Compare commits

..

2 Commits

Author SHA1 Message Date
Timmy Burn
99aab6c530 ci-test: add empty markdown to trigger gate failure
Some checks failed
Minimum PR Gate / minimum-pr-gate (pull_request) Failing after 19s
Self-Healing Smoke / self-healing-smoke (pull_request) Failing after 26s
Agent PR Gate / gate (pull_request) Failing after 56s
Smoke Test / smoke (pull_request) Failing after 24s
Agent PR Gate / report (pull_request) Successful in 20s
2026-04-28 22:52:58 -04:00
Timmy Burn
9def37e208 ci: add minimum PR gate (#521)
Some checks failed
Minimum PR Gate / minimum-pr-gate (pull_request) Failing after 17s
Agent PR Gate / gate (pull_request) Failing after 59s
Self-Healing Smoke / self-healing-smoke (pull_request) Failing after 27s
Smoke Test / smoke (pull_request) Failing after 25s
Agent PR Gate / report (pull_request) Successful in 20s
Adds .gitea/workflows/minimum-pr-gate.yml which enforces a lightweight
check on every pull request: Python syntax on changed files, secret scan,
and markdown sanity. Also documents the gate in README.

Closes #521
2026-04-28 22:52:06 -04:00
5 changed files with 97 additions and 322 deletions

View File

@@ -0,0 +1,84 @@
name: Minimum PR Gate
on:
pull_request:
branches: [main]
workflow_dispatch:
jobs:
minimum-pr-gate:
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Determine changed files
id: changes
run: |
if [ "${{ github.event_name }}" = "pull_request" ]; then
CHANGED=$(git diff --name-only ${{ github.event.pull_request.base.sha }} ${{ github.event.pull_request.head.sha }})
else
CHANGED=$(git ls-files)
fi
echo "changed=${CHANGED}" >> $GITHUB_OUTPUT
echo "Changed files:"
echo "$CHANGED"
- name: Python syntax check
if: steps.changes.outputs.changed != ''
run: |
CHANGED_FILES="${{ steps.changes.outputs.changed }}"
PY_FILES=$(echo "$CHANGED_FILES" | grep '\.py$' || true)
if [ -z "$PY_FILES" ]; then
echo "No Python files changed."
exit 0
fi
echo "Checking Python syntax on:"
echo "$PY_FILES"
echo "$PY_FILES" | while IFS= read -r f; do
python3 -m py_compile "$f" || { echo "FAIL: syntax error in $f"; exit 1; }
done
echo "PASS: Python syntax"
- name: Secret scan
if: steps.changes.outputs.changed != ''
run: |
CHANGED_FILES="${{ steps.changes.outputs.changed }}"
SCAN_FILES=$(echo "$CHANGED_FILES" | grep -E '\.(py|yaml|yml|sh|json)$' || true)
if [ -z "$SCAN_FILES" ]; then
echo "No files to scan for secrets."
exit 0
fi
echo "Scanning files for secrets:"
echo "$SCAN_FILES"
if echo "$SCAN_FILES" | xargs -r grep -E 'sk-or-|sk-ant-|ghp_|AKIA' 2>/dev/null | \
grep -v '.gitea' | grep -v 'detect_secrets' | grep -v 'test_trajectory_sanitize' | grep -v 'test_secret_detection' | grep -q .; then
echo "FAIL: Secrets or hardcoded tokens detected"
exit 1
fi
echo "PASS: No secrets detected"
- name: Markdown sanity check
if: steps.changes.outputs.changed != ''
run: |
CHANGED_FILES="${{ steps.changes.outputs.changed }}"
MD_FILES=$(echo "$CHANGED_FILES" | grep '\.md$' || true)
if [ -z "$MD_FILES" ]; then
echo "No markdown files changed."
exit 0
fi
echo "Checking markdown sanity on:"
echo "$MD_FILES"
echo "$MD_FILES" | while IFS= read -r f; do
if [ ! -s "$f" ]; then
echo "FAIL: empty markdown file: $f"
exit 1
fi
if ! grep -q '[^[:space:]]' "$f"; then
echo "FAIL: markdown file contains only whitespace: $f"
exit 1
fi
done
echo "PASS: Markdown sanity"

View File

@@ -99,6 +99,19 @@ python3 scripts/detect_secrets.py /tmp/test_secret.py
# Should report: OpenAI API key detected
```
## CI / PR Gate
A lightweight minimum PR gate runs automatically on every pull request targeting `main`. The gate performs:
- **Python syntax**: All changed Python files must compile without errors.
- **Secret scan**: Changed code files are scanned for common hardcoded tokens (OpenAI, Anthropic, GitHub, AWS keys).
- **Markdown sanity**: Changed Markdown documentation files must be nonempty and contain meaningful text.
The workflow is defined in `.gitea/workflows/minimum-pr-gate.yml`. It can also be triggered manually from the *Actions* panel (workflow_dispatch).
This gate protects the repository from introducing broken code, leaked credentials, or empty documentation.
## Development
### Running Tests

0
empty.md Normal file
View File

View File

@@ -1,245 +0,0 @@
#!/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())

View File

@@ -1,77 +0,0 @@
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()