open-swe/agent/middleware/task_retry.py

83 lines
2.5 KiB
Python
Raw Normal View History

feat: port durable dispatch hardening and startup latency improvements (#160) * feat: port plan-review & workflow-approval UX (#135) Port six upstream commits onto dev: - c03a6be7 (already ported): keep plan guidance high-level - 546042a4: add workflow approval UI with diff preview, approval URLs, web review links, and polling for approval status during active runs - 216cf181: remove workflow token elevation; approved pushes pass through directly without proxy token rewriting - 3dbc0282: preserve plan redirects after login by accepting relative same-origin redirect_to values and rejecting blocked paths - bb104d93: submit plan comments with cmd+enter - 90cb6caa: terse Slack replies, shared content via save_plan outside plan mode (PLAN_STATUS_SHARED), reject shared-content mutations Refs: #135 * feat: port durable dispatch hardening and startup latency improvements Port five upstream PRs onto dev: - #1621 / #1658: durable dispatch with loopback webhook defense, create_durable_run helper, _config_with_prepare_run_id, degradation to None for relative/loopback completion webhook URLs - #1696: run-level completion webhook deduplication (replace claim-then-post with post-then-flag per run_id), DeferredErrorModel for graph-factory resilience, ToolRetryMiddleware for task subagents, TimeoutWrapupMiddleware for all three graphs - #1697: lazy-load __init__.py for agent.middleware, agent.tools, agent.dashboard (PEP 562); defer heavy imports (exa_py in web_search, agent.webapp in request_pr_review, deepagents in sandbox.py); add ttl_cache.py with stale-while-revalidate for tool loaders Refs: #137 * fix: restore login page render and clear CI lint/format The plan-review port removed the authRedirectUrl import from login.tsx but left its call site, crashing the login page at runtime (blank page, no 'Sign in to open-swe'). Pass the relative path straight to loginUrl, matching the plan route and the backend relative-redirect handling. Also drop an unused os import in the guard test and reformat workflow_push_guard.py to satisfy ruff. * fix: restore RepairOrphaned middleware export and repoint model fake to deferred_model boundary * fix: restore RepairOrphanedToolCallsMiddleware, fix E2E model-fake patch, drop dead ttl_cache - Re-add RepairOrphanedToolCallsMiddleware to the lazy middleware __init__ (_MIDDLEWARE_MODULES, __all__, TYPE_CHECKING) so agent.reviewer can import it. - Reroute E2E model patching to deferred_model.make_model so make_model_or_defer (used by all three graph factories) returns the scripted fake instead of building a real model with fake credentials. - Drop unused agent/utils/ttl_cache.py — no agent module imports it. - Fix import ordering in agent/reviewer.py and agent/analyzer.py (ruff I001). - Format tests/test_dispatch.py. * fix: claim-then-post run-level failure dedup; stop permanent suppression --------- Co-authored-by: amoussa1229 <166072409+amoussa1229@users.noreply.github.com> Co-authored-by: Adam Moussa <adam@seahavenind.com>
2026-07-09 17:11:25 -04:00
from __future__ import annotations
import json
_RETURN_TO_MODEL_CODES = frozenset({"invalid_prompt", "context_length_exceeded"})
_RETURN_TO_MODEL_STATUS_CODES = frozenset({400, 422})
_RETRY_HTTP_STATUS_CODES = frozenset({408, 409, 425, 429, 500, 502, 503, 504, 529})
_TRANSIENT_ERROR_NAMES = frozenset(
{
"APIConnectionError",
"APITimeoutError",
"ConnectTimeout",
"ReadTimeout",
"TimeoutException",
"TransportError",
}
)
def _error_body(exc: Exception) -> dict[str, object]:
body = getattr(exc, "body", None)
if isinstance(body, dict):
nested = body.get("error")
return nested if isinstance(nested, dict) else body
return {}
def _status_code(exc: Exception) -> int | None:
status = getattr(exc, "status_code", None)
if isinstance(status, int):
return status
response = getattr(exc, "response", None)
status = getattr(response, "status_code", None)
return status if isinstance(status, int) else None
def _error_fields(exc: Exception) -> dict[str, object]:
body = _error_body(exc)
out: dict[str, object] = {}
status = _status_code(exc)
if status is not None:
out["status_code"] = status
for key in ("type", "code", "message"):
value = body.get(key)
if not isinstance(value, str) or not value:
value = getattr(exc, key, None)
if isinstance(value, str) and value:
out[key] = value
return out
def _is_httpx_transport_error(exc: Exception) -> bool:
try:
import httpx
except ImportError: # pragma: no cover - dependency is declared in production
return False
return isinstance(exc, httpx.TransportError)
def task_retry_on(exc: Exception) -> bool:
status = _status_code(exc)
if isinstance(status, int) and (status in _RETRY_HTTP_STATUS_CODES or status >= 500):
return True
return exc.__class__.__name__ in _TRANSIENT_ERROR_NAMES or _is_httpx_transport_error(exc)
def task_on_failure(exc: Exception) -> str:
error = _error_fields(exc)
code = error.get("code")
status = error.get("status_code")
returnable = code in _RETURN_TO_MODEL_CODES or (
code is None
and error.get("type") == "invalid_request_error"
and isinstance(status, int)
and status in _RETURN_TO_MODEL_STATUS_CODES
)
if not returnable:
raise exc
return json.dumps(
{"status": "failed", "source": "subagent", "error": error},
sort_keys=True,
)