autoreg-skills-max: initial public release (restored, redacted, hardened)

skills/llm-vision-captcha/scripts/test_agent_captcha_aurora.py

@@ -0,0 +1,93 @@
+# -*- coding: utf-8 -*-
+"""Verification script: agent_captcha (GoubaLab/reg-factory-github) on Aurora gateway.
+Run: env -u PYTHONPATH python -u scripts/test_agent_captcha_aurora.py
+Requires: repo clone (default C:/Users/User/tmp/reg-factory-github, override REPO_PATH),
+Aurora up on 127.0.0.1:8080, PIL installed. ~30s total (2 live vision rounds)."""
+import sys, os, json, base64, io, time, re
+
+REPO = os.environ.get("REPO_PATH", r"C:\Users\User\tmp\reg-factory-github")
+sys.path.insert(0, os.path.join(REPO, "common"))
+
+AURORA = "http://127.0.0.1:8080"
+KEY = os.environ.get("AURORA_KEY", "enigothbreach2026master")
+os.environ["VISION_API_BASE"] = AURORA
+os.environ["VISION_API_KEY"] = KEY
+os.environ["VISION_MODEL"] = "cleanapis_com/gemini-3.6-flash"
+os.environ["VOTE_ZZ_BASE"] = AURORA
+os.environ["VOTE_ZZ_KEY"] = KEY
+os.environ["VOTE_GPT_KEY"] = KEY
+
+import agent_captcha as AC
+from PIL import Image, ImageDraw, ImageFont
+
+PASSED, FAILED = [], []
+
+def check(name, cond, detail=""):
+    tag = "PASS" if cond else "FAIL"
+    print(f"  [{tag}] {name} {detail}")
+    (PASSED if cond else FAILED).append(name)
+
+print("=== T1: _looks_like_refusal ===")
+check("refusal caught", AC._looks_like_refusal("I cannot fulfill this request"))
+check("empty=refusal", AC._looks_like_refusal(""))
+check("valid answer passes", not AC._looks_like_refusal("ANSWER=2 the left one"))
+
+print("\n=== T2: parse_json_answer ===")
+check("fence after CoT", AC.parse_json_answer('Sure ```json\n{"answer": 3}\n```') == {"answer": 3})
+check("no json => None", AC.parse_json_answer("no json here") is None)
+
+print("\n=== T3: fixtures + grid stitch + enhance ===")
+def make_tile(color, kind):
+    img = Image.new("RGB", (100, 100), "#222")
+    d = ImageDraw.Draw(img)
+    if kind == "square": d.rectangle([25, 25, 75, 75], fill=color)
+    elif kind == "circle": d.ellipse([25, 25, 75, 75], fill=color)
+    else: d.polygon([(50, 20), (20, 80), (80, 80)], fill=color)
+    return img
+
+def b64(img):
+    buf = io.BytesIO(); img.save(buf, format="PNG")
+    return base64.b64encode(buf.getvalue()).decode()
+
+tiles = [make_tile("#44ff44", "circle"), make_tile("#4477ff", "triangle"),
+         make_tile("#ff4444", "square"), make_tile("#ffff44", "square")]  # truth: idx 2
+b64_tiles = [b64(t) for t in tiles]
+ref_b64 = b64(make_tile("#ff4444", "square"))
+
+grid_path = os.path.join(os.path.dirname(__file__), "..", "ac_grid_test.png")
+res = AC.stitch_options_grid(b64_tiles, grid_path, reference_b64=ref_b64, cols=4, return_geom=True)
+grid_b64 = res[0] if isinstance(res, tuple) else res
+check("grid stitched", bool(grid_b64))
+
+enh_path = os.path.join(os.path.dirname(__file__), "..", "ac_enh_test.png")
+AC.enhance_local(b64_tiles[2], enh_path, scale=2)
+enh_jpg = enh_path.rsplit(".", 1)[0] + ".jpg"  # saves .jpg, not .png!
+check("enhanced 2x (jpg)", os.path.exists(enh_jpg))
+
+print("\n=== T4: ask_vision (live, Aurora) ===")
+Q = ("Look at this 2x2 grid of colored shapes plus a reference image on top. "
+     "Which numbered tile shows a RED SQUARE exactly like the reference? "
+     "Reply ANSWER=N where N is 0-3.")
+t0 = time.time()
+txt = AC.ask_vision(Q, grid_b64, models=["cleanapis_com/gemini-3.6-flash"], max_tokens=150)
+check("ask_vision answered", txt is not None, f"{time.time()-t0:.1f}s")
+if txt:
+    m = re.findall(r"ANSWER\s*=\s*(\d+)", txt)
+    check("ask_vision correct (2)", m and int(m[-1]) == 2, f"got {m}")
+
+print("\n=== T5: vote_answer (live multi-model) ===")
+AC.VOTER_MODELS = [
+    (AURORA, KEY, "cleanapis_com/gemini-3.6-flash"),
+    (AURORA, KEY, "cleanapis_com/gemini-3.1-pro"),
+    (AURORA, KEY, "dashscope_aliyuncs_com/qwen-vl-max"),
+    (AURORA, KEY, "anthropic_com/claude-sonnet-4-6"),
+]
+t0 = time.time()
+best, votes, raws = AC.vote_answer(Q, grid_b64, n_options=4, deadline=60)
+print(f"  votes={votes} in {time.time()-t0:.1f}s")
+check("winner returned", best is not None)
+check("winner correct (2)", best == 2, f"best={best}")
+
+print("\n" + "=" * 40)
+print(f"RESULT: {len(PASSED)} PASS / {len(FAILED)} FAIL")
+if FAILED: print("FAILED:", FAILED)