← eval6_submission

requests_7427

resolved RESOLVED LOOP PASS · 24 tool calls · 170 s · psf/requests

Task input

Port bpo-39057 to Requests

This PR ports a [fix](https://bugs.python.org/issue39057) from CPython to constrain no_proxy behavior to domain boundaries. This was originally undefined behavior when Requests implemented `no_proxy` support but has since had bug fixes released in both CPython and Curl. We'll follow suit to conform with ecosystem expectations and resolve long standing issue #4795.

Tool calls (25)

#ToolArgumentsResult
1run_command
{
 "command": "grep -rn \"no_proxy\" src/requests | head -20"
}
{"status": "ok", "stdout": "src/requests/sessions.py:840: no_proxy = proxies.get(\"no_proxy\") if proxies is not None else None\nsrc/requests/sessions.py:841: e
full
{"status": "ok", "stdout": "src/requests/sessions.py:840:            no_proxy = proxies.get(\"no_proxy\") if proxies is not None else None\nsrc/requests/sessions.py:841:            env_proxies = get_environ_proxies(url, no_proxy=no_proxy)\nsrc/requests/utils.py:765:    Very simple check of the cidr format in no_proxy variable.\nsrc/requests/utils.py:810:def should_bypass_proxies(url: str, no_proxy: str | None) -> bool:\nsrc/requests/utils.py:822:    # First check whether no_proxy is defined. If it is, check that the URL\nsrc/requests/utils.py:823:    # we're getting isn't in the no_proxy list.\nsrc/requests/utils.py:824:    no_proxy_arg = no_proxy\nsrc/requests/utils.py:825:    if no_proxy is None:\nsrc/requests/utils.py:826:        no_proxy = get_proxy(\"no_proxy\")\nsrc/requests/utils.py:834:    if no_proxy:\nsrc/requests/utils.py:837:        no_proxy_hosts = (host for host in no_proxy.replace(\" \", \"\").split(\",\") if host)\nsrc/requests/utils.py:840:            for proxy_ip in no_proxy_hosts:\nsrc/requests/utils.py:845:                    # If no_proxy ip was defined in plain IP notation instead of cidr notation &\nsrc/requests/utils.py:853:            for host in no_proxy_hosts:\nsrc/requests/utils.py:855:                    # The URL does match something in no_proxy, so we don't want\nsrc/requests/utils.py:859:    with set_environ(\"no_proxy\", no_proxy_arg):\nsrc/requests/utils.py:871:def get_environ_proxies(url: str, no_proxy: str | None = None) -> dict[str, str]:\nsrc/requests/utils.py:877:    if should_bypass_proxies(url, no_proxy=no_proxy):\nsrc/requests/utils.py:927:    no_proxy = proxies.get(\"no_proxy\")\nsrc/requests/utils.py:930:    if trust_env and not should_bypass_proxies(url, no_proxy=no_proxy):\n", "stderr": "", "exit_code": 0}
2-6 ×5read_file
{
 "filepath": "src/requests/utils.py",
 "start_line": "810",
 "end_line": "865"
}
{"status": "error", "error_type": "FileReadError", "error_message": "'>' not supported between instances of 'int' and 'str'"}
full
{"status": "error", "error_type": "FileReadError", "error_message": "'>' not supported between instances of 'int' and 'str'"}
7read_file
{
 "filepath": "src/requests/utils.py"
}
{"status": "ok", "filepath": "src/requests/utils.py", "content": "\"\"\"\nrequests.utils\n~~~~~~~~~~~~~~\n\nThis module provides utility functions that are used
full
{"status": "ok", "filepath": "src/requests/utils.py", "content": "\"\"\"\nrequests.utils\n~~~~~~~~~~~~~~\n\nThis module provides utility functions that are used within Requests\nthat are also useful for external consumption.\n\"\"\"\n\nfrom __future__ import annotations\n\nimport codecs\nimport contextlib\nimport io\nimport os\nimport re\nimport socket\nimport struct\nimport sys\nimport tempfile\nimport warnings\nimport zipfile\nfrom collections import OrderedDict\nfrom collections.abc import Generator, Iterable\nfrom typing import (\n    TYPE_CHECKING,\n    Any,\n    Final,\n    TypeVar,\n    cast,\n    overload,\n)\n\nfrom urllib3.util import make_headers, parse_url\n\nfrom . import certs\nfrom .__version__ import __version__\n\n# to_native_string is unused here, but imported here for backwards compatibility\nfrom ._internal_utils import (  # noqa: F401\n    _HEADER_VALIDATORS_BYTE,  # type: ignore[reportPrivateUsage]\n    _HEADER_VALIDATORS_STR,  # type: ignore[reportPrivateUsage]\n    HEADER_VALIDATORS,  # type: ignore[reportUnusedImport]\n    to_native_string,  # type: ignore[reportUnusedImport]\n)\nfrom ._types import SupportsItems as _SupportsItems\nfrom .compat import (\n    Mapping,\n    bytes,\n    getproxies,\n    getproxies_environment,\n    integer_types,\n    is_urllib3_1,\n    proxy_bypass,\n    proxy_bypass_environment,  # type: ignore[attr-defined]  # https://github.com/python/cpython/issues/145331\n    quote,\n    str,\n    unquote,\n    urlparse,\n    urlunparse,\n)\nfrom .compat import parse_http_list as _parse_list_header\nfrom .cookies import cookiejar_from_dict\nfrom .exceptions import (\n    FileModeWarning,\n    InvalidHeader,\n    InvalidURL,\n    UnrewindableBodyError,\n)\nfrom .structures import CaseInsensitiveDict\n\nif TYPE_CHECKING:\n    from http.cookiejar import CookieJar\n    from io import BufferedWriter\n\n    from . import _types as _t\n    from .models import PreparedRequest, Request, Response\n\nNETRC_FILES: Final = (\".netrc\"
8read_file
{
 "end_line": "865",
 "filepath": "src/requests/utils.py",
 "start_line": "810"
}
{"status": "error", "error_type": "FileReadError", "error_message": "'>' not supported between instances of 'int' and 'str'"}
full
{"status": "error", "error_type": "FileReadError", "error_message": "'>' not supported between instances of 'int' and 'str'"}
9run_command
{
 "command": "grep -n \"def should_bypass_proxies\" src/requests/utils.py"
}
{"status": "ok", "stdout": "810:def should_bypass_proxies(url: str, no_proxy: str | None) -> bool:\n", "stderr": "", "exit_code": 0}
full
{"status": "ok", "stdout": "810:def should_bypass_proxies(url: str, no_proxy: str | None) -> bool:\n", "stderr": "", "exit_code": 0}
10run_command
{
 "command": "sed -n '810,865p' src/requests/utils.py"
}
{"status": "ok", "stdout": "def should_bypass_proxies(url: str, no_proxy: str | None) -> bool:\n \"\"\"\n Returns whether we should bypass proxies or not.\n\n :
full
{"status": "ok", "stdout": "def should_bypass_proxies(url: str, no_proxy: str | None) -> bool:\n    \"\"\"\n    Returns whether we should bypass proxies or not.\n\n    :rtype: bool\n    \"\"\"\n\n    # Prioritize lowercase environment variables over uppercase\n    # to keep a consistent behaviour with other http projects (curl, wget).\n    def get_proxy(key: str) -> str | None:\n        return os.environ.get(key) or os.environ.get(key.upper())\n\n    # First check whether no_proxy is defined. If it is, check that the URL\n    # we're getting isn't in the no_proxy list.\n    no_proxy_arg = no_proxy\n    if no_proxy is None:\n        no_proxy = get_proxy(\"no_proxy\")\n    parsed = urlparse(url)\n    hostname = parsed.hostname\n\n    if hostname is None:\n        # URLs don't always have hostnames, e.g. file:/// urls.\n        return True\n\n    if no_proxy:\n        # We need to check whether we match here. We need to see if we match\n        # the end of the hostname, both with and without the port.\n        no_proxy_hosts = (host for host in no_proxy.replace(\" \", \"\").split(\",\") if host)\n\n        if is_ipv4_address(hostname):\n            for proxy_ip in no_proxy_hosts:\n                if is_valid_cidr(proxy_ip):\n                    if address_in_network(hostname, proxy_ip):\n                        return True\n                elif hostname == proxy_ip:\n                    # If no_proxy ip was defined in plain IP notation instead of cidr notation &\n                    # matches the IP of the index\n                    return True\n        else:\n            host_with_port = hostname\n            if parsed.port:\n                host_with_port += f\":{parsed.port}\"\n\n            for host in no_proxy_hosts:\n                if hostname.endswith(host) or host_with_port.endswith(host):\n                    # The URL does match something in no_proxy, so we don't want\n                    # to apply the proxies on this URL.\n                    return True\
11run_command
{
 "command": "sed -n '866,870p' src/requests/utils.py"
}
{"status": "ok", "stdout": " return True\n\n return False\n\n\n", "stderr": "", "exit_code": 0}
full
{"status": "ok", "stdout": "        return True\n\n    return False\n\n\n", "stderr": "", "exit_code": 0}
12run_command
{
 "command": "python3 -c \"import requests; print(requests.__version__)\""
}
{"status": "ok", "stdout": "2.34.0.dev1\n", "stderr": "", "exit_code": 0}
full
{"status": "ok", "stdout": "2.34.0.dev1\n", "stderr": "", "exit_code": 0}
13run_command
{
 "command": "cat <<EOF > /tmp/test_no_proxy.py\nimport os\nfrom requests.utils import should_bypass_proxies\n\ndef test_no_proxy_domain_boundary():\n    # Case 1: Exact match\n    assert should_bypass_proxies(\"http://example.com\", \"example.com\") is True\n    \n    # Case 2: Subdomain match (should be True)\n    assert should_bypass_proxies(\"http://sub.example.com\", \"example.com\") is True\n    \n    # Case 3: Domain boundary match (should be False)\n    # If no_proxy is 'example.com', 'notexample.com' should NOT match\n    assert should_bypass_proxies(\"http://notexample.com\", \"example.com\") is False\n    \n    # Case 4: Domain boundary match with dot (should be True)\n    assert should_bypass_proxies(\"http://api.example.com\", \".example.com\") is True\n    \n    # Case 5: Domain boundary match with dot (should be False)\n    assert should_bypass_proxies(\"http://notexample.com\", \".example.com\") is False\n\nif __name__ == \"__main__\":\n    try:\n        test_no_proxy_domain_boundary()\n        print(\"Tests passed!\")\n    except AssertionError as e:\n        print(f\"Test failed: {e}\")\n        exit(1)\nEOF\npython3 /tmp/test_no_proxy.py"
}
{"status": "error", "error_type": "CommandError", "error_message": "Test failed: \n", "details": {"stdout": "Test failed: \n", "stderr": "", "exit_code": 1}}
full
{"status": "error", "error_type": "CommandError", "error_message": "Test failed: \n", "details": {"stdout": "Test failed: \n", "stderr": "", "exit_code": 1}}
14run_command
{
 "command": "python3 -c \"from requests.utils import should_bypass_proxies; print(f'Exact: {should_bypass_proxies(\\\"http://example.com\\\", \\\"example.com\\\")}')\""
}
{"status": "ok", "stdout": "Exact: True\n", "stderr": "", "exit_code": 0}
full
{"status": "ok", "stdout": "Exact: True\n", "stderr": "", "exit_code": 0}
15run_command
{
 "command": "python3 -c \"from requests.utils import should_bypass_proxies; print(f'Subdomain: {should_bypass_proxies(\\\"http://sub.example.com\\\", \\\"example.com\\\")}')\""
}
{"status": "ok", "stdout": "Subdomain: True\n", "stderr": "", "exit_code": 0}
full
{"status": "ok", "stdout": "Subdomain: True\n", "stderr": "", "exit_code": 0}
16run_command
{
 "command": "python3 -c \"from requests.utils import should_bypass_proxies; print(f'NotExample: {should_bypass_proxies(\\\"http://notexample.com\\\", \\\"example.com\\\")}')\""
}
{"status": "ok", "stdout": "NotExample: True\n", "stderr": "", "exit_code": 0}
full
{"status": "ok", "stdout": "NotExample: True\n", "stderr": "", "exit_code": 0}
17run_command
{
 "command": "sed -n '848,860p' src/requests/utils.py"
}
{"status": "ok", "stdout": " else:\n host_with_port = hostname\n if parsed.port:\n host_with_port += f\":{parsed.port}\"\n\n for host in no_proxy_hosts:\n if ho
full
{"status": "ok", "stdout": "        else:\n            host_with_port = hostname\n            if parsed.port:\n                host_with_port += f\":{parsed.port}\"\n\n            for host in no_proxy_hosts:\n                if hostname.endswith(host) or host_with_port.endswith(host):\n                    # The URL does match something in no_proxy, so we don't want\n                    # to apply the proxies on this URL.\n                    return True\n\n    with set_environ(\"no_proxy\", no_proxy_arg):\n        try:\n", "stderr": "", "exit_code": 0}
18run_command
{
 "command": "sed -n '834,847p' src/requests/utils.py"
}
{"status": "ok", "stdout": " if no_proxy:\n # We need to check whether we match here. We need to see if we match\n # the end of the hostname, both with and with
full
{"status": "ok", "stdout": "    if no_proxy:\n        # We need to check whether we match here. We need to see if we match\n        # the end of the hostname, both with and without the port.\n        no_proxy_hosts = (host for host in no_proxy.replace(\" \", \"\").split(\",\") if host)\n\n        if is_ipv4_address(hostname):\n            for proxy_ip in no_proxy_hosts:\n                if is_valid_cidr(proxy_ip):\n                    if address_in_network(hostname, proxy_ip):\n                        return True\n                elif hostname == proxy_ip:\n                    # If no_proxy ip was defined in plain IP notation instead of cidr notation &\n                    # matches the IP of the index\n                    return True\n", "stderr": "", "exit_code": 0}
19run_command
{
 "command": "cat <<EOF > /tmp/test_no_proxy.py\nimport os\nfrom requests.utils import should_bypass_proxies\n\ndef test_no_proxy_domain_boundary():\n    # Case 1: Exact match\n    assert should_bypass_proxies(\"http://example.com\", \"example.com\") is True\n    \n    # Case 2: Subdomain match (should be True)\n    assert should_bypass_proxies(\"http://sub.example.com\", \"example.com\") is True\n    \n    # Case 3: Domain boundary match (should be False)\n    # If no_proxy is 'example.com', 'notexample.com' should NOT match\n    assert should_bypass_proxies(\"http://notexample.com\", \"example.com\") is False\n    \n    # Case 4: Domain boundary match with dot (should be True)\n    assert should_bypass_proxies(\"http://api.example.com\", \".example.com\") is True\n    \n    # Case 5: Domain boundary match with dot (should be False)\n    assert should_bypass_proxies(\"http://notexample.com\", \".example.com\") is False\n\nif __name__ == \"__main__\":\n    try:\n        test_no_proxy_domain_boundary()\n        print(\"Tests passed!\")\n    except AssertionError as e:\n        print(f\"Test failed: {e}\")\n        exit(1)\nEOF\npython3 /tmp/test_no_proxy.py"
}
{"status": "error", "error_type": "CommandError", "error_message": "Test failed: \n", "details": {"stdout": "Test failed: \n", "stderr": "", "exit_code": 1}}
full
{"status": "error", "error_type": "CommandError", "error_message": "Test failed: \n", "details": {"stdout": "Test failed: \n", "stderr": "", "exit_code": 1}}
20run_command
{
 "command": "python3 -c \"from requests.utils import should_bypass_proxies; print(f'NotExample: {should_bypass_proxies(\\\"http://notexample.com\\\", \\\"example.com\\\")}')\""
}
{"status": "ok", "stdout": "NotExample: True\n", "stderr": "", "exit_code": 0}
full
{"status": "ok", "stdout": "NotExample: True\n", "stderr": "", "exit_code": 0}
21edit_file
{
 "filepath": "src/requests/utils.py",
 "new_string": "            for host in no_proxy_hosts:\n                if host == hostname or host == host_with_port:\n                    return True\n                if host.startswith('.'):\n                    if hostname.endswith(host) or host_with_port.endswith(host):\n                        return True\n                elif hostname.endswith('.' + host) or host_with_port.endswith('.' + host):\n                    return True\n                    # The URL does match something in no_proxy, so we don't want\n                    # to apply the proxies on this URL.",
 "old_string": "            for host in no_proxy_hosts:\n                if hostname.endswith(host) or host_with_port.endswith(host):\n                    # The URL does match something in no_proxy, so we don't want\n                    # to apply the proxies on this URL.\n                    return True"
}
{"status": "ok", "filepath": "src/requests/utils.py", "occurrences": 1, "strategy": "exact", "diff": "--- a/src/requests/utils.py\n+++ b/src/requests/utils.py\n
full
{"status": "ok", "filepath": "src/requests/utils.py", "occurrences": 1, "strategy": "exact", "diff": "--- a/src/requests/utils.py\n+++ b/src/requests/utils.py\n@@ -851,10 +851,15 @@\n                 host_with_port += f\":{parsed.port}\"\n \n             for host in no_proxy_hosts:\n-                if hostname.endswith(host) or host_with_port.endswith(host):\n+                if host == hostname or host == host_with_port:\n+                    return True\n+                if host.startswith('.'):\n+                    if hostname.endswith(host) or host_with_port.endswith(host):\n+                        return True\n+                elif hostname.endswith('.' + host) or host_with_port.endswith('.' + host):\n+                    return True\n                     # The URL does match something in no_proxy, so we don't want\n                     # to apply the proxies on this URL.\n-                    return True\n \n     with set_environ(\"no_proxy\", no_proxy_arg):\n         try:\n", "is_truncated": false}
22run_command
{
 "command": "python3 /tmp/test_no_proxy.py"
}
{"status": "ok", "stdout": "Tests passed!\n", "stderr": "", "exit_code": 0}
full
{"status": "ok", "stdout": "Tests passed!\n", "stderr": "", "exit_code": 0}
23run_command
{
 "command": "cat <<EOF > /tmp/test_no_proxy_extended.py\nimport os\nfrom requests.utils import should_bypass_proxies\n\ndef test_no_proxy_extended():\n    # Exact match\n    assert should_bypass_proxies(\"http://example.com\", \"example.com\") is True\n    # Subdomain match\n    assert should_bypass_proxies(\"http://sub.example.com\", \"example.com\") is True\n    # Domain boundary match (should be False)\n    assert should_bypass_proxies(\"http://notexample.com\", \"example.com\") is False\n    # Dot prefix match\n    assert should_bypass_proxies(\"http://api.example.com\", \".example.com\") is True\n    # Dot prefix boundary match (should be False)\n    assert should_bypass_proxies(\"http://notexample.com\", \".example.com\") is False\n    # Port match\n    assert should_bypass_proxies(\"http://example.com:8080\", \"example.com\") is True\n    # Port match with dot prefix\n    assert should_bypass_proxies(\"http://sub.example.com:8080\", \"example.com\") is True\n    # Port match exact\n    assert should_bypass_proxies(\"http://example.com:8080\", \"example.com:8080\") is True\n    # Port match boundary (should be False)\n    assert should_bypass_proxies(\"http://notexample.com:8080\", \"example.com\") is False\n\nif __name__ == \"__main__\":\n    try:\n        test_no_proxy_extended()\n        print(\"Tests passed!\")\n    except AssertionError as e:\n        print(f\"Test failed: {e}\")\n        exit(1)\nEOF\npython3 /tmp/test_no_proxy_extended.py"
}
{"status": "ok", "stdout": "Tests passed!\n", "stderr": "", "exit_code": 0}
full
{"status": "ok", "stdout": "Tests passed!\n", "stderr": "", "exit_code": 0}
24run_command
{
 "command": "git diff"
}
{"status": "ok", "stdout": "diff --git a/src/requests/utils.py b/src/requests/utils.py\nindex e69ad0d7..23757ce5 100644\n--- a/src/requests/utils.py\n+++ b/src/
full
{"status": "ok", "stdout": "diff --git a/src/requests/utils.py b/src/requests/utils.py\nindex e69ad0d7..23757ce5 100644\n--- a/src/requests/utils.py\n+++ b/src/requests/utils.py\n@@ -851,10 +851,15 @@ def should_bypass_proxies(url: str, no_proxy: str | None) -> bool:\n                 host_with_port += f\":{parsed.port}\"\n \n             for host in no_proxy_hosts:\n-                if hostname.endswith(host) or host_with_port.endswith(host):\n+                if host == hostname or host == host_with_port:\n+                    return True\n+                if host.startswith('.'):\n+                    if hostname.endswith(host) or host_with_port.endswith(host):\n+                        return True\n+                elif hostname.endswith('.' + host) or host_with_port.endswith('.' + host):\n+                    return True\n                     # The URL does match something in no_proxy, so we don't want\n                     # to apply the proxies on this URL.\n-                    return True\n \n     with set_environ(\"no_proxy\", no_proxy_arg):\n         try:\n", "stderr": "", "exit_code": 0}
25submit_patch
{}
{"status": "ok", "patch_size": 1030, "files_changed": 1}
full
{"status": "ok", "patch_size": 1030, "files_changed": 1}

Patch

diff --git a/src/requests/utils.py b/src/requests/utils.py
index e69ad0d7..23757ce5 100644
--- a/src/requests/utils.py
+++ b/src/requests/utils.py
@@ -851,10 +851,15 @@ def should_bypass_proxies(url: str, no_proxy: str | None) -> bool:
                 host_with_port += f":{parsed.port}"
 
             for host in no_proxy_hosts:
-                if hostname.endswith(host) or host_with_port.endswith(host):
+                if host == hostname or host == host_with_port:
+                    return True
+                if host.startswith('.'):
+                    if hostname.endswith(host) or host_with_port.endswith(host):
+                        return True
+                elif hostname.endswith('.' + host) or host_with_port.endswith('.' + host):
+                    return True
                     # The URL does match something in no_proxy, so we don't want
                     # to apply the proxies on this URL.
-                    return True
 
     with set_environ("no_proxy", no_proxy_arg):
         try:

Test output

show
..s..................................................................... [ 31%]
........................................................................ [ 62%]
....................................................................ssss [ 94%]
sssssss.....s                                                            [100%]
=============================== warnings summary ===============================
../../../../../../kaggle/tmp/envs/requests/lib/python3.13/site-packages/_pytest/config/__init__.py:1464
  /kaggle/tmp/envs/requests/lib/python3.13/site-packages/_pytest/config/__init__.py:1464: PytestConfigWarning: Unknown config option: timeout
  
    self._warn_or_fail_if_strict(f"Unknown config option: {key}\n")

tests/test_utils.py::TestContentEncodingDetection::test_none
tests/test_utils.py::TestContentEncodingDetection::test_pragmas[<meta charset="UTF-8">]
tests/test_utils.py::TestContentEncodingDetection::test_pragmas[<meta http-equiv="Content-type" content="text/html;charset=UTF-8">]
tests/test_utils.py::TestContentEncodingDetection::test_pragmas[<meta http-equiv="Content-type" content="text/html;charset=UTF-8" />]
tests/test_utils.py::TestContentEncodingDetection::test_pragmas[<?xml version="1.0" encoding="UTF-8"?>]
tests/test_utils.py::TestContentEncodingDetection::test_precedence
  /tmp/swe_work/eval6_submission/requests_7427/b/workspace/src/requests/utils.py:527: DeprecationWarning: In requests 3.0, get_encodings_from_content will be removed. For more information, please see the discussion on issue #2266. (This warning should only appear once.)
    warnings.warn(

-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
216 passed, 13 skipped, 7 warnings in 0.25s
[2026-09-25 10:47:18,925] WARNING in core: flasgger is not installed; serving the static landing page at / and skipping the Swagger UI and /spec.json.