0ea727a0b2* Studio RAG: disable trust_env on loopback llama-server httpx clients The RAG embedder health probe (embed_llama_server.py), its pooled httpx.Client, and the vision captioner (captioner.py) call the local 127.0.0.1 llama-server with httpx's default trust_env=True, so an ambient HTTP(S)_PROXY that returns 503 for loopback breaks embedder startup and captioning. Set trust_env=False on these loopback clients, matching the existing fix on the main llama_cpp and inference clients. External provider calls are untouched. Follow-up to the loopback trust_env fix; covers the remaining local llama-server clients in the RAG path. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Studio RAG tests: accept trust_env kwarg in captioner httpx.post mocks The loopback captioner now passes trust_env=False; update the _vision_complete fake_post stubs to accept it and assert it is False. * Trim comments in Studio RAG trust_env fix (comment-only) * RAG trust_env test: explicit UTF-8 read + scan all package .py files Addresses review: utf-8 open avoids a Windows decode error, and scanning every .py in core/rag catches any future file that adds an httpx call. --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
52 lines
1.9 KiB
Python
52 lines
1.9 KiB
Python
"""AST test locking in the RAG loopback trust_env fix: every httpx client/call in the RAG
|
|
package (all target the local 127.0.0.1 llama-server) must set trust_env=False."""
|
|
|
|
import ast
|
|
import os
|
|
|
|
RAG_DIR = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "core", "rag")
|
|
HTTPX_CALLEES = {"get", "post", "stream", "request", "Client", "AsyncClient"}
|
|
|
|
|
|
def _httpx_calls(path):
|
|
with open(path, encoding = "utf-8") as f:
|
|
tree = ast.parse(f.read(), filename = path)
|
|
calls = []
|
|
for node in ast.walk(tree):
|
|
if not isinstance(node, ast.Call):
|
|
continue
|
|
func = node.func
|
|
if (
|
|
isinstance(func, ast.Attribute)
|
|
and func.attr in HTTPX_CALLEES
|
|
and isinstance(func.value, ast.Name)
|
|
and func.value.id == "httpx"
|
|
):
|
|
calls.append(node)
|
|
return calls
|
|
|
|
|
|
def _sets_trust_env_false(call):
|
|
for kw in call.keywords:
|
|
if kw.arg == "trust_env" and isinstance(kw.value, ast.Constant) and kw.value.value is False:
|
|
return True
|
|
return False
|
|
|
|
|
|
def test_rag_loopback_httpx_clients_disable_trust_env():
|
|
# Scan every .py in the package so a new file with an httpx call can't bypass this.
|
|
checked = 0
|
|
for fname in sorted(f for f in os.listdir(RAG_DIR) if f.endswith(".py")):
|
|
path = os.path.join(RAG_DIR, fname)
|
|
for call in _httpx_calls(path):
|
|
checked += 1
|
|
assert _sets_trust_env_false(call), (
|
|
f"httpx.{call.func.attr} at {fname}:{call.lineno} must set trust_env=False "
|
|
f"(loopback llama-server client must not honor ambient HTTP(S)_PROXY)"
|
|
)
|
|
assert checked >= 3, f"expected at least 3 loopback httpx calls, found {checked}"
|
|
|
|
|
|
if __name__ == "__main__":
|
|
test_rag_loopback_httpx_clients_disable_trust_env()
|
|
print("OK: all RAG loopback httpx clients set trust_env=False")
|