feat: add fleet cost report for #520

scripts/README_big_brain.md

@@ -62,24 +62,6 @@ 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

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())

scripts/timmy_gemma4_mac.py

@@ -1,164 +0,0 @@
-#!/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()

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_timmy_gemma4_mac.py

@@ -1,85 +0,0 @@
-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