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>
144 lines
5.0 KiB
Python
144 lines
5.0 KiB
Python
"""The PR-gate turn cut: closure auto-submits assembled parents to the gate.
|
|
|
|
When every child of an assembled parent is terminal, the orchestrator used
|
|
to spawn the PM just to call submit_up/submit_root — a whole agent turn
|
|
whose substance (freshness rebase, integrity check, PR open) is
|
|
deterministic gate code. ``_try_auto_submit`` runs the REAL submit verb
|
|
through the internal API as the owning PM; only a gate rejection falls
|
|
back to the classic PM closure spawn. The PM's remaining turn is the one
|
|
that needs judgment: the final merge (or the revision).
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import Any
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
|
|
import pytest
|
|
from roboco.config import settings as cfg
|
|
from roboco.runtime.orchestrator import AGENT_UUIDS, AgentOrchestrator
|
|
|
|
# The commit/notes validator's minimum substantive length.
|
|
_MIN_NOTES = 20
|
|
|
|
_CELL_TASK: dict[str, Any] = {
|
|
"id": "11111111-1111-1111-1111-111111111111",
|
|
"team": "backend",
|
|
"branch_name": "feature/backend/AAAA1111",
|
|
"project_id": "22222222-2222-2222-2222-222222222222",
|
|
"assigned_to": "33333333-3333-3333-3333-333333333333",
|
|
"status": "in_progress",
|
|
}
|
|
|
|
|
|
def _orch() -> AgentOrchestrator:
|
|
orch = AgentOrchestrator.__new__(AgentOrchestrator)
|
|
orch._tick_handled_tasks = set()
|
|
orch._bg_tasks = set()
|
|
return orch
|
|
|
|
|
|
def _client(envelope: dict[str, Any]) -> MagicMock:
|
|
response = MagicMock()
|
|
response.json.return_value = envelope
|
|
client = MagicMock()
|
|
client.post = AsyncMock(return_value=response)
|
|
return client
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_cell_parent_auto_submits_as_owning_pm(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
monkeypatch.setattr(cfg, "pr_gate_auto_submit_enabled", True)
|
|
orch = _orch()
|
|
client = _client({"status": "awaiting_pr_review", "error": None})
|
|
|
|
assert await orch._try_auto_submit(client, _CELL_TASK, "be-pm") is True
|
|
|
|
(url,), kwargs = client.post.call_args
|
|
assert url == f"{orch._api_url}/v1/flow/cell_pm/submit_up"
|
|
assert kwargs["headers"]["X-Agent-ID"] == _CELL_TASK["assigned_to"]
|
|
assert kwargs["headers"]["X-Agent-Role"] == "cell_pm"
|
|
assert kwargs["json"]["task_id"] == _CELL_TASK["id"]
|
|
assert len(kwargs["json"]["notes"]) >= _MIN_NOTES
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_main_pm_root_auto_submits_submit_root(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
monkeypatch.setattr(cfg, "pr_gate_auto_submit_enabled", True)
|
|
orch = _orch()
|
|
client = _client({"status": "awaiting_pr_review", "error": None})
|
|
task = {**_CELL_TASK, "team": "main_pm"}
|
|
|
|
assert await orch._try_auto_submit(client, task, "main-pm") is True
|
|
(url,), kwargs = client.post.call_args
|
|
assert url == f"{orch._api_url}/v1/flow/main_pm/submit_root"
|
|
assert kwargs["headers"]["X-Agent-Role"] == "main_pm"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_branchless_parent_never_auto_submits(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
"""A branchless coordination parent (MegaTask umbrella) assembles no PR."""
|
|
monkeypatch.setattr(cfg, "pr_gate_auto_submit_enabled", True)
|
|
orch = _orch()
|
|
client = _client({"error": None})
|
|
task = {**_CELL_TASK, "branch_name": None}
|
|
|
|
assert await orch._try_auto_submit(client, task, "be-pm") is False
|
|
client.post.assert_not_called()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_flag_off_is_inert(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
monkeypatch.setattr(cfg, "pr_gate_auto_submit_enabled", False)
|
|
orch = _orch()
|
|
client = _client({"error": None})
|
|
|
|
assert await orch._try_auto_submit(client, _CELL_TASK, "be-pm") is False
|
|
client.post.assert_not_called()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_gate_rejection_falls_back_to_pm_spawn(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
"""A rejection envelope (e.g. integrity/freshness refusal) means the PM
|
|
turn is genuinely needed — auto-submit yields to the closure spawn."""
|
|
monkeypatch.setattr(cfg, "pr_gate_auto_submit_enabled", True)
|
|
orch = _orch()
|
|
client = _client(
|
|
{"error": "invalid_state", "message": "assembled branch behind base"}
|
|
)
|
|
|
|
assert await orch._try_auto_submit(client, _CELL_TASK, "be-pm") is False
|
|
client.post.assert_called_once()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_missing_assignment_falls_back_to_static_identity(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
monkeypatch.setattr(cfg, "pr_gate_auto_submit_enabled", True)
|
|
orch = _orch()
|
|
client = _client({"status": "awaiting_pr_review", "error": None})
|
|
task = {**_CELL_TASK, "assigned_to": None}
|
|
|
|
assert await orch._try_auto_submit(client, task, "be-pm") is True
|
|
(_, kwargs) = client.post.call_args
|
|
assert kwargs["headers"]["X-Agent-ID"] == AGENT_UUIDS["be-pm"]
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_transport_error_falls_back(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
monkeypatch.setattr(cfg, "pr_gate_auto_submit_enabled", True)
|
|
orch = _orch()
|
|
client = MagicMock()
|
|
client.post = AsyncMock(side_effect=RuntimeError("api down"))
|
|
|
|
assert await orch._try_auto_submit(client, _CELL_TASK, "be-pm") is False
|