fix(adapters): input-schema enforcement + header/cookie params (OAI-02, OAI-03, OAI-07, OAI-09)

- build_request takes the op's input_schema and rejects undeclared
  input keys (INVALID_INPUT) before any outbound request is built;
  explicit `additionalProperties: true` opts into catch-all input;
  non-object inputs rejected (OAI-02)
- in: header parameters are stamped `wire: header` in the generated
  input schema and sent as upstream request headers, not query params;
  in: cookie fails import with a clear error (OAI-03)
- a spec parameter named `body` is rejected at import unconditionally
  (OAI-07)
- FromJsonSchema::new returns Result and validates method/path template/
  base_url at construction; registered visibility forced to Internal
  like from_openapi; module doc corrected (OAI-09)

Verified: cargo test, cargo test --all-features, clippy (both feature
sets, -D warnings), cargo fmt --check
This commit is contained in:
2026-08-29 12:48:13 +00:00
parent 7b83161171
commit a9d17405a7
4 changed files with 741 additions and 48 deletions
+276 -12
View File
@@ -9,6 +9,18 @@
//! (ADR-014): it reads `OperationContext.capabilities`, never
//! `std::env::var`. Imported error codes are `HTTP_<status>` to avoid
//! collision with the protocol-level codes (ADR-023).
//!
//! Input-schema enforcement (review 001 OAI-02): every input key must be
//! declared by the operation's `input_schema` or consumed by a path
//! template placeholder; undeclared keys are rejected with `INVALID_INPUT`
//! at call time. There is no pass-through knob — a request the forwarder
//! sends must match what `/schema` advertises, so peer-supplied input
//! cannot add upstream query parameters, headers, or craft a request body
//! the contract does not declare. Declared keys route by designation: a
//! property marked [`HEADER_PARAM_IN_MARKER`]` = "header"` is sent as a
//! request header, the declared [`GATEWAY_BODY_KEY`] property becomes the
//! request body, and every other declared key becomes an upstream query
//! parameter.
use std::collections::HashMap;
use std::sync::Arc;
@@ -40,12 +52,33 @@ pub(crate) const RESPONSE_BODY_CAP: usize = 16 * 1024 * 1024;
/// that would otherwise be discarded (FWD-10).
pub(crate) const ERROR_BODY_ECHO_CAP: usize = 4096;
// Fractional-path helpers and body echo caps follow; the gateway body key
// and the header-param wire marker used by the input routing live with the
// other request-construction defaults here.
/// Upper bound on how much of a non-2xx upstream body is read, both for
/// the bounded echo and for connection reuse. A larger error body is
/// truncated in the surfaced message and the connection is dropped —
/// a deliberate trade of pool reuse against unbounded drain time (FWD-10).
const STATUS_BODY_DRAIN: usize = 64 * 1024;
/// The input key that carries the request body on the gateway shape
/// (ADR-047). Declared by `from_openapi`'s generated input schemas
/// (OAI-07 rejects a spec parameter with the same name at import) and
/// consumed by [`build_request`] ahead of the query-parameter routing.
pub(crate) const GATEWAY_BODY_KEY: &str = "body";
/// Property-level marker inside an operation's `input_schema` properties
/// that routes the declared value into an HTTP request header instead of
/// the query string (review 001 OAI-03). `from_openapi` stamps
/// `"wire": "header"` on properties generated from `in: header`
/// parameters; `from_jsonschema` callers can mark their declared
/// properties the same way. Unmarked properties default to query
/// placement, preserving the pre-OAI-03 wire behavior for
/// `in: query`/`in: path` parameters.
pub(crate) const HEADER_PARAM_IN_MARKER: &str = "wire";
pub(crate) const HEADER_PARAM_MARKER_VALUE: &str = "header";
#[derive(Clone)]
pub enum HttpAuthScheme {
Bearer,
@@ -68,27 +101,39 @@ pub(crate) fn build_request(
auth_scheme: &Option<HttpAuthScheme>,
default_headers: &HashMap<String, String>,
namespace: &str,
input_schema: &Value,
input: &Value,
context: &OperationContext,
) -> Result<(Method, Url, Option<Value>, HeaderMap), CallError> {
let inputs = input.as_object();
let inputs = input.as_object().ok_or_else(|| {
CallError::invalid_input(format!(
"input must be a JSON object (got {}); adapter operations take a named-key input",
type_name_of(input)
))
})?;
enforce_input_schema(input_schema, inputs)?;
let mut query_params: Vec<(String, String)> = Vec::new();
let mut header_params: Vec<(String, String)> = Vec::new();
let param_locations = param_locations(input_schema);
let mut body: Option<Value> = None;
if let Some(obj) = inputs {
for (key, value) in obj {
if is_path_placeholder(key, path_template) {
continue;
}
if key == "body" {
body = Some(value.clone());
} else {
query_params.push((key.clone(), value_to_query(value)));
}
for (key, value) in inputs {
if is_path_placeholder(key, path_template) {
continue;
}
if key == GATEWAY_BODY_KEY {
body = Some(value.clone());
continue;
}
if param_locations.get(key.as_str()) == Some(&ParamLocation::Header) {
header_params.push((key.clone(), value_to_query(value)));
} else {
query_params.push((key.clone(), value_to_query(value)));
}
}
let rendered_path = render_path_template(path_template, inputs)?;
let rendered_path = render_path_template(path_template, Some(inputs))?;
let mut url = assemble_request_url(base_url, &rendered_path)?;
if !query_params.is_empty() {
let mut pairs = url.query_pairs_mut();
@@ -98,6 +143,19 @@ pub(crate) fn build_request(
}
let mut headers = HeaderMap::new();
for (k, v) in &header_params {
let name = HeaderName::try_from(k.as_str()).map_err(|_| {
CallError::internal(format!(
"declared header parameter `{k}` is not a valid HTTP header name; refusing to build a request that silently drops it"
))
})?;
let value = HeaderValue::try_from(v.as_str()).map_err(|_| {
CallError::internal(format!(
"declared header parameter `{k}` has an invalid value (control or non-ASCII bytes are not permitted); refusing to build a request that silently drops it"
))
})?;
headers.insert(name, value);
}
for (k, v) in default_headers {
let name = HeaderName::try_from(k.as_str()).map_err(|_| {
CallError::internal(format!(
@@ -161,6 +219,92 @@ pub(crate) fn build_request(
Ok((http_method, url, body, headers))
}
/// Upstream placement of a declared input property (review 001 OAI-03).
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
enum ParamLocation {
Query,
Header,
}
/// Map of declared property name → upstream placement, read from the
/// `input_schema`'s `properties` entries via [`HEADER_PARAM_IN_MARKER`]
/// (query placement is the default).
fn param_locations(input_schema: &Value) -> HashMap<&str, ParamLocation> {
let mut out = HashMap::new();
let Some(properties) = input_schema.get("properties").and_then(|p| p.as_object()) else {
return out;
};
for (name, schema) in properties {
let is_header = schema
.get(HEADER_PARAM_IN_MARKER)
.and_then(|w| w.as_str())
.is_some_and(|w| w == HEADER_PARAM_MARKER_VALUE);
out.insert(
name.as_str(),
if is_header {
ParamLocation::Header
} else {
ParamLocation::Query
},
);
}
out
}
fn type_name_of(value: &Value) -> &'static str {
match value {
Value::Null => "null",
Value::Bool(_) => "a boolean",
Value::Number(_) => "a number",
Value::String(_) => "a string",
Value::Array(_) => "an array",
Value::Object(_) => "an object",
}
}
/// Input-schema enforcement at call time (review 001 OAI-02).
///
/// Every input key must be declared by the input schema's `properties` —
/// including the gateway body property, which `from_openapi` declares as
/// `body` whenever the operation has a requestBody, and including the
/// path-consumed placeholders, which `from_openapi` also declares. An
/// explicit `"additionalProperties": true` opts the operation into
/// catch-all input (JSON Schema semantics: the schema advertises that
/// extra properties are valid), which `from_jsonschema` callers can use
/// for open-shaped endpoints. Anything else undeclared is a rejected
/// `INVALID_INPUT` rather than a silently-added upstream query parameter,
/// so peer input like `{debug: true}` or `{impersonate_id: …}` cannot
/// decorate an upstream request the contract does not advertise.
fn enforce_input_schema(
input_schema: &Value,
inputs: &serde_json::Map<String, Value>,
) -> Result<(), CallError> {
let declared = input_schema
.get("properties")
.and_then(|p| p.as_object())
.map(|p| p.keys().cloned().collect::<Vec<_>>())
.unwrap_or_default();
let catch_all = input_schema.get("additionalProperties") == Some(&Value::Bool(true));
let unknown: Vec<String> = inputs
.keys()
.filter(|key| !catch_all && !declared.iter().any(|d| d == *key))
.cloned()
.collect();
if let Some(first) = unknown.first() {
let declared_list = if declared.is_empty() {
"none".to_string()
} else {
declared.join(", ")
};
return Err(CallError::invalid_input(format!(
"input key `{first}` is not declared by the operation's input schema \
(declared: {declared_list}); undeclared keys are rejected so peer \
input cannot shape the upstream request beyond the advertised contract"
)));
}
Ok(())
}
/// Percent-encode set for a spliced path-parameter value: the WHATWG
/// path set (controls, space, `"`, `<`, `>`, `` ` ``, `#`, `?`, `{`, `}`)
/// plus `/` so a value stays one literal segment, plus `%` `?` `#`
@@ -502,6 +646,7 @@ pub(crate) async fn forward(
auth_scheme: &Option<HttpAuthScheme>,
default_headers: &HashMap<String, String>,
namespace: &str,
input_schema: &Value,
error_status_codes: &[(u16, String)],
input: Value,
context: OperationContext,
@@ -515,6 +660,7 @@ pub(crate) async fn forward(
auth_scheme,
default_headers,
namespace,
input_schema,
&input,
&context,
) {
@@ -620,6 +766,7 @@ pub(crate) fn forward_stream(
auth_scheme: &Option<HttpAuthScheme>,
default_headers: &HashMap<String, String>,
namespace: &str,
input_schema: &Value,
error_status_codes: &[(u16, String)],
input: Value,
context: OperationContext,
@@ -633,6 +780,7 @@ pub(crate) fn forward_stream(
auth_scheme,
default_headers,
namespace,
input_schema,
&input,
&context,
) {
@@ -973,6 +1121,7 @@ mod tests {
&None,
&TestHashMap::new(),
"svc",
&serde_json::json!({"type": "object", "additionalProperties": true}),
&input,
&ctx,
)?;
@@ -1116,6 +1265,115 @@ mod tests {
assert_eq!(url.query(), Some("lang=en&q=a%26b%3Dc+d"));
}
#[test]
fn undeclared_input_keys_are_rejected_not_sent_upstream() {
let ctx = noop_context();
let schema = json!({
"type": "object",
"properties": {"owner": {"type": "string"}, "body": {"type": "object"}},
});
for input in [
json!({"owner": "a", "debug": "true"}),
json!({"owner": "a", "impersonate_id": "x"}),
json!({"debug": "true"}),
] {
let err = build_request(
"https://api.example.com",
"/x/{owner}",
"GET",
&None,
&TestHashMap::new(),
"svc",
&schema,
&input,
&ctx,
)
.expect_err("undeclared peer input must be rejected");
assert_eq!(err.code, "INVALID_INPUT", "input was: {input}");
assert!(err.message.contains("not declared"), "input was: {input}");
}
}
#[test]
fn declared_body_and_header_params_route_off_the_query_string() {
let ctx = noop_context();
let schema = json!({
"type": "object",
"properties": {
"q": {"type": "string"},
"X-Trace-Id": {"type": "string", "wire": "header"},
"body": {"type": "object"},
},
});
let (_, url, body, headers) = build_request(
"https://api.example.com",
"/search",
"POST",
&None,
&TestHashMap::new(),
"svc",
&schema,
&json!({"q": "rust", "X-Trace-Id": "t-1", "body": {"page": 2}}),
&ctx,
)
.expect("declared input builds");
assert_eq!(url.query(), Some("q=rust"));
assert_eq!(
headers
.get("x-trace-id")
.expect("header param sent as header")
.to_str()
.expect("ascii header"),
"t-1"
);
assert_eq!(body, Some(json!({"page": 2})));
}
#[test]
fn non_object_input_is_rejected() {
let ctx = noop_context();
let schema = json!({"type": "object", "properties": {"q": {"type": "string"}}});
for input in [json!(null), json!([1]), json!("str"), json!(42)] {
let err = build_request(
"https://api.example.com",
"/x",
"GET",
&None,
&TestHashMap::new(),
"svc",
&schema,
&input,
&ctx,
)
.expect_err("non-object input must be rejected");
assert_eq!(err.code, "INVALID_INPUT");
}
}
#[test]
fn additional_properties_true_opts_into_catch_all_input() {
let ctx = noop_context();
let schema = json!({
"type": "object",
"properties": {"q": {"type": "string"}},
"additionalProperties": true,
});
let (_, url, _, _) = build_request(
"https://api.example.com",
"/search",
"GET",
&None,
&TestHashMap::new(),
"svc",
&schema,
&json!({"q": "rust", "debug": "true"}),
&ctx,
)
.expect("catch-all input builds");
let q = url.query().expect("query present");
assert!(q.contains("q=rust") && q.contains("debug=true"), "{q}");
}
fn ctx_with_capability(namespace: &str, value: String) -> OperationContext {
let mut ctx = noop_context();
ctx.capabilities = Capabilities::new().with_http_token(namespace, value);
@@ -1228,6 +1486,7 @@ mod tests {
auth_scheme,
&TestHashMap::new(),
"svc",
&serde_json::json!({"type": "object"}),
&[],
json!({}),
ctx,
@@ -1310,6 +1569,7 @@ mod tests {
&None,
&TestHashMap::new(),
"svc",
&serde_json::json!({"type": "object"}),
&[],
json!({}),
noop_context(),
@@ -1348,6 +1608,7 @@ mod tests {
&None,
&TestHashMap::new(),
"svc",
&serde_json::json!({"type": "object"}),
&[],
json!({}),
noop_context(),
@@ -1399,6 +1660,7 @@ mod tests {
}),
&TestHashMap::new(),
"svc",
&serde_json::json!({"type": "object"}),
&json!({}),
&ctx,
);
@@ -1422,6 +1684,7 @@ mod tests {
&None,
&defaults,
"svc",
&serde_json::json!({"type": "object"}),
&json!({}),
&noop_context(),
)
@@ -1441,6 +1704,7 @@ mod tests {
&None,
&defaults,
"svc",
&serde_json::json!({"type": "object"}),
&json!({}),
&noop_context(),
)