Files
bot-bottle/tests/unit/test_contrib_codex_provider.py
T
didericis 7118480d0a
lint / lint (push) Successful in 2m39s
test / unit (pull_request) Successful in 1m37s
test / integration (pull_request) Successful in 29s
test / coverage (pull_request) Successful in 1m44s
fix(codex): register supervise MCP via config.toml http_headers, not mcp add --header
The Codex CLI has no `codex mcp add --header` flag (verified against
0.144.5 and the codex-rs `AddMcpStreamableHttpArgs` surface: only
`--url`, `--bearer-token-env-var`, `--oauth-*`, `--env`). The old call
therefore exited nonzero on every codex bottle; provisioning only
warned and continued, so supervise was silently unregistered — and
under mandatory (source_ip, token) attribution the suggested manual
recovery (`codex mcp add supervise --url ...`, no token) could not
restore access either.

Write the `[mcp_servers.supervise]` streamable-HTTP entry directly into
`~/.codex/config.toml` instead, delivering the identity token via the
Codex-supported `http_headers` key (the only way to attach a static
request header to an HTTP MCP server). Registration failure is now
FATAL when supervise is enabled, rather than a warning.

Test validates the generated entry against the real Codex config
surface: it must parse as TOML into a streamable-HTTP server carrying
the token as `http_headers["x-bot-bottle-identity"]`, and must use only
keys accepted by `RawMcpServerConfig` (config.toml is
`deny_unknown_fields`). Also covers custom `CODEX_HOME`, the no-token
case, and the now-fatal failure path.

Refs: PR #354 review (codex P1).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WBMWTEtQdJ4W5UrWuLHCck
2026-07-16 17:42:36 -04:00

427 lines
16 KiB
Python

"""Unit: CodexAgentProvider provisioning (PRD 0050, contrib/codex).
The Codex provider owns its own skills / prompt / provision /
supervise-mcp end-to-end — symmetric with the claude provider but
not sharing a helper module, since codex's apply steps include
the dummy-auth dance and a `codex login status` verify that have
no claude equivalent."""
from __future__ import annotations
import unittest
import tempfile
from pathlib import Path
from unittest.mock import MagicMock, patch
from bot_bottle.agent_provider import (
AgentProvisionCommand,
AgentProvisionDir,
AgentProvisionFile,
AgentProvisionPlan,
)
from bot_bottle.backend import Bottle, BottleSpec, ExecResult
from bot_bottle.backend.docker.bottle_plan import DockerBottlePlan
from bot_bottle.contrib.codex.agent_provider import CodexAgentProvider
from bot_bottle.egress import EgressPlan
from bot_bottle.git_gate import GitGatePlan
from bot_bottle.manifest import ManifestIndex
from bot_bottle.supervise import SupervisePlan
_URL = "http://supervise:9100/"
_CODEX_DOCKERFILE = (
Path(__file__).resolve().parents[2] / "bot_bottle/contrib/codex/Dockerfile"
)
def _make_bottle(exec_result: ExecResult | None = None) -> MagicMock:
bottle = MagicMock(spec=Bottle)
bottle.name = "bot-bottle-demo-abc12"
bottle.exec.return_value = (
exec_result if exec_result is not None
else ExecResult(returncode=0, stdout="", stderr="")
)
return bottle
def _exec_scripts(bottle: MagicMock) -> list[str]:
return [c.args[0] for c in bottle.exec.call_args_list]
def _plan(
*,
agent_prompt: str = "",
skills: list[str] | None = None,
agent_provision: AgentProvisionPlan | None = None,
supervise: bool = False,
identity_token: str = "",
) -> DockerBottlePlan:
bottle_json: dict = {"agent_provider": {"template": "codex"}} # type: ignore
if supervise:
bottle_json["supervise"] = True
index = ManifestIndex.from_json_obj({
"bottles": {"dev": bottle_json},
"agents": {
"demo": {
"skills": list(skills or []),
"prompt": agent_prompt,
"bottle": "dev",
},
},
})
manifest = index.load_for_agent("demo")
spec = BottleSpec(
manifest=index, agent_name="demo",
copy_cwd=False, user_cwd="/tmp/x",
)
supervise_plan = None
if supervise:
supervise_plan = SupervisePlan(
slug="demo-abc12",
db_path=Path("/tmp/bot-bottle.db"),
)
return DockerBottlePlan(
spec=spec,
manifest=manifest,
stage_dir=Path("/tmp/stage"),
slug="demo-abc12",
forwarded_env={},
git_gate_plan=GitGatePlan(
slug="demo-abc12",
entrypoint_script=Path("/tmp/git-gate-entrypoint.sh"),
hook_script=Path("/tmp/git-gate-hook"),
access_hook_script=Path("/tmp/git-gate-access-hook"),
upstreams=(),
),
egress_plan=EgressPlan(
slug="demo-abc12",
routes_path=Path("/tmp/routes.yaml"),
routes=(),
token_env_map={},
),
supervise_plan=supervise_plan,
use_runsc=False,
identity_token=identity_token,
agent_provision=agent_provision or AgentProvisionPlan(
template="codex", command="codex", prompt_mode="read_prompt_file",
image="bot-bottle-codex:latest", dockerfile="",
guest_home="/home/node",
instance_name="bot-bottle-demo-abc12",
prompt_file=Path("/tmp/state/demo-abc12/agent/prompt.txt"),
guest_env={},
),
)
class TestCodexProvisionPrompt(unittest.TestCase):
def test_cp_uses_bottle_cp_in_and_chowns(self):
bottle = _make_bottle()
r = CodexAgentProvider().provision_prompt(
_plan(agent_prompt="hello"), bottle,
)
self.assertEqual("/home/node/.bot-bottle-prompt.txt", r)
bottle.cp_in.assert_called_once_with(
"/tmp/state/demo-abc12/agent/prompt.txt",
"/home/node/.bot-bottle-prompt.txt",
)
scripts = _exec_scripts(bottle)
self.assertTrue(
any("chown node:node" in s
and "/home/node/.bot-bottle-prompt.txt" in s
for s in scripts)
)
def test_returns_none_when_agent_has_no_prompt(self):
bottle = _make_bottle()
r = CodexAgentProvider().provision_prompt(_plan(agent_prompt=""), bottle)
self.assertIsNone(r)
bottle.cp_in.assert_called_once()
def test_returns_path_when_provider_prompt_exists(self):
bottle = _make_bottle()
provision = AgentProvisionPlan(
template="codex", command="codex",
prompt_mode="read_prompt_file",
image="", dockerfile="", guest_home="/home/node",
instance_name="bot-bottle-demo-abc12",
prompt_file=Path("/tmp/prompt.txt"),
guest_env={},
has_prompt=True,
)
r = CodexAgentProvider().provision_prompt(
_plan(agent_prompt="", agent_provision=provision), bottle,
)
self.assertEqual("/home/node/.bot-bottle-prompt.txt", r)
def test_writes_tui_settings_into_codex_config(self):
with tempfile.TemporaryDirectory(prefix="bb-codex-ui.") as tmp:
state_dir = Path(tmp)
prompt_file = state_dir / "prompt.txt"
prompt_file.write_text("Existing instructions.\n")
plan = CodexAgentProvider().provision_plan(
dockerfile="",
state_dir=state_dir,
instance_name="bot-bottle-demo-abc12",
prompt_file=prompt_file,
label="research-ui",
color="cyan",
)
config = (state_dir / "codex-config.toml").read_text()
prompt_text = prompt_file.read_text()
self.assertTrue(plan.has_prompt)
self.assertEqual("Existing instructions.\n", prompt_text)
self.assertIn("[tui]", config)
self.assertIn('status_line = ["model-with-reasoning"]', config)
self.assertIn('terminal_title = ["spinner", "project"]', config)
self.assertIn('theme = "ansi"', config)
class TestCodexProvisionSkills(unittest.TestCase):
def test_noop_when_agent_has_no_skills(self):
bottle = _make_bottle()
CodexAgentProvider().provision_skills(_plan(skills=[]), bottle)
bottle.cp_in.assert_not_called()
bottle.exec.assert_not_called()
def test_mkdir_plus_cp_per_skill(self):
bottle = _make_bottle()
with patch(
"bot_bottle.backend.util.host_skill_dir",
side_effect=lambda n: f"/host/skills/{n}", # type: ignore
), patch(
"bot_bottle.contrib.codex.agent_provider.os.path.isdir",
return_value=True,
):
CodexAgentProvider().provision_skills(
_plan(skills=["init-prd"]), bottle,
)
scripts = _exec_scripts(bottle)
self.assertTrue(
any("mkdir -p" in s and "/home/node/.claude/skills" in s
for s in scripts)
)
bottle.cp_in.assert_called_once()
self.assertEqual(
"/home/node/.claude/skills/init-prd/",
bottle.cp_in.call_args.args[1],
)
class TestCodexProvision(unittest.TestCase):
"""Codex's declarative provision step: ~/.codex/ dir + config.toml
+ (optional) dummy-auth.json + `codex login status` verify."""
def test_creates_dir_and_copies_config(self):
provision = AgentProvisionPlan(
template="codex", command="codex",
prompt_mode="read_prompt_file",
image="", dockerfile="", guest_home="/home/node",
instance_name="bot-bottle-demo-abc12",
prompt_file=Path("/tmp/prompt.txt"),
guest_env={},
dirs=(AgentProvisionDir("/home/node/.codex"),),
files=(AgentProvisionFile(
Path("/tmp/codex-config.toml"),
"/home/node/.codex/config.toml",
),),
)
bottle = _make_bottle()
CodexAgentProvider().provision(
_plan(agent_provision=provision), bottle,
)
bottle.cp_in.assert_called_once_with(
"/tmp/codex-config.toml",
"/home/node/.codex/config.toml",
)
scripts = _exec_scripts(bottle)
self.assertTrue(any("mkdir -p" in s and "/home/node/.codex" in s for s in scripts))
self.assertTrue(any("chown" in s and "/home/node/.codex/config.toml" in s for s in scripts))
self.assertTrue(any("chmod" in s and "/home/node/.codex/config.toml" in s for s in scripts))
def test_runs_pre_copy_then_verify(self):
provision = AgentProvisionPlan(
template="codex", command="codex",
prompt_mode="read_prompt_file",
image="", dockerfile="", guest_home="/home/node",
instance_name="bot-bottle-demo-abc12",
prompt_file=Path("/tmp/prompt.txt"),
guest_env={},
pre_copy=(AgentProvisionCommand(
("find", "/home/node/.codex", "-name", "*.sqlite", "-delete"),
"could not reset runtime db files",
),),
verify=(AgentProvisionCommand(
("runuser", "-u", "node", "--", "codex", "login", "status"),
"codex rejected the dummy auth",
),),
)
bottle = _make_bottle()
CodexAgentProvider().provision(
_plan(agent_provision=provision), bottle,
)
scripts = _exec_scripts(bottle)
self.assertTrue(any("find" in s and "-delete" in s for s in scripts))
self.assertTrue(any("runuser" in s and "codex login status" in s for s in scripts))
def test_forwarded_credentials_verify_sets_codex_path(self):
with tempfile.TemporaryDirectory(prefix="bb-codex-auth.") as tmp:
state_dir = Path(tmp)
prompt_file = state_dir / "prompt.txt"
prompt_file.write_text("")
with patch(
"bot_bottle.contrib.codex.agent_provider.codex_host_access_token",
return_value="token",
), patch(
"bot_bottle.contrib.codex.agent_provider.write_codex_dummy_auth_file",
):
provision = CodexAgentProvider().provision_plan(
dockerfile="",
state_dir=state_dir,
instance_name="bot-bottle-demo-abc12",
prompt_file=prompt_file,
forward_host_credentials=True,
host_env={},
)
verify_argv = provision.verify[0].argv
self.assertTrue(any(
item.startswith("PATH=/home/node/.local/bin:")
for item in verify_argv
))
self.assertIn(
"/home/node/.codex/packages/standalone/current/bin/codex",
verify_argv,
)
def test_dies_when_dir_creation_fails(self):
provision = AgentProvisionPlan(
template="codex", command="codex",
prompt_mode="read_prompt_file",
image="", dockerfile="", guest_home="/home/node",
instance_name="bot-bottle-demo-abc12",
prompt_file=Path("/tmp/prompt.txt"),
guest_env={},
dirs=(AgentProvisionDir("/home/node/.codex"),),
)
bottle = _make_bottle(exec_result=ExecResult(1, "", "mkdir: nope\n"))
with self.assertRaises(SystemExit):
CodexAgentProvider().provision(
_plan(agent_provision=provision), bottle,
)
class TestCodexDockerfile(unittest.TestCase):
def test_installs_procps_for_remote_control_pid_management(self):
dockerfile = _CODEX_DOCKERFILE.read_text()
self.assertIn("procps", dockerfile)
# Codex-supported streamable-HTTP MCP config keys (RawMcpServerConfig in
# codex-rs/config/src/mcp_types.rs). config.toml uses deny_unknown_fields,
# so an entry that names anything outside this set is rejected by the CLI.
_CODEX_HTTP_MCP_KEYS = frozenset({
"url", "http_headers", "env_http_headers", "bearer_token_env_var",
# shared (transport-agnostic) keys
"environment_id", "auth", "startup_timeout_sec", "startup_timeout_ms",
"tool_timeout_sec", "enabled", "required", "supports_parallel_tool_calls",
"default_tools_approval_mode", "enabled_tools", "disabled_tools",
"scopes", "oauth", "oauth_resource", "name", "tools",
})
def _append_target(bottle: MagicMock) -> tuple[str, str]:
"""Reconstruct (config_path, appended_toml) from the base64 append
script the provider ran."""
import base64 as _b64
script = bottle.exec.call_args.args[0]
# printf %s '<b64>' | base64 -d >> '<path>'
b64 = script.split("printf %s ", 1)[1].split(" |", 1)[0].strip("'")
path = script.rsplit(">> ", 1)[1].strip().strip("'")
return path, _b64.b64decode(b64).decode()
class TestCodexSuperviseMcp(unittest.TestCase):
def test_noop_when_supervise_disabled(self):
bottle = _make_bottle()
CodexAgentProvider().provision_supervise_mcp(
_plan(supervise=False), bottle, _URL,
)
bottle.exec.assert_not_called()
def test_appends_streamable_http_entry_as_node(self):
import tomllib
bottle = _make_bottle()
plan = _plan(supervise=True, identity_token="tok-abc123")
CodexAgentProvider().provision_supervise_mcp(plan, bottle, _URL)
bottle.exec.assert_called_once()
self.assertEqual("node", bottle.exec.call_args.kwargs.get("user"))
config_path, appended = _append_target(bottle)
self.assertEqual("/home/node/.codex/config.toml", config_path)
# The appended block must be valid TOML and parse to a streamable
# HTTP server carrying the identity token as a static http header.
parsed = tomllib.loads(appended)
server = parsed["mcp_servers"]["supervise"]
self.assertEqual(_URL, server["url"])
self.assertEqual(
"tok-abc123", server["http_headers"]["x-bot-bottle-identity"],
)
# Never emit an unsupported key (config.toml is deny_unknown_fields);
# in particular there is no `--header` / `header` surface.
self.assertTrue(
set(server).issubset(_CODEX_HTTP_MCP_KEYS),
f"unsupported codex mcp keys: {set(server) - _CODEX_HTTP_MCP_KEYS}",
)
self.assertNotIn("mcp add", bottle.exec.call_args.args[0])
def test_appends_to_custom_codex_home(self):
bottle = _make_bottle()
provision = AgentProvisionPlan(
template="codex", command="codex", prompt_mode="read_prompt_file",
image="", dockerfile="", guest_home="/home/node",
instance_name="bot-bottle-demo-abc12",
prompt_file=Path("/tmp/prompt.txt"),
guest_env={"CODEX_HOME": "/home/node/alt-codex"},
)
plan = _plan(
supervise=True, agent_provision=provision, identity_token="tok",
)
CodexAgentProvider().provision_supervise_mcp(plan, bottle, _URL)
config_path, _ = _append_target(bottle)
self.assertEqual("/home/node/alt-codex/config.toml", config_path)
def test_omits_http_headers_when_no_token(self):
import tomllib
bottle = _make_bottle()
CodexAgentProvider().provision_supervise_mcp(
_plan(supervise=True), bottle, _URL,
)
_, appended = _append_target(bottle)
server = tomllib.loads(appended)["mcp_servers"]["supervise"]
self.assertNotIn("http_headers", server)
def test_registration_failure_is_fatal(self):
bottle = _make_bottle(
exec_result=ExecResult(returncode=1, stdout="", stderr="boom"),
)
with self.assertRaises(SystemExit):
CodexAgentProvider().provision_supervise_mcp(
_plan(supervise=True), bottle, _URL,
)
class TestCodexHeadlessPrompt(unittest.TestCase):
def test_returns_prompt_as_positional_arg(self):
self.assertEqual(["Do the task"], CodexAgentProvider().headless_prompt("Do the task"))
def test_preserves_prompt_text_verbatim(self):
text = "Fix issue #42: the widget breaks on empty input"
self.assertEqual([text], CodexAgentProvider().headless_prompt(text))
if __name__ == "__main__":
unittest.main()