rein-aharness/rein_aharness/metrics.py
tegwick f6930ad115 Rename package, CLI, and deploy artifacts to rein-aharness (HARNESS-WP-0002-T02)
agent_harness -> rein_aharness (package + all imports), CLI command
agent-harness -> rein-aharness, Docker image tag, k8s namespace/labels/
names, Makefile targets, deploy script env var/paths. In-repo identity
strings (hub event source, metrics harness field, default assignee,
argparse prog name, commit author identity) updated to match.

Historical documents left untouched on purpose: docs/adr/ADR-001-agent-harness-architecture.md,
docs/architecture.md (dated v0.1 snapshot), workplans/HARNESS-WP-0001
(completed under the old name), and the SSH host alias
"forgejo-agent-harness" (external ~/.ssh/config entry, not owned here).

Verified: 47/47 tests pass, CLI runs correctly from a fresh venv,
`make image` builds and the resulting container runs correctly.

deploy/README.md gained an explicit rename cutover checklist for what
this session cannot safely do unattended -- moving the host-side
secrets dir and checkout on railiance01, and not deleting the old k8s
namespace until the new one is confirmed working. The actual live
cutover (running that checklist against the real Railiance deployment)
is not attempted here -- real production surgery on binky-control's
live automation, needs the operator present.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-26 14:22:18 +02:00

160 lines
4.8 KiB
Python

"""Write per-run records into the target repo's `.kaizen/metrics` tree.
Follows kaizen-agentic ADR-004 conventions so the optimization loop can
observe harness-run agents:
.kaizen/metrics/<agent>/
executions.jsonl # append-only
summary.json # regenerated on write
"""
from __future__ import annotations
import json
from dataclasses import asdict, dataclass, field
from datetime import datetime, timezone
from pathlib import Path
from typing import Any
@dataclass
class ExecutionRecord:
timestamp: str
agent: str
success: bool
execution_time_s: float = 0.0
session_id: str | None = None
quality_score: float | None = None
primary_metric: dict[str, Any] | None = None
metadata: dict[str, Any] = field(default_factory=dict)
# Helix / harness correlation (ADR-004 optional fields)
repo: str | None = None
tokens: int | None = None
committed: bool | None = None
head_after: str | None = None
reason: str | None = None
harness: str = "rein-aharness"
def to_json_line(self) -> str:
data = asdict(self)
# Drop Nones for a compact record; required fields always present.
compact = {k: v for k, v in data.items() if v is not None}
return json.dumps(compact, sort_keys=True)
def metrics_dir(project_root: Path, agent: str) -> Path:
return Path(project_root) / ".kaizen" / "metrics" / agent
def _utc_now() -> str:
return datetime.now(timezone.utc).replace(microsecond=0).isoformat().replace(
"+00:00", "Z"
)
def _load_executions(path: Path) -> list[dict[str, Any]]:
if not path.is_file():
return []
records: list[dict[str, Any]] = []
for line in path.read_text(encoding="utf-8").splitlines():
line = line.strip()
if not line:
continue
try:
records.append(json.loads(line))
except json.JSONDecodeError:
continue
return records
def _trend(values: list[float]) -> str:
if len(values) < 4:
return "stable"
mid = len(values) // 2
early = sum(values[:mid]) / max(1, mid)
late = sum(values[mid:]) / max(1, len(values) - mid)
if late - early > 0.05:
return "up"
if early - late > 0.05:
return "down"
return "stable"
def regenerate_summary(agent: str, executions: list[dict[str, Any]]) -> dict[str, Any]:
count = len(executions)
successes = [e for e in executions if e.get("success")]
success_rate = (len(successes) / count) if count else 0.0
times = [float(e["execution_time_s"]) for e in executions if "execution_time_s" in e]
qualities = [
float(e["quality_score"])
for e in executions
if isinstance(e.get("quality_score"), (int, float))
]
last_ts = executions[-1].get("timestamp") if executions else None
return {
"agent": agent,
"execution_count": count,
"success_rate": round(success_rate, 3),
"avg_quality_score": (
round(sum(qualities) / len(qualities), 3) if qualities else None
),
"avg_execution_time_s": (
round(sum(times) / len(times), 3) if times else None
),
"last_execution": last_ts,
"trend": {
"success_rate": _trend(
[1.0 if e.get("success") else 0.0 for e in executions]
),
"quality_score": _trend(qualities) if qualities else "stable",
},
}
def record_execution(
project_root: Path | str,
agent: str,
*,
success: bool,
execution_time_s: float = 0.0,
tokens: int | None = None,
committed: bool | None = None,
head_after: str | None = None,
reason: str | None = None,
metadata: dict[str, Any] | None = None,
session_id: str | None = None,
) -> Path:
"""Append one execution record and regenerate summary.json.
Returns the path to executions.jsonl. Never raises for missing parent
dirs (creates them). Callers that must not write should skip this.
"""
root = Path(project_root)
directory = metrics_dir(root, agent)
directory.mkdir(parents=True, exist_ok=True)
record = ExecutionRecord(
timestamp=_utc_now(),
agent=agent,
success=success,
execution_time_s=float(execution_time_s),
session_id=session_id,
metadata=metadata or {},
repo=root.name,
tokens=tokens,
committed=committed,
head_after=head_after,
reason=reason,
)
executions_path = directory / "executions.jsonl"
with executions_path.open("a", encoding="utf-8") as fh:
fh.write(record.to_json_line() + "\n")
all_records = _load_executions(executions_path)
summary = regenerate_summary(agent, all_records)
(directory / "summary.json").write_text(
json.dumps(summary, indent=2, sort_keys=True) + "\n",
encoding="utf-8",
)
return executions_path