Compare commits

..

2 Commits

Author SHA1 Message Date
Alexander Whitestone
06a6b53a37 feat: add tower world-changing items for #514
Some checks failed
Agent PR Gate / gate (pull_request) Failing after 58s
Self-Healing Smoke / self-healing-smoke (pull_request) Failing after 26s
Agent PR Gate / report (pull_request) Successful in 23s
Smoke Test / smoke (pull_request) Failing after 27s
2026-04-22 02:54:56 -04:00
Alexander Whitestone
5ce4fa6cb8 test: define tower world items for #514 2026-04-22 02:43:29 -04:00
6 changed files with 203 additions and 503 deletions

View File

@@ -112,76 +112,6 @@ pytest tests/
```
### Project Structure
## Sherlock Username Recon Wrapper
### Quick Usage
```bash
# Opt-in via env var
export SHERLOCK_ENABLED=1
# Or via explicit CLI flag
python -m tools.sherlock_wrapper --query "alice" --opt-in --json
# With site whitelist
python -m tools.sherlock_wrapper --query "alice" --opt-in --sites github twitter --json
```
### What It Does
Builds a bounded local wrapper around the Sherlock username OSINT tool that:
- **Opt-in gate** — SHERLOCK_ENABLED=1 or `--opt-in` required before any external call
- **Local-first caching** — results cached in `~/.cache/timmy/sherlock_cache.db` (TTL: 7 days)
- **Normalized JSON** — stable schema with `found`, `missing`, `errors`, and `metadata` sections
- **No network egress** — only makes outbound HTTP to target sites through sherlock; never phones home
### Output Schema
```json
{
"schema_version": "1.0",
"query": "alice",
"timestamp": "2025-04-26T14:23:00+00:00",
"found": [
{"site": "github", "url": "https://github.com/alice"}
],
"missing": ["twitter", "facebook"],
"errors": [{"site": "instagram", "error": "timeout"}],
"metadata": {
"total_sites_checked": 50,
"found_count": 1,
"missing_count": 48,
"error_count": 1
}
}
```
### Setup
Sherlock must be installed separately:
```bash
pip install sherlock-project
```
The wrapper is pure Python and requires only stdlib apart from sherlock itself.
### Why an Opt-In Gate?
Sherlock makes outbound HTTP requests to dozens of third-party sites. The opt-in gate:
1. Ensures a human operator explicitly approves this dependency
2. Makes the outbound traffic auditable in session logs
3. Prevents accidental invocation in automated pipelines
### Running the Smoke Test
```bash
# Run unit + integration tests
pytest tests/test_sherlock_wrapper.py -v
```
```
.

View File

@@ -12,6 +12,29 @@ WORLD_DIR = Path('/Users/apayne/.timmy/evennia/timmy_world')
STATE_FILE = WORLD_DIR / 'game_state.json'
TIMMY_LOG = WORLD_DIR / 'timmy_log.md'
WORLD_ITEMS = {
"foraged key": {"effect": "unlock_tower_cache", "quest_item": True, "consumable": False, "effect_text": "A hidden cache clicks open in the Tower wall."},
"seed packet": {"effect": "grow_garden", "quest_item": False, "consumable": True, "effect_text": "Fresh growth pushes through the Garden soil."},
"notebook": {"effect": "write_notebook_rule", "quest_item": False, "consumable": False, "effect_text": "A new rule joins the whiteboard in the Tower."},
"cloth": {"effect": "patch_bridge", "quest_item": False, "consumable": True, "effect_text": "The Bridge railing is wrapped tight against the weather."},
"oil can": {"effect": "stoke_forge", "quest_item": False, "consumable": True, "effect_text": "The Forge fire answers with a hotter glow."},
"lantern": {"effect": "light_bridge", "quest_item": False, "consumable": False, "effect_text": "A steady lantern glow cuts through the dark over the Bridge."},
"rope spool": {"effect": "secure_bridge", "quest_item": False, "consumable": True, "effect_text": "The Bridge is lashed tight and feels safer underfoot."},
"chalk": {"effect": "mark_threshold", "quest_item": False, "consumable": True, "effect_text": "A chalk mark at the Threshold points wanderers home."},
"weather vane": {"effect": "read_weather", "quest_item": False, "consumable": False, "effect_text": "The weather vane settles and the coming storm makes sense."},
"sunstone": {"effect": "restore_tower_power", "quest_item": False, "consumable": False, "effect_text": "Warm light races through the Tower circuits."},
"iron nails": {"effect": "reinforce_bridge", "quest_item": False, "consumable": True, "effect_text": "The Bridge planks are pinned down against the flood."},
"river stone": {"effect": "water_garden", "quest_item": False, "consumable": True, "effect_text": "Moisture returns to the Garden beds."},
}
ROOM_DISCOVERABLES = {
"Threshold": ["chalk", "sunstone"],
"Tower": ["notebook", "lantern"],
"Forge": ["oil can", "iron nails"],
"Garden": ["seed packet", "foraged key"],
"Bridge": ["cloth", "rope spool", "weather vane", "river stone"],
}
# ============================================================
# NARRATIVE ARC — 4 phases that transform the world
# ============================================================
@@ -143,6 +166,8 @@ class World:
"visitors": [],
},
}
for room_name, items in ROOM_DISCOVERABLES.items():
self.rooms[room_name]["discoverables"] = list(items)
# Characters (not NPCs — they have lives)
self.characters = {
@@ -258,6 +283,14 @@ class World:
"items_crafted": 0,
"conflicts_resolved": 0,
"nights_survived": 0,
"bridge_patched": False,
"bridge_secured": False,
"bridge_reinforced": False,
"bridge_lantern_lit": False,
"tower_cache_unlocked": False,
"threshold_marked": False,
"weather_readable": False,
"sunstone_socketed": False,
}
def tick_time(self):
@@ -376,6 +409,14 @@ class World:
desc += " Rain mists on the dark water below."
if len(self.rooms["Bridge"]["carvings"]) > 1:
desc += f" There are {len(self.rooms['Bridge']['carvings'])} carvings now."
if self.state.get("bridge_patched"):
desc += " Cloth bindings keep the railing from splintering."
if self.state.get("bridge_secured"):
desc += " Rope lines keep the span steady against the flood."
if self.state.get("bridge_reinforced"):
desc += " Fresh iron nails hold the planks tight."
if self.state.get("bridge_lantern_lit"):
desc += " A lantern glows warm over the water."
elif room_name == "Tower":
power = self.state.get("tower_power_low", False)
@@ -384,6 +425,19 @@ class World:
if self.rooms["Tower"]["messages"]:
desc += f" The whiteboard holds {len(self.rooms['Tower']['messages'])} rules."
if self.state.get("tower_cache_unlocked"):
desc += " A hidden cache stands open beneath the whiteboard."
if room_name == "Threshold" and self.state.get("threshold_marked"):
desc += " A chalk arrow points late arrivals toward shelter."
if room_name == "Garden" and self.state.get("weather_readable"):
desc += " The beds are arranged to catch whatever weather comes next."
if room_name == "Tower" and self.state.get("sunstone_socketed"):
desc += " A sunstone keeps the room lit with a stubborn amber glow."
discoverables = room.get("discoverables", [])
if discoverables:
desc += f" Discoverable items: {', '.join(discoverables)}."
# Who's here
here = [n for n, c in self.characters.items() if c["room"] == room_name and n != char_name]
@@ -485,6 +539,10 @@ class ActionSystem:
"cost": 1,
"description": "Take an item from the room",
},
"use": {
"cost": 1,
"description": "Use an item from your inventory to change the world",
},
"examine": {
"cost": 0,
"description": "Examine something in detail",
@@ -530,6 +588,13 @@ class ActionSystem:
available.append("rest")
available.append("examine")
discoverables = world.rooms[room].get("discoverables", [])
for item in discoverables:
available.append(f"take:{item}")
for item in char["inventory"]:
available.append(f"use:{item}")
if char["inventory"]:
available.append("give:item")
@@ -1072,6 +1137,76 @@ class GameEngine:
f.write(f"\n*Began: {datetime.now().strftime('%Y-%m-%d %H:%M')}*\n\n")
f.write("---\n\n")
f.write(message + "\n")
def _take_item(self, item_name, scene):
room_name = self.world.characters["Timmy"]["room"]
discoverables = self.world.rooms[room_name].get("discoverables", [])
if item_name not in discoverables:
scene["log"].append(f"There is no {item_name} here.")
return
discoverables.remove(item_name)
self.world.characters["Timmy"]["inventory"].append(item_name)
scene["log"].append(f"You take the {item_name}.")
if WORLD_ITEMS.get(item_name, {}).get("quest_item"):
scene["world_events"].append(f"The {item_name} feels important. It might open a quest route.")
def _use_item(self, item_name, scene):
inventory = self.world.characters["Timmy"]["inventory"]
if item_name not in inventory:
scene["log"].append(f"You are not carrying {item_name}.")
return
item = WORLD_ITEMS.get(item_name)
if not item:
scene["log"].append(f"The {item_name} doesn't seem to do anything.")
return
effect = item["effect"]
effect_text = item["effect_text"]
if effect == "grow_garden":
self.world.rooms["Garden"]["growth"] = min(5, self.world.rooms["Garden"]["growth"] + 2)
self.world.state["garden_drought"] = False
elif effect == "unlock_tower_cache":
self.world.state["tower_cache_unlocked"] = True
cache_rule = "Rule: Keys open more than doors when the world trusts you."
if cache_rule not in self.world.rooms["Tower"]["messages"]:
self.world.rooms["Tower"]["messages"].append(cache_rule)
elif effect == "write_notebook_rule":
note_rule = f"Rule #{self.world.tick}: A notebook can turn memory into structure."
self.world.rooms["Tower"]["messages"].append(note_rule)
elif effect == "patch_bridge":
self.world.state["bridge_patched"] = True
self.world.state["bridge_flooding"] = False
self.world.rooms["Bridge"]["weather"] = None
self.world.rooms["Bridge"]["rain_ticks"] = 0
elif effect == "stoke_forge":
self.world.rooms["Forge"]["fire"] = "glowing"
self.world.state["forge_fire_dying"] = False
elif effect == "light_bridge":
self.world.state["bridge_lantern_lit"] = True
elif effect == "secure_bridge":
self.world.state["bridge_secured"] = True
self.world.state["bridge_flooding"] = False
self.world.rooms["Bridge"]["weather"] = None
self.world.rooms["Bridge"]["rain_ticks"] = 0
elif effect == "mark_threshold":
self.world.state["threshold_marked"] = True
elif effect == "read_weather":
self.world.state["weather_readable"] = True
self.world.state["garden_drought"] = False
elif effect == "restore_tower_power":
self.world.state["tower_power_low"] = False
self.world.state["sunstone_socketed"] = True
elif effect == "reinforce_bridge":
self.world.state["bridge_reinforced"] = True
self.world.state["bridge_flooding"] = False
elif effect == "water_garden":
self.world.state["garden_drought"] = False
self.world.rooms["Garden"]["growth"] = min(5, self.world.rooms["Garden"]["growth"] + 1)
scene["log"].append(f"You use the {item_name}. {effect_text}")
scene["world_events"].append(effect_text)
if item.get("consumable"):
inventory.remove(item_name)
def run_tick(self, timmy_action="look"):
"""Run one tick. Return the scene and available choices."""
@@ -1100,7 +1235,7 @@ class GameEngine:
action_costs = {
"move": 2, "tend_fire": 3, "write_rule": 2, "carve": 2,
"plant": 2, "study": 2, "forge": 3, "help": 2, "speak": 1,
"listen": 0, "rest": -2, "examine": 0, "give": 0, "take": 1,
"listen": 0, "rest": -2, "examine": 0, "give": 0, "take": 1, "use": 1,
}
# Extract action name
@@ -1360,9 +1495,17 @@ class GameEngine:
elif timmy_action == "examine":
room = self.world.characters["Timmy"]["room"]
room_data = self.world.rooms[room]
items = room_data.get("items", [])
items = room_data.get("items", []) + room_data.get("discoverables", [])
scene["log"].append(f"You examine The {room}. You see: {', '.join(items) if items else 'nothing special'}")
elif timmy_action.startswith("take:"):
item_name = timmy_action.split(":", 1)[1]
self._take_item(item_name, scene)
elif timmy_action.startswith("use:"):
item_name = timmy_action.split(":", 1)[1]
self._use_item(item_name, scene)
elif timmy_action.startswith("help:"):
# Help increases trust
target_name = timmy_action.split(":")[1]

View File

@@ -1,182 +0,0 @@
#!/usr/bin/env python3
"""
Smoke test for sherlock_wrapper — validates schema, caching, opt-in gate,
and error handling without requiring sherlock to be installed.
"""
import json
import os
import sys
import tempfile
import unittest
from pathlib import Path
from unittest.mock import patch, MagicMock
sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "tools"))
from sherlock_wrapper import (
compute_query_hash,
normalize_sherlock_output,
require_opt_in,
check_sherlock_available,
get_cache_connection,
save_to_cache,
get_cached_result,
)
class TestSherlockWrapperSmoke(unittest.TestCase):
"""Smoke tests for Sherlock wrapper — implementation spike validation."""
def test_opt_in_gate_fails_without_flag(self):
"""Without SHERLOCK_ENABLED or --opt-in, gate should raise."""
with patch("sherlock_wrapper.SHERLOCK_ENABLED", False):
with self.assertRaises(RuntimeError) as ctx:
require_opt_in(opt_in=False)
self.assertIn("opt-in only", str(ctx.exception).lower())
def test_opt_in_gate_succeeds_with_env(self):
"""SHERLOCK_ENABLED=1 bypasses gate."""
with patch("sherlock_wrapper.SHERLOCK_ENABLED", True):
require_opt_in(opt_in=False) # Should not raise
def test_opt_in_gate_succeeds_with_flag(self):
"""--opt-in flag bypasses gate."""
with patch("sherlock_wrapper.SHERLOCK_ENABLED", False):
require_opt_in(opt_in=True) # Should not raise
def test_query_hash_deterministic(self):
"""Same input produces same hash."""
h1 = compute_query_hash("alice")
h2 = compute_query_hash("alice")
self.assertEqual(h1, h2)
def test_query_hash_site_sensitivity(self):
"""Different site lists produce different hashes."""
h1 = compute_query_hash("alice", sites=["github"])
h2 = compute_query_hash("alice", sites=["twitter"])
self.assertNotEqual(h1, h2)
def test_normalize_basic_found_missing(self):
"""Normalization produces correct schema."""
raw = {
"github": {"status": "found", "url": "https://github.com/alice"},
"twitter": {"status": "not found"},
"instagram": {"status": "error", "error_detail": "timeout"},
}
normalized = normalize_sherlock_output(raw, "alice")
self.assertEqual(normalized["query"], "alice")
self.assertEqual(normalized["metadata"]["found_count"], 1)
self.assertEqual(normalized["metadata"]["missing_count"], 1)
self.assertEqual(normalized["metadata"]["error_count"], 1)
self.assertEqual(len(normalized["found"]), 1)
self.assertEqual(normalized["found"][0]["site"], "github")
self.assertIn("twitter", normalized["missing"])
self.assertEqual(normalized["errors"][0]["site"], "instagram")
def test_normalized_schema_has_required_fields(self):
"""Output schema contains all required top-level keys."""
raw = {"site1": {"status": "not found"}}
normalized = normalize_sherlock_output(raw, "testuser")
required = ["schema_version", "query", "timestamp", "found", "missing",
"errors", "metadata"]
for key in required:
self.assertIn(key, normalized)
self.assertIsInstance(normalized["timestamp"], str)
self.assertIsInstance(normalized["found"], list)
self.assertIsInstance(normalized["missing"], list)
self.assertIsInstance(normalized["errors"], list)
self.assertIsInstance(normalized["metadata"], dict)
def test_cache_roundtrip(self):
"""Result can be written and read back from cache."""
with tempfile.TemporaryDirectory() as tmp:
with patch("sherlock_wrapper.CACHE_DB", Path(tmp) / "cache.db"):
test_result = {
"schema_version": "1.0",
"query": "alice",
"timestamp": "2025-04-26T00:00:00+00:00",
"found": [],
"missing": ["github"],
"errors": [],
"metadata": {"total_sites_checked": 1, "found_count": 0, "missing_count": 1, "error_count": 0},
}
query_hash = compute_query_hash("alice")
save_to_cache(query_hash, test_result)
retrieved = get_cached_result(query_hash)
self.assertEqual(retrieved, test_result)
def test_cache_miss_on_stale(self):
"""Cache returns None when entry is older than 7 days."""
with tempfile.TemporaryDirectory() as tmp:
db_path = Path(tmp) / "cache.db"
with patch("sherlock_wrapper.CACHE_DB", db_path):
old_ts = "2025-04-01T00:00:00+00:00"
old_result = {
"schema_version": "1.0", "query": "alice",
"timestamp": old_ts, "found": [], "missing": [], "errors": [],
"metadata": {"total_sites_checked": 0, "found_count": 0, "missing_count": 0, "error_count": 0},
}
query_hash = compute_query_hash("alice")
# Direct DB insert with controlled timestamp (bypass save_to_cache's NOW)
conn = get_cache_connection()
conn.execute(
"INSERT INTO cache (query_hash, result_json, timestamp) VALUES (?, ?, ?)",
(query_hash, json.dumps(old_result), old_ts)
)
conn.commit()
retrieved = get_cached_result(query_hash)
self.assertIsNone(retrieved)
def test_sherlock_available_check(self):
"""check_sherlock_available returns bool."""
available = check_sherlock_available()
self.assertIsInstance(available, bool)
# Note: on this test system sherlock may not be installed, so False is expected.
# The important thing is the function returns a bool.
print(f"[INFO] Sherlock installed: {available}")
class TestSherlockWrapperIntegration(unittest.TestCase):
"""Integration tests with mocked sherlock module."""
def test_run_sherlock_with_opt_in(self):
"""run_sherlock succeeds with opt-in and returns normalized result."""
fake_sherlock = MagicMock()
fake_sherlock.sherlock = MagicMock(return_value={
"github": {"status": "found", "url": "https://github.com/alice"},
"twitter": {"status": "not found"},
})
with patch.dict("sys.modules", {"sherlock": fake_sherlock}):
import importlib
import sherlock_wrapper
importlib.reload(sherlock_wrapper)
with patch.dict(os.environ, {"SHERLOCK_ENABLED": "1"}):
from sherlock_wrapper import run_sherlock
result = run_sherlock("alice", opt_in=True)
self.assertEqual(result["query"], "alice")
self.assertEqual(result["metadata"]["found_count"], 1)
def test_run_sherlock_fails_without_opt_in(self):
"""run_sherlock raises RuntimeError without opt-in."""
from sherlock_wrapper import run_sherlock
with self.assertRaises(RuntimeError) as ctx:
run_sherlock("alice", opt_in=False)
self.assertIn("opt-in only", str(ctx.exception).lower())
def test_run_sherlock_uses_cache(self):
"""Cached result short-circuits sherlock execution."""
cached = {
"schema_version": "1.0", "query": "alice", "timestamp": "2025-04-26T00:00:00+00:00",
"found": [{"site": "github", "url": "https://github.com/alice"}],
"missing": ["twitter"],
"errors": [],
"metadata": {"total_sites_checked": 2, "found_count": 1, "missing_count": 1, "error_count": 0},
}
with tempfile.TemporaryDirectory() as tmp:
with patch("sherlock_wrapper.CACHE_DB", Path(tmp) / "cache.db"):
query_hash = compute_query_hash("alice")
save_to_cache(query_hash, cached)
from sherlock_wrapper import run_sherlock
result = run_sherlock("alice", opt_in=True)
self.assertEqual(result, cached)

View File

@@ -0,0 +1,58 @@
from importlib.util import module_from_spec, spec_from_file_location
from pathlib import Path
import unittest
ROOT = Path(__file__).resolve().parent.parent
GAME_PATH = ROOT / "evennia" / "timmy_world" / "game.py"
def load_game_module():
spec = spec_from_file_location("tower_game_items", GAME_PATH)
module = module_from_spec(spec)
assert spec.loader is not None
spec.loader.exec_module(module)
module.random.seed(0)
return module
class TestTowerGameWorldItems(unittest.TestCase):
def test_world_has_ten_unique_items_and_a_quest_item(self):
module = load_game_module()
world = module.World()
room_items = {
item
for room in world.rooms.values()
for item in room.get("discoverables", [])
}
self.assertGreaterEqual(len(room_items), 10)
self.assertIn("foraged key", room_items)
self.assertTrue(module.WORLD_ITEMS["foraged key"]["quest_item"])
def test_items_change_world_state_when_used(self):
module = load_game_module()
engine = module.GameEngine()
engine.start_new_game()
engine.world.characters["Timmy"]["energy"] = 10
engine.world.characters["Timmy"]["room"] = "Garden"
initial_growth = engine.world.rooms["Garden"]["growth"]
engine.run_tick("take:seed packet")
use_seed = engine.run_tick("use:seed packet")
self.assertGreater(engine.world.rooms["Garden"]["growth"], initial_growth)
self.assertNotIn("seed packet", engine.world.characters["Timmy"]["inventory"])
self.assertTrue(any("garden" in line.lower() for line in use_seed["world_events"] + use_seed["log"]))
engine.world.characters["Timmy"]["energy"] = 10
engine.run_tick("take:foraged key")
use_key = engine.run_tick("use:foraged key")
self.assertTrue(engine.world.state["tower_cache_unlocked"])
self.assertTrue(any("cache" in line.lower() or "quest" in line.lower() for line in use_key["world_events"] + use_key["log"]))
if __name__ == "__main__":
unittest.main()

View File

View File

@@ -1,249 +0,0 @@
#!/usr/bin/env python3
"""
Sherlock username recon wrapper — opt-in, cached, normalized JSON output.
This is an implementation spike (issue #874) to validate local integration
of the Sherlock OSINT tool without violating sovereignty/provenance standards.
"""
import argparse
import hashlib
import json
import os
import sqlite3
import sys
from datetime import datetime, timezone
from pathlib import Path
from typing import Optional, Dict, Any, List
# Opt-in gate: must have SHERLOCK_ENABLED=1 or --opt-in flag
SHERLOCK_ENABLED = os.environ.get("SHERLOCK_ENABLED", "0") == "1"
# Cache location
CACHE_DIR = Path.home() / ".cache" / "timmy"
CACHE_DB = CACHE_DIR / "sherlock_cache.db"
# Normalized output schema version
SCHEMA_VERSION = "1.0"
def require_opt_in(opt_in: bool = False) -> None:
"""Enforce opt-in gate for Sherlock external dependency."""
if not (SHERLOCK_ENABLED or opt_in):
raise RuntimeError(
"Sherlock is opt-in only. Set SHERLOCK_ENABLED=1 or pass --opt-in."
)
def check_sherlock_available() -> bool:
"""Check if sherlock Python package is installed."""
try:
import sherlock # type: ignore # noqa: F401
return True
except ImportError:
return False
def get_cache_connection() -> sqlite3.Connection:
"""Initialize cache directory and return DB connection."""
CACHE_DIR.mkdir(parents=True, exist_ok=True)
conn = sqlite3.connect(str(CACHE_DB))
conn.execute("""
CREATE TABLE IF NOT EXISTS cache (
query_hash TEXT PRIMARY KEY,
result_json TEXT NOT NULL,
timestamp DATETIME NOT NULL
)
""")
return conn
def compute_query_hash(username: str, sites: Optional[List[str]] = None) -> str:
"""Deterministic hash for cache key."""
components = [username.lower().strip()]
if sites:
components.extend(sorted(sites))
raw = "|".join(components)
return hashlib.sha256(raw.encode()).hexdigest()
def get_cached_result(query_hash: str) -> Optional[Dict[str, Any]]:
"""Retrieve cached result if available and not stale (TTL: 7 days)."""
conn = get_cache_connection()
cur = conn.execute(
"SELECT result_json, timestamp FROM cache WHERE query_hash = ?",
(query_hash,)
)
row = cur.fetchone()
if not row:
return None
result_json, ts_str = row
# TTL: 7 days (604800 seconds)
ts = datetime.fromisoformat(ts_str)
age_seconds = (datetime.now(timezone.utc) - ts).total_seconds()
if age_seconds >= 604800:
return None
return json.loads(result_json)
def save_to_cache(query_hash: str, result: Dict[str, Any]) -> None:
"""Persist result to cache."""
conn = get_cache_connection()
conn.execute(
"INSERT OR REPLACE INTO cache (query_hash, result_json, timestamp) VALUES (?, ?, ?)",
(query_hash, json.dumps(result), datetime.now(timezone.utc).isoformat())
)
conn.commit()
conn.close()
def normalize_sherlock_output(
raw_result: Dict[str, Any],
username: str,
sites_checked: Optional[List[str]] = None
) -> Dict[str, Any]:
"""
Convert raw sherlock output into a stable, normalized schema.
Expected sherlock result shape (via Python API):
{
"site_name": {"url": "...", "status": "found"|"not found"|"error", ...},
...
}
"""
found: List[Dict[str, str]] = []
missing: List[str] = []
errors: List[Dict[str, str]] = []
for site_name, site_data in raw_result.items():
status = site_data.get("status", "")
url = site_data.get("url", "")
if status == "found" and url:
found.append({"site": site_name, "url": url})
elif status == "not found":
missing.append(site_name)
else:
errors.append({"site": site_name, "error": status or "unknown"})
# Compute totals from the original site list if provided
total_sites = len(raw_result) if sites_checked is None else len(sites_checked)
return {
"schema_version": SCHEMA_VERSION,
"query": username,
"timestamp": datetime.now(timezone.utc).isoformat(),
"found": found,
"missing": missing,
"errors": errors,
"metadata": {
"total_sites_checked": total_sites,
"found_count": len(found),
"missing_count": len(missing),
"error_count": len(errors),
},
}
def run_sherlock(
username: str,
sites: Optional[List[str]] = None,
timeout: Optional[int] = None,
opt_in: bool = False
) -> Dict[str, Any]:
"""
Execute Sherlock wrapper with opt-in gate, caching, and normalization.
"""
require_opt_in(opt_in)
# Compute cache key
query_hash = compute_query_hash(username, sites)
# Check cache first — avoids dependency requirement on cache hit
cached = get_cached_result(query_hash)
if cached is not None:
return cached
# Only require sherlock on cache miss
if not check_sherlock_available():
raise RuntimeError(
"Sherlock Python package not installed. "
"Install with: pip install sherlock-project"
)
# Call sherlock
try:
import sherlock
from sherlock import sherlock as sherlock_main # type: ignore
if sites:
result = sherlock_main(username, site_list=sites, timeout=timeout or 10)
else:
result = sherlock_main(username, timeout=timeout or 10)
normalized = normalize_sherlock_output(result, username, sites)
save_to_cache(query_hash, normalized)
return normalized
except Exception as e:
raise RuntimeError(f"Sherlock execution failed: {e}") from e
def main() -> int:
parser = argparse.ArgumentParser(
description="Sherlock username OSINT wrapper — opt-in, cached, normalized JSON"
)
parser.add_argument(
"--query", "-q", required=True,
help="Username to search across sites"
)
parser.add_argument(
"--opt-in", action="store_true",
help="Explicit opt-in flag (alternatively set SHERLOCK_ENABLED=1)"
)
parser.add_argument(
"--sites", "-s", nargs="+",
help="Specific sites to check (default: all supported)"
)
parser.add_argument(
"--timeout", "-t", type=int, default=10,
help="Request timeout per site (default: 10)"
)
parser.add_argument(
"--json", action="store_true",
help="Output normalized JSON to stdout"
)
parser.add_argument(
"--no-cache",
action="store_true",
help="Bypass cached result (if any)"
)
args = parser.parse_args()
try:
result = run_sherlock(
username=args.query,
sites=args.sites,
timeout=args.timeout,
opt_in=args.opt_in
)
if args.json:
print(json.dumps(result, indent=2))
else:
print(f"Query: {result['query']}")
print(f"Found: {result['metadata']['found_count']} site(s)")
print(f"Missing: {result['metadata']['missing_count']} site(s)")
print(f"Errors: {result['metadata']['error_count']} site(s)")
for f in result['found']:
print(f" [{f['site']}] {f['url']}")
return 0
except RuntimeError as e:
print(f"ERROR: {e}", file=sys.stderr)
return 1
if __name__ == "__main__":
sys.exit(main())