Trust only the upstream X-Gateway-Model header in the AI gateway

An upstream the gateway forwards to may itself emit X-Gateway-* headers
(e.g. another DevPlace-style gateway), which can collide with the ones
about to be built for the response. Only X-Gateway-Model is ever trusted
from upstream and relayed as-is - it is the one field an upstream can
legitimately know better than we do (it may have resolved an alias or
served a different pinned version). Every other header (cost, tokens,
latency, context, app-reference) is always our own measurement and is
never overwritten, since blending in an upstream's own accounting would
corrupt the usage ledger's per-model rollups and the quota math built on
top of it.

usage.upstream_reported_model() extracts that one header defensively
(case-insensitive lookup, rejects anything oversized or containing a
control character) and gateway._apply_served_model() applies it, display-
only, at the tail of every response-header build across chat, streaming,
embeddings, images, and passthrough.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BWJy6PrMMt5hwWxQwia2rd
This commit is contained in:
2026-09-08 03:44:06 +02:00
co-authored by Claude Sonnet 5
parent 7880bf4b31
commit c0e6abb923
6 changed files with 420 additions and 12 deletions
@@ -11,6 +11,7 @@ from devplacepy.services.openai_gateway.usage import (
new_usage_totals,
normalize_usage,
parse_usage_headers,
upstream_reported_model,
usage_metric_cards,
)
@@ -248,3 +249,79 @@ def test_validate_app_reference_strips_whitespace():
assert _validate_app_reference(" my-app ") == "my-app"
assert _validate_app_reference("\tdevplace\t") == "devplace"
class DictOnlyHeaders(dict):
"""A plain mapping with no case-insensitive .get, like a hand-rolled
fake response's headers dict in a test double - exercises the
manual case-insensitive fallback scan."""
def test_upstream_reported_model_reads_exact_case_via_get():
assert upstream_reported_model({"X-Gateway-Model": "vendor/served-model"}) == (
"vendor/served-model"
)
def test_upstream_reported_model_is_case_insensitive_via_real_headers():
import httpx
headers = httpx.Headers({"x-gateway-model": "vendor/lowercase-model"})
assert upstream_reported_model(headers) == "vendor/lowercase-model"
def test_upstream_reported_model_falls_back_to_manual_scan_for_plain_dicts():
headers = DictOnlyHeaders({"x-GATEWAY-model": "vendor/mixed-case"})
assert upstream_reported_model(headers) == "vendor/mixed-case"
def test_upstream_reported_model_strips_surrounding_whitespace():
assert upstream_reported_model({"X-Gateway-Model": " vendor/spaced "}) == (
"vendor/spaced"
)
def test_upstream_reported_model_missing_header_returns_none():
assert upstream_reported_model({}) is None
assert upstream_reported_model({"Content-Type": "application/json"}) is None
def test_upstream_reported_model_handles_falsy_and_malformed_containers():
assert upstream_reported_model(None) is None
assert upstream_reported_model({}) is None
assert upstream_reported_model(object()) is None
assert upstream_reported_model(["not", "a", "mapping"]) is None
def test_upstream_reported_model_rejects_empty_or_whitespace_only():
assert upstream_reported_model({"X-Gateway-Model": ""}) is None
assert upstream_reported_model({"X-Gateway-Model": " "}) is None
def test_upstream_reported_model_rejects_non_string_value():
assert upstream_reported_model({"X-Gateway-Model": 12345}) is None
assert upstream_reported_model({"X-Gateway-Model": None}) is None
def test_upstream_reported_model_rejects_oversized_value():
huge = "x" * 201
assert upstream_reported_model({"X-Gateway-Model": huge}) is None
exactly_max = "x" * 200
assert upstream_reported_model({"X-Gateway-Model": exactly_max}) == exactly_max
def test_upstream_reported_model_rejects_control_characters():
assert upstream_reported_model({"X-Gateway-Model": "vendor\r\nInjected: header"}) is None
assert upstream_reported_model({"X-Gateway-Model": "vendor\nmodel"}) is None
assert upstream_reported_model({"X-Gateway-Model": "vendor\x00model"}) is None
def test_upstream_reported_model_get_raising_never_propagates():
class HostileHeaders:
def get(self, key, default=None):
raise RuntimeError("boom")
def items(self):
raise RuntimeError("boom too")
assert upstream_reported_model(HostileHeaders()) is None