mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
Renn F
a88045aacf
Move the last Grok runtime off opencode onto xAI's official `grok` CLI, for full parity with the Claude path. The intake/secretary chat now runs per-turn headless `grok -p` invocations that resume one session id (proven live: context carries across runs), with streaming-json deltas mapped to the existing panel StreamChunk kinds — the IntakeDriver loop, message source, relay, and idle reaper are reused unchanged; only the SessionFactory differs (GrokCliSession replaces the opencode-serve session). - GrokCliSession + a pure, unit-tested streaming-json -> StreamChunk assembler (thought coalesced to one block, text streamed live, end captures the session id for -r, fenced-draft fallback, clear errors incl. rate-limit). - intake propose_draft and secretary read_company_state/read_task/submit_directive are now FastMCP servers (roboco-intake / roboco-secretary) wired into ~/.grok/config.toml, launched via `uv run --directory /app` to resolve the installed package. The secretary tools reuse the shared backend helpers. - Orchestrator: interactive spawn mounts the subscription auth + per-agent usage dir (no metered xAI key, no permission env — grok flags carry per-role perms); usage/cost now read a captured usage.json (drop the opencode.db reader, the _opencode_db_path/_grok_usage_from_opencode methods, and the cost-cap's opencode read). hosts["opencode"] -> hosts["grok_usage"]; OPENCODE_DATA_DIR -> GROK_USAGE_DATA_DIR. - Fix one-shot usage capture: `-s` does not pin the session id (grok generates its own), so the entrypoint now reads the real id back from the JSON run log and the reader uses it; usage is captured per-turn on the interactive path. - Delete the opencode layer: opencode_config/opencode_usage/opencode_session, the docker/grok/*.js plugins, the old one-shot entrypoint, and their tests. - Compose (all three files), .env.example, and stale comments updated to the grok-CLI runtime; add the SuperGrok auth mount + grok-usage dir. Gate green: ruff, mypy (296 files), xenon, tests. NAS build/verify pending.
82 lines
2.7 KiB
Python
82 lines
2.7 KiB
Python
"""GROK cost budget kill-switch: kill a live container over the cost ceiling.
|
|
|
|
The grok CLI exposes no live usage hook, so the budget kill-switch lives in the
|
|
orchestrator: it reads each live GROK container's captured cost (from its
|
|
usage.json, via ``_grok_cost_usd``) and kills + evicts it past
|
|
ROBOCO_GROK_MAX_COST_USD (also catching runaway-loop token burn). The usage.json
|
|
read is covered in the grok usage tests; here ``_grok_cost_usd`` is stubbed so the
|
|
kill DECISION is exercised deterministically.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from unittest.mock import AsyncMock
|
|
|
|
import pytest
|
|
from roboco.models.runtime import AgentInstance
|
|
from roboco.runtime.orchestrator import AgentOrchestrator, AgentState
|
|
|
|
|
|
def _grok_instance(provider_type: str = "grok") -> AgentInstance:
|
|
cfg = type("C", (), {"provider_type": provider_type, "model": "grok-build"})()
|
|
return AgentInstance(agent_id="be-dev-1", state=AgentState.ACTIVE, config=cfg)
|
|
|
|
|
|
def _orch(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
*,
|
|
cap: float,
|
|
cost: float,
|
|
provider_type: str = "grok",
|
|
) -> tuple[AgentOrchestrator, AsyncMock]:
|
|
"""A bare orchestrator with the cost reader + container removal stubbed."""
|
|
orch = AgentOrchestrator.__new__(AgentOrchestrator)
|
|
orch._grok_max_cost_usd = cap
|
|
orch._instances = {"be-dev-1": _grok_instance(provider_type)}
|
|
monkeypatch.setattr(orch, "_grok_cost_usd", lambda _agent_id: cost)
|
|
remove_mock = AsyncMock()
|
|
monkeypatch.setattr(orch, "_remove_container", remove_mock)
|
|
return orch, remove_mock
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_cost_over_cap_kills_and_evicts(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
orch, remove_mock = _orch(monkeypatch, cap=5.0, cost=7.5)
|
|
|
|
await orch._enforce_grok_cost_budget()
|
|
|
|
remove_mock.assert_awaited_once_with("roboco-agent-be-dev-1")
|
|
assert "be-dev-1" not in orch._instances
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_cost_under_cap_spares(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
orch, remove_mock = _orch(monkeypatch, cap=5.0, cost=1.0)
|
|
|
|
await orch._enforce_grok_cost_budget()
|
|
|
|
remove_mock.assert_not_awaited()
|
|
assert "be-dev-1" in orch._instances
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_cap_zero_disables_the_sweep(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
orch, remove_mock = _orch(monkeypatch, cap=0.0, cost=999.0)
|
|
|
|
await orch._enforce_grok_cost_budget()
|
|
|
|
remove_mock.assert_not_awaited()
|
|
assert "be-dev-1" in orch._instances
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_non_grok_container_is_ignored(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
orch, remove_mock = _orch(
|
|
monkeypatch, cap=5.0, cost=999.0, provider_type="anthropic"
|
|
)
|
|
|
|
await orch._enforce_grok_cost_budget()
|
|
|
|
remove_mock.assert_not_awaited()
|
|
assert "be-dev-1" in orch._instances
|