Compare commits
2 Commits
step35/874
...
fix/543
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
24985a29db | ||
|
|
d6c90df391 |
70
README.md
70
README.md
@@ -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
|
||||
```
|
||||
|
||||
|
||||
|
||||
```
|
||||
.
|
||||
|
||||
@@ -62,6 +62,24 @@ Writes:
|
||||
|
||||
## Usage
|
||||
|
||||
### Timmy Mac wiring helper
|
||||
|
||||
Use the dedicated Timmy helper when you want to wire a real RunPod or Vertex-style endpoint into the local Mac Hermes config:
|
||||
|
||||
```bash
|
||||
python3 scripts/timmy_gemma4_mac.py --base-url https://your-openai-bridge.example/v1 --write-config
|
||||
python3 scripts/timmy_gemma4_mac.py --vertex-base-url https://your-vertex-bridge.example --write-config
|
||||
python3 scripts/timmy_gemma4_mac.py --pod-id <runpod-id> --write-config --verify-chat
|
||||
```
|
||||
|
||||
The helper writes to `~/.hermes/config.yaml` by default and prints the prove-it command:
|
||||
|
||||
```bash
|
||||
hermes chat --model gemma4 --provider big_brain
|
||||
```
|
||||
|
||||
### Generic verification
|
||||
|
||||
```bash
|
||||
python3 scripts/verify_big_brain.py
|
||||
python3 scripts/big_brain_manager.py
|
||||
|
||||
164
scripts/timmy_gemma4_mac.py
Normal file
164
scripts/timmy_gemma4_mac.py
Normal file
@@ -0,0 +1,164 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Timmy Mac Gemma 4 wiring helper for RunPod / Vertex-style Big Brain providers.
|
||||
|
||||
Refs: timmy-home #543
|
||||
|
||||
Safe by default:
|
||||
- computes a Big Brain base URL from an explicit URL, Vertex bridge URL, or RunPod pod id
|
||||
- can provision a RunPod pod when --apply-runpod is used and a token is available
|
||||
- can write the resolved endpoint into a Hermes config when --write-config is used
|
||||
- can verify an OpenAI-compatible chat endpoint when --verify-chat is used
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
from urllib import request
|
||||
|
||||
from scripts.bezalel_gemma4_vps import (
|
||||
DEFAULT_CLOUD_TYPE,
|
||||
DEFAULT_GPU_TYPE,
|
||||
DEFAULT_MODEL,
|
||||
DEFAULT_PROVIDER_NAME,
|
||||
build_runpod_endpoint,
|
||||
deploy_runpod,
|
||||
update_config_text,
|
||||
)
|
||||
|
||||
DEFAULT_TOKEN_FILE = Path.home() / ".config" / "runpod" / "access_key"
|
||||
DEFAULT_CONFIG_PATH = Path.home() / ".hermes" / "config.yaml"
|
||||
|
||||
|
||||
def _normalize_openai_base(base_url: str | None) -> str:
|
||||
if not base_url:
|
||||
return ""
|
||||
cleaned = str(base_url).strip().rstrip("/")
|
||||
return cleaned if cleaned.endswith("/v1") else f"{cleaned}/v1"
|
||||
|
||||
|
||||
def choose_base_url(*, vertex_base_url: str | None = None, base_url: str | None = None, pod_id: str | None = None) -> str:
|
||||
if vertex_base_url:
|
||||
return _normalize_openai_base(vertex_base_url)
|
||||
if base_url:
|
||||
return _normalize_openai_base(base_url)
|
||||
if pod_id:
|
||||
return build_runpod_endpoint(pod_id)
|
||||
return "https://YOUR_BIG_BRAIN_HOST/v1"
|
||||
|
||||
|
||||
def write_config_file(config_path: Path, *, base_url: str, model: str = DEFAULT_MODEL, provider_name: str = DEFAULT_PROVIDER_NAME) -> str:
|
||||
original = config_path.read_text() if config_path.exists() else ""
|
||||
updated = update_config_text(original, base_url=base_url, model=model, provider_name=provider_name)
|
||||
config_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
config_path.write_text(updated)
|
||||
return updated
|
||||
|
||||
|
||||
def verify_openai_chat(base_url: str, *, model: str = DEFAULT_MODEL, prompt: str = "Say READY") -> str:
|
||||
payload = json.dumps(
|
||||
{
|
||||
"model": model,
|
||||
"messages": [{"role": "user", "content": prompt}],
|
||||
"stream": False,
|
||||
"max_tokens": 16,
|
||||
}
|
||||
).encode()
|
||||
req = request.Request(
|
||||
f"{base_url.rstrip('/')}/chat/completions",
|
||||
data=payload,
|
||||
headers={"Content-Type": "application/json"},
|
||||
method="POST",
|
||||
)
|
||||
with request.urlopen(req, timeout=30) as resp:
|
||||
data = json.loads(resp.read().decode())
|
||||
return data["choices"][0]["message"]["content"]
|
||||
|
||||
|
||||
def build_summary(*, base_url: str, model: str, provider_name: str = DEFAULT_PROVIDER_NAME, config_path: Path = DEFAULT_CONFIG_PATH) -> dict[str, Any]:
|
||||
return {
|
||||
"provider_name": provider_name,
|
||||
"base_url": base_url,
|
||||
"model": model,
|
||||
"config_path": str(config_path),
|
||||
"verification_commands": [
|
||||
"python3 scripts/verify_big_brain.py",
|
||||
f"python3 scripts/timmy_gemma4_mac.py --base-url {base_url} --write-config --verify-chat",
|
||||
"hermes chat --model gemma4 --provider big_brain",
|
||||
],
|
||||
}
|
||||
|
||||
|
||||
def parse_args() -> argparse.Namespace:
|
||||
parser = argparse.ArgumentParser(description="Wire a RunPod/Vertex Gemma 4 endpoint into Timmy's Mac Hermes config.")
|
||||
parser.add_argument("--pod-name", default="timmy-gemma4")
|
||||
parser.add_argument("--gpu-type", default=DEFAULT_GPU_TYPE)
|
||||
parser.add_argument("--cloud-type", default=DEFAULT_CLOUD_TYPE)
|
||||
parser.add_argument("--model", default=DEFAULT_MODEL)
|
||||
parser.add_argument("--provider-name", default=DEFAULT_PROVIDER_NAME)
|
||||
parser.add_argument("--token-file", type=Path, default=DEFAULT_TOKEN_FILE)
|
||||
parser.add_argument("--config-path", type=Path, default=DEFAULT_CONFIG_PATH)
|
||||
parser.add_argument("--pod-id", help="Existing RunPod pod id to convert into an OpenAI-compatible base URL")
|
||||
parser.add_argument("--base-url", help="Explicit OpenAI-compatible base URL")
|
||||
parser.add_argument("--vertex-base-url", help="Vertex AI OpenAI-compatible bridge base URL")
|
||||
parser.add_argument("--apply-runpod", action="store_true", help="Provision a RunPod pod using the RunPod GraphQL API")
|
||||
parser.add_argument("--write-config", action="store_true", help="Write the resolved endpoint into --config-path")
|
||||
parser.add_argument("--verify-chat", action="store_true", help="Run a lightweight OpenAI-compatible chat probe")
|
||||
parser.add_argument("--json", action="store_true", help="Emit machine-readable JSON")
|
||||
return parser.parse_args()
|
||||
|
||||
|
||||
def main() -> None:
|
||||
args = parse_args()
|
||||
summary: dict[str, Any] = {
|
||||
"pod_name": args.pod_name,
|
||||
"gpu_type": args.gpu_type,
|
||||
"cloud_type": args.cloud_type,
|
||||
"model": args.model,
|
||||
"provider_name": args.provider_name,
|
||||
"actions": [],
|
||||
}
|
||||
|
||||
base_url = choose_base_url(vertex_base_url=args.vertex_base_url, base_url=args.base_url, pod_id=args.pod_id)
|
||||
|
||||
if args.apply_runpod:
|
||||
if not args.token_file.exists():
|
||||
raise SystemExit(f"RunPod token file not found: {args.token_file}")
|
||||
api_key = args.token_file.read_text().strip()
|
||||
deployed = deploy_runpod(api_key=api_key, name=args.pod_name, gpu_type=args.gpu_type, cloud_type=args.cloud_type, model=args.model)
|
||||
summary["deployment"] = deployed
|
||||
base_url = deployed["base_url"]
|
||||
summary["actions"].append("deployed_runpod_pod")
|
||||
|
||||
summary.update(build_summary(base_url=base_url, model=args.model, provider_name=args.provider_name, config_path=args.config_path))
|
||||
|
||||
if args.write_config:
|
||||
write_config_file(args.config_path, base_url=base_url, model=args.model, provider_name=args.provider_name)
|
||||
summary["actions"].append("wrote_config")
|
||||
|
||||
if args.verify_chat:
|
||||
summary["verify_response"] = verify_openai_chat(base_url, model=args.model)
|
||||
summary["actions"].append("verified_chat")
|
||||
|
||||
if args.json:
|
||||
print(json.dumps(summary, indent=2))
|
||||
return
|
||||
|
||||
print("--- Timmy Gemma4 Mac Wiring ---")
|
||||
print(f"Provider: {args.provider_name}")
|
||||
print(f"Base URL: {base_url}")
|
||||
print(f"Model: {args.model}")
|
||||
print(f"Config path: {args.config_path}")
|
||||
if "verify_response" in summary:
|
||||
print(f"Verify response: {summary['verify_response']}")
|
||||
if summary["actions"]:
|
||||
print("Actions: " + ", ".join(summary["actions"]))
|
||||
print("Verification commands:")
|
||||
for command in summary["verification_commands"]:
|
||||
print(f" - {command}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -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)
|
||||
85
tests/test_timmy_gemma4_mac.py
Normal file
85
tests/test_timmy_gemma4_mac.py
Normal file
@@ -0,0 +1,85 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import importlib.util
|
||||
import json
|
||||
import sys
|
||||
from pathlib import Path
|
||||
from unittest.mock import patch
|
||||
|
||||
|
||||
ROOT = Path(__file__).resolve().parent.parent
|
||||
SCRIPT = ROOT / "scripts" / "timmy_gemma4_mac.py"
|
||||
README = ROOT / "scripts" / "README_big_brain.md"
|
||||
|
||||
|
||||
def load_module():
|
||||
spec = importlib.util.spec_from_file_location("timmy_gemma4_mac", str(SCRIPT))
|
||||
mod = importlib.util.module_from_spec(spec)
|
||||
sys.modules["timmy_gemma4_mac"] = mod
|
||||
spec.loader.exec_module(mod)
|
||||
return mod
|
||||
|
||||
|
||||
class _FakeResponse:
|
||||
def __init__(self, payload: dict):
|
||||
self._payload = json.dumps(payload).encode()
|
||||
|
||||
def read(self) -> bytes:
|
||||
return self._payload
|
||||
|
||||
def __enter__(self):
|
||||
return self
|
||||
|
||||
def __exit__(self, exc_type, exc, tb):
|
||||
return False
|
||||
|
||||
|
||||
def test_script_exists() -> None:
|
||||
assert SCRIPT.exists(), "scripts/timmy_gemma4_mac.py must exist"
|
||||
|
||||
|
||||
def test_default_paths_target_timmy_mac_hermes() -> None:
|
||||
mod = load_module()
|
||||
assert mod.DEFAULT_CONFIG_PATH == Path.home() / ".hermes" / "config.yaml"
|
||||
assert mod.DEFAULT_TOKEN_FILE == Path.home() / ".config" / "runpod" / "access_key"
|
||||
|
||||
|
||||
def test_choose_base_url_prefers_vertex_then_explicit_then_runpod() -> None:
|
||||
mod = load_module()
|
||||
assert mod.choose_base_url(vertex_base_url="https://vertex-proxy.example/v1") == "https://vertex-proxy.example/v1"
|
||||
assert mod.choose_base_url(base_url="https://custom-endpoint/v1") == "https://custom-endpoint/v1"
|
||||
assert mod.choose_base_url(pod_id="abc123") == "https://abc123-11434.proxy.runpod.net/v1"
|
||||
|
||||
|
||||
def test_build_summary_includes_prove_it_commands() -> None:
|
||||
mod = load_module()
|
||||
summary = mod.build_summary(base_url="https://vertex-proxy.example/v1", model="gemma4:latest")
|
||||
assert summary["verification_commands"][0] == "python3 scripts/verify_big_brain.py"
|
||||
assert any("hermes chat --model gemma4 --provider big_brain" in cmd for cmd in summary["verification_commands"])
|
||||
|
||||
|
||||
def test_verify_openai_chat_targets_chat_completions() -> None:
|
||||
mod = load_module()
|
||||
response_payload = {
|
||||
"choices": [{"message": {"content": "READY"}}]
|
||||
}
|
||||
|
||||
with patch("timmy_gemma4_mac.request.urlopen", return_value=_FakeResponse(response_payload)) as mocked:
|
||||
result = mod.verify_openai_chat("https://vertex-proxy.example/v1", model="gemma4:latest", prompt="say READY")
|
||||
|
||||
assert result == "READY"
|
||||
req = mocked.call_args.args[0]
|
||||
assert req.full_url == "https://vertex-proxy.example/v1/chat/completions"
|
||||
|
||||
|
||||
def test_readme_mentions_timmy_mac_wiring_flow() -> None:
|
||||
text = README.read_text(encoding="utf-8")
|
||||
required = [
|
||||
"scripts/timmy_gemma4_mac.py",
|
||||
"--vertex-base-url",
|
||||
"--write-config",
|
||||
"python3 scripts/verify_big_brain.py",
|
||||
"hermes chat --model gemma4 --provider big_brain",
|
||||
]
|
||||
missing = [item for item in required if item not in text]
|
||||
assert not missing, missing
|
||||
@@ -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())
|
||||
Reference in New Issue
Block a user