mirror of
https://github.com/likelovewant/ollama-for-amd.git
synced 2025-12-22 06:43:57 +00:00
llama: preserve field order in user-defined JSON schemas (#8002)
Previously we decoded and re-encoded JSON schemas during validation, which served no purpose since json.RawMessage already validates JSON syntax. Worse, the re-encoding lost field ordering from the original schema, which affects inference quality during step-by-step reasoning. While fixing this ordering issue by using json.RawMessage directly, testing revealed that schema_to_grammar (from llama.cpp) also fails to preserve field order during grammar generation. This appears to be the root cause of inference degradation. This change prevents us from mangling the user's original schema order, but we still need to address the ordering issue in schema_to_grammar. That will be a separate change. Updates #7978
This commit is contained in:
@@ -1,70 +1 @@
|
||||
package llama
|
||||
|
||||
import (
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/google/go-cmp/cmp"
|
||||
)
|
||||
|
||||
func TestJsonSchema(t *testing.T) {
|
||||
testCases := []struct {
|
||||
name string
|
||||
schema JsonSchema
|
||||
expected string
|
||||
}{
|
||||
{
|
||||
name: "empty schema",
|
||||
schema: JsonSchema{
|
||||
Type: "object",
|
||||
},
|
||||
expected: `array ::= "[" space ( value ("," space value)* )? "]" space
|
||||
boolean ::= ("true" | "false") space
|
||||
char ::= [^"\\\x7F\x00-\x1F] | [\\] (["\\bfnrt] | "u" [0-9a-fA-F]{4})
|
||||
decimal-part ::= [0-9]{1,16}
|
||||
integral-part ::= [0] | [1-9] [0-9]{0,15}
|
||||
null ::= "null" space
|
||||
number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
|
||||
object ::= "{" space ( string ":" space value ("," space string ":" space value)* )? "}" space
|
||||
root ::= object
|
||||
space ::= | " " | "\n" [ \t]{0,20}
|
||||
string ::= "\"" char* "\"" space
|
||||
value ::= object | array | string | number | boolean | null`,
|
||||
},
|
||||
{
|
||||
name: "invalid schema with circular reference",
|
||||
schema: JsonSchema{
|
||||
Type: "object",
|
||||
Properties: map[string]any{
|
||||
"self": map[string]any{
|
||||
"$ref": "#", // Self reference
|
||||
},
|
||||
},
|
||||
},
|
||||
expected: "", // Should return empty string for invalid schema
|
||||
},
|
||||
{
|
||||
name: "schema with invalid type",
|
||||
schema: JsonSchema{
|
||||
Type: "invalid_type", // Invalid type
|
||||
Properties: map[string]any{
|
||||
"foo": map[string]any{
|
||||
"type": "string",
|
||||
},
|
||||
},
|
||||
},
|
||||
expected: "", // Should return empty string for invalid schema
|
||||
},
|
||||
}
|
||||
|
||||
for _, tc := range testCases {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
result := tc.schema.AsGrammar()
|
||||
if !strings.EqualFold(strings.TrimSpace(result), strings.TrimSpace(tc.expected)) {
|
||||
if diff := cmp.Diff(tc.expected, result); diff != "" {
|
||||
t.Fatalf("grammar mismatch (-want +got):\n%s", diff)
|
||||
}
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user