23 01:00` | End: `2026-08-23 01:08`*
+- [x] **R04-T03 (Team Duy)**: Xây dựng `ConversationApplicationService` điều phối thực thi từ `core/chat_agent.py` ➔ `application/conversations/conversation_application_service.py` (+ `turn_runtime.py` định nghĩa 2 port/6 callable, `core_runtime_adapter.py` cầu nối sang `core/*`, `domain/agents/agent_result.py`)  
+  *Start: `2026-08-23 01:08` | End: `2026-08-23 07:10`*  
+  Chưa đổi call site nào — `run_cowork` giữ nguyên (Co4E vẫn dùng); việc chuyển call site là T04/T05. Bằng chứng tương đương: `tests/integration/test_conversation_service_parity.py` chạy cùng 1 script provider qua 2 đường và so khớp từng event/message/tool list trên 7 kịch bản.
+- [x] **R04-T04 (Team Duy)**: Di chuyển `ui/cowork_tab.py::build_job` sang sử dụng `ConversationExecutionRequest`  
+  *Start: `2026-08-23 07:10` | End: `2026-08-23 07:23`*  
+  `build_job` không còn gọi `run_cowork`: nó chụp state widget tại submit time ➔ `build_cowork_turn_request()` (mới, `application/conversations/cowork_turn_request.py`) ➔ `ConversationApplicationService`. Thêm `combine_instructions()` vào `turn_runtime.py` (project context + admin agent, T05 dùng lại) và tham số `messages=` cho `execute()` để service append vào **đúng list của widget** — `_reattach_running_turn` đọc list đó trong lúc turn đang chạy và `_finalize_turn` slice nó sau đó. Kiểm chứng: `tests/integration/test_cowork_tab_turn.py` gọi thẳng `CoworkTab.build_job` (widget stub, không cần Qt) và chạy turn thật với `FakeProvider`.  
+  ⚠️ `ui/cowork_tab.py` 416 ➔ 455 LOC — file này **vốn đã vượt 400 trước khi sửa**; phân rã thuộc EPIC R08.
+- [x] **R04-T05 (Team Duy)**: Di chuyển `core/task_executors.py` sang dùng chung `ConversationApplicationService`  
+  *Start: `2026-08-23 07:23` | End: `2026-08-23 07:31`*  
+  Nhánh `task_type == "cowork"` của `_run_agent` gọi service thay vì `run_cowork`; 5 hành vi riêng của unattended run giữ nguyên (plan reminder, `history_ready`, autosave History mỗi `assistant_done`, timeout notice, `plan_incomplete_reason`). Tách `_unattended_prompt()` dùng `combine_instructions` để thứ tự reminder → skill → persona → prompt nằm ở 1 chỗ đọc được. Lưới an toàn: `tests/integration/test_task_executor_turn.py` viết **trước** khi migrate và pass 8/8 trên code cũ, vẫn pass sau khi migrate.  
+  ⚠️ `core/task_executors.py` 476 ➔ 524 LOC — file này **vốn đã vượt 400 trước khi sửa**; phân rã thuộc EPIC R07 (`application/scheduling/`).  
+  Còn lại gọi `run_cowork`: `core/co4e_runner.py` (×2) và `ui/co4e_tab.py` — phân hệ Co4E của 🟣 Team Nam, R04 không chạm theo luật 1 file 1 team.
 
 ---
 

tests/fakes/turn_runtime_fakes.py

@@ -0,0 +1,141 @@
+"""Offline test doubles for the R04 turn runtime seams.
+
+Sits beside ``fake_provider.py``/``fake_tool_executor.py`` (R01-T02) and plays
+the same role one level up: those fake a *provider*, these fake the ports
+``ConversationApplicationService`` is driven through
+(``application/conversations/turn_runtime.py``).
+
+Deliberately dumb — they record what they were asked and return canned answers.
+A failing test then points at the service under test rather than at a mock
+framework's configuration.
+"""
+
+from __future__ import annotations
+
+from typing import Any, Dict, List, Optional, Tuple
+
+from cowork_local.domain.agents.agent_event import ToolPreview
+from cowork_local.domain.agents.conversation_execution_request import (
+    ConversationExecutionRequest,
+)
+
+
+class FakeSpec:
+    """An advertised tool. The service only ever reads ``.name`` off a spec."""
+
+    def __init__(self, name: str) -> None:
+        self.name = name
+
+
+class FakeReply:
+    """One programmed provider answer."""
+
+    def __init__(self, content: str = "", tool_calls=None, chunks=None, reasoning: str = ""):
+        self.content = content
+        self.tool_calls = tool_calls or []
+        # Default to streaming the whole content as a single chunk, which is what
+        # a non-streaming gateway effectively does.
+        self.chunks = chunks if chunks is not None else ([content] if content else [])
+        self.reasoning = reasoning
+
+
+class FakeModelCall:
+    """:class:`ModelCallPort` returning programmed replies in order.
+
+    A programmed entry may be an exception instead of a reply, which is how a
+    test simulates the gateway dying mid-turn.
+    """
+
+    def __init__(self, replies: List[Any]) -> None:
+        self.replies = list(replies)
+        self.calls: List[Dict[str, Any]] = []
+
+    def call(self, messages, tools, on_text=None, on_reasoning=None, cancel=None):
+        # Snapshot the messages: the service keeps mutating its own list, so
+        # storing it by reference would make every recorded call look identical.
+        self.calls.append({"messages": [dict(m) for m in messages],
+                           "tool_names": [getattr(t, "name", "") for t in tools]})
+        reply = self.replies.pop(0) if self.replies else FakeReply(content="(default)")
+        if isinstance(reply, BaseException):
+            raise reply
+        if reply.reasoning and on_reasoning:
+            on_reasoning(reply.reasoning)
+        for chunk in reply.chunks:
+            if on_text and chunk:
+                on_text(chunk)
+        assistant: Dict[str, Any] = {"role": "assistant", "content": reply.content}
+        if reply.tool_calls:
+            assistant["tool_calls"] = reply.tool_calls
+        return assistant
+
+
+class FakeToolRuntime:
+    """:class:`ToolRuntimePort` over an imaginary output folder."""
+
+    def __init__(self, specs=("save_file", "run_command", "update_plan"),
+                 results: Optional[Dict[str, Dict[str, Any]]] = None,
+                 removed: Tuple[str, ...] = (), added: Tuple[str, ...] = ()) -> None:
+        self._specs = [FakeSpec(n) for n in specs]
+        self._results = results or {}
+        self._removed, self._added = removed, added
+        self.executed: List[Tuple[str, Dict[str, Any]]] = []
+        self.finalize_calls: List[Dict[str, Any]] = []
+        # When set, every executed tool streams this string through ``on_output``.
+        self.emit_output: Optional[str] = None
+
+    def specs(self, allowed_tools=None):
+        if allowed_tools is None:
+            return list(self._specs)
+        return [s for s in self._specs if s.name in allowed_tools]
+
+    def preview(self, name, args):
+        return ToolPreview(kind="info", title=name, text=str(args))
+
+    def execute(self, name, args, on_output=None, cancel=None):
+        self.executed.append((name, dict(args)))
+        if self.emit_output and on_output:
+            on_output(self.emit_output)
+        return dict(self._results.get(name, {"ok": True, "output": f"{name} ok"}))
+
+    def snapshot(self):
+        return "before"
+
+    def finalize(self, before, cancelled=False):
+        self.finalize_calls.append({"before": before, "cancelled": cancelled})
+        return list(self._removed), list(self._added)
+
+
+# --------------------------------------------------------------------------- #
+# Small helpers shared by the turn tests.
+# --------------------------------------------------------------------------- #
+def make_request(**overrides) -> ConversationExecutionRequest:
+    """A minimal valid request; each test overrides only what it exercises."""
+    base: Dict[str, Any] = {"turn_id": "t1", "session_id": "s1", "prompt": "do it"}
+    base.update(overrides)
+    return ConversationExecutionRequest(**base)
+
+
+def run_turn(service, request=None, cancel=None):
+    """Execute a turn and return ``(result, events)``."""
+    events: List[Any] = []
+    result = service.execute(request or make_request(), events.append, cancel=cancel)
+    return result, events
+
+
+def events_of_type(events, cls):
+    """Every emitted event of one type, in order."""
+    return [e for e in events if isinstance(e, cls)]
+
+
+def tool_turn(tool_name: str = "save_file", args=None, **tool_kwargs):
+    """A turn that calls one tool and then answers — ``(model, tools)``."""
+    calls = [{"id": "c1", "name": tool_name, "arguments": args or {"filename": "a.md"}}]
+    model = FakeModelCall([FakeReply(content="working", tool_calls=calls),
+                           FakeReply(content="done")])
+    return model, FakeToolRuntime(**tool_kwargs)
+
+
+__all__ = [
+    "FakeSpec", "FakeReply", "FakeModelCall", "FakeToolRuntime",
+    "make_request", "run_turn", "events_of_type", "tool_turn",
+]

tests/integration/test_conversation_service_parity.py

@@ -0,0 +1,207 @@
+"""R04-T03 (c) — the service must behave exactly like ``run_cowork``.
+
+The unit tests prove the loop follows the rules I wrote down. They cannot prove
+those rules are the ones the shipped runtime actually follows. This file does:
+each test scripts one provider, runs the SAME turn twice — once through
+``core/chat_agent.py::run_cowork``, once through
+``ConversationApplicationService`` wired by ``core_runtime_adapter`` — and
+compares the emitted event stream, the resulting conversation and the tool list
+the model was shown.
+
+Anything the port got wrong (a missing event, a reordered guard, a different
+tool set, a changed message) fails here rather than in front of a user. The only
+allowed difference is the extra ``turn_completed`` event R04 introduces, which
+has no legacy consumer.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Tuple
+
+from cowork_local.application.conversations.core_runtime_adapter import (
+    build_cowork_conversation_service,
+    legacy_event_sink,
+)
+from cowork_local.core import chat_agent
+from cowork_local.domain.agents.conversation_execution_request import (
+    ConversationExecutionRequest,
+)
+from cowork_local.tests.fakes.fake_provider import FakeProvider
+
+_USER_TURN = [{"role": "user", "content": "make me a report"}]
+
+
+class _FakeGate:
+    """Stands in for ``core/permissions.py::PermissionGate``."""
+
+    def __init__(self, approve: bool) -> None:
+        self.approve = approve
+        self.requests: List[Dict[str, Any]] = []
+
+    def request(self, action: Dict[str, Any]) -> bool:
+        self.requests.append(action)
+        return self.approve
+
+
+def _normalise(events: List[Dict[str, Any]], out_dir: Path) -> List[Dict[str, Any]]:
+    """Replace the run's own output path with a placeholder.
+
+    The two runs write into different temp folders, so absolute paths in
+    ``tool_result``/``outputs_*`` events differ by construction. Everything else
+    must match verbatim.
+    """
+    marker, raw = "<OUT>", str(out_dir)
+
+    def scrub(value: Any) -> Any:
+        if isinstance(value, str):
+            return value.replace(raw, marker).replace(raw.replace("\\", "/"), marker)
+        if isinstance(value, list):
+            return [scrub(v) for v in value]
+        if isinstance(value, dict):
+            return {k: scrub(v) for k, v in value.items()}
+        return value
+
+    return [scrub(e) for e in events]
+
+
+def _run_legacy(tmp_path: Path, provider: FakeProvider, *, allowed_tools=None,
+                gate: Optional[_FakeGate] = None, max_steps: int = 30
+                ) -> Tuple[List[Dict[str, Any]], List[Dict[str, Any]], List[str]]:
+    """Run the turn through the existing ``run_cowork``."""
+    out_dir = tmp_path / "legacy"
+    out_dir.mkdir(parents=True, exist_ok=True)
+    events: List[Dict[str, Any]] = []
+    messages = [dict(m) for m in _USER_TURN]
+
+    chat_agent.run_cowork(
+        provider, messages, out_dir, events.append, title="Report",
+        security_config=None, allowed_tools=allowed_tools, gate=gate, max_steps=max_steps,
+    )
+    tool_names = [t.name for t in (provider.last_tools or [])]
+    return _normalise(events, out_dir), messages, tool_names
+
+
+def _run_service(tmp_path: Path, provider: FakeProvider, *, allowed_tools=None,
+                 gate: Optional[_FakeGate] = None, max_steps: int = 30
+                 ) -> Tuple[List[Dict[str, Any]], List[Dict[str, Any]], List[str]]:
+    """Run the same turn through the application service."""
+    out_dir = tmp_path / "service"
+    out_dir.mkdir(parents=True, exist_ok=True)
+    events: List[Dict[str, Any]] = []
+
+    service = build_cowork_conversation_service(
+        provider, out_dir, events.append, title="Report", security_config=None, gate=gate)
+    request = ConversationExecutionRequest(
+        turn_id="t1", session_id="s1",
+        # run_cowork receives the user message already appended; the request
+        # carries the history and this turn's prompt separately.
+        messages=_USER_TURN[:-1], prompt=_USER_TURN[-1]["content"],
+        output_dir=out_dir, allowed_tools=allowed_tools, max_steps=max_steps,
+        gate_mode="confirm" if gate is not None else "auto",
+    )
+    result = service.execute(request, legacy_event_sink(events.append))
+
+    # The end-of-turn event is new in R04 and has no legacy counterpart.
+    kept = [e for e in events if e.get("type") != "turn_completed"]
+    tool_names = [t.name for t in (provider.last_tools or [])]
+    return _normalise(kept, out_dir), list(result.messages), tool_names
+
+
+def _assert_parity(tmp_path: Path, script, *, approve: Optional[bool] = None, **kwargs) -> None:
+    """Script two identical providers, run both paths, compare everything."""
+    legacy_provider, service_provider = FakeProvider(), FakeProvider()
+    script(legacy_provider)
+    script(service_provider)
+
+    legacy_gate = _FakeGate(approve) if approve is not None else None
+    service_gate = _FakeGate(approve) if approve is not None else None
+
+    legacy_events, legacy_messages, legacy_tools = _run_legacy(
+        tmp_path, legacy_provider, gate=legacy_gate, **kwargs)
+    service_events, service_messages, service_tools = _run_service(
+        tmp_path, service_provider, gate=service_gate, **kwargs)
+
+    assert service_events == legacy_events
+    assert service_messages == legacy_messages
+    assert service_tools == legacy_tools
+    if legacy_gate is not None and service_gate is not None:
+        assert [r["name"] for r in service_gate.requests] == \
+               [r["name"] for r in legacy_gate.requests]
+
+
+# --------------------------------------------------------------------------- #
+# Scenarios.
+# --------------------------------------------------------------------------- #
+def test_a_plain_answer_turn_behaves_identically(tmp_path: Path) -> None:
+    def script(provider: FakeProvider) -> None:
+        provider.queue_response(content="Here you go.", chunks=["Here ", "you go."])
+
+    _assert_parity(tmp_path, script)
+
+
+def test_a_save_file_turn_behaves_identically(tmp_path: Path) -> None:
+    def script(provider: FakeProvider) -> None:
+        provider.queue_response(
+            content="Writing it.",
+            tool_calls=[{"id": "c1", "name": "save_file",
+                         "arguments": {"filename": "report.md", "content": "# Report\n"}}],
+        )
+        provider.queue_response(content="Saved.")
+
+    _assert_parity(tmp_path, script)
+
+
+def test_an_update_plan_turn_behaves_identically(tmp_path: Path) -> None:
+    def script(provider: FakeProvider) -> None:
+        provider.queue_response(
+            content="Planning.",
+            tool_calls=[{"id": "c1", "name": "update_plan",
+                         "arguments": {"steps": [{"title": "Draft", "status": "running"},
+                                                 {"title": "Ship", "status": "pending"}]}}],
+        )
+        provider.queue_response(content="Done.")
+
+    _assert_parity(tmp_path, script)
+
+
+def test_a_reasoning_only_reply_behaves_identically(tmp_path: Path) -> None:
+    def script(provider: FakeProvider) -> None:
+        provider.queue_response(content="", reasoning="thinking hard")
+
+    _assert_parity(tmp_path, script)
+
+
+def test_restricting_the_tool_scope_advertises_the_same_tools(tmp_path: Path) -> None:
+    def script(provider: FakeProvider) -> None:
+        provider.queue_response(content="ok")
+
+    _assert_parity(tmp_path, script, allowed_tools=["save_file"])
+
+
+def test_a_rejected_command_behaves_identically(tmp_path: Path) -> None:
+    # The security-critical path: the gate says no, so the command must never
+    # run and the model must read back the same refusal in both designs.
+    def script(provider: FakeProvider) -> None:
+        provider.queue_response(
+            content="Running it.",
+            tool_calls=[{"id": "c1", "name": "run_command",
+                         "arguments": {"command": "echo hi"}}],
+        )
+        provider.queue_response(content="Understood.")
+
+    _assert_parity(tmp_path, script, approve=False)
+
+
+def test_hitting_the_step_ceiling_behaves_identically(tmp_path: Path) -> None:
+    # The model never stops calling tools, so both paths must stop at the same
+    # place and say so the same way.
+    def script(provider: FakeProvider) -> None:
+        for i in range(4):
+            provider.queue_response(
+                content=f"step {i}",
+                tool_calls=[{"id": f"c{i}", "name": "save_file",
+                             "arguments": {"filename": f"f{i}.md", "content": "x"}}],
+            )
+
+    _assert_parity(tmp_path, script, max_steps=2)

tests/integration/test_cowork_tab_turn.py

@@ -0,0 +1,220 @@
+"""R04-T04 — the migrated Cowork call site, exercised end to end without Qt.
+
+``CoworkTab.build_job`` only ever *reads attributes* off its widget, so the real
+production method can be invoked against a stand-in that supplies those
+attributes. That is what happens here: the actual ``build_job`` body runs, builds
+a request, wires the service through ``core_runtime_adapter``, and drives a real
+turn (real tool execution, real output-folder cleanup) against ``FakeProvider``.
+
+Why it matters: this is the only automated check that the widget's contract with
+the service still holds — that the worker's list is appended to in place (the
+transcript re-render and history merge both read it), that events still arrive as
+legacy dicts, and that a produced file really lands in the turn's folder. None of
+it needs a display server, so it runs in CI like every other test.
+"""
+
+from __future__ import annotations
+
+import copy
+from pathlib import Path
+from typing import Any, Dict, List, Optional
+
+import pytest
+from cowork_local.config import DEFAULT_CONFIG, AppConfig
+from cowork_local.tests.fakes.fake_provider import FakeProvider
+
+
+class _FakeWorker:
+    """The parts of ``core/worker.py::AgentWorker`` a job actually touches."""
+
+    def __init__(self, approve_commands: bool = True) -> None:
+        self.events: List[Dict[str, Any]] = []
+        self.gate: Optional[Any] = None
+        self._approve = approve_commands
+        self.cancelled = False
+
+    def emit_event(self, event: Dict[str, Any]) -> None:
+        self.events.append(event)
+
+    def is_cancelled(self) -> bool:
+        return self.cancelled
+
+    def new_gate(self, mode: str, agent_role: str = "") -> Any:
+        # Mirrors AgentWorker.new_gate: the gate is stored on the worker so the
+        # UI thread can resolve it, and answers request() from the worker thread.
+        worker = self
+
+        class _Gate:
+            requests: List[Dict[str, Any]] = []
+
+            def request(self, action: Dict[str, Any]) -> bool:
+                self.requests.append(action)
+                return worker._approve
+
+        self.gate = _Gate()
+        return self.gate
+
+
+class _FakeCtx:
+    """The ``AppContext`` surface ``build_job`` uses."""
+
+    def __init__(self, config: AppConfig, confirm_commands: bool = False) -> None:
+        self.config = config
+        self._confirm = confirm_commands
+
+    def project_confirm_commands(self) -> bool:
+        return self._confirm
+
+    def build_mcp_tools(self):
+        return [], None
+
+
+class _WidgetStub:
+    """Stands in for the CoworkTab instance ``build_job`` reads its state from."""
+
+    kind = "cowork"
+
+    def __init__(self, out_root: Path, ctx: _FakeCtx, provider: FakeProvider) -> None:
+        self._out_root = out_root
+        self.ctx = ctx
+        self._provider = provider
+        self.title = "Report"
+        self.session_id = "s1"
+        self.project_id = ""          # the auto-seeded default workspace
+        self._model = ""
+        self._routed_provider = None
+        self._routed_model = None
+
+    def _session_output_dir(self) -> Path:
+        return self._out_root
+
+    def workspace_dir(self) -> Path:
+        return self._out_root
+
+    def admin_agent_prompt(self) -> str:
+        return ""
+
+    def build_provider(self) -> FakeProvider:
+        return self._provider
+
+
+def _config() -> AppConfig:
+    """A real AppConfig that never touches ``~/.cowork_local``.
+
+    The AI security guardrails are switched off: they would call the model to
+    review the prompt, which is a separate feature with its own tests and would
+    make this one depend on what the fake answers.
+    """
+    data = copy.deepcopy(DEFAULT_CONFIG)
+    data["agent_security"]["enabled"] = False
+    return AppConfig(data)
+
+
+def _run_turn(tmp_path: Path, provider: FakeProvider, messages: List[Dict[str, Any]],
+              *, confirm_commands: bool = False, approve: bool = True):
+    """Invoke the real ``CoworkTab.build_job`` against the stub and run its job."""
+    from cowork_local.ui.cowork_tab import CoworkTab
+
+    out_dir = tmp_path / ".turns" / "t1"
+    out_dir.mkdir(parents=True, exist_ok=True)
+    widget = _WidgetStub(tmp_path, _FakeCtx(_config(), confirm_commands), provider)
+    worker = _FakeWorker(approve_commands=approve)
+
+    job = CoworkTab.build_job(widget, "make me a report", messages, out_dir)
+    result = job(worker)
+    return result, worker
+
+
+def test_the_turn_runs_and_reports_its_folder(tmp_path: Path) -> None:
+    provider = FakeProvider()
+    provider.queue_response(content="Here you go.", chunks=["Here ", "you go."])
+    messages = [{"role": "user", "content": "make me a report"}]
+
+    result, worker = _run_turn(tmp_path, provider, messages)
+
+    assert result["turn_dir"] == str(tmp_path / ".turns" / "t1")
+    assert [e["type"] for e in worker.events] == [
+        "text", "text", "assistant_done", "turn_completed"]
+
+
+def test_the_worker_list_is_appended_to_in_place(tmp_path: Path) -> None:
+    # _reattach_running_turn replays from this very list while the turn runs, and
+    # _finalize_turn slices it by the pre-turn length afterwards.
+    provider = FakeProvider()
+    provider.queue_response(content="Done.")
+    user = {"role": "user", "content": "make me a report"}
+    messages = [user]
+
+    result, _ = _run_turn(tmp_path, provider, messages)
+
+    assert result["messages"] is messages
+    # Identity, not just equality: _reattach_running_turn locates the turn's user
+    # message with ``m is ctx["user_msg"]`` to replay the steps after it.
+    assert any(m is user for m in messages)
+    # Several system blocks are expected — the tool prompt plus the tagged
+    # skills/security-rules blocks the runtime refreshes on every turn.
+    assert [m["role"] for m in messages if m["role"] != "system"] == ["user", "assistant"]
+    assert messages[-1]["content"] == "Done."
+
+
+def test_a_saved_file_lands_in_the_turn_folder(tmp_path: Path) -> None:
+    provider = FakeProvider()
+    provider.queue_response(
+        content="Writing it.",
+        tool_calls=[{"id": "c1", "name": "save_file",
+                     "arguments": {"filename": "report.md", "content": "# Report\n"}}],
+    )
+    provider.queue_response(content="Saved.")
+    messages = [{"role": "user", "content": "make me a report"}]
+
+    _, worker = _run_turn(tmp_path, provider, messages)
+
+    produced = list((tmp_path / ".turns" / "t1").glob("*.md"))
+    assert len(produced) == 1
+    assert produced[0].read_text(encoding="utf-8") == "# Report\n"
+    results = [e for e in worker.events if e["type"] == "tool_result"]
+    assert results and results[0]["ok"] is True
+
+
+def test_auto_run_mode_never_creates_a_permission_gate(tmp_path: Path) -> None:
+    provider = FakeProvider()
+    provider.queue_response(content="ok")
+
+    _, worker = _run_turn(tmp_path, provider, [{"role": "user", "content": "hi"}],
+                          confirm_commands=False)
+
+    assert worker.gate is None
+
+
+def test_confirm_mode_creates_the_gate_and_a_refusal_stops_the_command(tmp_path: Path) -> None:
+    provider = FakeProvider()
+    provider.queue_response(
+        content="Running it.",
+        tool_calls=[{"id": "c1", "name": "run_command",
+                     "arguments": {"command": "echo hi"}}],
+    )
+    provider.queue_response(content="Understood.")
+
+    _, worker = _run_turn(tmp_path, provider, [{"role": "user", "content": "run it"}],
+                          confirm_commands=True, approve=False)
+
+    assert worker.gate is not None
+    refusals = [e for e in worker.events
+                if e["type"] == "tool_result" and e["output"] == "Rejected by user."]
+    assert len(refusals) == 1
+
+
+def test_cancelling_before_the_turn_starts_calls_no_model(tmp_path: Path) -> None:
+    from cowork_local.ui.cowork_tab import CoworkTab
+
+    provider = FakeProvider()
+    provider.queue_response(content="never")
+    out_dir = tmp_path / ".turns" / "t1"
+    out_dir.mkdir(parents=True)
+    widget = _WidgetStub(tmp_path, _FakeCtx(_config()), provider)
+    worker = _FakeWorker()
+    worker.cancelled = True
+
+    CoworkTab.build_job(widget, "x", [{"role": "user", "content": "x"}], out_dir)(worker)
+
+    assert provider.call_count == 0

tests/integration/test_task_executor_turn.py

@@ -0,0 +1,191 @@
+"""R04-T05 — the Schedule Task runner's cowork branch, pinned before and after.
+
+Written against the CURRENT ``_run_agent`` first, as the safety net for moving it
+onto ``ConversationApplicationService``: an unattended run has five behaviours the
+interactive path does not have (the plan reminder prefixed to the prompt, the
+session registered in History before the model starts, a re-save after every
+assistant message, the timeout notice, and the "did the agent's own checklist
+finish?" report), and none of them was covered by a test.
+
+Everything is isolated from the user's real config: history goes to ``tmp_path``
+via ``history.custom_dir`` and the AI guardrails are off, so no run touches
+``~/.cowork_local`` or calls a model to review a prompt.
+"""
+
+from __future__ import annotations
+
+import copy
+import json
+from pathlib import Path
+from typing import Any, Dict, List, Optional
+
+from cowork_local.config import DEFAULT_CONFIG, AppConfig
+from cowork_local.core import task_executors
+from cowork_local.tests.fakes.fake_provider import FakeProvider
+
+
+class _FakeCtx:
+    """The ``AppContext`` surface ``_run_agent`` touches."""
+
+    def __init__(self, config: AppConfig, provider: FakeProvider) -> None:
+        self.config = config
+        self._provider = provider
+
+    def build_active_provider(self) -> FakeProvider:
+        return self._provider
+
+    def build_provider_for(self, name=None, model=None) -> FakeProvider:
+        return self._provider
+
+
+def _config(tmp_path: Path) -> AppConfig:
+    data = copy.deepcopy(DEFAULT_CONFIG)
+    # Keep the run entirely offline and off the real config dir.
+    data["agent_security"]["enabled"] = False
+    data["history"]["custom_dir"] = str(tmp_path / "history")
+    return AppConfig(data)
+
+
+def _run(tmp_path: Path, provider: FakeProvider, *, prompt: str = "write the report",
+         timeout_sec: Optional[int] = None, admin_agent: Any = None):
+    """Run one cowork task and return ``(result_tuple, events, config)``."""
+    out_dir = tmp_path / "run"
+    out_dir.mkdir(parents=True, exist_ok=True)
+    config = _config(tmp_path)
+    events: List[Dict[str, Any]] = []
+
+    result = task_executors._run_agent(
+        _FakeCtx(config, provider), "cowork", prompt, out_dir,
+        events.append, lambda: False, title="Weekly report",
+        timeout_sec=timeout_sec, admin_agent=admin_agent,
+    )
+    return result, events, config
+
+
+def _saved_conversation(config: AppConfig) -> Dict[str, Any]:
+    """The single conversation the run wrote into the isolated history folder."""
+    files = list(Path(config.history_dir()).rglob("*.json"))
+    assert len(files) == 1, f"expected one saved conversation, found {files}"
+    return json.loads(files[0].read_text(encoding="utf-8"))
+
+
+# --------------------------------------------------------------------------- #
+def test_a_cowork_task_returns_the_final_answer(tmp_path: Path) -> None:
+    provider = FakeProvider()
+    provider.queue_response(content="Report is ready.")
+
+    (answer, timed_out, incomplete), _events, _config = _run(tmp_path, provider)
+
+    assert answer == "Report is ready."
+    assert timed_out is False
+    assert incomplete == ""
+
+
+def test_the_plan_reminder_is_prefixed_to_the_prompt(tmp_path: Path) -> None:
+    # An unattended run has nobody watching, so the agent is pushed to keep its
+    # own checklist honest. The reminder must lead the message.
+    provider = FakeProvider()
+    provider.queue_response(content="ok")
+
+    _run(tmp_path, provider, prompt="write the report")
+
+    sent = provider.call_history[0][-1]["content"]
+    assert sent.startswith("This runs unattended (Schedule Task)")
+    assert sent.endswith("write the report")
+
+
+def test_an_admin_agent_persona_sits_between_the_reminder_and_the_prompt(
+        tmp_path: Path) -> None:
+    class _Agent:
+        # An admin agent may pin its own provider/model; blank means "use the
+        # machine's Settings default", which is what build_agent_provider reads.
+        provider = ""
+        model = ""
+
+        def effective_prompt(self) -> str:
+            return "You are the reporting agent."
+
+    provider = FakeProvider()
+    provider.queue_response(content="ok")
+
+    _run(tmp_path, provider, prompt="write the report", admin_agent=_Agent())
+
+    sent = provider.call_history[0][-1]["content"]
+    assert sent.index("This runs unattended") < sent.index("You are the reporting agent.")
+    assert sent.index("You are the reporting agent.") < sent.index("write the report")
+
+
+def test_the_session_is_announced_once_it_exists_on_disk(tmp_path: Path) -> None:
+    # The scheduler refreshes History on this event, so it must not fire before
+    # the conversation is really there.
+    provider = FakeProvider()
+    provider.queue_response(content="ok")
+
+    _result, events, config = _run(tmp_path, provider)
+
+    ready = [e for e in events if e["type"] == "history_ready"]
+    assert len(ready) == 1
+    assert ready[0]["session_id"]
+    assert _saved_conversation(config)["session_id"] == ready[0]["session_id"]
+
+
+def test_the_saved_conversation_carries_the_answer_and_the_task_title(
+        tmp_path: Path) -> None:
+    provider = FakeProvider()
+    provider.queue_response(content="Report is ready.")
+
+    _result, _events, config = _run(tmp_path, provider)
+
+    saved = _saved_conversation(config)
+    assert saved["title"] == "[Task] Weekly report"
+    assert saved["messages"][-1] == {"role": "assistant", "content": "Report is ready."}
+
+
+def test_an_unfinished_checklist_is_reported_back_to_the_scheduler(
+        tmp_path: Path) -> None:
+    # The agent ticked no step to done, so the task must not be called finished
+    # just because no exception was raised.
+    provider = FakeProvider()
+    provider.queue_response(
+        content="Working on it.",
+        tool_calls=[{"id": "c1", "name": "update_plan",
+                     "arguments": {"steps": [{"title": "Draft", "status": "running"}]}}],
+    )
+    provider.queue_response(content="Stopping here.")
+
+    (_answer, _timed_out, incomplete), _events, _config = _run(tmp_path, provider)
+
+    assert incomplete
+    assert "Draft" in incomplete
+
+
+def test_a_finished_checklist_reports_nothing_outstanding(tmp_path: Path) -> None:
+    provider = FakeProvider()
+    provider.queue_response(
+        content="Done.",
+        tool_calls=[{"id": "c1", "name": "update_plan",
+                     "arguments": {"steps": [{"title": "Draft", "status": "done"}]}}],
+    )
+    provider.queue_response(content="All done.")
+
+    (_answer, _timed_out, incomplete), _events, _config = _run(tmp_path, provider)
+
+    assert incomplete == ""
+
+
+def test_running_out_of_time_appends_the_timeout_notice_to_the_conversation(
+        tmp_path: Path) -> None:
+    # A negative timeout puts the deadline in the past, which is the only
+    # deterministic way to exercise a wall-clock branch in a unit test.
+    provider = FakeProvider()
+    provider.queue_response(content="never gets there")
+
+    (answer, timed_out, incomplete), events, config = _run(
+        tmp_path, provider, timeout_sec=-1)
+
+    assert timed_out is True
+    assert incomplete == ""          # a timeout is not an unfinished checklist
+    assert "quá thời gian chờ" in answer
+    assert any(e["type"] == "assistant_done" and "quá thời gian chờ" in e["content"]
+               for e in events)
+    assert "quá thời gian chờ" in _saved_conversation(config)["messages"][-1]["content"]

tests/unit/test_conversation_application_service.py

@@ -0,0 +1,293 @@
+"""R04-T03 (b) — the turn loop: composition, tool dispatch, budget, cancel.
+
+Behaviour that used to be reachable only by running the real widget. Every
+dependency is a fake from ``tests/fakes/turn_runtime_fakes.py``, so the file
+runs in milliseconds and each test states one rule of the loop.
+"""
+
+from __future__ import annotations
+
+from typing import Any, Dict, List, Tuple
+
+from cowork_local.application.conversations.conversation_application_service import (
+    ConversationApplicationService,
+)
+from cowork_local.domain.agents.agent_event import (
+    AssistantMessageCompletedEvent,
+    PlanStep,
+    PlanUpdatedEvent,
+    TextChunkEvent,
+    ToolCallFinishedEvent,
+    ToolCallStartedEvent,
+    ToolOutputChunkEvent,
+    ToolPreview,
+    TurnCompletedEvent,
+)
+from cowork_local.tests.fakes.turn_runtime_fakes import (
+    FakeModelCall,
+    FakeReply,
+    FakeToolRuntime,
+    events_of_type,
+    make_request,
+    run_turn,
+    tool_turn,
+)
+
+
+def _service(model, tools, **overrides) -> ConversationApplicationService:
+    return ConversationApplicationService(model, tools, **overrides)
+
+
+# --------------------------------------------------------------------------- #
+# The happy path.
+# --------------------------------------------------------------------------- #
+def test_a_plain_answer_streams_text_then_reports_the_message_and_the_turn() -> None:
+    model = FakeModelCall([FakeReply(content="Hello there", chunks=["Hello ", "there"])])
+
+    result, events = run_turn(_service(model, FakeToolRuntime()))
+
+    assert [e.delta for e in events_of_type(events, TextChunkEvent)] == ["Hello ", "there"]
+    assert events_of_type(events, AssistantMessageCompletedEvent) == [
+        AssistantMessageCompletedEvent(content="Hello there")]
+    assert events_of_type(events, TurnCompletedEvent) == [
+        TurnCompletedEvent(final_text="Hello there", steps_used=1)]
+    assert result.final_text == "Hello there"
+    assert result.ok is True
+
+
+def test_the_composed_user_message_is_appended_before_the_first_call() -> None:
+    model = FakeModelCall([FakeReply(content="ok")])
+    request = make_request(prompt="ship it", instruction_prefix="RULES",
+                       session_notes="earlier: a.md",
+                       messages=[{"role": "user", "content": "previous"}])
+
+    run_turn(_service(model, FakeToolRuntime()), request)
+
+    sent = model.calls[0]["messages"]
+    assert sent[-1] == {"role": "user",
+                        "content": "RULES\n\n---\n\nship it\n\nearlier: a.md"}
+    assert sent[-2] == {"role": "user", "content": "previous"}
+
+
+def test_attachments_are_read_when_the_turn_runs_not_when_it_was_built() -> None:
+    # Extraction can pip-install a parser or shell out to LibreOffice, so it must
+    # happen here (worker thread), not while the UI was assembling the request.
+    seen: List[Tuple[str, Tuple[str, ...]]] = []
+
+    def reader(prompt: str, attachments: Tuple[str, ...]) -> str:
+        seen.append((prompt, attachments))
+        return f"{prompt}\n\n<contents of {len(attachments)} file(s)>"
+
+    model = FakeModelCall([FakeReply(content="ok")])
+    request = make_request(prompt="summarise", attachments=["a.docx", "b.pdf"])
+
+    run_turn(_service(model, FakeToolRuntime(), attachment_reader=reader), request)
+
+    assert seen == [("summarise", ("a.docx", "b.pdf"))]
+    assert "contents of 2 file(s)" in model.calls[0]["messages"][-1]["content"]
+
+
+def test_the_prompt_preparer_is_told_which_tools_the_turn_advertises() -> None:
+    # The system prompt gains an MS365 paragraph only when ms365__* tools are
+    # present, so the preparer has to see the real list.
+    seen: List[Tuple[str, ...]] = []
+    model = FakeModelCall([FakeReply(content="ok")])
+    tools = FakeToolRuntime(specs=("save_file", "ms365__send_mail"))
+
+    run_turn(_service(model, tools,
+                  prepare_prompt=lambda messages, names: seen.append(names)))
+
+    assert seen == [("save_file", "ms365__send_mail")]
+
+
+def test_only_the_allowed_tools_are_advertised() -> None:
+    model = FakeModelCall([FakeReply(content="ok")])
+    tools = FakeToolRuntime(specs=("save_file", "run_command", "update_plan"))
+
+    run_turn(_service(model, tools), make_request(allowed_tools=("save_file", "update_plan")))
+
+    assert model.calls[0]["tool_names"] == ["save_file", "update_plan"]
+
+
+# --------------------------------------------------------------------------- #
+# Tool dispatch.
+# --------------------------------------------------------------------------- #
+def tool_turn(tool_name: str = "save_file", args=None, **tool_kwargs):
+    """A turn that calls one tool, then answers."""
+    calls = [{"id": "c1", "name": tool_name, "arguments": args or {"filename": "a.md"}}]
+    model = FakeModelCall([FakeReply(content="working", tool_calls=calls),
+                        FakeReply(content="done")])
+    return model, FakeToolRuntime(**tool_kwargs)
+
+
+def test_a_tool_call_is_announced_executed_and_answered_in_the_message_list() -> None:
+    model, tools = tool_turn(results={"save_file": {"ok": True, "output": "saved",
+                                                     "path": "out/a.md"}})
+
+    result, events = run_turn(_service(model, tools))
+
+    assert events_of_type(events, ToolCallStartedEvent) == [ToolCallStartedEvent(
+        call_id="c1", name="save_file", arguments={"filename": "a.md"},
+        preview=ToolPreview(kind="info", title="save_file", text="{'filename': 'a.md'}"))]
+    assert events_of_type(events, ToolCallFinishedEvent) == [ToolCallFinishedEvent(
+        call_id="c1", name="save_file", ok=True, output="saved", path="out/a.md")]
+    assert tools.executed == [("save_file", {"filename": "a.md"})]
+    assert result.messages[-2] == {"role": "tool", "tool_call_id": "c1",
+                                   "name": "save_file", "content": "saved"}
+
+
+def test_live_tool_output_is_streamed_while_the_tool_runs() -> None:
+    model, tools = tool_turn("run_command", {"command": "ls"})
+    tools.emit_output = "file-a\n"
+
+    _, events = run_turn(_service(model, tools))
+
+    assert events_of_type(events, ToolOutputChunkEvent) == [ToolOutputChunkEvent(
+        call_id="c1", name="run_command", delta="file-a\n")]
+
+
+def test_the_loop_ends_as_soon_as_the_model_stops_calling_tools() -> None:
+    model, tools = tool_turn()
+
+    result, _ = run_turn(_service(model, tools))
+
+    assert result.steps_used == 2
+    assert result.budget_exhausted is False
+
+
+def test_the_plan_tool_reports_a_plan_update_and_no_tool_bubble() -> None:
+    calls = [{"id": "c1", "name": "update_plan",
+              "arguments": {"steps": [{"title": "Draft", "status": "running"}]}}]
+    model = FakeModelCall([FakeReply(content="planning", tool_calls=calls), FakeReply(content="done")])
+    tools = FakeToolRuntime(results={"update_plan": {
+        "ok": True, "output": "Plan updated.",
+        "plan_steps": [PlanStep(title="Draft", status="running")]}})
+
+    result, events = run_turn(_service(model, tools))
+
+    assert events_of_type(events, PlanUpdatedEvent) == [
+        PlanUpdatedEvent(steps=(PlanStep(title="Draft", status="running"),))]
+    assert events_of_type(events, ToolCallStartedEvent) == []
+    assert events_of_type(events, ToolCallFinishedEvent) == []
+    assert result.plan_steps == (PlanStep(title="Draft", status="running"),)
+
+
+# --------------------------------------------------------------------------- #
+# Budget, cancellation.
+# --------------------------------------------------------------------------- #
+def test_running_out_of_steps_is_flagged_and_announced() -> None:
+    # The model keeps calling tools forever; the ceiling must stop it visibly.
+    forever = [FakeReply(content=f"step {i}",
+                      tool_calls=[{"id": f"c{i}", "name": "save_file", "arguments": {}}])
+               for i in range(5)]
+    model = FakeModelCall(forever)
+
+    result, events = run_turn(_service(model, FakeToolRuntime()), make_request(max_steps=2))
+
+    assert result.steps_used == 2
+    assert result.budget_exhausted is True
+    assert "2-step safety limit" in events_of_type(events, TextChunkEvent)[-1].delta
+    # The note reaches the transcript but NOT the stored answer: a turn that hits
+    # the ceiling always ends on a tool message, and the existing runtime only
+    # merges the note when the last message is the assistant's. Pinned here so a
+    # future change to that rule is a deliberate decision, not a silent drift.
+    assert result.final_text == "step 1"
+
+
+def test_run_to_completion_uses_the_higher_ceiling() -> None:
+    forever = [FakeReply(content="x", tool_calls=[{"id": "c", "name": "save_file", "arguments": {}}])
+               for _ in range(6)]
+    model = FakeModelCall(forever)
+
+    result, _ = run_turn(_service(model, FakeToolRuntime()),
+                     make_request(max_steps=2, completion_max_steps=5, run_to_completion=True))
+
+    assert result.steps_used == 5
+
+
+def test_a_turn_cancelled_before_it_starts_never_calls_the_model() -> None:
+    model = FakeModelCall([FakeReply(content="never")])
+
+    result, events = run_turn(_service(model, FakeToolRuntime()), cancel=lambda: True)
+
+    assert model.calls == []
+    assert result.cancelled is True
+    assert result.budget_exhausted is False
+    assert events_of_type(events, TurnCompletedEvent) == [TurnCompletedEvent(cancelled=True)]
+
+
+def test_cancelling_during_a_turn_stops_dispatching_the_remaining_tool_calls() -> None:
+    calls = [{"id": "c1", "name": "save_file", "arguments": {}},
+             {"id": "c2", "name": "save_file", "arguments": {}}]
+    model = FakeModelCall([FakeReply(content="two tools", tool_calls=calls)])
+    tools = FakeToolRuntime()
+    stop = {"now": False}
+
+    def cancel() -> bool:
+        return stop["now"]
+
+    original_execute = tools.execute
+
+    def execute(name, args, on_output=None, cancel=None):
+        stop["now"] = True            # cancel raised while the first tool runs
+        return original_execute(name, args, on_output=on_output, cancel=cancel)
+
+    tools.execute = execute
+
+    result, _ = run_turn(_service(model, tools), cancel=cancel)
+
+    assert len(tools.executed) == 1
+    assert result.cancelled is True
+
+
+# --------------------------------------------------------------------------- #
+# Bring-your-own working list.
+#
+# ``ui/chat_panel.py`` holds the turn's message list in its own turn context and
+# reads it WHILE the worker appends (``_reattach_running_turn`` replays the steps
+# done so far when the user reopens a running conversation; ``_finalize_turn``
+# slices it by ``snapshot_len``). A service that built its own private list would
+# silently break both, so a caller can hand its list over instead.
+# --------------------------------------------------------------------------- #
+def test_a_caller_supplied_list_is_appended_to_in_place() -> None:
+    model, tools = tool_turn()
+    live: List[Dict[str, Any]] = [{"role": "user", "content": "already composed"}]
+
+    result = ConversationApplicationService(model, tools).execute(
+        make_request(), lambda event: None, messages=live)
+
+    roles = [m["role"] for m in live]
+    assert roles == ["user", "assistant", "tool", "assistant"]
+    assert result.messages == tuple(live)
+
+
+def test_a_caller_supplied_list_is_used_as_is_without_recomposing_the_prompt() -> None:
+    # The widget already applied the skill prefix and the session notes when it
+    # built its message; composing again would duplicate them.
+    model = FakeModelCall([FakeReply(content="ok")])
+    user = {"role": "user", "content": "already composed"}
+    live = [user]
+
+    ConversationApplicationService(model, FakeToolRuntime()).execute(
+        make_request(prompt="typed text", instruction_prefix="RULES",
+                     session_notes="notes"),
+        lambda event: None, messages=live)
+
+    assert live[0] is user
+    assert live[0]["content"] == "already composed"
+    assert [m["role"] for m in live].count("user") == 1
+
+
+def test_a_caller_supplied_list_skips_the_attachment_reader() -> None:
+    # Reading the attachments is what produced the caller's message in the first
+    # place; doing it again would re-parse every file.
+    model = FakeModelCall([FakeReply(content="ok")])
+    calls: List[Any] = []
+
+    ConversationApplicationService(
+        model, FakeToolRuntime(),
+        attachment_reader=lambda prompt, attachments: calls.append(prompt) or prompt,
+    ).execute(make_request(attachments=["a.docx"]), lambda event: None,
+              messages=[{"role": "user", "content": "composed"}])
+
+    assert calls == []

tests/unit/test_conversation_turn_guards.py

@@ -0,0 +1,210 @@
+"""R04-T03 (b) — the turn loop: guards, permission gate, compaction, cleanup.
+
+Split out of ``test_conversation_application_service.py`` to keep each file
+inside the 400-LOC limit. Same fakes, same service; this half pins the ORDER of
+the safety steps (guard before model, guard before execute, gate before execute)
+and the promise that the output sandbox is tidied on the way out.
+"""
+
+from __future__ import annotations
+
+from typing import Any, Dict, List
+
+import pytest
+from cowork_local.application.conversations.conversation_application_service import (
+    ConversationApplicationService,
+)
+from cowork_local.domain.agents.agent_event import (
+    ErrorEvent,
+    OutputsAddedEvent,
+    ReasoningChunkEvent,
+    TextChunkEvent,
+    ToolCallFinishedEvent,
+)
+from cowork_local.tests.fakes.turn_runtime_fakes import (
+    FakeModelCall,
+    FakeReply,
+    FakeToolRuntime,
+    events_of_type,
+    make_request,
+    run_turn,
+    tool_turn,
+)
+
+
+def _service(model, tools, **overrides) -> ConversationApplicationService:
+    return ConversationApplicationService(model, tools, **overrides)
+
+
+# --------------------------------------------------------------------------- #
+# Guards and the permission gate.
+# --------------------------------------------------------------------------- #
+def test_the_prompt_guard_runs_before_the_model_is_ever_called() -> None:
+    order: List[str] = []
+    model = FakeModelCall([FakeReply(content="ok")])
+    model_call = model.call
+
+    def call(*a, **kw):
+        order.append("model")
+        return model_call(*a, **kw)
+
+    model.call = call
+
+    run_turn(_service(model, FakeToolRuntime(), prompt_guard=lambda messages: order.append("guard")))
+
+    assert order == ["guard", "model"]
+
+
+def test_a_blocked_prompt_propagates_before_the_output_folder_is_touched() -> None:
+    model = FakeModelCall([FakeReply(content="never")])
+    tools = FakeToolRuntime()
+    events: List[Any] = []
+
+    def guard(messages) -> None:
+        raise RuntimeError("SecurityBlocked: nope")
+
+    service = _service(model, tools, prompt_guard=guard)
+
+    with pytest.raises(RuntimeError, match="SecurityBlocked"):
+        service.execute(make_request(), events.append)
+
+    assert model.calls == []
+    assert events_of_type(events, ErrorEvent) == [ErrorEvent(message="SecurityBlocked: nope")]
+    # Cleanup is NOT a read-only operation (it deletes a stale .scratch and every
+    # empty sub-folder), so a turn rejected before it started must not run it.
+    assert tools.finalize_calls == []
+
+
+def test_output_cleanup_still_runs_when_the_turn_fails_mid_loop() -> None:
+    # Once the turn has started producing files, the sandbox must be tidied on
+    # the way out no matter how the turn ends.
+    model = FakeModelCall([RuntimeError("gateway exploded")])
+    tools = FakeToolRuntime()
+    events: List[Any] = []
+
+    with pytest.raises(RuntimeError, match="gateway exploded"):
+        _service(model, tools).execute(make_request(), events.append)
+
+    assert tools.finalize_calls == [{"before": "before", "cancelled": False}]
+    assert events_of_type(events, ErrorEvent) == [ErrorEvent(message="gateway exploded")]
+
+
+def test_the_command_guard_runs_before_the_tool_executes() -> None:
+    order: List[str] = []
+    model, tools = tool_turn("run_command", {"command": "ls"})
+    original = tools.execute
+
+    def execute(name, args, on_output=None, cancel=None):
+        order.append("execute")
+        return original(name, args, on_output=on_output, cancel=cancel)
+
+    tools.execute = execute
+
+    run_turn(_service(model, tools,
+                  command_guard=lambda name, args: order.append(f"guard:{name}")))
+
+    assert order == ["guard:run_command", "execute"]
+
+
+def test_disabling_rule_enforcement_skips_both_guards() -> None:
+    # Co4E flow steps run inside the workspace sandbox and opt out on purpose.
+    calls: List[str] = []
+    model, tools = tool_turn("run_command", {"command": "ls"})
+
+    run_turn(_service(model, tools,
+                  prompt_guard=lambda messages: calls.append("prompt"),
+                  command_guard=lambda name, args: calls.append("command")),
+         make_request(enforce_rules=False))
+
+    assert calls == []
+
+
+def test_the_permission_gate_is_asked_only_for_command_tools() -> None:
+    asked: List[str] = []
+    model, tools = tool_turn("save_file", {"filename": "a.md"})
+
+    run_turn(_service(model, tools,
+                  permission_request=lambda action: asked.append(action["name"]) or True),
+         make_request(gate_mode="confirm"))
+
+    assert asked == []          # save_file writes into the sandbox: never gated
+
+
+def test_a_command_tool_in_confirm_mode_asks_before_running() -> None:
+    asked: List[Dict[str, Any]] = []
+    model, tools = tool_turn("run_command", {"command": "ls"})
+
+    def approve(action: Dict[str, Any]) -> bool:
+        asked.append(action)
+        return True
+
+    run_turn(_service(model, tools, permission_request=approve), make_request(gate_mode="confirm"))
+
+    assert [a["name"] for a in asked] == ["run_command"]
+    assert tools.executed == [("run_command", {"command": "ls"})]
+
+
+def test_a_rejected_command_is_reported_as_a_failed_tool_and_never_runs() -> None:
+    model, tools = tool_turn("run_command", {"command": "rm -rf /"})
+
+    result, events = run_turn(_service(model, tools, permission_request=lambda action: False),
+                          make_request(gate_mode="confirm"))
+
+    assert tools.executed == []
+    assert events_of_type(events, ToolCallFinishedEvent) == [ToolCallFinishedEvent(
+        call_id="c1", name="run_command", ok=False, output="Rejected by user.")]
+    assert result.messages[-2]["content"] == "Rejected by user."
+
+
+def test_auto_mode_never_asks_even_for_a_command() -> None:
+    model, tools = tool_turn("run_command", {"command": "ls"})
+
+    def refuse(action):     # would block the turn if it were consulted
+        raise AssertionError("the gate must not be consulted in auto mode")
+
+    run_turn(_service(model, tools, permission_request=refuse), make_request(gate_mode="auto"))
+
+    assert tools.executed == [("run_command", {"command": "ls"})]
+
+
+# --------------------------------------------------------------------------- #
+# Context compaction, reasoning, output cleanup.
+# --------------------------------------------------------------------------- #
+def test_the_conversation_is_offered_for_compaction_before_every_call() -> None:
+    compactions: List[int] = []
+    model, tools = tool_turn()
+
+    run_turn(_service(model, tools,
+                     compact=lambda messages, cancel: compactions.append(len(messages))))
+
+    assert len(compactions) == 2      # once per provider call
+
+
+def test_reasoning_is_streamed_as_its_own_event() -> None:
+    model = FakeModelCall([FakeReply(content="42", reasoning="thinking...")])
+
+    _, events = run_turn(_service(model, FakeToolRuntime()))
+
+    assert events_of_type(events, ReasoningChunkEvent) == [ReasoningChunkEvent(delta="thinking...")]
+
+
+def test_a_reasoning_only_reply_gets_a_visible_note_in_the_transcript() -> None:
+    # Otherwise a Schedule Task run reads back an empty answer and writes
+    # "(no output)" into its report.
+    model = FakeModelCall([FakeReply(content="", reasoning="thought hard")])
+
+    result, events = run_turn(_service(model, FakeToolRuntime()))
+
+    assert "only its reasoning" in events_of_type(events, TextChunkEvent)[-1].delta
+    assert "only its reasoning" in result.final_text
+
+
+def test_promoted_and_discarded_output_files_are_reported_at_the_end() -> None:
+    model = FakeModelCall([FakeReply(content="ok")])
+    tools = FakeToolRuntime(added=("out/report.pptx",))
+
+    _, events = run_turn(_service(model, tools))
+
+    assert events_of_type(events, OutputsAddedEvent) == [
+        OutputsAddedEvent(paths=("out/report.pptx",))]
+    assert tools.finalize_calls == [{"before": "before", "cancelled": False}]

tests/unit/test_cowork_turn_request.py

@@ -0,0 +1,76 @@
+"""R04-T04 — unit tests for the UI-state -> request mapping.
+
+Three small rules used to sit inline in ``ui/cowork_tab.py::build_job``, where no
+test could reach them: the turn's prompt is the last message in the working list,
+the history is everything before it, and the confirm-commands flag becomes a gate
+mode. Getting any of them wrong is silent (a duplicated user message, a command
+that stops asking for approval), so they are pinned here.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from cowork_local.application.conversations.cowork_turn_request import (
+    build_cowork_turn_request,
+)
+
+
+def _build(**overrides):
+    base = {
+        "turn_id": "t3",
+        "session_id": "s1",
+        "messages": [{"role": "user", "content": "make me a report"}],
+    }
+    base.update(overrides)
+    return build_cowork_turn_request(**base)
+
+
+def test_the_last_message_becomes_the_prompt_and_the_rest_the_history() -> None:
+    request = _build(messages=[
+        {"role": "user", "content": "earlier"},
+        {"role": "assistant", "content": "sure"},
+        {"role": "user", "content": "now this"},
+    ])
+
+    assert request.prompt == "now this"
+    assert request.messages == ({"role": "user", "content": "earlier"},
+                                {"role": "assistant", "content": "sure"})
+
+
+def test_an_empty_working_list_yields_an_empty_prompt() -> None:
+    # Defensive: a turn with no message at all must not raise on messages[-1].
+    request = _build(messages=[])
+
+    assert request.prompt == ""
+    assert request.messages == ()
+
+
+def test_confirming_commands_puts_the_turn_in_confirm_gate_mode() -> None:
+    assert _build(confirm_commands=True).gate_mode == "confirm"
+    assert _build(confirm_commands=False).gate_mode == "auto"
+    assert _build().gate_mode == "auto"          # auto-run is the default
+
+
+def test_the_captured_widget_state_is_carried_into_the_request() -> None:
+    request = _build(
+        surface="cowork", project_id="p7", title="Weekly report",
+        provider_id="anthropic", model="claude-sonnet-4-6",
+        instructions="PROJECT RULES", output_dir="out/.turns/t3",
+        home_output_root="out", agent_role="cowork",
+    )
+
+    assert (request.turn_id, request.session_id) == ("t3", "s1")
+    assert (request.surface, request.project_id, request.title) == \
+           ("cowork", "p7", "Weekly report")
+    assert (request.provider_id, request.model) == ("anthropic", "claude-sonnet-4-6")
+    assert request.project_context == "PROJECT RULES"
+    assert request.output_dir == Path("out/.turns/t3")
+    assert request.home_output_root == Path("out")
+    assert request.agent_role == "cowork"
+
+
+def test_the_prompt_survives_a_message_whose_content_is_missing() -> None:
+    request = _build(messages=[{"role": "user"}])
+
+    assert request.prompt == ""

tests/unit/test_task_prompt_assembly.py

@@ -0,0 +1,34 @@
+"""R04-T05 — unit tests for the unattended-run prompt assembly.
+
+``_run_agent`` used to build this by rebinding ``prompt`` three times, each with
+its own ``f"{block}\n\n{prompt}"``. The ORDER that produced is load-bearing (the
+plan reminder has to lead, the task's own words have to trail) and it was
+readable only by replaying the rebindings in your head.
+"""
+
+from __future__ import annotations
+
+from cowork_local.core.task_executors import _unattended_prompt
+
+
+def test_the_plan_reminder_leads_and_the_task_prompt_trails() -> None:
+    built = _unattended_prompt("write the report")
+
+    assert built.startswith("This runs unattended (Schedule Task)")
+    assert built.endswith("write the report")
+
+
+def test_a_skill_block_sits_between_the_reminder_and_the_agent_persona() -> None:
+    built = _unattended_prompt("write the report", skill_text="SKILL",
+                               agent_instructions="PERSONA")
+
+    assert built.index("This runs unattended") < built.index("SKILL")
+    assert built.index("SKILL") < built.index("PERSONA")
+    assert built.index("PERSONA") < built.index("write the report")
+
+
+def test_absent_blocks_leave_no_extra_blank_lines() -> None:
+    built = _unattended_prompt("do it", skill_text="", agent_instructions=None)
+
+    assert "\n\n\n" not in built
+    assert built.count("do it") == 1

tests/unit/test_turn_runtime.py

@@ -0,0 +1,36 @@
+"""R04-T04 — unit tests for the shared turn-runtime helpers.
+
+``combine_instructions`` is the small rule the UI applied inline: a turn's
+standing instructions are several independent blocks (project context, an Admin
+agent's persona, a skill's rules, an unattended-run reminder) that must be joined
+with one blank line, skipping whatever is absent. Two call sites need it (T04's
+widget and T05's task runner), which is exactly when a rule stops being an inline
+expression.
+"""
+
+from __future__ import annotations
+
+from cowork_local.application.conversations.turn_runtime import combine_instructions
+
+
+def test_two_blocks_are_joined_by_a_blank_line() -> None:
+    assert combine_instructions("PROJECT", "AGENT") == "PROJECT\n\nAGENT"
+
+
+def test_an_absent_block_leaves_no_blank_line_behind() -> None:
+    assert combine_instructions("", "AGENT") == "AGENT"
+    assert combine_instructions("PROJECT", "") == "PROJECT"
+    assert combine_instructions("PROJECT", None) == "PROJECT"
+
+
+def test_whitespace_only_blocks_do_not_count_as_instructions() -> None:
+    assert combine_instructions("   \n ", "AGENT") == "AGENT"
+
+
+def test_nothing_to_say_produces_an_empty_string() -> None:
+    assert combine_instructions() == ""
+    assert combine_instructions("", None, "  ") == ""
+
+
+def test_more_than_two_blocks_keep_their_order() -> None:
+    assert combine_instructions("A", "B", "C") == "A\n\nB\n\nC"

ui/cowork_tab.py

@@ -346,19 +346,45 @@ class CoworkTab(ChatPanel):
         self._apply_output_folder_label()  # picks up edits made via Settings too
 
     def build_job(self, text: str, messages, out_dir):
-        # Each turn writes into its OWN isolated folder (out_dir) and works on its
-        # OWN message list, so several turns can run in parallel without clobbering
-        # each other's files or history. Deliverables are moved up to the session
-        # Output root when the turn finishes (see _cleanup_turn).
+        """This turn's job: a frozen request run through the conversation service.
+
+        Since R04-T04 the widget no longer drives the turn loop. Every value a
+        turn depends on is read HERE, on the UI thread at submit time, and packed
+        into an immutable ``ConversationExecutionRequest`` — so clicking a
+        different model or switching workspace mid-answer cannot reach work
+        already in flight.
+        """
         output_dir = out_dir or self._session_output_dir()
+        # The sandbox folder is named by the turn id ('.turns/t3'); with no
+        # sandbox the session id identifies the turn well enough for the audit log.
+        turn_id = out_dir.name if out_dir is not None else self.session_id
+        session_id = self.session_id
         title = self.title
         project_id = self.project_id
+        home_output_root = self.workspace_dir()
         # Captured at submit time (UI thread): the Admin-defined agent
         # preset's instructions, if one is selected in the Agent picker.
         agent_prompt = self.admin_agent_prompt()
+        # Per-workspace Auto-run override wins, else the global "confirm before
+        # running commands" setting. Frozen now, so a Settings change mid-turn
+        # cannot flip the rules this turn started under.
+        confirm_commands = self.ctx.project_confirm_commands()
+        # What the turn is recorded as running on. A routing override (R03) wins
+        # over the tab's own picker; '' means the provider's configured default.
+        # Informational only — an Admin-agent preset builds its own provider
+        # below, so treat these as the record, not the decision.
+        provider_id = self._routed_provider or self.ctx.config.active_provider
+        model = self._routed_model or self._model or ""
 
         def job(worker: AgentWorker):
-            from ..core.chat_agent import run_cowork
+            from ..application.conversations.core_runtime_adapter import (
+                build_cowork_conversation_service,
+                legacy_event_sink,
+            )
+            from ..application.conversations.cowork_turn_request import (
+                build_cowork_turn_request,
+            )
+            from ..application.conversations.turn_runtime import combine_instructions
             from ..core.projects import load_project, project_context_text
 
             provider = self.build_provider()  # this tab's selected agent/model
@@ -367,23 +393,36 @@ class CoworkTab(ChatPanel):
             # built-in MCP server auto-registered while signed in, see
             # AppContext._ms365_builtin_connection / mcp_servers/ms365_server.py).
             extra_tools, extra_exec = self.ctx.build_mcp_tools()
-            # Shared project instructions (Claude-Projects style) — refreshed
-            # each turn so edits in the Workspace screen apply immediately.
-            proj_ctx = project_context_text(load_project(project_id))
-            if agent_prompt:
-                proj_ctx = f"{proj_ctx}\n\n{agent_prompt}" if proj_ctx else agent_prompt
+            # Shared project instructions (Claude-Projects style) plus the Admin
+            # agent's persona, refreshed each turn so edits in the Workspace
+            # screen apply immediately.
+            instructions = combine_instructions(
+                project_context_text(load_project(project_id)), agent_prompt)
             # Permission Management (Sandbox Security Layer): off by default —
-            # matches the pre-existing auto-run behavior. Now resolved PER
-            # WORKSPACE: this project's Auto-run override wins, else the global
-            # "confirm before running commands" setting (project_confirm_commands).
+            # matches the pre-existing auto-run behavior. The gate lives on the
+            # worker because the UI resolves it from the main thread.
             gate = None
-            if self.ctx.project_confirm_commands():
+            if confirm_commands:
                 gate = worker.new_gate("confirm", agent_role=agent_roles.COWORK)
-            run_cowork(provider, messages, output_dir, worker.emit_event,
-                       worker.is_cancelled, title=title,
-                       extra_tools=extra_tools, extra_executor=extra_exec,
-                       project_context=proj_ctx, security_config=self.ctx.config,
-                       gate=gate)
+
+            service = build_cowork_conversation_service(
+                provider, output_dir, worker.emit_event, title=title,
+                project_context=instructions, extra_tools=extra_tools,
+                extra_executor=extra_exec, security_config=self.ctx.config,
+                gate=gate, agent_role=agent_roles.COWORK,
+            )
+            request = build_cowork_turn_request(
+                turn_id=turn_id, session_id=session_id, surface=self.kind,
+                project_id=project_id, title=title, messages=messages,
+                provider_id=provider_id, model=model, instructions=instructions,
+                output_dir=output_dir, home_output_root=home_output_root,
+                confirm_commands=gate is not None, agent_role=agent_roles.COWORK,
+            )
+            # Hand the widget's own list over: _reattach_running_turn replays
+            # from it while the turn is still running, and _finalize_turn slices
+            # it afterwards, so the service must append into that very object.
+            service.execute(request, legacy_event_sink(worker.emit_event),
+                            cancel=worker.is_cancelled, messages=messages)
             return {"messages": messages, "turn_dir": str(output_dir)}
 
         return job