mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
* feat(tests): e2e scenario 2 — the PM merge chain through the PR gate
Shared arcs extracted (arcs.py: canonical-company seeding + dev/qa/doc
segments); scenario 2 seeds a root->cell->dev hierarchy mid-flight, rides
the child through the scenario-1 arc into the cell branch (real squash
via the fake GitHub), then submit_up -> claim_gate_review/pr_pass ->
dispatcher re-claim (mirrored) -> PM complete merging cell->root. This is
the exact PM->reviewer->PM turn sequence the wave-1 turn cut shortens —
the BEFORE-net. Learned seams scripted: commit-subject validator (>=20
chars), reviewer learning-note gate, pr_pass clears ownership by design.
* feat(runtime): PR-gate turn cut — assembled parents auto-submit to the reviewer
When every child of an assembled parent is terminal, the closure
dispatcher now runs the real submit_up/submit_root through the internal
API as the owning PM (_try_auto_submit) instead of spawning the PM for
that turn — the submit's substance is deterministic gate code. Any gate
refusal falls back to the classic PM closure spawn; pr_fail routing and
the PM's final merge turn are unchanged; umbrellas never auto-submit.
ROBOCO_PR_GATE_AUTO_SUBMIT_ENABLED default-on; task.auto_submitted audit
row per cut. Proven by e2e scenario 2b (real API, real gates, real git)
against scenario 2 as the before-net.
* feat(notes): structured note sections carry a written_at trace stamp
Sections are overwrite-in-place, so without a stamp there was no way to
reconstruct WHEN a dev/qa/doc/reviewer note landed (CEO reMarkable item:
trace TIMESTAMPS). apply_structured_note stamps ISO written_at beside
the model fields; the panel notes tab renders it next to each card
title (pre-stamp rows render nothing). Progress updates, commits, and
journal entries already carried timestamps — this was the one gap.
* feat(tasks): server-side task search — title, details, and id prefix
The task list's search box only matched titles client-side, and the
trimmed summary payload deliberately carries no description — so
keyword/details/id search was impossible in the browser by design.
GET /tasks/summary gains q (ILIKE over title+description, id-prefix
match, composed with team/status and the view-permission scoping);
the panel debounces the box into the summary fetch and drops the
title-only client filter that would have hidden description matches.
* feat(wave-1): trace timestamps, real task search, Secretary task edits
- apply_structured_note stamps written_at per section; the panel notes
tab shows it (the one trace surface without a timestamp).
- GET /tasks/summary?q= searches title+description+id-prefix server-side
(summaries carry no description by design); panel debounces into the
fetch and drops the title-only client filter.
- Secretary control_task gains a CEO-gated edit action over the content
allowlist, and GET /secretary/tasks?q= resolves task names to ids for
the chat. PM-side expansion deferred per the CEO's 'not that much'.
* fix(workspace): dep-update probe scrubs the inherited venv pin
Under uv run the orchestrator's process tree carries VIRTUAL_ENV, and a
uv-based dep_update_command in the throwaway probe clone would target
that venv instead of the clone's — the same hazard _uv_subprocess_env
already guards on the install path.
* build: private per-repo uv cache — isolate from machine-wide uvx servers
Root cause of the recurring rich/pip/bandit rot, with evidence: uv cache
clean timed out on the ~/.cache/uv lock ('is another uv process
running?') — three uvx mcp-server-fetch processes (Claude Code fetch MCP,
one alive since Wednesday) share that cache and race repo syncs on it;
poisoned entries then survive venv rebuilds because rm -rf .venv never
touches the cache, and every re-link reproduces the breakage. UV_CACHE_DIR
now pins <repo>/.uv-cache (gitignored). The earlier UV_NO_SYNC
serialization stays as defense-in-depth but was not the whole story.
* feat(tests): e2e scenario 3 — pr_fail revision loop + root→CEO chain
3a: reviewer pr_fail with a concrete issue -> needs_revision ->
i_will_plan re-entry (full plan gates) -> real fix lands on the cell
branch (the unchanged-PR hard gate refuses resubmit until it does) ->
clean second pass -> merge. 3b: submit_root -> gate -> Main PM complete
escalates the root to the CEO -> the REAL approve-and-merge endpoint
squash-merges to the origin's master. Harness gains the tasks router, a
seeded CEO identity, origin_commit, and a fake GitHub whose head.sha is
recomputed live (real-GitHub semantics the unchanged gate reads). Seeds
now encode the real shape: delivery roots are team=main_pm and
planning-typed.
---------
Co-authored-by: Renn F <rennf93@users.noreply.github.com>
196 lines
6.2 KiB
Python
196 lines
6.2 KiB
Python
"""roboco.api.routes.secretary — role gates + directive flow (direct-call style)."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from http import HTTPStatus
|
|
from typing import Any
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
from uuid import uuid4
|
|
|
|
import pytest
|
|
from fastapi import HTTPException
|
|
from roboco.api.routes import secretary as sec_route
|
|
from roboco.api.schemas.secretary import DirectiveDecision, DirectiveSubmit
|
|
from roboco.models import AgentRole
|
|
from roboco.models.permissions import AgentContext
|
|
from roboco.services.base import ConflictError
|
|
|
|
_ROW = object()
|
|
_DIRECTIVE_DICT: dict[str, Any] = {
|
|
"id": "11111111-1111-1111-1111-111111111111",
|
|
"kind": "relay_message",
|
|
"status": "executed",
|
|
"payload": {},
|
|
"requested_by": "22222222-2222-2222-2222-222222222222",
|
|
"requested_at": None,
|
|
"decided_by": None,
|
|
"decided_at": None,
|
|
"result": "posted to #all-hands",
|
|
}
|
|
|
|
|
|
def _agent(role: AgentRole) -> AgentContext:
|
|
return AgentContext(agent_id=uuid4(), role=role, team=None)
|
|
|
|
|
|
def _db() -> MagicMock:
|
|
db = MagicMock()
|
|
db.commit = AsyncMock()
|
|
return db
|
|
|
|
|
|
class _FakeService:
|
|
def __init__(self, *, exc: Exception | None = None) -> None:
|
|
self._exc = exc
|
|
|
|
async def submit_directive(self, _kind: Any, _payload: Any, _by: Any) -> object:
|
|
if self._exc is not None:
|
|
raise self._exc
|
|
return _ROW
|
|
|
|
async def confirm_directive(self, _directive_id: Any, _by: Any) -> object:
|
|
if self._exc is not None:
|
|
raise self._exc
|
|
return _ROW
|
|
|
|
async def reject_directive(
|
|
self, _directive_id: Any, _by: Any, _reason: Any
|
|
) -> object:
|
|
if self._exc is not None:
|
|
raise self._exc
|
|
return _ROW
|
|
|
|
async def list_directives(self, _status: Any = None) -> list[object]:
|
|
return [_ROW]
|
|
|
|
async def read_company_state(self) -> dict[str, Any]:
|
|
return {
|
|
"goals": {},
|
|
"task_counts": {},
|
|
"pending_pitches": [],
|
|
"pending_directives": [],
|
|
}
|
|
|
|
def to_dict(self, _row: object) -> dict[str, Any]:
|
|
return dict(_DIRECTIVE_DICT)
|
|
|
|
|
|
def _install(monkeypatch: pytest.MonkeyPatch, service: _FakeService) -> None:
|
|
monkeypatch.setattr(sec_route, "get_secretary_service", lambda _db: service)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_submit_forbidden_for_developer() -> None:
|
|
with pytest.raises(HTTPException) as exc:
|
|
await sec_route.submit_directive(
|
|
DirectiveSubmit(kind="relay_message"), _db(), _agent(AgentRole.DEVELOPER)
|
|
)
|
|
assert exc.value.status_code == HTTPStatus.FORBIDDEN
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_submit_bad_kind_422() -> None:
|
|
with pytest.raises(HTTPException) as exc:
|
|
await sec_route.submit_directive(
|
|
DirectiveSubmit(kind="bogus"), _db(), _agent(AgentRole.SECRETARY)
|
|
)
|
|
assert exc.value.status_code == HTTPStatus.UNPROCESSABLE_ENTITY
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_submit_success(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
db = _db()
|
|
_install(monkeypatch, _FakeService())
|
|
resp = await sec_route.submit_directive(
|
|
DirectiveSubmit(
|
|
kind="relay_message", payload={"channel": "all-hands", "text": "hi"}
|
|
),
|
|
db,
|
|
_agent(AgentRole.SECRETARY),
|
|
)
|
|
assert resp.status == "executed"
|
|
db.commit.assert_awaited_once()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_confirm_forbidden_for_secretary() -> None:
|
|
with pytest.raises(HTTPException) as exc:
|
|
await sec_route.confirm_directive(uuid4(), _db(), _agent(AgentRole.SECRETARY))
|
|
assert exc.value.status_code == HTTPStatus.FORBIDDEN
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_confirm_success(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
db = _db()
|
|
_install(monkeypatch, _FakeService())
|
|
resp = await sec_route.confirm_directive(uuid4(), db, _agent(AgentRole.CEO))
|
|
assert resp.id == _DIRECTIVE_DICT["id"]
|
|
db.commit.assert_awaited_once()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_confirm_conflict_409(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
_install(monkeypatch, _FakeService(exc=ConflictError("already decided")))
|
|
with pytest.raises(HTTPException) as exc:
|
|
await sec_route.confirm_directive(uuid4(), _db(), _agent(AgentRole.CEO))
|
|
assert exc.value.status_code == HTTPStatus.CONFLICT
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_list_forbidden_for_secretary() -> None:
|
|
with pytest.raises(HTTPException) as exc:
|
|
await sec_route.list_directives(_db(), _agent(AgentRole.SECRETARY))
|
|
assert exc.value.status_code == HTTPStatus.FORBIDDEN
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_reject_success(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
db = _db()
|
|
_install(monkeypatch, _FakeService())
|
|
resp = await sec_route.reject_directive(
|
|
uuid4(), DirectiveDecision(reason="no"), db, _agent(AgentRole.CEO)
|
|
)
|
|
assert resp.id == _DIRECTIVE_DICT["id"]
|
|
db.commit.assert_awaited_once()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_state_allows_secretary(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
_install(monkeypatch, _FakeService())
|
|
resp = await sec_route.read_state(_db(), _agent(AgentRole.SECRETARY))
|
|
assert resp.pending_pitches == []
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_search_tasks_forbidden_for_developer() -> None:
|
|
with pytest.raises(HTTPException) as exc:
|
|
await sec_route.search_tasks(_db(), _agent(AgentRole.DEVELOPER), q="greeting")
|
|
assert exc.value.status_code == HTTPStatus.FORBIDDEN
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_search_tasks_returns_compact_rows(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
"""The CEO refers to tasks by NAME in the Secretary chat — the search
|
|
resolves names to ids so a directive can target the right task."""
|
|
row = MagicMock()
|
|
row.id = uuid4()
|
|
row.title = "Rework the greeting banner"
|
|
row.status = "pending"
|
|
row.team = "backend"
|
|
row.priority = 2
|
|
task_svc = MagicMock()
|
|
task_svc.search_tasks = AsyncMock(return_value=[row])
|
|
monkeypatch.setattr("roboco.services.task.get_task_service", lambda _db: task_svc)
|
|
out = await sec_route.search_tasks(_db(), _agent(AgentRole.SECRETARY), q="greeting")
|
|
assert out == [
|
|
{
|
|
"id": str(row.id),
|
|
"title": "Rework the greeting banner",
|
|
"status": "pending",
|
|
"team": "backend",
|
|
"priority": 2,
|
|
}
|
|
]
|