mirror of
https://github.com/openai/codex.git
synced 2026-05-15 08:42:34 +00:00
## 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>
169 lines
3.9 KiB
Python
169 lines
3.9 KiB
Python
from __future__ import annotations
|
|
|
|
from collections.abc import AsyncIterator, Iterable, Iterator
|
|
from typing import Any
|
|
|
|
from app_server_harness import (
|
|
ev_assistant_message,
|
|
ev_completed,
|
|
ev_message_item_added,
|
|
ev_output_text_delta,
|
|
ev_response_created,
|
|
sse,
|
|
)
|
|
from openai_codex.generated.v2_all import (
|
|
AgentMessageDeltaNotification,
|
|
ItemCompletedNotification,
|
|
MessagePhase,
|
|
)
|
|
from openai_codex.models import Notification
|
|
|
|
TINY_PNG_BYTES = bytes(
|
|
[
|
|
137,
|
|
80,
|
|
78,
|
|
71,
|
|
13,
|
|
10,
|
|
26,
|
|
10,
|
|
0,
|
|
0,
|
|
0,
|
|
13,
|
|
73,
|
|
72,
|
|
68,
|
|
82,
|
|
0,
|
|
0,
|
|
0,
|
|
1,
|
|
0,
|
|
0,
|
|
0,
|
|
1,
|
|
8,
|
|
6,
|
|
0,
|
|
0,
|
|
0,
|
|
31,
|
|
21,
|
|
196,
|
|
137,
|
|
0,
|
|
0,
|
|
0,
|
|
11,
|
|
73,
|
|
68,
|
|
65,
|
|
84,
|
|
120,
|
|
156,
|
|
99,
|
|
96,
|
|
0,
|
|
2,
|
|
0,
|
|
0,
|
|
5,
|
|
0,
|
|
1,
|
|
122,
|
|
94,
|
|
171,
|
|
63,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
73,
|
|
69,
|
|
78,
|
|
68,
|
|
174,
|
|
66,
|
|
96,
|
|
130,
|
|
]
|
|
)
|
|
|
|
|
|
def response_approval_policy(response: Any) -> str:
|
|
"""Return serialized approvalPolicy from a generated thread response."""
|
|
return response.model_dump(by_alias=True, mode="json")["approvalPolicy"]
|
|
|
|
|
|
def agent_message_texts(events: list[Notification]) -> list[str]:
|
|
"""Extract completed agent-message text from SDK notifications."""
|
|
texts: list[str] = []
|
|
for event in events:
|
|
if not isinstance(event.payload, ItemCompletedNotification):
|
|
continue
|
|
item = event.payload.item.root
|
|
if item.type == "agentMessage":
|
|
texts.append(item.text)
|
|
return texts
|
|
|
|
|
|
def agent_message_texts_from_items(items: Iterable[Any]) -> list[str]:
|
|
"""Extract agent-message text from completed run result items."""
|
|
texts: list[str] = []
|
|
for item in items:
|
|
root = item.root
|
|
if root.type == "agentMessage":
|
|
texts.append(root.text)
|
|
return texts
|
|
|
|
|
|
def next_sync_delta(stream: Iterator[Notification]) -> str:
|
|
"""Advance a sync turn stream until the next agent-message text delta."""
|
|
for event in stream:
|
|
if isinstance(event.payload, AgentMessageDeltaNotification):
|
|
return event.payload.delta
|
|
raise AssertionError("stream completed before an agent-message delta")
|
|
|
|
|
|
async def next_async_delta(stream: AsyncIterator[Notification]) -> str:
|
|
"""Advance an async turn stream until the next agent-message text delta."""
|
|
async for event in stream:
|
|
if isinstance(event.payload, AgentMessageDeltaNotification):
|
|
return event.payload.delta
|
|
raise AssertionError("stream completed before an agent-message delta")
|
|
|
|
|
|
def streaming_response(response_id: str, item_id: str, parts: list[str]) -> str:
|
|
"""Build an SSE stream with text deltas and a final assistant message."""
|
|
return sse(
|
|
[
|
|
ev_response_created(response_id),
|
|
ev_message_item_added(item_id),
|
|
*[ev_output_text_delta(part) for part in parts],
|
|
ev_assistant_message(item_id, "".join(parts)),
|
|
ev_completed(response_id),
|
|
]
|
|
)
|
|
|
|
|
|
def assistant_message_with_phase(
|
|
item_id: str,
|
|
text: str,
|
|
phase: MessagePhase,
|
|
) -> dict[str, Any]:
|
|
"""Build an assistant message event carrying app-server phase metadata."""
|
|
event = ev_assistant_message(item_id, text)
|
|
event["item"] = {**event["item"], "phase": phase.value}
|
|
return event
|
|
|
|
|
|
def request_kind(request_path: str) -> str:
|
|
"""Classify captured mock-server request paths for compact assertions."""
|
|
if request_path.endswith("/responses/compact"):
|
|
return "compact"
|
|
if request_path.endswith("/responses"):
|
|
return "responses"
|
|
return request_path
|