mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-25 00:51:20 +00:00
dbb7e00e7e
Completes the hostname-hardening sweep — every substring check against a provider host in live-routing code is now hostname-based. This closes the same false-positive class for OpenRouter, GitHub Copilot, Kimi, Qwen, ChatGPT/Codex, Bedrock, GitHub Models, Vercel AI Gateway, Nous, Z.AI, Moonshot, Arcee, and MiniMax that the original PR closed for OpenAI, xAI, and Anthropic. New helper: - utils.base_url_host_matches(base_url, domain) — safe counterpart to 'domain in base_url'. Accepts hostname equality and subdomain matches; rejects path segments, host suffixes, and prefix collisions. Call sites converted (real-code only; tests, optional-skills, red-teaming scripts untouched): run_agent.py (10 sites): - AIAgent.__init__ Bedrock branch, ChatGPT/Codex branch (also path check) - header cascade for openrouter / copilot / kimi / qwen / chatgpt - interleaved-thinking trigger (openrouter + claude) - _is_openrouter_url(), _is_qwen_portal() - is_native_anthropic check - github-models-vs-copilot detection (3 sites) - reasoning-capable route gate (nousresearch, vercel, github) - codex-backend detection in API kwargs build - fallback api_mode Bedrock detection agent/auxiliary_client.py (7 sites): - extra-headers cascades in 4 distinct client-construction paths (resolve custom, resolve auto, OpenRouter-fallback-to-custom, _async_client_from_sync, resolve_provider_client explicit-custom, resolve_auto_with_codex) - _is_openrouter_client() base_url sniff agent/usage_pricing.py: - resolve_billing_route openrouter branch agent/model_metadata.py: - _is_openrouter_base_url(), Bedrock context-length lookup hermes_cli/providers.py: - determine_api_mode Bedrock heuristic hermes_cli/runtime_provider.py: - _is_openrouter_url flag for API-key preference (issues #420, #560) hermes_cli/doctor.py: - Kimi User-Agent header for /models probes tools/delegate_tool.py: - subagent Codex endpoint detection trajectory_compressor.py: - _detect_provider() cascade (8 providers: openrouter, nous, codex, zai, kimi-coding, arcee, minimax-cn, minimax) cli.py, gateway/run.py: - /model-switch cache-enabled hint (openrouter + claude) Bedrock detection tightened from 'bedrock-runtime in url' to 'hostname starts with bedrock-runtime. AND host is under amazonaws.com'. ChatGPT/Codex detection tightened from 'chatgpt.com/backend-api/codex in url' to 'hostname is chatgpt.com AND path contains /backend-api/codex'. Tests: - tests/test_base_url_hostname.py extended with a base_url_host_matches suite (exact match, subdomain, path-segment rejection, host-suffix rejection, host-prefix rejection, empty-input, case-insensitivity, trailing dot). Validation: 651 targeted tests pass (runtime_provider, minimax, bedrock, gemini, auxiliary, codex_cloudflare, usage_pricing, compressor_fallback, fallback_model, openai_client_lifecycle, provider_parity, cli_provider_resolution, delegate, credential_pool, context_compressor, plus the 4 hostname test modules). 26-assertion E2E call-site verification across 6 modules passes.
108 lines
4.8 KiB
Python
108 lines
4.8 KiB
Python
"""Targeted tests for ``utils.base_url_hostname`` and ``base_url_host_matches``.
|
|
|
|
These helpers are used across provider routing, auxiliary client, setup
|
|
wizards, billing routes, and the trajectory compressor to avoid the
|
|
substring-match false-positive class documented in
|
|
tests/agent/test_direct_provider_url_detection.py.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from utils import base_url_hostname, base_url_host_matches
|
|
|
|
|
|
# ─── base_url_hostname ────────────────────────────────────────────────────
|
|
|
|
|
|
def test_empty_returns_empty_string():
|
|
assert base_url_hostname("") == ""
|
|
assert base_url_hostname(None) == "" # type: ignore[arg-type]
|
|
|
|
|
|
def test_plain_host_without_scheme():
|
|
assert base_url_hostname("api.openai.com") == "api.openai.com"
|
|
assert base_url_hostname("api.openai.com/v1") == "api.openai.com"
|
|
|
|
|
|
def test_https_url_extracts_hostname_only():
|
|
assert base_url_hostname("https://api.openai.com/v1") == "api.openai.com"
|
|
assert base_url_hostname("https://api.x.ai/v1") == "api.x.ai"
|
|
assert base_url_hostname("https://api.anthropic.com") == "api.anthropic.com"
|
|
|
|
|
|
def test_hostname_case_insensitive():
|
|
assert base_url_hostname("https://API.OpenAI.com/v1") == "api.openai.com"
|
|
|
|
|
|
def test_trailing_dot_stripped():
|
|
assert base_url_hostname("https://api.openai.com./v1") == "api.openai.com"
|
|
|
|
|
|
def test_path_containing_provider_host_is_not_the_hostname():
|
|
assert base_url_hostname("https://proxy.example.test/api.openai.com/v1") == "proxy.example.test"
|
|
assert base_url_hostname("https://proxy.example.test/api.anthropic.com/v1") == "proxy.example.test"
|
|
|
|
|
|
def test_host_suffix_is_not_the_provider():
|
|
assert base_url_hostname("https://api.openai.com.example/v1") == "api.openai.com.example"
|
|
assert base_url_hostname("https://api.x.ai.example/v1") == "api.x.ai.example"
|
|
|
|
|
|
def test_port_is_ignored():
|
|
assert base_url_hostname("https://api.openai.com:443/v1") == "api.openai.com"
|
|
|
|
|
|
def test_whitespace_stripped():
|
|
assert base_url_hostname(" https://api.openai.com/v1 ") == "api.openai.com"
|
|
|
|
|
|
# ─── base_url_host_matches ────────────────────────────────────────────────
|
|
|
|
|
|
class TestBaseUrlHostMatchesExact:
|
|
def test_exact_domain_matches(self):
|
|
assert base_url_host_matches("https://openrouter.ai/api/v1", "openrouter.ai") is True
|
|
assert base_url_host_matches("https://moonshot.ai", "moonshot.ai") is True
|
|
|
|
def test_subdomain_matches(self):
|
|
# A subdomain of the registered domain should match — needed for
|
|
# api.moonshot.ai / api.kimi.com / portal.qwen.ai lookups that
|
|
# accept both the bare registrable domain and any subdomain under it.
|
|
assert base_url_host_matches("https://api.moonshot.ai/v1", "moonshot.ai") is True
|
|
assert base_url_host_matches("https://api.kimi.com/v1", "api.kimi.com") is True
|
|
assert base_url_host_matches("https://portal.qwen.ai/v1", "portal.qwen.ai") is True
|
|
|
|
|
|
class TestBaseUrlHostMatchesNegatives:
|
|
"""The reason this helper exists — defend against substring collisions."""
|
|
|
|
def test_path_segment_containing_domain_does_not_match(self):
|
|
assert base_url_host_matches("https://evil.test/moonshot.ai/v1", "moonshot.ai") is False
|
|
assert base_url_host_matches("https://proxy.example.test/openrouter.ai/v1", "openrouter.ai") is False
|
|
assert base_url_host_matches("https://proxy/api.kimi.com/v1", "api.kimi.com") is False
|
|
|
|
def test_host_suffix_does_not_match(self):
|
|
# Attacker-controlled hosts that end with the domain string are not
|
|
# the domain.
|
|
assert base_url_host_matches("https://moonshot.ai.evil/v1", "moonshot.ai") is False
|
|
assert base_url_host_matches("https://openrouter.ai.example/v1", "openrouter.ai") is False
|
|
|
|
def test_host_prefix_does_not_match(self):
|
|
# "fake-openrouter.ai" is not a subdomain of openrouter.ai.
|
|
assert base_url_host_matches("https://fake-openrouter.ai/v1", "openrouter.ai") is False
|
|
|
|
|
|
class TestBaseUrlHostMatchesEdgeCases:
|
|
def test_empty_base_url_returns_false(self):
|
|
assert base_url_host_matches("", "openrouter.ai") is False
|
|
assert base_url_host_matches(None, "openrouter.ai") is False # type: ignore[arg-type]
|
|
|
|
def test_empty_domain_returns_false(self):
|
|
assert base_url_host_matches("https://openrouter.ai/v1", "") is False
|
|
|
|
def test_case_insensitive(self):
|
|
assert base_url_host_matches("https://OpenRouter.AI/v1", "openrouter.ai") is True
|
|
assert base_url_host_matches("https://openrouter.ai/v1", "OPENROUTER.AI") is True
|
|
|
|
def test_trailing_dot_on_domain_stripped(self):
|
|
assert base_url_host_matches("https://openrouter.ai/v1", "openrouter.ai.") is True
|