feat: add fleet cost report for #520

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
-```
-
-
 
 ```
 .

scripts/fleet_cost_report.py

@@ -0,0 +1,245 @@
+#!/usr/bin/env python3
+"""Fleet cost report generator.
+
+Reads Timmy's sovereignty metrics database and estimates paid API spend by
+agent/provider lane. Default output targets the local timmy-config reports
+folder so the cost report can be filed from the sidecar repo.
+"""
+
+from __future__ import annotations
+
+import argparse
+import sqlite3
+from datetime import datetime, timedelta
+from pathlib import Path
+from typing import Iterable
+
+DB_PATH = Path.home() / ".timmy" / "metrics" / "model_metrics.db"
+
+
+AGENT_LANES = (
+    {
+        "agent": "Timmy Cloud Lane",
+        "provider": "OpenRouter",
+        "patterns": ("openrouter/", "google/", "deepseek/", "x-ai/", "mistral/"),
+        "notes": "Cloud fallback and external reasoning routed through OpenRouter-compatible lanes.",
+    },
+    {
+        "agent": "Ezra",
+        "provider": "Anthropic",
+        "patterns": ("claude-", "anthropic/claude"),
+        "notes": "Archivist / long-form reasoning house on Claude-family models.",
+    },
+    {
+        "agent": "Bezalel",
+        "provider": "OpenAI",
+        "patterns": ("gpt-", "openai/", "codex"),
+        "notes": "Forge / implementation house on Codex/OpenAI-backed execution lanes.",
+    },
+    {
+        "agent": "Allegro",
+        "provider": "Kimi / Moonshot",
+        "patterns": ("kimi", "moonshot"),
+        "notes": "Tempo-and-dispatch house on Kimi / Moonshot direct API lanes.",
+    },
+)
+
+
+def default_report_path(report_date: str | None = None) -> Path:
+    if report_date is None:
+        report_date = datetime.now().strftime("%Y-%m-%d")
+    return Path.home() / "code" / "timmy-config" / "reports" / "production" / f"{report_date}-fleet-cost-report.md"
+
+
+def match_lane(model: str) -> dict | None:
+    lowered = (model or "").lower()
+    for lane in AGENT_LANES:
+        if any(pattern in lowered for pattern in lane["patterns"]):
+            return lane
+    return None
+
+
+def load_cost_rows(days: int = 30, db_path: Path = DB_PATH) -> list[tuple[str, int, int, int, float]]:
+    if not db_path.exists():
+        return []
+    cutoff = (datetime.now() - timedelta(days=days)).timestamp()
+    with sqlite3.connect(str(db_path)) as conn:
+        rows = conn.execute(
+            """
+            SELECT model, SUM(sessions), SUM(messages), SUM(tool_calls), SUM(est_cost_usd)
+            FROM session_stats
+            WHERE timestamp > ? AND is_local = 0
+            GROUP BY model
+            ORDER BY SUM(est_cost_usd) DESC, model ASC
+            """,
+            (cutoff,),
+        ).fetchall()
+    return [
+        (model, int(sessions or 0), int(messages or 0), int(tool_calls or 0), float(cost or 0.0))
+        for model, sessions, messages, tool_calls, cost in rows
+    ]
+
+
+def summarize_rows(rows: Iterable[tuple[str, int, int, int, float]], days: int = 30) -> dict:
+    rows = list(rows)
+    agents: dict[str, dict] = {}
+    providers_seen: set[str] = set()
+    inventory = [
+        {
+            "agent": lane["agent"],
+            "provider": lane["provider"],
+            "notes": lane["notes"],
+        }
+        for lane in AGENT_LANES
+    ]
+
+    for lane in AGENT_LANES:
+        agents[lane["agent"]] = {
+            "provider": lane["provider"],
+            "models": [],
+            "sessions": 0,
+            "messages": 0,
+            "tool_calls": 0,
+            "monthly_cost_usd": 0.0,
+            "daily_cost_usd": 0.0,
+            "notes": lane["notes"],
+        }
+
+    unassigned = {
+        "provider": "Unassigned",
+        "models": [],
+        "sessions": 0,
+        "messages": 0,
+        "tool_calls": 0,
+        "monthly_cost_usd": 0.0,
+        "daily_cost_usd": 0.0,
+        "notes": "Observed paid-model spend not yet mapped to a named wizard house.",
+    }
+
+    for model, sessions, messages, tool_calls, monthly_cost in rows:
+        lane = match_lane(model)
+        if lane is None:
+            bucket = unassigned
+        else:
+            bucket = agents[lane["agent"]]
+            providers_seen.add(lane["provider"])
+        bucket["models"].append(
+            {
+                "model": model,
+                "sessions": sessions,
+                "messages": messages,
+                "tool_calls": tool_calls,
+                "monthly_cost_usd": round(monthly_cost, 4),
+            }
+        )
+        bucket["sessions"] += sessions
+        bucket["messages"] += messages
+        bucket["tool_calls"] += tool_calls
+        bucket["monthly_cost_usd"] += monthly_cost
+
+    for bucket in list(agents.values()) + [unassigned]:
+        bucket["monthly_cost_usd"] = round(bucket["monthly_cost_usd"], 4)
+        bucket["daily_cost_usd"] = round(bucket["monthly_cost_usd"] / max(days, 1), 4)
+
+    if unassigned["models"]:
+        agents["Unassigned"] = unassigned
+        providers_seen.add("Unassigned")
+
+    total_monthly = round(sum(item["monthly_cost_usd"] for item in agents.values()), 4)
+    total_daily = round(sum(item["daily_cost_usd"] for item in agents.values()), 4)
+
+    provider_order = sorted(providers_seen)
+    if "Unassigned" in provider_order:
+        provider_order = [p for p in provider_order if p != "Unassigned"] + ["Unassigned"]
+
+    return {
+        "days": days,
+        "providers": provider_order,
+        "inventory": inventory,
+        "agents": agents,
+        "total_monthly_cost_usd": total_monthly,
+        "total_daily_cost_usd": total_daily,
+    }
+
+
+def render_markdown(summary: dict, report_date: str | None = None) -> str:
+    if report_date is None:
+        report_date = datetime.now().strftime("%Y-%m-%d")
+    lines = [
+        f"# Fleet Cost Report — {report_date}",
+        "",
+        f"Window: last {summary['days']} days of paid-model session stats from `~/.timmy/metrics/model_metrics.db`.",
+        "",
+        "## Paid API inventory",
+        "",
+        "| Agent | Provider | Notes |",
+        "| --- | --- | --- |",
+    ]
+    for item in summary["inventory"]:
+        lines.append(f"| {item['agent']} | {item['provider']} | {item['notes']} |")
+
+    lines.extend(
+        [
+            "",
+            "## Estimated cost per agent per day",
+            "",
+            "| Agent | Provider | Daily cost | Monthly estimate | Sessions | Messages | Tool calls |",
+            "| --- | --- | ---: | ---: | ---: | ---: | ---: |",
+        ]
+    )
+    for agent, data in summary["agents"].items():
+        lines.append(
+            f"| {agent} | {data['provider']} | ${data['daily_cost_usd']:.2f} | ${data['monthly_cost_usd']:.2f} | {data['sessions']} | {data['messages']} | {data['tool_calls']} |"
+        )
+
+    lines.extend(
+        [
+            "",
+            f"Total estimated daily paid spend: ${summary['total_daily_cost_usd']:.2f}",
+            f"Total estimated monthly paid spend: ${summary['total_monthly_cost_usd']:.2f}",
+            "",
+            "## Model evidence",
+            "",
+        ]
+    )
+    for agent, data in summary["agents"].items():
+        lines.append(f"### {agent}")
+        if not data["models"]:
+            lines.append("- No paid-model sessions observed in the selected window.")
+        else:
+            for model in data["models"]:
+                lines.append(
+                    f"- `{model['model']}` — {model['sessions']} sessions / {model['messages']} messages / {model['tool_calls']} tool calls / ${model['monthly_cost_usd']:.2f} est."
+                )
+        lines.append("")
+
+    lines.append("Generated by `python3 scripts/fleet_cost_report.py --days 30`. Default output path targets the local timmy-config report lane.")
+    lines.append("")
+    return "\n".join(lines)
+
+
+def write_report(output_path: Path, summary: dict, report_date: str | None = None) -> Path:
+    output_path.parent.mkdir(parents=True, exist_ok=True)
+    output_path.write_text(render_markdown(summary, report_date=report_date), encoding="utf-8")
+    return output_path
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(description="Estimate paid API spend per fleet agent")
+    parser.add_argument("--days", type=int, default=30, help="Lookback window in days")
+    parser.add_argument("--db-path", default=str(DB_PATH), help="Path to model_metrics.db")
+    parser.add_argument("--output", help="Optional markdown output path")
+    parser.add_argument("--date", help="Override report date (YYYY-MM-DD)")
+    args = parser.parse_args()
+
+    rows = load_cost_rows(days=args.days, db_path=Path(args.db_path).expanduser())
+    summary = summarize_rows(rows, days=args.days)
+    report_date = args.date or datetime.now().strftime("%Y-%m-%d")
+    output_path = Path(args.output).expanduser() if args.output else default_report_path(report_date)
+    write_report(output_path, summary, report_date=report_date)
+    print(output_path)
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

tests/test_fleet_cost_report.py

@@ -0,0 +1,77 @@
+from importlib.util import module_from_spec, spec_from_file_location
+from pathlib import Path
+import tempfile
+import unittest
+
+
+ROOT = Path(__file__).resolve().parent.parent
+SCRIPT_PATH = ROOT / "scripts" / "fleet_cost_report.py"
+
+
+def load_module():
+    spec = spec_from_file_location("fleet_cost_report", SCRIPT_PATH)
+    module = module_from_spec(spec)
+    assert spec.loader is not None
+    spec.loader.exec_module(module)
+    return module
+
+
+class TestFleetCostReport(unittest.TestCase):
+    def test_default_output_targets_timmy_config_report_path(self):
+        module = load_module()
+        output_path = module.default_report_path("2026-04-22")
+        self.assertIn("timmy-config", str(output_path))
+        self.assertTrue(str(output_path).endswith("2026-04-22-fleet-cost-report.md"))
+
+    def test_summary_groups_paid_costs_by_agent_and_provider(self):
+        module = load_module()
+        rows = [
+            ("claude-sonnet-4-6", 12, 120, 24, 6.0),
+            ("gpt-5.4", 6, 60, 12, 3.0),
+            ("openrouter/google/gemini-2.5-pro", 4, 40, 8, 2.0),
+            ("kimi-k2", 2, 20, 4, 1.0),
+        ]
+        summary = module.summarize_rows(rows, days=30)
+
+        self.assertEqual(summary["providers"], ["Anthropic", "Kimi / Moonshot", "OpenAI", "OpenRouter"])
+        self.assertAlmostEqual(summary["agents"]["Ezra"]["monthly_cost_usd"], 6.0)
+        self.assertAlmostEqual(summary["agents"]["Bezalel"]["monthly_cost_usd"], 3.0)
+        self.assertAlmostEqual(summary["agents"]["Timmy Cloud Lane"]["monthly_cost_usd"], 2.0)
+        self.assertAlmostEqual(summary["agents"]["Allegro"]["monthly_cost_usd"], 1.0)
+        self.assertAlmostEqual(summary["agents"]["Ezra"]["daily_cost_usd"], 0.2)
+
+    def test_report_render_mentions_inventory_and_agent_costs(self):
+        module = load_module()
+        rows = [
+            ("claude-sonnet-4-6", 12, 120, 24, 6.0),
+            ("gpt-5.4", 6, 60, 12, 3.0),
+            ("openrouter/google/gemini-2.5-pro", 4, 40, 8, 2.0),
+        ]
+        summary = module.summarize_rows(rows, days=30)
+        report = module.render_markdown(summary, report_date="2026-04-22")
+
+        self.assertIn("# Fleet Cost Report — 2026-04-22", report)
+        self.assertIn("## Paid API inventory", report)
+        self.assertIn("Anthropic", report)
+        self.assertIn("OpenRouter", report)
+        self.assertIn("OpenAI", report)
+        self.assertIn("## Estimated cost per agent per day", report)
+        self.assertIn("Timmy Cloud Lane", report)
+        self.assertIn("Ezra", report)
+        self.assertIn("Bezalel", report)
+
+    def test_write_report_creates_markdown_file(self):
+        module = load_module()
+        rows = [("claude-sonnet-4-6", 1, 10, 2, 0.5)]
+        summary = module.summarize_rows(rows, days=30)
+        with tempfile.TemporaryDirectory() as tmpdir:
+            dest = Path(tmpdir) / "fleet-cost.md"
+            module.write_report(dest, summary, report_date="2026-04-22")
+            self.assertTrue(dest.exists())
+            text = dest.read_text()
+            self.assertIn("Fleet Cost Report", text)
+            self.assertIn("Ezra", text)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_sherlock_wrapper.py

@@ -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)

tools/sherlock_wrapper.py

@@ -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())