mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
Renn F
a402de61bc
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.
112 lines
4.1 KiB
Python
112 lines
4.1 KiB
Python
"""GROK agents capture token usage/cost from their captured ``usage.json``.
|
|
|
|
A Grok agent runs the grok CLI — no SDK /usage/status server and no Claude
|
|
transcript — so finalize reads the ``usage.json`` the entrypoint / interactive
|
|
driver wrote to the per-agent data dir (mounted into the orchestrator). grok
|
|
reports a single cumulative total with no input/output split, so it folds into
|
|
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:
|
|
from pathlib import Path
|
|
|
|
|
|
def _write_usage(path: Path, total_tokens: int, cost_usd: float) -> None:
|
|
path.write_text(
|
|
json.dumps(
|
|
{"model": "grok-build", "total_tokens": total_tokens, "cost_usd": cost_usd}
|
|
),
|
|
encoding="utf-8",
|
|
)
|
|
|
|
|
|
def test_grok_usage_folds_total_into_output(
|
|
tmp_path: Path, monkeypatch: pytest.MonkeyPatch
|
|
) -> None:
|
|
usage = tmp_path / "usage.json"
|
|
_write_usage(usage, total_tokens=180, cost_usd=0.02)
|
|
orch = AgentOrchestrator.__new__(AgentOrchestrator)
|
|
monkeypatch.setattr(
|
|
orch, "_grok_usage_json", lambda _aid: json.loads(usage.read_text())
|
|
)
|
|
|
|
# The whole total folds into output (no input/output split from the CLI).
|
|
assert orch._grok_usage_tokens("be-dev-1") == (0, 180, 0, 0)
|
|
|
|
|
|
def test_grok_usage_zero_when_store_missing(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
orch = AgentOrchestrator.__new__(AgentOrchestrator)
|
|
monkeypatch.setattr(orch, "_grok_usage_json", lambda _aid: None)
|
|
assert orch._grok_usage_tokens("be-dev-1") == (0, 0, 0, 0)
|
|
|
|
|
|
def test_grok_cost_read_from_usage_json(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
captured_cost = 3.25
|
|
orch = AgentOrchestrator.__new__(AgentOrchestrator)
|
|
monkeypatch.setattr(
|
|
orch,
|
|
"_grok_usage_json",
|
|
lambda _aid: {"cost_usd": captured_cost, "total_tokens": 9},
|
|
)
|
|
assert orch._grok_cost_usd("be-dev-1") == captured_cost
|
|
monkeypatch.setattr(orch, "_grok_usage_json", lambda _aid: None)
|
|
assert orch._grok_cost_usd("be-dev-1") == 0.0
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_resolve_final_usage_routes_grok_to_usage_json(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
orch = AgentOrchestrator.__new__(AgentOrchestrator)
|
|
monkeypatch.setattr(
|
|
orch, "_grok_usage_json", lambda _aid: {"total_tokens": 12, "cost_usd": 0.01}
|
|
)
|
|
cfg = type("C", (), {"provider_type": "grok"})()
|
|
orch._instances = {"be-dev-1": AgentInstance(agent_id="be-dev-1", config=cfg)}
|
|
|
|
# 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
|