iop/packages/go/singlerequesttemplate/template.go
toki 39fa1da55b fix(benchmark): 원샷 비교 실행 실패를 해소한다
호출기별 격리 쓰기 계약과 Gemini ingress, 단일 요청 stage 처리를 맞춰 실제 9-cell 비교가 생성물을 남길 수 있게 한다.
2026-08-12 14:37:17 +09:00

329 lines
9.4 KiB
Go

package singlerequesttemplate
import (
"crypto/sha256"
"encoding/hex"
"errors"
"fmt"
"regexp"
"strings"
)
const MaxTemplateBytes = 8192
const DefaultPlanTemplate = `# Plan
## Goal
{{goal}}
## Steps
{{steps}}
## Verification
{{verification}}
`
const DefaultReviewTemplate = `# Review
## Result
PASS
## Checks
{{checks}}
## Verification
{{verification}}
## Summary
{{summary}}
`
var (
ErrInvalidTemplate = errors.New("single-request template: invalid template")
ErrTemplateTooLarge = errors.New("single-request template: exceeds maximum size")
ErrMalformedPlan = errors.New("single-request template: malformed plan output")
ErrMalformedReview = errors.New("single-request template: malformed review fields")
)
var placeholderRegex = regexp.MustCompile(`\{\{[^}]*\}\}`)
var (
planPlaceholders = []string{"{{goal}}", "{{steps}}", "{{verification}}"}
planHeadings = []string{"# Plan", "## Goal", "## Steps", "## Verification"}
reviewPlaceholders = []string{"{{checks}}", "{{verification}}", "{{summary}}"}
reviewLines = []string{"# Review", "## Result", "PASS", "## Checks", "## Verification", "## Summary"}
)
type ReviewFields struct {
Checks string
Verification string
Summary string
}
// exactLineOffsets returns the byte offset of the first standalone line equal to
// want and how many standalone lines matched. A standalone line is a maximal
// "\n"-delimited segment compared byte for byte, so decorated variants such as
// "### Plan", "# Plan Mismatch", or "NOTPASS" never satisfy a required line.
func exactLineOffsets(tmpl, want string) (int, int) {
index, count, offset := -1, 0, 0
for {
var line string
end := strings.IndexByte(tmpl[offset:], '\n')
if end < 0 {
line = tmpl[offset:]
} else {
line = tmpl[offset : offset+end]
}
if line == want {
count++
if index < 0 {
index = offset
}
}
if end < 0 {
return index, count
}
offset += end + 1
}
}
// requireExactLines resolves every required standalone line, rejecting missing
// and duplicated occurrences, and returns their offsets in the requested order.
// Only the documented required line is echoed on failure; template content is
// never included in the error.
func requireExactLines(tmpl string, lines []string) ([]int, error) {
offsets := make([]int, len(lines))
for i, line := range lines {
index, count := exactLineOffsets(tmpl, line)
if count != 1 {
return nil, fmt.Errorf("%w: must contain the standalone line %q exactly once", ErrInvalidTemplate, line)
}
offsets[i] = index
}
return offsets, nil
}
// requirePlaceholderInventory closes the placeholder grammar. Each documented
// placeholder must appear exactly once; after removing those exact occurrences
// no template delimiter may survive, so unknown placeholders and unbalanced
// "{{"/"}}" residue are both rejected. Only documented placeholder names are
// echoed on failure; template content is never included in the error.
func requirePlaceholderInventory(tmpl string, placeholders []string) ([]int, error) {
offsets := make([]int, len(placeholders))
residue := tmpl
for i, placeholder := range placeholders {
if strings.Count(tmpl, placeholder) != 1 {
return nil, fmt.Errorf("%w: must contain %s exactly once", ErrInvalidTemplate, placeholder)
}
offsets[i] = strings.Index(tmpl, placeholder)
residue = strings.Replace(residue, placeholder, "", 1)
}
if placeholderRegex.MatchString(residue) {
return nil, fmt.Errorf("%w: template declares an unknown placeholder", ErrInvalidTemplate)
}
if strings.Contains(residue, "{{") || strings.Contains(residue, "}}") {
return nil, fmt.Errorf("%w: template leaves an unbalanced placeholder delimiter", ErrInvalidTemplate)
}
return offsets, nil
}
func ascending(values ...int) bool {
for i := 1; i < len(values); i++ {
if values[i-1] >= values[i] {
return false
}
}
return true
}
func Digest(content string) string {
h := sha256.Sum256([]byte(content))
return hex.EncodeToString(h[:])
}
func ValidatePlanTemplate(tmpl string) error {
if len(tmpl) == 0 {
return fmt.Errorf("%w: template is empty", ErrInvalidTemplate)
}
if len(tmpl) > MaxTemplateBytes {
return fmt.Errorf("%w: template size %d exceeds max %d", ErrTemplateTooLarge, len(tmpl), MaxTemplateBytes)
}
placeholders, err := requirePlaceholderInventory(tmpl, planPlaceholders)
if err != nil {
return err
}
idxGoal, idxSteps, idxVerif := placeholders[0], placeholders[1], placeholders[2]
if !ascending(idxGoal, idxSteps, idxVerif) {
return fmt.Errorf("%w: placeholders must appear in order {{goal}}, {{steps}}, {{verification}}", ErrInvalidTemplate)
}
headings, err := requireExactLines(tmpl, planHeadings)
if err != nil {
return err
}
idxPlanH, idxGoalH, idxStepsH, idxVerifH := headings[0], headings[1], headings[2], headings[3]
if !ascending(idxPlanH, idxGoalH, idxGoal, idxStepsH, idxSteps, idxVerifH, idxVerif) {
return fmt.Errorf("%w: headings and placeholders must follow exact structural order", ErrInvalidTemplate)
}
return nil
}
func ValidateReviewTemplate(tmpl string) error {
if len(tmpl) == 0 {
return fmt.Errorf("%w: template is empty", ErrInvalidTemplate)
}
if len(tmpl) > MaxTemplateBytes {
return fmt.Errorf("%w: template size %d exceeds max %d", ErrTemplateTooLarge, len(tmpl), MaxTemplateBytes)
}
placeholders, err := requirePlaceholderInventory(tmpl, reviewPlaceholders)
if err != nil {
return err
}
idxChecks, idxVerif, idxSumm := placeholders[0], placeholders[1], placeholders[2]
if !ascending(idxChecks, idxVerif, idxSumm) {
return fmt.Errorf("%w: placeholders must appear in order {{checks}}, {{verification}}, {{summary}}", ErrInvalidTemplate)
}
lines, err := requireExactLines(tmpl, reviewLines)
if err != nil {
return err
}
idxReviewH, idxResultH, idxPass := lines[0], lines[1], lines[2]
idxChecksH, idxVerifH, idxSummH := lines[3], lines[4], lines[5]
if !ascending(idxReviewH, idxResultH, idxPass, idxChecksH, idxChecks, idxVerifH, idxVerif, idxSummH, idxSumm) {
return fmt.Errorf("%w: headings and placeholders must follow exact structural order", ErrInvalidTemplate)
}
return nil
}
func ParsePlan(tmpl string, rawOutput string, maxOutputBytes int) ([]byte, error) {
if maxOutputBytes < 1 || len(rawOutput) > maxOutputBytes {
return nil, ErrMalformedPlan
}
if err := ValidatePlanTemplate(tmpl); err != nil {
return nil, err
}
if strings.Contains(rawOutput, "{{") || strings.Contains(rawOutput, "}}") {
return nil, ErrMalformedPlan
}
idxGoalPlaceholder := strings.Index(tmpl, "{{goal}}")
idxStepsPlaceholder := strings.Index(tmpl, "{{steps}}")
idxVerifPlaceholder := strings.Index(tmpl, "{{verification}}")
f0 := tmpl[:idxGoalPlaceholder]
f1 := tmpl[idxGoalPlaceholder+len("{{goal}}") : idxStepsPlaceholder]
f2 := tmpl[idxStepsPlaceholder+len("{{steps}}") : idxVerifPlaceholder]
f3 := tmpl[idxVerifPlaceholder+len("{{verification}}"):]
if !strings.HasPrefix(rawOutput, f0) {
return nil, ErrMalformedPlan
}
rem := rawOutput[len(f0):]
i1 := strings.Index(rem, f1)
if i1 < 0 {
return nil, ErrMalformedPlan
}
vGoal := rem[:i1]
rem = rem[i1+len(f1):]
i2 := strings.Index(rem, f2)
if i2 < 0 {
return nil, ErrMalformedPlan
}
vSteps := rem[:i2]
rem = rem[i2+len(f2):]
var vVerif string
if f3 == "" {
vVerif = rem
} else {
suffix := f3
if !strings.HasSuffix(rem, suffix) {
// Provider chat APIs commonly omit the model's final line feed. Treat
// only that last byte as optional; all other static suffix text must
// still match the configured template exactly.
if !strings.HasSuffix(f3, "\n") {
return nil, ErrMalformedPlan
}
suffix = strings.TrimSuffix(f3, "\n")
if !strings.HasSuffix(rem, suffix) {
return nil, ErrMalformedPlan
}
}
vVerif = rem[:len(rem)-len(suffix)]
}
trimmedGoal := strings.TrimSpace(vGoal)
if trimmedGoal == "" || strings.Contains(trimmedGoal, "\n") {
return nil, ErrMalformedPlan
}
trimmedSteps := strings.TrimSpace(vSteps)
if trimmedSteps == "" {
return nil, ErrMalformedPlan
}
stepLines := strings.Split(trimmedSteps, "\n")
if len(stepLines) < 2 || len(stepLines) > 6 {
return nil, ErrMalformedPlan
}
for _, l := range stepLines {
trimmedLine := strings.TrimSpace(l)
if !strings.HasPrefix(trimmedLine, "- ") || strings.TrimSpace(trimmedLine[2:]) == "" {
return nil, ErrMalformedPlan
}
}
trimmedVerif := strings.TrimSpace(vVerif)
if trimmedVerif == "" {
return nil, ErrMalformedPlan
}
verifLines := strings.Split(trimmedVerif, "\n")
if len(verifLines) < 1 || len(verifLines) > 3 {
return nil, ErrMalformedPlan
}
for _, l := range verifLines {
trimmedLine := strings.TrimSpace(l)
if !strings.HasPrefix(trimmedLine, "- ") || strings.TrimSpace(trimmedLine[2:]) == "" {
return nil, ErrMalformedPlan
}
}
return []byte(rawOutput), nil
}
func RenderReview(tmpl string, fields ReviewFields, maxOutputBytes int) ([]byte, error) {
if maxOutputBytes < 1 {
return nil, ErrMalformedReview
}
if err := ValidateReviewTemplate(tmpl); err != nil {
return nil, err
}
c := strings.TrimSpace(fields.Checks)
v := strings.TrimSpace(fields.Verification)
s := strings.TrimSpace(fields.Summary)
if c == "" || v == "" || s == "" {
return nil, ErrMalformedReview
}
res := strings.ReplaceAll(tmpl, "{{checks}}", c)
res = strings.ReplaceAll(res, "{{verification}}", v)
res = strings.ReplaceAll(res, "{{summary}}", s)
if strings.Contains(res, "{{") || strings.Contains(res, "}}") {
return nil, ErrMalformedReview
}
if len(res) > maxOutputBytes {
return nil, ErrMalformedReview
}
return []byte(res), nil
}