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 +1,208 @@
using Dapper;
using Microsoft.AspNetCore.Http;
using Microsoft.Extensions.Logging;
using Npgsql;
namespace KArtSell.Host.Infrastructure;
/// <summary>
/// Central rate limiter using token bucket pattern.
/// Per-API quotas: KRX 100/min, OpenDart 1000/day, KIS 50/sec.
/// Atomic token consumption, no partial success, HTTP 429 with retry-after header.
/// </summary>
public class RateLimiterService
{
private readonly NpgsqlDataSource _dataSource;
private readonly ILogger<RateLimiterService> _logger;
private static readonly Dictionary<string, RateLimitConfig> ApiConfigs = new()
{
{ "krx", new RateLimitConfig { Limit = 100, WindowSeconds = 60 } },
{ "opendart", new RateLimitConfig { Limit = 1000, WindowSeconds = 86400 } }, // 1 day
{ "kis", new RateLimitConfig { Limit = 50, WindowSeconds = 1 } }
};
private static readonly Action<ILogger, string, int, Exception?> LogTokenConsumed =
LoggerMessage.Define<string, int>(
LogLevel.Debug,
new EventId(1, nameof(LogTokenConsumed)),
"Rate limit: {ApiName} consumed 1 token, {RemainTokens} remaining");
private static readonly Action<ILogger, string, int, Exception?> LogQuotaExceeded =
LoggerMessage.Define<string, int>(
LogLevel.Warning,
new EventId(2, nameof(LogQuotaExceeded)),
"Rate limit: {ApiName} quota exceeded, retry after {RetryAfter}s");
public RateLimiterService(NpgsqlDataSource dataSource, ILogger<RateLimiterService> logger)
{
_dataSource = dataSource;
_logger = logger;
}
/// <summary>
/// Attempt to consume 1 token from the rate limit bucket for the given API.
/// Returns true if successful; false if quota exhausted.
/// </summary>
public async Task<(bool Success, int RetryAfterSeconds)> TryConsumeAsync(
string apiName,
CancellationToken cancellationToken = default)
{
if (!ApiConfigs.TryGetValue(apiName.ToLower(), out var config))
{
_logger.LogWarning("Unknown API for rate limiting: {ApiName}", apiName);
return (false, 0);
}
// Atomic consumption in database
const string sql = """
UPDATE infrastructure.rate_limit_quota
SET current_tokens = current_tokens - 1, updated_at = @now
WHERE api_name = @apiName
AND current_tokens > 0
RETURNING current_tokens, window_seconds, limit_count
""";
await using var connection = await _dataSource.OpenConnectionAsync(cancellationToken);
var result = await connection.QueryFirstOrDefaultAsync<(int CurrentTokens, int WindowSeconds, int LimitCount)?>(
sql,
new { apiName = apiName.ToLower(), now = DateTime.UtcNow },
commandTimeout: 5);
if (result == null)
{
// Quota exhausted
var retryAfter = config.WindowSeconds;
LogQuotaExceeded(_logger, apiName, retryAfter, null);
// Log rejection event
await LogEventAsync(apiName, "rejected", cancellationToken);
return (false, retryAfter);
}
// Token consumed successfully
LogTokenConsumed(_logger, apiName, result.Value.CurrentTokens, null);
await LogEventAsync(apiName, "allowed", cancellationToken);
return (true, 0);
}
/// <summary>
/// Reset quota for the given API (e.g., daily reset for OpenDart).
/// Called by scheduled job at window boundary.
/// </summary>
public async Task ResetQuotaAsync(string apiName, CancellationToken cancellationToken = default)
{
if (!ApiConfigs.TryGetValue(apiName.ToLower(), out var config))
return;
const string sql = """
UPDATE infrastructure.rate_limit_quota
SET current_tokens = @limit, last_reset_at = @now, updated_at = @now
WHERE api_name = @apiName
""";
await using var connection = await _dataSource.OpenConnectionAsync(cancellationToken);
await connection.ExecuteAsync(
sql,
new { apiName = apiName.ToLower(), limit = config.Limit, now = DateTime.UtcNow },
commandTimeout: 5);
_logger.LogInformation("Rate limit quota reset for {ApiName}: {Limit}/{WindowSeconds}s", apiName, config.Limit, config.WindowSeconds);
}
/// <summary>
/// Initialize rate limit quotas (called at startup).
/// </summary>
public async Task InitializeAsync(CancellationToken cancellationToken = default)
{
const string sql = """
INSERT INTO infrastructure.rate_limit_quota (api_name, limit_count, window_seconds, current_tokens, last_reset_at, updated_at, published_at)
VALUES (@apiName, @limit, @window, @limit, @now, @now, @now)
ON CONFLICT (api_name) DO NOTHING
""";
await using var connection = await _dataSource.OpenConnectionAsync(cancellationToken);
foreach (var (apiName, config) in ApiConfigs)
{
await connection.ExecuteAsync(
sql,
new { apiName, limit = config.Limit, window = config.WindowSeconds, now = DateTime.UtcNow },
commandTimeout: 5);
}
_logger.LogInformation("Rate limit quotas initialized: {Count} APIs", ApiConfigs.Count);
}
private async Task LogEventAsync(string apiName, string action, CancellationToken cancellationToken)
{
const string sql = """
INSERT INTO infrastructure.rate_limit_events (api_name, action, executed_at, published_at)
VALUES (@apiName, @action, @now, @now)
""";
try
{
await using var connection = await _dataSource.OpenConnectionAsync(cancellationToken);
await connection.ExecuteAsync(
sql,
new { apiName = apiName.ToLower(), action, now = DateTime.UtcNow },
commandTimeout: 5);
}
catch (Exception ex)
{
_logger.LogError(ex, "Failed to log rate limit event for {ApiName}", apiName);
}
}
}
public class RateLimitConfig
{
public int Limit { get; set; }
public int WindowSeconds { get; set; }
}
/// <summary>
/// Middleware: Apply rate limiting to incoming HTTP requests.
/// Returns HTTP 429 (Too Many Requests) if quota exhausted.
/// </summary>
public class RateLimiterMiddleware
{
private readonly RequestDelegate _next;
private readonly ILogger<RateLimiterMiddleware> _logger;
public RateLimiterMiddleware(RequestDelegate next, ILogger<RateLimiterMiddleware> logger)
{
_next = next;
_logger = logger;
}
public async Task InvokeAsync(HttpContext context, RateLimiterService rateLimiter)
{
// Determine API from route (e.g., /api/krx/* → krx)
var path = context.Request.Path.Value?.ToLower() ?? "";
string? apiName = null;
if (path.Contains("/krx/")) apiName = "krx";
else if (path.Contains("/opendart/")) apiName = "opendart";
else if (path.Contains("/kis/")) apiName = "kis";
// Only rate limit if API is identified
if (apiName != null)
{
var (success, retryAfter) = await rateLimiter.TryConsumeAsync(apiName, context.RequestAborted);
if (!success)
{
context.Response.StatusCode = StatusCodes.Status429TooManyRequests;
context.Response.Headers.Add("Retry-After", retryAfter.ToString());
await context.Response.WriteAsync($"Rate limit exceeded for {apiName}. Retry after {retryAfter}s");
return;
}
}
await _next(context);
}
}