Files
roboco/tests/unit/mcp_servers/test_optimal_role_scope.py
T
cfde4369b1 Token optimization levers — claim-scoped briefing, payload caps, role-scoped optimal, notification-spawn cooldown (#292)
* feat(gateway): claim-scoped context briefing — heavy sections only on context-acquisition verbs

* feat(gateway): cap unbounded LLM-facing payloads — embedded diffs, notification bodies, handoff journal content, north star

* feat(mcp): role-scope the optimal server's tool groups; index management becomes dev/test-only

* feat(mcp): cap per-result content on kb/error/learning search, mentor sources, rag citations

* refactor(gateway): extract heavy-briefing sections + clip helper to keep xenon ranks

* feat(orchestrator): cross-tick cooldown for notification-triggered spawns

* feat(usage,orchestrator): scope spawn-waste to anthropic sessions; cap agent Bash output via settings env

* docs: claim-scoped briefing, payload caps, optimal role-scoping, notification-spawn cooldown

* test(mcp): type the mixed-item cap fixture explicitly

* fix(orchestrator): lazy-init the notification-spawn cooldown store

* fix(lifecycle): admin-override claim reconciliation + PM request_changes verb (S6 postmortem B3+B4)

B3 — admin_set_status now reconciles claim ownership when leaving BLOCKED:
review/queue targets clear claimed_by/claimed_at/active_claimant_id and
consume the pre-block snapshot (a stale escalation claim was stranding the
next claimant: give_me_work handed the task out while note() bounced
not_authorized — the live b8fe0494 wedge). The pending/in_progress restore
path also syncs active_claimant_id, and a REST PATCH unassign releases the
claim with it.

B4 — new PM verb request_changes: awaiting_pm_review -> needs_revision with
concrete issues. The PM previously had no reject at merge review (only
complete/escalate), so an AC/scope violation looped i_am_blocked->escalate
4x live. Full vertical: lifecycle transition + ActionSpec + IntentSpec,
TaskService.request_changes (routes like a QA fail — original dev for a
leaf, revision PM for assembled; issues appended to dev_notes), verb-runner
compose, choreographer verb (spec gate + non-empty issues + soup check +
a2a delivery of the reject reason), HTTP routes on both PM flows, MCP tool,
journal:decision tracing, PM prompts, regenerated lifecycle artifacts.

* fix(panel): stop scorecard fetches for fallback-roster placeholder ids

useAgents() serves the static AGENT_ROSTER (ids "1".."22") while agent
definitions load; the Scorecards tab fetched a member scorecard per row
immediately, firing 22 guaranteed-422 requests per refetch cycle. Through
the browser's per-origin connection limit those queued every metrics-page
query behind them (~10s of skeletons on every tab). Gate the fetch on a
real member id (agent UUID or the "ceo" alias).

* Upgraded uv.lock

* fix(sequencing): declared deps become real edges + full loop-breaker coverage + assembled-branch freshness (S6 postmortem B1/B2/B6 + breaker)

B1a — code delegations REQUIRE a collision surface: new TASK_AT_DELEGATE
completeness spec (conditional FieldRequirement, when=('task_type','code'))
enforced at the gateway delegate gate. A no-surface code sibling is
'parallel to everything' by analyzer design, which is how two devs ran the
CEO's explicitly-ordered work out of order (f3e1afc5: seq#1 started before
seq#0, zero dependency edges). PM prompts updated; REST/manual creation
(TASK_AT_CREATE) unchanged.

B1b — the CEO's declared 'Depends on' lists become real edges: DraftSurface
gains declared_depends_on; SequencingService.analyze unions declared edges
(validated: self/out-of-range rejected) with the derived collision rules,
cycle-checked by the existing toposort. confirm_live_batch/preview_batch
map each draft's depends_on through (string indices coerced); intake tool
doc + prompter role prompt instruct verbatim copying. The live S6 root got
1 of its 3 declared in-batch edges and started alongside still-running R3.

Breaker coverage — the progress-aware respawn circuit breaker
(_pm_respawn_should_gate: strike counting, status-advance reset,
tracing-gap budget, DB durability, one-shot CEO notification) was consulted
by only 3 spawn paths; the doc/QA/dev/PR-review/PR-gate/revision/board
paths spawned unguarded at fixed cadence (the 26-respawn fe-doc loop,
~$7.20). Now consulted at every task-keyed spawn site (14 total).

B2 — assembled-branch freshness: submit_up/submit_root auto-sync the
assembled branch when it has fallen behind its base (children are terminal
at submit time, so the rebase is safe; master is never written). A rebase
conflict is a hard reject naming the files instead of a blind re-review —
kills the needs_revision↔awaiting_pr_review ping-pong of re-submitting a
stale head. Leaf i_am_done already had the behind-base gate; claim-time
fetch-fresh cut already existed.

B6 — documenter revision-pass loop: the awaiting_documentation bail
rejections (i_am_blocked/unclaim) now name the actual exit (i_documented
re-affirm) and the documenter prompt gets an explicit revision-pass rule.

* fix(orchestration): assembly-integrity gate + dispatcher heartbeat (incidents #11, #1)

Assembly integrity — submit_up/submit_root refuse when a completed child's
commits are not patch-present in the assembled branch (git cherry —
rebase-safe; branch pruned after merge or any git error fails open). Live
incident #11: a completed revert subtask's merge was lost from the cell
branch and the review gate re-flagged the exact violation the revert fixed,
spawning another revision cycle.

Dispatcher heartbeat — a dispatcher.alive audit row every 5 minutes from
the dispatch loop. The 2026-07-01 outage was 4h25m of fleet-wide silence
with no way to distinguish 'loop dead' from 'no work'; the loop's stdout
died with the container while audit_log survives. CHANGELOG for tonight's
full sweep included.

* style: ruff format for the orchestration sweep

* refactor(gateway): fold the assembled-submit guards + trim complexity under the xenon gate

_assembled_submit_guards combines the #11 integrity check and B2 freshen for
submit_up/submit_root; lifecycle's invalid-source remediate and git's
per-child cherry probe extracted into helpers. Test harnesses built via
__new__ stub the respawn tracker (the breaker now runs on their paths).

---------

Co-authored-by: Renn F <rennf93@users.noreply.github.com>
2026-07-02 05:46:01 +02:00

100 lines
3.5 KiB
Python

"""Optimal MCP server registers role-scoped tool groups.
Every registered schema rides in each turn's context, so a role carries only
the groups its duties use; unknown roles fail open to the full set (minus the
destructive index-management group, which is dev/test-only).
"""
from __future__ import annotations
from typing import Any
import pytest
from roboco.mcp.optimal_server import (
_RESULT_CONTENT_CAP,
_cap_result_content,
create_optimal_mcp_server,
)
async def _tool_names(role: str, monkeypatch: pytest.MonkeyPatch) -> set[str]:
monkeypatch.delenv("ROBOCO_ALLOW_FULL_TOOLSET", raising=False)
if role:
monkeypatch.setenv("ROBOCO_AGENT_ROLE", role)
else:
monkeypatch.delenv("ROBOCO_AGENT_ROLE", raising=False)
server = create_optimal_mcp_server("00000000-0000-0000-0000-000000000042")
return {t.name for t in await server.list_tools()}
@pytest.mark.asyncio
async def test_developer_scope(monkeypatch: pytest.MonkeyPatch) -> None:
names = await _tool_names("developer", monkeypatch)
# Universal + dev-duty groups present.
assert "roboco_kb_search" in names
assert "roboco_ask_mentor" in names
assert "roboco_search_error" in names
assert "roboco_review_code" in names
# PM/board decision tools, indexing and destructive admin absent.
assert "roboco_record_decision" not in names
assert "roboco_kb_index_code" not in names
assert "roboco_reindex_all" not in names
assert "roboco_clear_index" not in names
@pytest.mark.asyncio
async def test_pm_scope_carries_decisions_not_error_tools(
monkeypatch: pytest.MonkeyPatch,
) -> None:
names = await _tool_names("cell_pm", monkeypatch)
assert "roboco_record_decision" in names
assert "roboco_search_error" not in names
assert "roboco_review_code" not in names
@pytest.mark.asyncio
async def test_documenter_carries_indexing(monkeypatch: pytest.MonkeyPatch) -> None:
names = await _tool_names("documenter", monkeypatch)
assert "roboco_kb_index_docs" in names
assert "roboco_get_standards" in names
assert "roboco_record_decision" not in names
@pytest.mark.asyncio
async def test_unknown_role_fails_open_except_admin(
monkeypatch: pytest.MonkeyPatch,
) -> None:
names = await _tool_names("", monkeypatch)
assert "roboco_search_error" in names
assert "roboco_record_decision" in names
# Destructive index management never registers without the escape hatch.
assert "roboco_reindex_all" not in names
_ITEM_LIMIT = 2
def test_cap_result_content_caps_text_and_count() -> None:
items: list[Any] = [
{"content": "x" * (_RESULT_CONTENT_CAP + 200), "source": "a"},
{"content": "short", "source": "b"},
"bare-string-item",
]
capped = _cap_result_content(items, limit=_ITEM_LIMIT)
assert len(capped) == _ITEM_LIMIT
assert len(capped[0]["content"]) == _RESULT_CONTENT_CAP + 1 # + ellipsis
assert capped[0]["content"].endswith("…")
assert capped[1]["content"] == "short"
# Original items are not mutated.
assert len(items[0]["content"]) == _RESULT_CONTENT_CAP + 200
@pytest.mark.asyncio
async def test_full_toolset_escape_hatch(monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.setenv("ROBOCO_AGENT_ROLE", "developer")
monkeypatch.setenv("ROBOCO_ALLOW_FULL_TOOLSET", "1")
server = create_optimal_mcp_server("00000000-0000-0000-0000-000000000042")
names = {t.name for t in await server.list_tools()}
assert "roboco_reindex_all" in names
assert "roboco_record_decision" in names