mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
fix(grok): address adversarial-review findings across the grok-CLI conversion
A 7-dimension adversarial review (find -> independently refute) surfaced 14 real issues; fixed each: Runtime bugs - GrokCliSession.send drained stdout fully BEFORE stderr — a >64KB stderr burst would deadlock the turn forever (spinner never clears). Drain stderr concurrently, and add a per-turn watchdog (ROBOCO_GROK_TURN_TIMEOUT_SECONDS, default 600s) that kills a wedged process and emits error+turn_end. - Crash-restarted grok agents launched `grok -p ""` (empty prompt) — Claude gets a scan-for-work fallback. Default the prompt in _spawn_container so every dedicated provider gets it too. - _grok_usage_json read /data/grok-usage unconditionally while its writers branch compose-vs-local, so a local-mode agent finalized at $0 and the cost-cap was inert. Single-source the path in a new _grok_usage_dir helper (read == write). - GrokCliSession secretary role fell through to "unknown" (get_agent_role returns a truthy sentinel, never None), defeating the ROBOCO_AGENT_ROLE fallback. Parity / hardening - --deny set was missing `git tag -d` / `git reflog delete` that the Claude bash-guard blocks — added them (the "same set" claim is now true). - Interactive mains now install the bash-guard hook too (defense-in-depth). - Compose: collapse the GROK_AUTH_DIR / ROBOCO_HOST_GROK_DIR auth-mount pair into one canonical var so a partial override can't silently break agent auth. Docs / comments - Panel routing card + architecture security doc no longer say Grok runs on the deleted opencode runtime; orchestrator comments point at the renamed entrypoint. Tests - Cover the interactive _render_grok_config MCP wiring (ModuleNotFound guard + secretary HMAC env), the cost-cap kill-failure + interactive relay-close paths, the local-mode usage read, the role fallback, the turn timeout, and the new git denies. (#13 — a separate grok "Write" tool — investigated: grok's only built-in file-mutation tool is search_replace, already removed; no gap.) Gate green: ruff, mypy, xenon, tests.
This commit is contained in:
@@ -14,12 +14,18 @@ from unittest.mock import AsyncMock
|
||||
|
||||
import pytest
|
||||
from roboco.models.runtime import AgentInstance
|
||||
from roboco.runtime.orchestrator import AgentOrchestrator, AgentState
|
||||
from roboco.runtime.orchestrator import (
|
||||
INTAKE_AGENT_ID,
|
||||
AgentOrchestrator,
|
||||
AgentState,
|
||||
)
|
||||
|
||||
|
||||
def _grok_instance(provider_type: str = "grok") -> AgentInstance:
|
||||
def _grok_instance(
|
||||
provider_type: str = "grok", agent_id: str = "be-dev-1"
|
||||
) -> AgentInstance:
|
||||
cfg = type("C", (), {"provider_type": provider_type, "model": "grok-build"})()
|
||||
return AgentInstance(agent_id="be-dev-1", state=AgentState.ACTIVE, config=cfg)
|
||||
return AgentInstance(agent_id=agent_id, state=AgentState.ACTIVE, config=cfg)
|
||||
|
||||
|
||||
def _orch(
|
||||
@@ -28,11 +34,12 @@ def _orch(
|
||||
cap: float,
|
||||
cost: float,
|
||||
provider_type: str = "grok",
|
||||
agent_id: str = "be-dev-1",
|
||||
) -> 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)}
|
||||
orch._instances = {agent_id: _grok_instance(provider_type, agent_id)}
|
||||
monkeypatch.setattr(orch, "_grok_cost_usd", lambda _agent_id: cost)
|
||||
remove_mock = AsyncMock()
|
||||
monkeypatch.setattr(orch, "_remove_container", remove_mock)
|
||||
@@ -79,3 +86,42 @@ async def test_non_grok_container_is_ignored(monkeypatch: pytest.MonkeyPatch) ->
|
||||
|
||||
remove_mock.assert_not_awaited()
|
||||
assert "be-dev-1" in orch._instances
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_kill_failure_keeps_instance_for_retry(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
# If `docker rm` raises, the over-budget container must STAY registered so the
|
||||
# sweep retries next tick (the except `continue` resilience contract).
|
||||
orch, remove_mock = _orch(monkeypatch, cap=5.0, cost=7.5)
|
||||
remove_mock.side_effect = RuntimeError("docker rm failed")
|
||||
|
||||
await orch._enforce_grok_cost_budget()
|
||||
|
||||
remove_mock.assert_awaited_once()
|
||||
assert "be-dev-1" in orch._instances # not evicted -> retried next tick
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_interactive_kill_closes_the_relay(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
# Killing an interactive (intake/secretary) container over budget must close
|
||||
# its panel relay with a reason so the chat ends cleanly, not a frozen SSE.
|
||||
orch, remove_mock = _orch(monkeypatch, cap=5.0, cost=9.0, agent_id=INTAKE_AGENT_ID)
|
||||
registry = type("R", (), {"calls": []})()
|
||||
registry.close_by_agent = lambda agent_id, error: registry.calls.append(
|
||||
(agent_id, error)
|
||||
)
|
||||
monkeypatch.setattr(
|
||||
"roboco.services.prompter_live.get_live_registry", lambda: registry
|
||||
)
|
||||
|
||||
await orch._enforce_grok_cost_budget()
|
||||
|
||||
remove_mock.assert_awaited_once_with(f"roboco-agent-{INTAKE_AGENT_ID}")
|
||||
assert INTAKE_AGENT_ID not in orch._instances
|
||||
assert len(registry.calls) == 1
|
||||
assert registry.calls[0][0] == INTAKE_AGENT_ID
|
||||
assert "cost" in registry.calls[0][1].lower()
|
||||
|
||||
@@ -10,10 +10,12 @@ output (it bills at the output rate).
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import tempfile
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import pytest
|
||||
from roboco.models.runtime import AgentInstance
|
||||
from roboco.runtime import orchestrator as orch_mod
|
||||
from roboco.runtime.orchestrator import AgentOrchestrator
|
||||
|
||||
if TYPE_CHECKING:
|
||||
@@ -75,3 +77,35 @@ async def test_resolve_final_usage_routes_grok_to_usage_json(
|
||||
|
||||
# No SDK fetch / transcript read for GROK — usage comes from usage.json.
|
||||
assert await orch._resolve_final_token_usage("be-dev-1") == (0, 12, 0, 0)
|
||||
|
||||
|
||||
def test_grok_usage_dir_branches_compose_vs_local(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
monkeypatch.setattr(orch_mod, "PROJECT_HOST_PATH", "")
|
||||
local = AgentOrchestrator._grok_usage_dir("be-dev-1")
|
||||
assert "roboco-grok-usage" in str(local)
|
||||
assert local.name == "be-dev-1"
|
||||
|
||||
monkeypatch.setattr(orch_mod, "PROJECT_HOST_PATH", "/volume1/roboco")
|
||||
monkeypatch.setattr(orch_mod, "GROK_USAGE_DATA_DIR", "/data/grok-usage")
|
||||
assert str(AgentOrchestrator._grok_usage_dir("be-dev-1")) == (
|
||||
"/data/grok-usage/be-dev-1"
|
||||
)
|
||||
|
||||
|
||||
def test_grok_usage_json_reads_the_real_local_dir(
|
||||
tmp_path: Path, monkeypatch: pytest.MonkeyPatch
|
||||
) -> None:
|
||||
# The un-mocked read path must find usage.json in the SAME branched dir the
|
||||
# writer mounts (the local-mode fix: read side mirrors the write side).
|
||||
monkeypatch.setattr(orch_mod, "PROJECT_HOST_PATH", "")
|
||||
monkeypatch.setattr(tempfile, "gettempdir", lambda: str(tmp_path))
|
||||
udir = tmp_path / "roboco-grok-usage" / "be-dev-1"
|
||||
udir.mkdir(parents=True)
|
||||
(udir / "usage.json").write_text(
|
||||
json.dumps({"total_tokens": 55, "cost_usd": 0.1}), encoding="utf-8"
|
||||
)
|
||||
orch = AgentOrchestrator.__new__(AgentOrchestrator)
|
||||
assert orch._grok_usage_tokens("be-dev-1") == (0, 55, 0, 0)
|
||||
assert orch._grok_cost_usd("be-dev-1") == 0.1 # noqa: PLR2004
|
||||
|
||||
Reference in New Issue
Block a user