mirror of
https://github.com/lukaszraczylo/mcp-captcharesolver.git
synced 2026-10-12 00:45:28 +00:00
lukaszraczylo
edb655f590
- Add Samples to TextOptions/GridOptions; N>1 runs N solves at temp 0.5 and majority-votes (text: most frequent; grid: tiles in strict majority). N<=1 keeps the single deterministic call path unchanged. - Add NoTargets to GridResult so callers know to click Verify instead of looping; prompt instructs empty tiles + no_targets:true when nothing matches. - Grid prompt: numbered cells 0..R*C-1, select any partial overlap. - Text prompt: disambiguate similar glyphs (0/O 1/l/I 5/S 2/Z 8/B). - Rotation prompt: reason step-by-step then emit final JSON.
37 lines
1.3 KiB
Go
37 lines
1.3 KiB
Go
package captcha
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"fmt"
|
|
|
|
"github.com/lukaszraczylo/captcha-solver-mcp/internal/llm"
|
|
)
|
|
|
|
// RotationResult is a best-effort FunCaptcha/rotation answer.
|
|
type RotationResult struct {
|
|
Choice int `json:"choice"`
|
|
Rotations int `json:"rotations"`
|
|
Confidence float64 `json:"confidence"`
|
|
}
|
|
|
|
// SolveRotation handles FunCaptcha-style rotation/choice puzzles (best-effort).
|
|
func SolveRotation(ctx context.Context, c llm.Client, img []byte, mediaType, instruction string) (RotationResult, error) {
|
|
prompt := fmt.Sprintf(
|
|
"You are solving a rotation/choice puzzle captcha. Instruction: %q. "+
|
|
"If asked to pick one image, return its 0-based index as choice. "+
|
|
"If asked to rotate, return the number of clockwise steps as rotations. "+
|
|
"First reason step-by-step about the correct orientation/choice, then give the final answer "+
|
|
`as the last thing you output: compact JSON {"choice":<int>,"rotations":<int>,"confidence":<0..1>}.`,
|
|
instruction)
|
|
raw, err := c.Vision(ctx, prompt, []llm.Image{{MediaType: mediaType, Data: img}}, llm.Options{})
|
|
if err != nil {
|
|
return RotationResult{}, err
|
|
}
|
|
var res RotationResult
|
|
if err := json.Unmarshal([]byte(extractJSON(raw)), &res); err != nil {
|
|
return RotationResult{}, fmt.Errorf("model did not return parseable rotation answer")
|
|
}
|
|
return res, nil
|
|
}
|