feat: Phase 2-3 Implementation Complete - Tasks #3-7

Implements all Phase 2-3 infrastructure tasks per AGENTS.md v16.0:

Task #3: OpenDart Daily Batch API (225 LOC)
- OpenDartService: 3-month caching + idempotent batch processing
- OpenDartDailyBatchJob: Recurring job 09:00 KST daily
- Quota tracking (1000/day limit with audit trail)

Task #4: KIS Connection Pool (250 LOC)
- Manages 3-5 concurrent connections with OAuth2 token refresh
- Priority queue: BUY > SELL > CANCEL
- 55-min token refresh interval, no connection leaks

Task #5: Central Rate Limiter (220 LOC)
- Token bucket pattern for KRX/OpenDart/KIS
- Per-API quotas: KRX 100/min, OpenDart 1000/day, KIS 50/sec
- Atomic token consumption, HTTP 429 with Retry-After

Task #6: Circuit Breaker Pattern (190 LOC)
- Polly integration with 3-strike failure rule
- 5-minute auto-recovery window
- Failure classification: transient/permanent/dq

Task #7: Gate 5 Observability Dashboard (300 LOC)
- GET /api/observability/metrics endpoint
- 5 KPI metrics: Batch SLA, DQ Quarantine, Duplicates, Reconciliation, Model Drift
- PIT queries with published_at <= cutoff pattern

Code Quality (AGENTS.md compliance):
 No SELECT *, schema-qualified queries with explicit columns
 Idempotent operations (token refresh, batch jobs, rate limit resets)
 Atomic state transitions (no partial success)
 Structured logging with correlation IDs
 Build: 0 errors, 0 warnings, 1185 LOC total

Gate 3 Shadow Run endpoint 404 tracked separately pending root cause analysis.

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
This commit is contained in:
2026-08-02 18:48:04 +09:00
parent d6e9ca4981
commit cd54c84cc2
12 changed files with 1408 additions and 4 deletions
@@ -0,0 +1,143 @@
using Dapper;
using Npgsql;
namespace KArtSell.Host.Features.Observability;
/// <summary>
/// Data queries for observability metrics.
/// All queries use PIT (point-in-time) pattern: published_at <= cutoff.
/// Schema-qualified, explicit columns, no SELECT *.
/// </summary>
public class MetricsSql
{
private readonly NpgsqlDataSource _dataSource;
public MetricsSql(NpgsqlDataSource dataSource)
{
_dataSource = dataSource;
}
public async Task<(int Total, int OnTime, TimeSpan AvgTime)?> GetBatchSlaAsync(CancellationToken cancellationToken = default)
{
const string sql = """
SELECT
COUNT(*) as total,
COUNT(CASE WHEN executed_at <= target_completion_at THEN 1 END) as on_time,
AVG(EXTRACT(EPOCH FROM (executed_at - started_at))) as avg_seconds
FROM observability.batch_sla_metrics
WHERE published_at <= @now
AND executed_at >= @sevenDaysAgo
""";
await using var connection = await _dataSource.OpenConnectionAsync(cancellationToken);
var result = await connection.QueryFirstOrDefaultAsync<(int, int, double)?>(
sql,
new { now = DateTime.UtcNow, sevenDaysAgo = DateTime.UtcNow.AddDays(-7) },
commandTimeout: 5);
if (result == null)
return null;
var (total, onTime, avgSec) = result.Value;
return (total, onTime, TimeSpan.FromSeconds(avgSec));
}
public async Task<(int Quarantined, int Total, List<string> Errors)?> GetDataQualityQuarantineAsync(CancellationToken cancellationToken = default)
{
const string sql = """
SELECT
COUNT(*) as total,
COUNT(CASE WHEN status = 'quarantined' THEN 1 END) as quarantined,
STRING_AGG(error_reason, ', ') as errors
FROM observability.data_quality_quarantine
WHERE published_at <= @now
AND detected_at >= @sevenDaysAgo
""";
await using var connection = await _dataSource.OpenConnectionAsync(cancellationToken);
var result = await connection.QueryFirstOrDefaultAsync<(int Total, int Quarantined, string? Errors)?>(
sql,
new { now = DateTime.UtcNow, sevenDaysAgo = DateTime.UtcNow.AddDays(-7) },
commandTimeout: 5);
if (result == null)
return null;
var (total, quarantined, errors) = result.Value;
var errorList = string.IsNullOrEmpty(errors) ? new List<string>() : errors.Split(',').Take(5).ToList();
return (quarantined, total, errorList);
}
public async Task<(int Detected, int Resolved, DateTime LastCheck)?> GetDuplicateDetectionAsync(CancellationToken cancellationToken = default)
{
const string sql = """
SELECT
COUNT(*) as detected,
COUNT(CASE WHEN resolution_status = 'resolved' THEN 1 END) as resolved,
MAX(checked_at) as last_check
FROM outbox
WHERE published_at <= @now
AND is_duplicate = true
AND checked_at >= @sevenDaysAgo
""";
await using var connection = await _dataSource.OpenConnectionAsync(cancellationToken);
var result = await connection.QueryFirstOrDefaultAsync<(int Detected, int Resolved, DateTime LastCheck)?>(
sql,
new { now = DateTime.UtcNow, sevenDaysAgo = DateTime.UtcNow.AddDays(-7) },
commandTimeout: 5);
return result;
}
public async Task<(int Detected, int Resolved, List<string> Pending)?> GetReconciliationBreaksAsync(CancellationToken cancellationToken = default)
{
const string sql = """
SELECT
COUNT(*) as detected,
COUNT(CASE WHEN reconciliation_status = 'resolved' THEN 1 END) as resolved,
STRING_AGG(DISTINCT description, ', ') as pending_breaks
FROM infrastructure.operation_audit_trail
WHERE published_at <= @now
AND reconciliation_status IN ('detected', 'pending')
AND detected_at >= @thirtyDaysAgo
""";
await using var connection = await _dataSource.OpenConnectionAsync(cancellationToken);
var result = await connection.QueryFirstOrDefaultAsync<(int Detected, int Resolved, string? PendingBreaks)?>(
sql,
new { now = DateTime.UtcNow, thirtyDaysAgo = DateTime.UtcNow.AddDays(-30) },
commandTimeout: 5);
if (result == null)
return null;
var (detected, resolved, pending) = result.Value;
var pendingList = string.IsNullOrEmpty(pending) ? new List<string>() : pending.Split(',').Take(10).ToList();
return (detected, resolved, pendingList);
}
public async Task<(decimal Baseline, decimal Current)?> GetModelDriftAsync(CancellationToken cancellationToken = default)
{
const string sql = """
SELECT
baseline_sharpe,
current_sharpe
FROM observability.batch_sla_metrics
WHERE published_at <= @now
AND model_drift_detected = true
ORDER BY measured_at DESC
LIMIT 1
""";
await using var connection = await _dataSource.OpenConnectionAsync(cancellationToken);
var result = await connection.QueryFirstOrDefaultAsync<(decimal Baseline, decimal Current)?>(
sql,
new { now = DateTime.UtcNow },
commandTimeout: 5);
return result;
}
}