fix: route strategy health to issue-only optimization monitoring #107
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,13 +1,12 @@ | ||
| #!/usr/bin/env python3 | ||
| """VPS health cycle — route strategy evidence to issue-only optimization monitoring.""" | ||
|
|
||
| from __future__ import annotations | ||
|
|
||
| import hashlib | ||
| import json | ||
| import os | ||
| import re | ||
| import sys | ||
| import tempfile | ||
| from datetime import datetime, timedelta, timezone | ||
|
|
@@ -151,25 +150,10 @@ def _alert_fingerprint(lines: list[str]) -> str: | |
| return hashlib.sha256(payload.encode("utf-8")).hexdigest() | ||
|
|
||
|
|
||
| def _build_alert_body(lines: list[str]) -> str: | ||
| return ( | ||
| "🚨 quant-monitor operational\n" | ||
| "• scope: data/evidence or optimization-record delivery failure\n" | ||
| + "\n".join(f"• {line}" for line in lines) | ||
| ) | ||
|
|
||
|
|
@@ -213,17 +197,83 @@ def _clear_alert(root: Path) -> None: | |
| pass | ||
|
|
||
|
|
||
| def _build_monitoring_findings( | ||
| strategies: list[dict[str, Any]], | ||
| drift_results: dict[str, list[Any]], | ||
| ) -> list[Any]: | ||
| from service.strategy_watch import build_strategy_monitoring_finding | ||
|
|
||
| records: dict[tuple[str, str], dict[str, Any]] = {} | ||
| metric_keys = ( | ||
| "overall_score", | ||
| "performance_score", | ||
| "risk_score", | ||
| "decay_score", | ||
| "stability_score", | ||
| "operational_score", | ||
| "status", | ||
| "as_of", | ||
| ) | ||
| for row in strategies: | ||
| try: | ||
| score = float(row.get("overall_score")) | ||
| except (TypeError, ValueError): | ||
| continue | ||
| if score >= SCORE_ALERT: | ||
| continue | ||
| domain = str(row.get("domain") or "").strip() | ||
| profile = str(row.get("strategy_profile") or "").strip() | ||
| if not domain or not profile: | ||
| continue | ||
| record = records.setdefault( | ||
| (domain, profile), | ||
| {"metrics": {}, "signals": [], "severity": "medium", "generated_at": ""}, | ||
| ) | ||
| record["metrics"].update({key: row[key] for key in metric_keys if key in row}) | ||
| record["signals"].append( | ||
| { | ||
| "metric": "overall_score", | ||
| "reason": f"overall_score={score:.1f} is below monitoring threshold {SCORE_ALERT:.1f}", | ||
| } | ||
| ) | ||
| record["generated_at"] = str(row.get("as_of") or "") | ||
| if str(row.get("status") or "").lower() == "critical" or score <= 40.0: | ||
| record["severity"] = "high" | ||
|
|
||
| for domain, drifts in drift_results.items(): | ||
| for drift in drifts: | ||
| score = float(drift.drift_score or 0.0) | ||
| if score < DRIFT_REVIEW: | ||
| continue | ||
| profile = str(drift.strategy_profile or "").strip() | ||
| if not profile: | ||
| continue | ||
| record = records.setdefault( | ||
| (domain, profile), | ||
| {"metrics": {}, "signals": [], "severity": "medium", "generated_at": ""}, | ||
| ) | ||
| record["metrics"]["drift_score"] = score | ||
| record["signals"].append( | ||
| { | ||
| "metric": "drift_score", | ||
| "reason": f"drift_score={score:.2f} exceeds monitoring threshold {DRIFT_REVIEW:.2f}", | ||
| } | ||
| ) | ||
| if score >= DRIFT_CRITICAL: | ||
| record["severity"] = "high" | ||
|
|
||
| return [ | ||
| build_strategy_monitoring_finding( | ||
| domain=domain, | ||
| profile=profile, | ||
| severity=record["severity"], | ||
| metrics=record["metrics"], | ||
| signals=record["signals"], | ||
| source="quant-monitor/health-cycle", | ||
| generated_at=record["generated_at"], | ||
| ) | ||
| for (domain, profile), record in sorted(records.items()) | ||
| ] | ||
|
|
||
|
|
||
| def _send_telegram(text: str) -> bool: | ||
|
|
@@ -239,46 +289,16 @@ def _send_telegram(text: str) -> bool: | |
| return False | ||
|
|
||
|
|
||
| def main() -> int: | ||
| root = Path(os.environ.get("QUANT_MONITOR_ROOT") or Path(__file__).resolve().parents[1]) | ||
| out_dir = root / "data" / "health" | ||
| dash_dir = out_dir / "dashboard" | ||
| out_dir.mkdir(parents=True, exist_ok=True) | ||
|
|
||
| from quant_platform_kit.strategy_lifecycle.drift_detector import run_drift_detection | ||
| from quant_platform_kit.strategy_lifecycle.health_dashboard import build_dashboard | ||
| from quant_platform_kit.strategy_lifecycle.performance_monitor import run_monitor | ||
| from scripts.run_strategy_optimization_watcher import dispatch_strategy_watch_findings | ||
|
|
||
| ready_domains, artifact_errors = _load_lifecycle_artifact_status(root) | ||
| snapshot_results, drift_results, lifecycle_errors = _refresh_and_collect_drift( | ||
|
|
@@ -338,41 +358,14 @@ def main() -> int: | |
| elif not json_path.is_file(): | ||
| collector_payload_invalid = True | ||
|
|
||
| alert_identities: list[str] = [] | ||
| monitoring_findings = _build_monitoring_findings(strategies, drift_results) | ||
| optimization_watch = dispatch_strategy_watch_findings( | ||
|
There was a problem hiding this comment.
When AGENTS.md reference: ops/quant-monitor/AGENTS.md:L45-L46 Useful? React with 👍 / 👎. |
||
| monitoring_findings, | ||
| dry_run=False, | ||
| comment_existing=False, | ||
| ) | ||
|
|
||
| data_error_lines: list[str] = [] | ||
| for error in data_errors: | ||
| data_error_lines.append( | ||
|
|
@@ -384,7 +377,16 @@ def main() -> int: | |
| if collector_payload_invalid: | ||
| data_error_lines.append("[collector] dashboard_data_unavailable") | ||
| alert_identities.append("data_error:collector:dashboard_data_unavailable") | ||
| optimization_error_lines: list[str] = [] | ||
| optimization_errors = int(optimization_watch.get("errors") or 0) | ||
| if optimization_errors: | ||
| optimization_error_lines.append( | ||
| f"[optimization] issue_record_failed ({optimization_errors})" | ||
| ) | ||
| alert_identities.append( | ||
| f"optimization_error:issue_record_failed:{optimization_errors}" | ||
| ) | ||
|
Comment on lines
+386
to
+388
There was a problem hiding this comment.
When consecutive cycles each have the same number of issue-record failures but for different repositories or strategies, this identity is unchanged, so AGENTS.md reference: ops/quant-monitor/AGENTS.md:L45-L46 Useful? React with 👍 / 👎. |
||
| notify_lines = data_error_lines + optimization_error_lines | ||
| telegram_sent = False | ||
| duplicate_alert_suppressed = False | ||
| if notify_lines: | ||
|
|
@@ -407,7 +409,11 @@ def main() -> int: | |
| "duplicate_alert_suppressed": duplicate_alert_suppressed, | ||
| "data_errors": data_errors, | ||
| "snapshot_count": sum(len(rows) for rows in snapshot_results.values()), | ||
| "optimization_findings": len(monitoring_findings), | ||
| "optimization_issues_created": len( | ||
| [result for result in optimization_watch.get("issues", []) if result.get("created")] | ||
| ), | ||
| "optimization_issue_errors": optimization_errors, | ||
| "ok": not notify_lines and not collector_payload_invalid, | ||
| "collector_payload_valid": not collector_payload_invalid, | ||
| "snapshot_data_status": normalized_payload.get("data_status"), | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
When a lifecycle row is
revieworcriticalbutoverall_scoreis missing or non-numeric, this earlycontinuedrops the row before its status is considered; the dashboard normalizer permits such rows by retaining the status and representing an invalid score as null. A status-only degradation therefore produces neither an optimization issue nor an operational error, so classify status independently of score parsing.AGENTS.md reference: ops/quant-monitor/AGENTS.md:L45-L45
Useful? React with 👍 / 👎.