mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
6b81590c55
Systematic prune per AGENTS.md test policy, one pass over every major test tree (gateway, hermes_cli, tools, agent, run_agent, plugins, cli, cron, tui_gateway, honcho/openviking, root-level): - DELETE: source-reading tests (read_text/getsource on prod files), change-detector tests (exact catalog counts, model-name snapshots, config version literals), mock-echo tests (assert a mock returns what it was told), assertion-free/trivial tests, near-duplicate parametrizations (boundaries + one representative kept), async/sync twin duplicates, cosmetic within-file variations. - KEEP (mandatory): security/redaction/approval guards, message-role alternation invariants, prompt-caching/deterministic-call-id invariants, issue-number regression tests (deduped), E2E tests. - 6 test files deleted outright (script-style/no-assert or fully redundant); conftest.py, fakes/, fixtures/ untouched. - tests/acp/conftest.py added: autouse fixture stubs the live models.dev/GitHub/Copilot/Anthropic inventory fetches that ACP server tests performed on every session create — test_server.py 147s → 3.4s, and the tests are now genuinely hermetic. - Sleep-based slowness shrunk where safe (codex_ttfb_watchdog, compression_concurrent_fork, etc.); no wall-clock assertion tightened. Verification: full hermetic suite via scripts/run_tests.sh — 2439 files, 31,130 tests passed, 0 failed, 0 flaky retries, 315s wall (baseline: 583s wall, 13,564s subprocess CPU).
246 lines
10 KiB
Python
246 lines
10 KiB
Python
"""Tests for the /codex-runtime slash-command shared logic.
|
|
|
|
These cover the pure-Python state machine; CLI and gateway handlers are
|
|
tested separately because they involve config persistence and prompt
|
|
formatting that's surface-specific."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from unittest.mock import patch
|
|
|
|
import pytest
|
|
|
|
from hermes_cli import codex_runtime_switch as crs
|
|
|
|
|
|
class TestParseArgs:
|
|
@pytest.mark.parametrize("arg,expected", [
|
|
("", None),
|
|
(" ", None),
|
|
("auto", "auto"),
|
|
("codex_app_server", "codex_app_server"),
|
|
("on", "codex_app_server"),
|
|
("off", "auto"),
|
|
("codex", "codex_app_server"),
|
|
("default", "auto"),
|
|
("hermes", "auto"),
|
|
("ENABLE", "codex_app_server"), # case-insensitive
|
|
("DiSaBlE", "auto"),
|
|
])
|
|
def test_valid_args(self, arg, expected):
|
|
value, errors = crs.parse_args(arg)
|
|
assert errors == []
|
|
assert value == expected
|
|
|
|
|
|
class TestGetCurrentRuntime:
|
|
def test_default_when_unset(self):
|
|
assert crs.get_current_runtime({}) == "auto"
|
|
assert crs.get_current_runtime({"model": {}}) == "auto"
|
|
assert crs.get_current_runtime({"model": {"openai_runtime": ""}}) == "auto"
|
|
|
|
def test_unrecognized_falls_back_to_auto(self):
|
|
assert crs.get_current_runtime(
|
|
{"model": {"openai_runtime": "garbage"}}
|
|
) == "auto"
|
|
|
|
|
|
class TestSetRuntime:
|
|
def test_creates_model_section_if_missing(self):
|
|
cfg = {}
|
|
old = crs.set_runtime(cfg, "codex_app_server")
|
|
assert old == "auto"
|
|
assert cfg["model"]["openai_runtime"] == "codex_app_server"
|
|
|
|
|
|
def test_invalid_value_raises(self):
|
|
with pytest.raises(ValueError):
|
|
crs.set_runtime({}, "garbage")
|
|
|
|
|
|
class TestApply:
|
|
def test_read_only_call_reports_state(self):
|
|
cfg = {"model": {"openai_runtime": "codex_app_server"}}
|
|
with patch.object(crs, "check_codex_binary_ok",
|
|
return_value=(True, "0.130.0")):
|
|
r = crs.apply(cfg, None)
|
|
assert r.success
|
|
assert r.new_value == "codex_app_server"
|
|
assert r.old_value == "codex_app_server"
|
|
assert "codex_app_server" in r.message
|
|
assert "0.130.0" in r.message
|
|
|
|
|
|
def test_reapply_codex_app_server_runs_migration(self):
|
|
"""Re-applying codex_app_server when already enabled must still
|
|
run the migration. Common footgun: user pre-sets
|
|
`openai_runtime: codex_app_server` in config.yaml, then runs
|
|
/codex-runtime codex_app_server expecting the migration. Without
|
|
this, the slash command short-circuits with "already set" and
|
|
~/.codex/config.toml never gets the hermes-tools MCP callback
|
|
or plugin migration — silent partial setup.
|
|
"""
|
|
cfg = {
|
|
"model": {"openai_runtime": "codex_app_server"},
|
|
"mcp_servers": {
|
|
"filesystem": {"command": "npx", "args": ["-y", "fs-server"]},
|
|
},
|
|
}
|
|
persisted = {}
|
|
|
|
def persist(c):
|
|
persisted.update(c)
|
|
|
|
with patch.object(crs, "check_codex_binary_ok",
|
|
return_value=(True, "0.130.0")), \
|
|
patch("hermes_cli.codex_runtime_plugin_migration.migrate") as mig:
|
|
mig.return_value.migrated = ["filesystem", "hermes-tools"]
|
|
mig.return_value.migrated_plugins = []
|
|
mig.return_value.plugin_query_error = None
|
|
mig.return_value.wrote_permissions_default = ":workspace"
|
|
mig.return_value.errors = []
|
|
mig.return_value.target_path = "/fake/.codex/config.toml"
|
|
r = crs.apply(cfg, "codex_app_server",
|
|
persist_callback=persist)
|
|
assert r.success
|
|
assert mig.called, "migration must run on reapply, not just first enable"
|
|
# Re-apply should signal "already set" but still announce migration ran
|
|
assert "already set" in r.message
|
|
assert "re-applying migration" in r.message
|
|
# Migration output still surfaces
|
|
assert "Migrated 1 MCP server" in r.message
|
|
assert "filesystem" in r.message
|
|
assert "Default sandbox: :workspace" in r.message
|
|
# No config write needed when value is unchanged — the persist
|
|
# callback should NOT have fired (avoids spurious config.yaml mtimes
|
|
# on every re-apply).
|
|
assert persisted == {}, (
|
|
"persist_callback fired despite no config-value change"
|
|
)
|
|
# Caller still needs a fresh session for the cached agent to pick
|
|
# up any migration-driven changes.
|
|
assert r.requires_new_session is True
|
|
|
|
def test_enable_blocked_when_codex_missing(self):
|
|
cfg = {}
|
|
with patch.object(crs, "check_codex_binary_ok",
|
|
return_value=(False, "codex not found")):
|
|
r = crs.apply(cfg, "codex_app_server")
|
|
assert r.success is False
|
|
assert "Cannot enable" in r.message
|
|
assert "npm i -g @openai/codex" in r.message
|
|
# Config NOT mutated on failure
|
|
assert cfg.get("model", {}).get("openai_runtime") in {None, ""}
|
|
|
|
def test_enable_succeeds_when_codex_present(self):
|
|
cfg = {}
|
|
persisted = {}
|
|
|
|
def persist(c):
|
|
persisted.update(c)
|
|
|
|
# Patch migrate so this test doesn't reach into the user's real
|
|
# ~/.codex/config.toml. See issue #26250 Bug C — without this patch,
|
|
# crs.apply() invokes the real migrate() which writes to
|
|
# Path.home() / ".codex" using whatever HERMES_HOME the running pytest
|
|
# session has set, leaking pytest tempdir paths into the user's
|
|
# codex config.
|
|
with patch.object(crs, "check_codex_binary_ok",
|
|
return_value=(True, "0.130.0")), \
|
|
patch("hermes_cli.codex_runtime_plugin_migration.migrate"):
|
|
r = crs.apply(cfg, "codex_app_server", persist_callback=persist)
|
|
assert r.success
|
|
assert r.new_value == "codex_app_server"
|
|
assert r.old_value == "auto"
|
|
assert r.requires_new_session is True
|
|
assert "via MCP" in r.message # hermes-tools callback message
|
|
assert cfg["model"]["openai_runtime"] == "codex_app_server"
|
|
assert persisted["model"]["openai_runtime"] == "codex_app_server"
|
|
|
|
|
|
def test_persist_callback_failure_reported(self):
|
|
cfg = {}
|
|
|
|
def persist_boom(c):
|
|
raise IOError("disk full")
|
|
|
|
with patch.object(crs, "check_codex_binary_ok",
|
|
return_value=(True, "0.130.0")):
|
|
r = crs.apply(cfg, "codex_app_server", persist_callback=persist_boom)
|
|
assert r.success is False
|
|
assert "persist failed" in r.message
|
|
assert "disk full" in r.message
|
|
|
|
def test_enable_triggers_mcp_migration(self):
|
|
"""Enabling codex_app_server should auto-migrate Hermes mcp_servers
|
|
to ~/.codex/config.toml so the spawned subprocess sees them."""
|
|
cfg = {
|
|
"mcp_servers": {
|
|
"filesystem": {"command": "npx", "args": ["-y", "fs-server"]},
|
|
}
|
|
}
|
|
|
|
with patch.object(crs, "check_codex_binary_ok",
|
|
return_value=(True, "0.130.0")), \
|
|
patch("hermes_cli.codex_runtime_plugin_migration.migrate") as mig:
|
|
mig.return_value.migrated = ["filesystem", "hermes-tools"]
|
|
mig.return_value.migrated_plugins = []
|
|
mig.return_value.plugin_query_error = None
|
|
mig.return_value.wrote_permissions_default = ":workspace"
|
|
mig.return_value.errors = []
|
|
mig.return_value.target_path = "/fake/.codex/config.toml"
|
|
r = crs.apply(cfg, "codex_app_server")
|
|
assert r.success
|
|
assert mig.called # migration was triggered
|
|
# User MCP servers are reported (excluding internal hermes-tools)
|
|
assert "Migrated 1 MCP server" in r.message
|
|
assert "filesystem" in r.message
|
|
# Permissions default surfaces
|
|
assert "Default sandbox: :workspace" in r.message
|
|
# Hermes tool callback announcement
|
|
assert "via MCP" in r.message
|
|
|
|
def test_disable_does_not_trigger_migration(self):
|
|
"""Switching back to auto must not write to ~/.codex/."""
|
|
cfg = {
|
|
"model": {"openai_runtime": "codex_app_server"},
|
|
"mcp_servers": {"x": {"command": "y"}},
|
|
}
|
|
with patch("hermes_cli.codex_runtime_plugin_migration.migrate") as mig:
|
|
r = crs.apply(cfg, "auto")
|
|
assert r.success
|
|
assert not mig.called # disabling does not migrate
|
|
|
|
def test_migration_failure_does_not_block_enable(self):
|
|
"""If MCP migration raises, the runtime change still proceeds —
|
|
users can manually re-run migration later."""
|
|
cfg = {"mcp_servers": {"x": {"command": "y"}}}
|
|
with patch.object(crs, "check_codex_binary_ok",
|
|
return_value=(True, "0.130.0")), \
|
|
patch("hermes_cli.codex_runtime_plugin_migration.migrate",
|
|
side_effect=RuntimeError("disk full")):
|
|
r = crs.apply(cfg, "codex_app_server")
|
|
assert r.success # change still applied
|
|
assert r.new_value == "codex_app_server"
|
|
assert "MCP migration skipped" in r.message
|
|
assert "disk full" in r.message
|
|
|
|
def test_binary_check_cached_within_apply(self):
|
|
"""check_codex_binary_ok is invoked at most once per apply() call.
|
|
|
|
The enable path has three sites that need the version (state report,
|
|
enable gate, success message). Without caching, a single
|
|
/codex-runtime invocation spawns `codex --version` three times.
|
|
Regression guard against a refactor that drops the cache.
|
|
"""
|
|
cfg = {}
|
|
with patch.object(crs, "check_codex_binary_ok",
|
|
return_value=(True, "0.130.0")) as bin_check, \
|
|
patch("hermes_cli.codex_runtime_plugin_migration.migrate"):
|
|
r = crs.apply(cfg, "codex_app_server")
|
|
assert r.success
|
|
assert bin_check.call_count == 1, (
|
|
f"check_codex_binary_ok was called {bin_check.call_count} time(s); "
|
|
"should be cached and called exactly once per apply()"
|
|
)
|
|
|