chore(board): revive dormant board wiring — research key, pitch flow, auditor playbooks (#684)

* chore(compose): pass research key/provider + provisioning token/org through to the orchestrator

ROBOCO_RESEARCH_API_KEY / ROBOCO_RESEARCH_PROVIDER and ROBOCO_PROVISIONING_TOKEN /
ROBOCO_PROVISIONING_ORG were absent from every compose environment stanza, so .env
values never reached the container: research silently ran on the NullProvider
(empty results forever) and any approved pitch died on ProvisioningDisabledError.
.env.example also falsely claimed the provisioning creds are panel-managed.

* feat(board): pitch CEO notification + auditor playbook-draft surfacing

A proposed pitch now nudges the CEO (APPROVAL notification + Telegram link to the
Pitches tab, best-effort — a send failure never fails the verb). auditor_triage
surfaces the oldest pending playbook draft once anomalies are clear — the curation
verbs were granted but nothing ever pointed the Auditor at the review queue; the
scheduled audit prompt names the discovery path.

* docs(prompts): pitch doctrine section + auditor reply-only-dm drift fix

board.md never mentioned the pitch verb, so no board agent ever had a reason to
call it — it gets a dedicated section mirroring the roadmap/spotlight ones, plus
a roadmap-exploration escape hatch (needs-its-own-repo ideas pitch instead).
product-owner.md gains its missing propose_roadmap + pitch entries. The flat
'Auditor has no dm' claims are corrected to the real grant: never initiates,
reply-only in a CEO-opened thread. Doctrine guarded by a prompt-content test.

---------

Co-authored-by: Renn F <rennf93@users.noreply.github.com>
This commit is contained in:
Renzo F
2026-07-24 14:41:14 +02:00
committed by GitHub
co-authored by Renn F
parent 71f5426e40
commit 21910d75ea
15 changed files with 270 additions and 23 deletions
@@ -0,0 +1,53 @@
"""Board pitch doctrine + the Auditor dm nuance are actually in the prose.
Guards two prompt-drift classes: the `pitch` verb had no doctrine section
anywhere (no board agent ever had a reason to call it), and board.md /
auditor.md both flatly claimed the Auditor has NO `dm` when role_config.py
grants it a reply-only, CEO-thread-only `dm`/`read_a2a`.
"""
from __future__ import annotations
from roboco.agents.factories._base import _get_prompts_base_path, _load_layer
_PROMPTS = _get_prompts_base_path()
def test_board_role_prompt_documents_pitch() -> None:
text = _load_layer(_PROMPTS / "roles" / "board.md")
assert text, "board.md is missing or empty"
assert "pitch(" in text
assert "## Pitching a new product" in text
def test_product_owner_identity_lists_propose_roadmap_and_pitch() -> None:
text = _load_layer(_PROMPTS / "identities" / "product-owner.md")
assert text, "product-owner.md is missing or empty"
assert "propose_roadmap" in text
assert "pitch(" in text
def test_head_marketing_identity_lists_pitch() -> None:
text = _load_layer(_PROMPTS / "identities" / "head-marketing.md")
assert text, "head-marketing.md is missing or empty"
assert "pitch(" in text
def test_board_role_prompt_no_longer_claims_flat_no_dm_for_auditor() -> None:
text = _load_layer(_PROMPTS / "roles" / "board.md")
assert "The Auditor is silent: read-only, no `dm`" not in text
assert "You have no `dm`/`escalate_*`" not in text
assert "reply in-thread when the CEO opens a DM with it" in text
def test_auditor_identity_no_longer_claims_flat_no_dm() -> None:
text = _load_layer(_PROMPTS / "identities" / "auditor.md")
assert text, "auditor.md is missing or empty"
assert "You have **no** `dm` verb" not in text
assert "only to read and reply in-thread when the CEO opens a DM" in text
def test_auditor_identity_documents_playbook_discovery_via_triage() -> None:
text = _load_layer(_PROMPTS / "identities" / "auditor.md")
assert "pending playbook draft" in text
assert "triage()" in text
@@ -7,7 +7,7 @@ from __future__ import annotations
from datetime import UTC, datetime
from typing import Any
from unittest.mock import AsyncMock, MagicMock
from unittest.mock import AsyncMock, MagicMock, patch
from uuid import uuid4
import pytest
@@ -76,13 +76,44 @@ async def test_auditor_triage_returns_idle_when_no_anomalies() -> None:
deps = _make_deps(task=task_svc)
c = Choreographer(deps)
env = await c.auditor_triage(auditor_id)
playbook_svc = AsyncMock()
playbook_svc.list_drafts.return_value = []
with patch(
"roboco.services.playbook.get_playbook_service", return_value=playbook_svc
):
env = await c.auditor_triage(auditor_id)
body = env.as_dict()
assert body["status"] == "idle"
assert body["task_id"] is None
assert "i_am_idle" in body["next"]
@pytest.mark.asyncio
async def test_auditor_triage_surfaces_playbook_draft_when_no_anomalies() -> None:
"""No anomalies, but a pending playbook draft — surfaced instead of idle
so the Auditor's approve_playbook/reject_playbook duty is discoverable."""
auditor_id = uuid4()
task_svc = AsyncMock()
task_svc.agent_for.return_value = MagicMock(role="auditor", team="board")
task_svc.list_long_running_blocked.return_value = []
deps = _make_deps(task=task_svc)
c = Choreographer(deps)
draft = MagicMock(id=uuid4(), title="Rebase onto a live rung before cutting")
playbook_svc = AsyncMock()
playbook_svc.list_drafts.return_value = [draft]
with patch(
"roboco.services.playbook.get_playbook_service", return_value=playbook_svc
):
env = await c.auditor_triage(auditor_id)
body = env.as_dict()
assert body["status"] == "draft"
assert body["task_id"] is None
assert str(draft.id)[:8] in body["next"]
assert "approve_playbook" in body["next"]
assert "reject_playbook" in body["next"]
@pytest.mark.asyncio
async def test_auditor_triage_only_first_anomaly_surfaces() -> None:
"""Auditor gets the most-stale blocked task; others wait until next call."""
@@ -2,6 +2,7 @@
from __future__ import annotations
from typing import Any
from unittest.mock import AsyncMock, MagicMock
from uuid import uuid4
@@ -9,7 +10,7 @@ import pytest
from roboco.services.gateway.content_actions import ContentActions, ContentActionsDeps
def _actions(role: str) -> ContentActions:
def _actions(role: str, *, notification_delivery: Any = None) -> ContentActions:
task = MagicMock()
agent = MagicMock()
agent.role = role
@@ -22,6 +23,7 @@ def _actions(role: str) -> ContentActions:
journal=MagicMock(),
workspace=MagicMock(),
notifications=MagicMock(),
notification_delivery=notification_delivery,
)
return ContentActions(deps)
@@ -75,3 +77,54 @@ async def test_pitch_rejects_non_cell_target() -> None:
target_cells=["board"],
)
assert env.error == "invalid_state"
@pytest.mark.asyncio
async def test_pitch_notifies_ceo_on_success(monkeypatch: pytest.MonkeyPatch) -> None:
"""A successful pitch nudges the CEO via the notification-delivery seam."""
created = MagicMock()
created.id = uuid4()
svc = MagicMock()
svc.create = AsyncMock(return_value=created)
monkeypatch.setattr("roboco.services.pitch.get_pitch_service", lambda _s: svc)
notification_delivery = AsyncMock()
env = await _actions(
"product_owner", notification_delivery=notification_delivery
).pitch(
agent_id=uuid4(),
title="Widget",
slug="widget",
problem="people need widgets",
proposed_solution="build a widget service",
target_cells=["backend", "frontend"],
)
assert env.error is None
assert env.status == "proposed"
notification_delivery.notify_ceo_of_pitch.assert_awaited_once_with(pitch=created)
@pytest.mark.asyncio
async def test_pitch_survives_notification_failure(
monkeypatch: pytest.MonkeyPatch,
) -> None:
"""A CEO-notification failure never fails pitch() — best-effort only."""
created = MagicMock()
created.id = uuid4()
svc = MagicMock()
svc.create = AsyncMock(return_value=created)
monkeypatch.setattr("roboco.services.pitch.get_pitch_service", lambda _s: svc)
notification_delivery = AsyncMock()
notification_delivery.notify_ceo_of_pitch.side_effect = RuntimeError("db down")
env = await _actions(
"product_owner", notification_delivery=notification_delivery
).pitch(
agent_id=uuid4(),
title="Widget",
slug="widget",
problem="people need widgets",
proposed_solution="build a widget service",
target_cells=["backend", "frontend"],
)
assert env.error is None
assert env.status == "proposed"
notification_delivery.notify_ceo_of_pitch.assert_awaited_once()