fix: dont compact standalone websearch schema (#24660)

add new `parse_tool_input_schema_without_compaction` to bypass the
existing compaction/trimming of client-provided tool schemas that are
over 4k bytes.

we want this for standalone web search to keep field guidance/metadata
on certain fields; this keeps us closer to parity with existing hosted
tool schema (which didnt go through this 4k byte filter).

codex-rs/tools/src/json_schema.rs

@@ -157,10 +157,26 @@ impl From<JsonSchema> for AdditionalProperties {
 
 /// Parse the tool `input_schema` or return an error for invalid schema.
 pub fn parse_tool_input_schema(input_schema: &JsonValue) -> Result<JsonSchema, serde_json::Error> {
+    let mut input_schema = prepare_tool_input_schema(input_schema);
+    compact_large_tool_schema(&mut input_schema);
+    deserialize_tool_input_schema(input_schema)
+}
+
+/// Parse a trusted tool `input_schema` without running large-schema compaction.
+pub fn parse_tool_input_schema_without_compaction(
+    input_schema: &JsonValue,
+) -> Result<JsonSchema, serde_json::Error> {
+    deserialize_tool_input_schema(prepare_tool_input_schema(input_schema))
+}
+
+fn prepare_tool_input_schema(input_schema: &JsonValue) -> JsonValue {
     let mut input_schema = input_schema.clone();
     sanitize_json_schema(&mut input_schema);
     prune_unreachable_definitions(&mut input_schema);
-    compact_large_tool_schema(&mut input_schema);
+    input_schema
+}
+
+fn deserialize_tool_input_schema(input_schema: JsonValue) -> Result<JsonSchema, serde_json::Error> {
     let schema: JsonSchema = serde_json::from_value(input_schema)?;
     if matches!(
         schema.schema_type,

codex-rs/tools/src/json_schema_tests.rs

@@ -3,6 +3,7 @@ use super::JsonSchema;
 use super::JsonSchemaPrimitiveType;
 use super::JsonSchemaType;
 use super::parse_tool_input_schema;
+use super::parse_tool_input_schema_without_compaction;
 use pretty_assertions::assert_eq;
 use std::collections::BTreeMap;
 
@@ -791,8 +792,8 @@ fn many_string_properties(count: usize) -> serde_json::Map<String, serde_json::V
 }
 
 #[test]
-fn parse_large_tool_input_schema_stops_after_descriptions_when_under_budget() {
-    let schema = parse_tool_input_schema(&serde_json::json!({
+fn parse_large_tool_input_schema_compacts_descriptions_only_on_default_path() {
+    let input_schema = serde_json::json!({
         "type": "object",
         "description": "x".repeat(4_500),
         "properties": {
@@ -806,8 +807,8 @@ fn parse_large_tool_input_schema_stops_after_descriptions_when_under_budget() {
                 "description": "Metadata value"
             }
         }
-    }))
-    .expect("parse schema");
+    });
+    let schema = parse_tool_input_schema(&input_schema).expect("parse schema");
 
     assert_eq!(
         serde_json::to_value(schema).expect("serialize schema"),
@@ -825,6 +826,26 @@ fn parse_large_tool_input_schema_stops_after_descriptions_when_under_budget() {
             }
         })
     );
+
+    let schema = parse_tool_input_schema_without_compaction(&input_schema).expect("parse schema");
+    assert_eq!(
+        serde_json::to_value(schema).expect("serialize schema"),
+        serde_json::json!({
+            "type": "object",
+            "description": "x".repeat(4_500),
+            "properties": {
+                "metadata": {
+                    "$ref": "#/$defs/metadata"
+                }
+            },
+            "$defs": {
+                "metadata": {
+                    "type": "string",
+                    "description": "Metadata value"
+                }
+            }
+        })
+    );
 }
 
 #[test]

codex-rs/tools/src/lib.rs

@@ -35,6 +35,7 @@ pub use json_schema::JsonSchema;
 pub use json_schema::JsonSchemaPrimitiveType;
 pub use json_schema::JsonSchemaType;
 pub use json_schema::parse_tool_input_schema;
+pub use json_schema::parse_tool_input_schema_without_compaction;
 pub use mcp_tool::mcp_call_tool_result_output_schema;
 pub use mcp_tool::parse_mcp_tool;
 pub use request_plugin_install::REQUEST_PLUGIN_INSTALL_APPROVAL_KIND_VALUE;