feat(engine): the manager — chat orders, team, triage, verdicts, bootstrap

Phase 3 of the AI-workforce engine (TODO-agent-2):

- engine/manager.py: ManagerTurns.chat (CREATE_TASK/PAUSE/RESUME/CANCEL,
  HIRE/UPDATE_EMPLOYEE/FIRE, KNOWLEDGE), triage (ASSIGN/REJECT/ASK_USER),
  final_review (COMPLETE/REVISE +cycle), error_review (RESOLVE_ERROR/CANCEL),
  bootstrap_team; post_user_message now delegates to it.
- One billing path: call_model/BillingScope in runner.py is the single model
  entry point (fixes the agybot chat-billing bug).
- Team changes capped at 3/turn, employee cap, last manager cannot be fired,
  hires pick a granted model of the requested tier strictly.
- container_engine.py wires the real WorkforceBootstrapPort.
- Fixes: REVISE is a body tag (prompt and parser now agree); ASSIGN
  employee="" means pick-for-me; the runner's protocol-error retry is capped by
  engine_max_protocol_retries (was unbounded until the turn timeout).
- 20 new manager tests + regression tests; report in
  docs/plan/reports/agent-2-phase-3.md.

apps/api/app/application/container_engine.py

@@ -1,17 +1,73 @@
 """Wiring for the AI-workforce workstream (team bootstrap).
 
-Foundation default: a no-op. The engine agent replaces the body with the real bootstrap;
-the function name and return type are FROZEN.
+The org wizard calls ``build_workforce_bootstrap(session)`` after it commits a
+new organization, then ``bootstrap_team`` creates the starting team. The team
+is built on the *caller's* session, so the employees and the "waiting for a
+model" note land in the same transaction as the organization.
 """
 
 from __future__ import annotations
 
 from sqlalchemy.ext.asyncio import AsyncSession
 
-from app.application.ports.workforce_bootstrap import NullWorkforceBootstrap, WorkforceBootstrapPort
+from app.application.ports.workforce_bootstrap import WorkforceBootstrapPort
 
-_null_bootstrap = NullWorkforceBootstrap()
+
+class _EngineWorkforceBootstrap:
+    """The real bootstrap: one manager, planner, developer and tester.
+
+    Everything is built here, lazily, from the session: ``container.py`` is a
+    frozen composition root and the engine must not widen it, so the repos and
+    ports the manager needs are assembled where they are used.
+    """
+
+    def __init__(self, session: AsyncSession) -> None:
+        self.session = session
+
+    async def bootstrap_team(self, *, organization_id: str, project_id: str) -> None:
+        from app.application.container import get_model_provider
+        from app.application.container_org import build_memory, build_model_grants
+        from app.application.engine.manager import ManagerTurns
+        from app.infrastructure.repositories.ai_control import (
+            AiModelRepository,
+            ModelCredentialRepository,
+            RateCardRepository,
+        )
+        from app.infrastructure.repositories.audit import UsageLedgerRepository
+        from app.infrastructure.repositories.engine import (
+            EmployeeProfileRepository,
+            PipelineStateRepository,
+        )
+        from app.infrastructure.repositories.workforce import (
+            EmployeeRepository,
+            MessageRepository,
+            TaskRepository,
+            ThreadRepository,
+        )
+
+        session = self.session
+        manager = ManagerTurns(
+            provider=get_model_provider(),
+            employees=EmployeeRepository(session),
+            messages=MessageRepository(session),
+            tasks=TaskRepository(session),
+            threads=ThreadRepository(session),
+            models=AiModelRepository(session),
+            credentials=ModelCredentialRepository(session),
+            rate_cards=RateCardRepository(session),
+            ledger=UsageLedgerRepository(session),
+            grants=build_model_grants(session),
+            memory=build_memory(session),
+            profiles=EmployeeProfileRepository(session),
+            states=PipelineStateRepository(session),
+        )
+        await manager.bootstrap_team(
+            organization_id=organization_id, project_id=project_id
+        )
 
 
 def build_workforce_bootstrap(session: AsyncSession) -> WorkforceBootstrapPort:
-    return _null_bootstrap
+    return _EngineWorkforceBootstrap(session)
+
+
+__all__ = ["build_workforce_bootstrap"]

apps/api/app/application/engine/events.py

@@ -186,4 +186,22 @@ class RunFeed:
         return stream
 
 
-__all__ = ["RunFeed"]
+async def emit_team_changed(
+    *, organization_id: str, change: str, employee_id: str
+) -> None:
+    """The team changed (hired, fired, re-tiered): the workforce page reloads."""
+    await publish(
+        RealtimeEvent(
+            type="team.changed",
+            channels=(org_channel(organization_id),),
+            organization_id=organization_id,
+            data={
+                "change": change,
+                "employee_id": employee_id,
+                "organization_id": organization_id,
+            },
+        )
+    )
+
+
+__all__ = ["RunFeed", "emit_team_changed"]

apps/api/app/application/engine/prompt.py

@@ -59,6 +59,8 @@ _PROTOCOL_HINTS: dict[tuple[RoleKey, Mode], str] = {
         "تو مدیر هستی و کار را ارزیابی می‌کنی.\n"
         "برچسب‌های مجاز:\n"
         '[[ASSIGN employee="نام کارمند" pipeline="plan_code_test"/]]\n'
+        'اگر خودت باید کارمند را انتخاب کنی، بنویس [[ASSIGN employee="" '
+        'pipeline="plan_code_test"/]] تا کم‌مشغول‌ترین انتخاب شود.\n'
         "[[REJECT reason=\"دلیل\"/]]\n"
         "[[ASK_USER]]سؤالت را اینجا بنویس[[/ASK_USER]]\n"
         '[[KNOWLEDGE kind="rule" key="..."]]قاعده‌ای که یاد گرفتی[[/KNOWLEDGE]]\n'
@@ -92,7 +94,8 @@ _PROTOCOL_HINTS: dict[tuple[RoleKey, Mode], str] = {
         '[[KNOWLEDGE kind="rule|fact" key="..."]'
         "]]متن[[/KNOWLEDGE]]\n"
         "پاسخ متنی‌ات برای کاربر نمایش داده می‌شود؛ برچسب‌ها کنارش اجرا می‌شوند. "
-        "کارها را اتمیک بساز و نگو که کدام فایل‌ها را هم‌زمان تغییر می‌دهند."
+        "کارها را اتمیک بساز و طوری تقسیم کن که دو کار هم‌زمان فایل‌های یکسان را "
+        "تغییر ندهند."
     ),
     (RoleKey.PLANNER, Mode.WORK): (
         "تو برنامه‌ریز هستی.\n"

apps/api/app/application/engine/protocol.py

@@ -104,6 +104,7 @@ BODY_TAGS: frozenset[TagName] = frozenset(
         TagName.EDIT_FILE,
         TagName.KNOWLEDGE,
         TagName.ASK_USER,
+        TagName.REVISE,
         TagName.CREATE_TASK,
         TagName.SPLIT,
         TagName.PLAN_SPEC,
@@ -282,14 +283,15 @@ _EDIT_BLOCK_RE = re.compile(
 def assign_of(tag: Tag) -> AssignTag:
     """Read an ``ASSIGN`` tag. ``employee=""`` means "pick for me"."""
     employee = tag.attr("employee", "").strip()
-    if not employee and not tag.attr("task_id", "").strip():
+    task_id = tag.attr("task_id", "").strip()
+    # ``employee=""`` is a deliberate "pick the least busy one"; a tag with
+    # neither attribute at all is a mistake we quote back to the model.
+    if "employee" not in tag.attrs and "task_id" not in tag.attrs:
         raise ProtocolError("[[ASSIGN]] needs employee=... or task_id=...")
     pipeline = tag.attr("pipeline", "").strip()
     if pipeline and pipeline not in ASSIGNABLE_PIPELINES:
         raise ProtocolError(f"unknown pipeline: {pipeline}")
-    return AssignTag(
-        employee=employee, pipeline=pipeline, task_id=tag.attr("task_id", "").strip()
-    )
+    return AssignTag(employee=employee, pipeline=pipeline, task_id=task_id)
 
 
 def task_draft_of(tag: Tag) -> TaskDraft:

apps/api/app/application/engine/runner.py

@@ -46,7 +46,7 @@ from app.application.engine.prompt import (
 )
 from app.application.engine.protocol import TOOL_TAGS, Tag, TagName, parse_reply
 from app.application.engine.tools import ToolExecutor, ToolOutcome, tool_key_for
-from app.application.ports import ModelProviderPort
+from app.application.ports import ModelProviderPort, ModelResponse
 from app.application.ports.memory import MemoryPort, NullMemory
 from app.application.ports.model_grants import ModelGrantPort
 from app.application.ports.sandbox_provider import SandboxProviderPort
@@ -179,6 +179,62 @@ def classify_error(exc: BaseException) -> ErrorKind:
     return ErrorKind.UNAVAILABLE
 
 
+@dataclass(slots=True, kw_only=True)
+class BillingScope:
+    """What a model call is billed to. One scope per call, never a default."""
+
+    organization_id: str
+    project_id: str | None = None
+    employee_id: str | None = None
+    user_id: str | None = None
+    run_id: str | None = None
+
+
+async def call_model(
+    *,
+    provider: ModelProviderPort,
+    credentials: ModelCredentialRepository,
+    rate_cards: RateCardRepository,
+    ledger: UsageLedgerRepository,
+    model: AiModel,
+    prompt,
+    scope: BillingScope,
+) -> ModelResponse:
+    """Call the model and bill it. **The** single model entry point.
+
+    Every model call in the platform goes through here — a task turn, a
+    triage turn, a final verdict and the manager's chat alike. Billing reads
+    the internal ledger, never the provider's invoice, so a call that skips
+    this function is a call the platform never charges for (agybot's manager
+    chat bug).
+    """
+    pool = await credentials.list_active_for_provider(model.provider_id)
+    credential = pool[0] if pool else None
+    response = await provider.complete(
+        model=model,
+        credential=credential,
+        credentials=pool or None,
+        messages=prompt.messages,
+        system=prompt.system,
+    )
+    for unit, tokens in (
+        (RateUnit.MODEL_INPUT_TOKENS, float(response.input_tokens)),
+        (RateUnit.MODEL_OUTPUT_TOKENS, float(response.output_tokens)),
+    ):
+        await record_model_usage(
+            ledger=ledger,
+            rate_cards=rate_cards,
+            organization_id=scope.organization_id,
+            unit=unit,
+            quantity=tokens,
+            project_id=scope.project_id,
+            user_id=scope.user_id,
+            employee_id=scope.employee_id,
+            run_id=scope.run_id,
+        )
+    return response
+
+
 class TurnRunner:
     """Runs one turn at a time. One instance per process is enough."""
 
@@ -224,6 +280,7 @@ class TurnRunner:
         history: list[TurnMessage] = list(request.history)
         tool_calls_made = 0
         model_calls = 0
+        protocol_errors = 0
         reply_text = ""
         tags: tuple[Tag, ...] = ()
         turn_row = await self._open_turn_row(request)
@@ -272,6 +329,17 @@ class TurnRunner:
 
             parsed = parse_reply(response.content, role=request.role, mode=request.mode)
             if parsed.errors:
+                protocol_errors += 1
+                if protocol_errors > settings.engine_max_protocol_retries:
+                    return await self._fail(
+                        request,
+                        turn_row,
+                        ErrorKind.PROTOCOL.value,
+                        "پاسخ مدل مکرراً ناقض پروتکل بود.",
+                        tool_calls_made,
+                        model_calls,
+                        incomplete=True,
+                    )
                 # The model learns the protocol from what it just got wrong.
                 history.append(
                     TurnMessage(kind="result", text=protocol_error_feedback(parsed.errors))
@@ -358,32 +426,22 @@ class TurnRunner:
         return model
 
     async def _complete(self, request: TurnRequest, model: AiModel, prompt):
-        """One model call, billed exactly like every other model call."""
-        pool = await self.credentials.list_active_for_provider(model.provider_id)
-        credential = pool[0] if pool else None
-        response = await self.provider.complete(
+        """One model call, billed through the one shared model entry point."""
+        return await call_model(
+            provider=self.provider,
+            credentials=self.credentials,
+            rate_cards=self.rate_cards,
+            ledger=self.ledger,
             model=model,
-            credential=credential,
-            credentials=pool or None,
-            messages=prompt.messages,
-            system=prompt.system,
-        )
-        for unit, tokens in (
-            (RateUnit.MODEL_INPUT_TOKENS, float(response.input_tokens)),
-            (RateUnit.MODEL_OUTPUT_TOKENS, float(response.output_tokens)),
-        ):
-            await record_model_usage(
-                ledger=self.ledger,
-                rate_cards=self.rate_cards,
+            prompt=prompt,
+            scope=BillingScope(
                 organization_id=request.organization_id,
-                unit=unit,
-                quantity=tokens,
                 project_id=request.task.project_id,
-                user_id=request.user_id,
                 employee_id=request.employee.id if request.employee else None,
+                user_id=request.user_id,
                 run_id=request.run_id,
-            )
-        return response
+            ),
+        )
 
     # -- tools ------------------------------------------------------------- #
 
@@ -579,4 +637,12 @@ class _ModelUnavailable(Exception):
         self.kind = kind
 
 
-__all__ = ["TERMINAL_TAGS", "TurnRequest", "TurnResult", "TurnRunner", "classify_error"]
+__all__ = [
+    "TERMINAL_TAGS",
+    "BillingScope",
+    "TurnRequest",
+    "TurnResult",
+    "TurnRunner",
+    "call_model",
+    "classify_error",
+]

apps/api/app/application/services/workforce_service.py

@@ -27,8 +27,6 @@ from app.application.ports import (
 from app.application.ports.realtime import (
     emit_approval_pending,
     emit_artifact_created,
-    emit_chat_pending,
-    emit_message_created,
     emit_run_status,
     emit_run_step,
     emit_task_created,
@@ -51,7 +49,6 @@ from app.domain.workforce.models import (
     EmployeeStatus,
     EmployeeToolPermission,
     Message,
-    MessageRole,
     PromptVersion,
     RoleKey,
     Run,
@@ -364,67 +361,48 @@ class WorkforceService:
         user_id: str,
         employee_id: str | None = None,
     ) -> tuple[Message, Message]:
-        """Append the user's message, then produce the assistant reply.
+        """Append the user's message, then let the manager answer it.
 
-        Returns ``(user_message, assistant_message)`` so the caller can render
-        both without a second round-trip.
+        The manager's turn is the engine's job (``engine/manager.py``): it
+        replies, and it may create tasks, change the team or pause work in the
+        same breath. This method stays the single entry point the router calls;
+        it builds the engine's manager from the same session, so the message,
+        the task and the usage events commit together.
         """
-        thread = await self.get_thread_or_404(
-            organization_id=organization_id, thread_id=thread_id
-        )
-        if not content.strip():
-            raise ValidationError("متن پیام نمی‌تواند خالی باشد.")
-
-        user_message = await self.messages.create(
-            Message(thread_id=thread.id, role=MessageRole.USER, content=content)
-        )
-
-        employee: Employee | None = None
-        if employee_id:
-            employee = await self.get_employee_or_404(
-                organization_id=organization_id, employee_id=employee_id
-            )
-        else:
-            employee = await self._default_manager(organization_id)
-
-        # The manager is about to call a model. Tell the thread so the UI can
-        # show a thinking indicator immediately.
-        await emit_chat_pending(thread_id=thread.id, organization_id=organization_id)
-
-        history = await self.messages.list_for_thread(thread.id)
-        system_prompt = await self._system_prompt_for(employee)
-        reply = await self._complete(
+        manager = self._manager_turns()
+        return await manager.chat(
             organization_id=organization_id,
-            employee=employee,
-            project_id=thread.project_id,
+            thread_id=thread_id,
+            content=content,
             user_id=user_id,
-            system=system_prompt,
-            messages=[
-                ChatMessage(role=m.role.value, content=m.content)
-                for m in history
-                if m.role in (MessageRole.USER, MessageRole.ASSISTANT)
-            ],
+            employee_id=employee_id,
         )
 
-        assistant_message = await self.messages.create(
-            Message(
-                thread_id=thread.id,
-                role=MessageRole.ASSISTANT,
-                content=reply,
-                employee_id=employee.id if employee else None,
-            )
+    def _manager_turns(self):
+        """The engine's manager service, wired on this service's session.
+
+        Ports that take a session (model grants, memory) are built here rather
+        than injected: ``container.py`` is a frozen composition root, and the
+        engine must not widen a constructor it does not own. Sharing the
+        session is the point — a reply, a task and its usage events belong to
+        one transaction.
+        """
+        from app.application.container_org import build_memory, build_model_grants
+        from app.application.engine.manager import ManagerTurns
+
+        return ManagerTurns(
+            provider=self.provider,
+            employees=self.employees,
+            messages=self.messages,
+            tasks=self.tasks,
+            threads=self.threads,
+            models=self.models,
+            credentials=self.credentials,
+            rate_cards=self.rate_cards,
+            ledger=self.ledger,
+            grants=build_model_grants(self.tasks.session),
+            memory=build_memory(self.tasks.session),
         )
-        # Live push: any browser on this thread sees the reply arrive, and the
-        # pending indicator clears, without waiting for a reload.
-        await emit_message_created(
-            thread_id=thread.id,
-            organization_id=organization_id,
-            message_id=assistant_message.id,
-            role=MessageRole.ASSISTANT.value,
-            content=reply,
-            employee_id=employee.id if employee else None,
-        )
-        return user_message, assistant_message
 
     # ------------------------------------------------------------------ #
     # Tasks                                                               #

apps/api/app/core/config.py

@@ -144,6 +144,10 @@ class Settings(BaseSettings):
 
     # >>> agent-2 (AI workforce engine): add settings ONLY between these markers
     engine_max_tool_calls_per_turn: int = 40
+    #: Consecutive malformed replies tolerated before a turn gives up. Without
+    #: it a model that repeats the same protocol mistake would be called until
+    #: the turn timeout, hundreds of paid calls later.
+    engine_max_protocol_retries: int = 3
     engine_turn_timeout_seconds: int = 900
     engine_max_cycles: int = 6
     engine_max_employees: int = 20

apps/api/app/infrastructure/repositories/workforce.py

@@ -482,6 +482,15 @@ class TaskRepository:
         await self.session.flush()
         return _task(row)
 
+    async def set_assignee(self, task_id: str, employee_id: str | None) -> Task | None:
+        """Point a task at an employee. The last step of the manager's triage."""
+        row = await self.session.get(TaskRow, task_id)
+        if row is None:
+            return None
+        row.assigned_employee_id = employee_id
+        await self.session.flush()
+        return _task(row)
+
     async def set_status(self, task_id: str, status: TaskStatus) -> Task | None:
         row = await self.session.get(TaskRow, task_id)
         if row is None: