mirror of
https://github.com/openai/codex.git
synced 2026-05-15 16:53:05 +00:00
3e10e09e24
## Why The SDK had behavioral tests that replaced SDK client internals. Those tests could catch wrapper mistakes, but they did not prove the pinned app-server runtime, generated notification models, request routing, and sync/async public clients worked together. This PR adds deterministic integration coverage that starts the pinned `codex app-server` process and mocks only the upstream Responses HTTP boundary. ## What - Add `AppServerHarness` and `MockResponsesServer` helpers for isolated `CODEX_HOME`, mock-provider config, queued SSE responses, and captured `/v1/responses` requests. - Add shared helpers for SSE construction, stream assertions, approval-policy inspection, and image fixtures. - Split integration coverage into focused modules for run behavior, inputs, streaming, turn controls, approvals, and thread lifecycle. - Cover sync and async `Thread.run`, `TurnHandle.stream`, interleaved streams, approval-mode persistence, lifecycle helpers, final-answer phase handling, image inputs, loaded skill input injection, steering, interruption, listing, history reads, run overrides, and token usage mapping. - Replace public-wrapper tests that duplicated integration-test behavior with lower-level client tests only where direct client behavior is the thing under test. ## Stack 1. #21891 `[1/8]` Pin Python SDK runtime dependency 2. #21893 `[2/8]` Generate Python SDK types from pinned runtime 3. #21895 `[3/8]` Run Python SDK tests in CI 4. #21896 `[4/8]` Define Python SDK public API surface 5. #21905 `[5/8]` Rename Python SDK package to `openai-codex` 6. #21910 `[6/8]` Add high-level Python SDK approval mode 7. This PR `[7/8]` Add Python SDK app-server integration harness 8. #22021 `[8/8]` Add Python SDK Ruff formatting ## Verification - Added pinned app-server integration tests under `sdk/python/tests/test_app_server_*.py` and `test_real_app_server_integration.py`. --------- Co-authored-by: Codex <noreply@openai.com>
83 lines
3.0 KiB
Python
83 lines
3.0 KiB
Python
from __future__ import annotations
|
|
|
|
from app_server_harness import AppServerHarness
|
|
from openai_codex import Codex, TextInput
|
|
from openai_codex.generated.v2_all import TurnStatus
|
|
from app_server_helpers import agent_message_texts, streaming_response
|
|
|
|
|
|
def test_turn_steer_adds_follow_up_input(tmp_path) -> None:
|
|
"""Steering an active turn should create a follow-up Responses request."""
|
|
with AppServerHarness(tmp_path) as harness:
|
|
harness.responses.enqueue_sse(
|
|
streaming_response("steer-first", "msg-steer-first", ["before steer"]),
|
|
delay_between_events_s=0.2,
|
|
)
|
|
harness.responses.enqueue_assistant_message(
|
|
"after steer",
|
|
response_id="steer-second",
|
|
)
|
|
|
|
with Codex(config=harness.app_server_config()) as codex:
|
|
thread = codex.thread_start()
|
|
turn = thread.turn(TextInput("Start a steerable turn."))
|
|
harness.responses.wait_for_requests(1)
|
|
steer = turn.steer(TextInput("Use this steering input."))
|
|
events = list(turn.stream())
|
|
requests = harness.responses.wait_for_requests(2)
|
|
|
|
assert {
|
|
"steered_turn_id": steer.turn_id,
|
|
"turn_id": turn.id,
|
|
"agent_messages": agent_message_texts(events),
|
|
"last_user_texts": [
|
|
request.message_input_texts("user")[-1] for request in requests
|
|
],
|
|
} == {
|
|
"steered_turn_id": turn.id,
|
|
"turn_id": turn.id,
|
|
"agent_messages": ["before steer", "after steer"],
|
|
"last_user_texts": [
|
|
"Start a steerable turn.",
|
|
"Use this steering input.",
|
|
],
|
|
}
|
|
|
|
|
|
def test_turn_interrupt_stops_active_turn_and_follow_up_runs(tmp_path) -> None:
|
|
"""Interrupting an active turn should complete it and leave the thread usable."""
|
|
with AppServerHarness(tmp_path) as harness:
|
|
harness.responses.enqueue_sse(
|
|
streaming_response(
|
|
"interrupt-first",
|
|
"msg-interrupt-first",
|
|
["still ", "running"],
|
|
),
|
|
delay_between_events_s=0.2,
|
|
)
|
|
harness.responses.enqueue_assistant_message(
|
|
"after interrupt",
|
|
response_id="interrupt-follow-up",
|
|
)
|
|
|
|
with Codex(config=harness.app_server_config()) as codex:
|
|
thread = codex.thread_start()
|
|
interrupted_turn = thread.turn(TextInput("Start a long turn."))
|
|
harness.responses.wait_for_requests(1)
|
|
interrupt_response = interrupted_turn.interrupt()
|
|
completed = interrupted_turn.run()
|
|
follow_up = thread.run("Continue after the interrupt.")
|
|
|
|
assert {
|
|
"interrupt_response": interrupt_response.model_dump(
|
|
by_alias=True,
|
|
mode="json",
|
|
),
|
|
"interrupted_status": completed.status,
|
|
"follow_up": follow_up.final_response,
|
|
} == {
|
|
"interrupt_response": {},
|
|
"interrupted_status": TurnStatus.interrupted,
|
|
"follow_up": "after interrupt",
|
|
}
|