8 Commits

Author SHA1 Message Date
claude 99e5cfb76b Fix job search: location filtering, keyword quality, anchor filter bypass
Closes #41

- Add RequireKeywordInAnchor per-provider flag (default true); set false for
  ejobs.ro and bestjobs.eu so Stage 2 anchor-text filter is skipped — their
  search URL already filters by relevance server-side
- Update AI system prompts (en + ro) to extract concise job-board-friendly
  keywords (role title + key tech, not abstract concepts) and candidate location
- Propagate location through JobMatchResponse -> CreateJobSearchTokenRequest ->
  JobSearchTokenEntity -> JobSearchSessionEntity
- Add {location} and {location-slug} substitution in HtmlJobSearcher
- Update provider SearchUrlTemplates to include location:
    ejobs.ro:    /locuri-de-munca/{location-slug}?q={keywords}
    bestjobs.eu: /ro/locuri-de-munca-in-{location-slug}?keywords={keywords}
    linkedin.com: ?keywords={keywords}&location={location}
- Three new migrations: AddRequireKeywordInAnchorAndLocation,
  ImproveKeywordsAndAddLocation, AddLocationToProviders

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-08 15:45:45 +03:00
claude 91b2baa445 Fix email-api middleware order: API key check before swagger
Build and Push Docker Images Staging / build (push) Successful in 17m14s
UseInternalApiKeyProtection was registered after UseSwaggerInDevelopment,
allowing unauthenticated access to /swagger. Swapped order to match
rag-api and cv-matcher-api.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-01 22:41:29 +03:00
claude 0f64cb8d99 Fix email-api Dockerfile: add missing shared-data COPY
email-data references shared-data but the email-api Dockerfile never
copied it into the build context, causing MSB9008 during Docker build.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-01 22:30:25 +03:00
claude b67e926c5f Fix Serilog email sink: configure in code, not JSON config
Serilog.Settings.Configuration cannot deserialize NetworkCredential or
MailKit's SecureSocketOptions from JSON, causing an InvalidOperationException
in the binder and preventing containers from starting.

Fix: remove Email from the WriteTo JSON array entirely and wire it in code
inside ConfigureJsonSerilog using a dedicated SerilogEmail:* config section.
The sink is skipped when From/To/Host are absent, so local dev is unaffected.

Also renames the docker-compose env vars from the verbose
Serilog__WriteTo__2__Args__* prefix to the clean SerilogEmail__* prefix.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-01 22:25:26 +03:00
claude f7d856147e Escalate provider fetch failures to Error for alert emails
HTTP and Playwright fetch failures in HtmlJobSearcher are now logged at
Error so that Serilog's email sink triggers an alert when a job provider
is unreachable. Per-URL match failures remain at Warning (expected noise).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-01 22:03:46 +03:00
claude 8679bd1efd Fix Serilog email sink config for v4 API breaking changes
Serilog.Sinks.Email v4 renamed all configuration parameters from their
v2 names. The old names were silently ignored, so no error alert emails
were ever sent.

Parameter renames applied across all 6 appsettings.json and docker-compose:
  fromEmail → from
  toEmail   → to
  mailServer → host
  networkCredential → credentials
  enableSsl: true → connectionSecurity: StartTls
  emailSubject → subject
  outputTemplate → body
  batchPostingLimit / period removed (v4 batching uses a separate overload)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-01 21:57:06 +03:00
claude 1bcf95d8d4 Add download rate limit policy to template and docker-compose
Build and Push Docker Images Staging / build (push) Failing after 1m38s
5 requests / 1 min per IP. docker-compose.yml wired with ${VAR:-default}.
Staging and production .env files updated locally (gitignored).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-01 20:40:25 +03:00
claude 73f67d1342 Protect FileDownloadController with reCAPTCHA v3 and rate limiting
- Require captchaToken query param on initial (non-range) download requests
- Range requests (HTTP resume) bypass captcha — they are continuations of an already-validated download
- Add download rate limit policy: 5 requests / 1 min per IP (configured in .env)
- Inject ICaptchaVerifier; action name is file_download

UI change required: execute grecaptcha.execute(siteKey, {action: 'file_download'})
before triggering the download and append ?captchaToken=<token> to the URL.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-01 20:37:44 +03:00
31 changed files with 999 additions and 190 deletions
+1 -1
View File
@@ -181,7 +181,7 @@ public sealed class CvMatcherController : ControllerBase
try
{
var tokenResp = await _jobSearchApi.CreateTokenAsync(
new CreateJobSearchTokenRequest { CvDocumentId = request.CvDocumentId, Email = request.Email, Language = language, Keywords = res.Keywords },
new CreateJobSearchTokenRequest { CvDocumentId = request.CvDocumentId, Email = request.Email, Language = language, Keywords = res.Keywords, Location = res.Location },
ct);
if (!string.IsNullOrWhiteSpace(tokenResp.TokenId))
{
+33 -7
View File
@@ -7,6 +7,7 @@ using Microsoft.Extensions.Options;
using Microsoft.Net.Http.Headers;
using Swashbuckle.AspNetCore.Annotations;
using Common.Responses;
using Microsoft.AspNetCore.RateLimiting;
namespace Api.Controllers
{
@@ -17,38 +18,44 @@ namespace Api.Controllers
[ApiController]
[Route("api/[controller]")]
[EnableCors("FrontendOnly")]
[EnableRateLimiting("download")]
public sealed class FileDownloadController : ControllerBase
{
private readonly ILogger<FileDownloadController> _logger;
private readonly FileStorageSettings _fileStorageSettings;
private readonly IContentTypeProvider _contentTypeProvider;
private readonly IEmailSender _emailSender;
private const int BufferSize = 81920; // 80 KB buffer for optimal streaming performance
private readonly ICaptchaVerifier _captcha;
private const int BufferSize = 81920;
public FileDownloadController(
ILogger<FileDownloadController> logger,
IOptions<FileStorageSettings> fileStorageSettings,
IContentTypeProvider contentTypeProvider,
IEmailSender emailSender)
IEmailSender emailSender,
ICaptchaVerifier captcha)
{
_logger = logger;
_fileStorageSettings = fileStorageSettings.Value;
_contentTypeProvider = contentTypeProvider;
_emailSender = emailSender;
_captcha = captcha;
}
/// <summary>
/// Downloads a file with support for resume (range requests) and chunked transfer.
/// Supports HTTP 206 Partial Content for efficient downloads and resume capability.
/// Requires a valid reCAPTCHA v3 token on the initial (non-range) request.
/// Sends email notification when download starts.
/// </summary>
/// <param name="fileName">The name of the file to download (optional - uses default from settings if not provided)</param>
/// <param name="fileName">The name of the file to download (optional - uses default from settings if not provided).</param>
/// <param name="captchaToken">reCAPTCHA v3 token — required on the initial download request; omit on subsequent range requests.</param>
/// <returns>File stream with appropriate headers for resumable downloads</returns>
[HttpGet("{fileName?}")]
[SwaggerOperation(Summary = "Download file", Description = "Downloads a file with support for full and ranged (resumable) transfers.")]
[SwaggerOperation(Summary = "Download file", Description = "Downloads a file. Requires a reCAPTCHA v3 token on the initial request. Range requests for resume do not require a token.")]
[SwaggerResponse(StatusCodes.Status200OK, "Full file content returned")]
[SwaggerResponse(StatusCodes.Status206PartialContent, "Partial file content returned for a range request")]
[SwaggerResponse(StatusCodes.Status400BadRequest, "No file name provided and no default configured")]
[SwaggerResponse(StatusCodes.Status400BadRequest, "Missing/invalid captcha token, no file name, or no default configured")]
[SwaggerResponse(StatusCodes.Status404NotFound, "Requested file was not found")]
[SwaggerResponse(StatusCodes.Status416RangeNotSatisfiable, "Requested byte range is invalid")]
[SwaggerResponse(StatusCodes.Status500InternalServerError, "Unexpected server error while downloading")]
@@ -58,10 +65,30 @@ namespace Api.Controllers
[ProducesResponseType(typeof(ErrorResponse), StatusCodes.Status404NotFound)]
[ProducesResponseType(StatusCodes.Status416RangeNotSatisfiable)]
[ProducesResponseType(typeof(ErrorResponse), StatusCodes.Status500InternalServerError)]
public async Task<IActionResult> DownloadFile(string? fileName = null)
public async Task<IActionResult> DownloadFile(string? fileName = null, [FromQuery] string? captchaToken = null)
{
try
{
var userIp = HttpContext.Connection.RemoteIpAddress?.ToString();
// Captcha required on the initial (full) download only — range requests are resume continuations.
var isRangeRequest = !string.IsNullOrEmpty(Request.Headers[HeaderNames.Range].ToString());
if (!isRangeRequest)
{
if (string.IsNullOrWhiteSpace(captchaToken))
{
_logger.LogWarning("Download attempt without captcha token from IP={IP}", HttpContext.Connection.RemoteIpAddress);
return BadRequest(new ErrorResponse { Error = "Captcha token is required.", Code = "captcha_token_missing" });
}
var verdict = await _captcha.VerifyAsync(captchaToken, userIp, "file_download", CancellationToken.None);
if (!verdict.Success)
{
_logger.LogWarning("Download blocked by captcha. IP={IP} Score={Score}", userIp, verdict.Score);
return BadRequest(new ErrorResponse { Error = "Captcha verification failed.", Code = "captcha_verification_failed" });
}
}
if (string.IsNullOrWhiteSpace(fileName))
{
fileName = _fileStorageSettings.DefaultFileName;
@@ -99,7 +126,6 @@ namespace Api.Controllers
if (!_contentTypeProvider.TryGetContentType(filePath, out var contentType))
contentType = "application/octet-stream";
var userIp = HttpContext.Connection.RemoteIpAddress?.ToString();
_ = Task.Run(async () =>
{
try
+1 -21
View File
@@ -2,8 +2,7 @@
"Serilog": {
"Using": [
"Serilog.Sinks.Console",
"Serilog.Sinks.File",
"Serilog.Sinks.Email"
"Serilog.Sinks.File"
],
"MinimumLevel": {
"Default": "Information",
@@ -30,25 +29,6 @@
"retainedFileCountLimit": 30,
"outputTemplate": "{Timestamp:yyyy-MM-dd HH:mm:ss.fff zzz} [{Level:u3}] {SourceContext}: {Message:lj}{NewLine}{Exception}"
}
},
{
"Name": "Email",
"Args": {
"restrictedToMinimumLevel": "Error",
"fromEmail": "",
"toEmail": "",
"mailServer": "",
"networkCredential": {
"userName": "",
"password": ""
},
"port": 587,
"enableSsl": true,
"emailSubject": "[mihes.ro API] Error Alert",
"outputTemplate": "{Timestamp:yyyy-MM-dd HH:mm:ss.fff zzz} [{Level:u3}] {SourceContext}{NewLine}{Message:lj}{NewLine}{Exception}",
"batchPostingLimit": 10,
"period": "0.00:05:00"
}
}
],
"Enrich": [
@@ -6,4 +6,5 @@ public sealed class CreateJobSearchTokenRequest
public string Email { get; set; } = string.Empty;
public string Language { get; set; } = "en";
public List<string> Keywords { get; set; } = [];
public string? Location { get; set; }
}
@@ -9,6 +9,7 @@
public List<string> Recommendations { get; set; } = [];
public List<string> Evidence { get; set; } = [];
public List<string> Keywords { get; set; } = [];
public string? Location { get; set; }
public bool Cached { get; set; }
public string? JobDocumentId { get; set; }
public string? JobUrl { get; set; }
@@ -23,4 +23,9 @@ public sealed class JobProviderConfig
public int MaxResults { get; set; } = 20;
/// <summary>When true the scraper uses a headless Chromium browser to render JS-heavy pages.</summary>
public bool UseHeadlessBrowser { get; set; }
/// <summary>
/// When false, the Stage 2 anchor-text keyword filter is skipped.
/// Set to false for providers whose search URL already filters by relevance server-side.
/// </summary>
public bool RequireKeywordInAnchor { get; set; } = true;
}
@@ -53,7 +53,7 @@ public sealed class JobSearchController : ControllerBase
if (string.IsNullOrWhiteSpace(request.CvDocumentId) || string.IsNullOrWhiteSpace(request.Email))
return BadRequest(new ErrorResponse { Error = "CvDocumentId and Email are required.", Code = "invalid_request" });
var tokenId = await _tokenService.CreateTokenAsync(request.CvDocumentId, request.Email, request.Language, request.Keywords, ct);
var tokenId = await _tokenService.CreateTokenAsync(request.CvDocumentId, request.Email, request.Language, request.Keywords, request.Location, ct);
return Ok(new CreateJobSearchTokenResponse { TokenId = tokenId });
}
catch (Exception ex)
@@ -13,12 +13,13 @@ public interface IJobTokenService
/// <param name="email">Email address of the user who will receive the results.</param>
/// <param name="language">Preferred language for result emails (e.g. <c>"en"</c>, <c>"ro"</c>).</param>
/// <param name="keywords">Job search keywords extracted by the LLM during the match call.</param>
/// <param name="location">Candidate location extracted from the CV (e.g. "Cluj-Napoca, Romania"). Null if not available.</param>
/// <param name="ct">Cancellation token.</param>
/// <returns>
/// The generated token ID to embed in the one-click job search link,
/// or <c>null</c> when no job providers are currently enabled (link should be suppressed).
/// </returns>
Task<string?> CreateTokenAsync(string cvDocumentId, string email, string language, IReadOnlyList<string> keywords, CancellationToken ct);
Task<string?> CreateTokenAsync(string cvDocumentId, string email, string language, IReadOnlyList<string> keywords, string? location, CancellationToken ct);
/// <summary>
/// Validates the token and, if valid, marks it as used and creates a <c>Pending</c> job search session.
@@ -34,7 +34,7 @@ public sealed class JobTokenService : IJobTokenService
}
/// <inheritdoc />
public async Task<string?> CreateTokenAsync(string cvDocumentId, string email, string language, IReadOnlyList<string> keywords, CancellationToken ct)
public async Task<string?> CreateTokenAsync(string cvDocumentId, string email, string language, IReadOnlyList<string> keywords, string? location, CancellationToken ct)
{
var hasEnabledProviders = await _db.JobProviders.AnyAsync(p => p.Enabled, ct);
if (!hasEnabledProviders)
@@ -50,6 +50,7 @@ public sealed class JobTokenService : IJobTokenService
Email = email,
Language = language,
Keywords = string.Join(",", keywords),
Location = location,
ExpiresAt = DateTime.UtcNow.AddDays(_settings.TokenExpiryDays),
Used = false,
CreatedAt = DateTime.UtcNow
@@ -57,7 +58,7 @@ public sealed class JobTokenService : IJobTokenService
_db.JobSearchTokens.Add(token);
await _db.SaveChangesAsync(ct);
_logger.LogInformation("Job search token created. TokenId={TokenId}, CvDocumentId={CvDocumentId}, Keywords={Keywords}", token.Id, cvDocumentId, token.Keywords);
_logger.LogInformation("Job search token created. TokenId={TokenId}, CvDocumentId={CvDocumentId}, Keywords={Keywords}, Location={Location}", token.Id, cvDocumentId, token.Keywords, token.Location);
return token.Id;
}
@@ -92,6 +93,7 @@ public sealed class JobTokenService : IJobTokenService
Language = token.Language,
Status = JobSearchStatus.Pending,
Keywords = keywords,
Location = token.Location,
ProviderConfigJson = providerConfigJson,
CreatedAt = DateTime.UtcNow
};
@@ -126,7 +128,8 @@ public sealed class JobTokenService : IJobTokenService
JobLinkContains = entity.JobLinkContains,
InitialKeywords = keywords,
MaxResults = entity.MaxResults,
UseHeadlessBrowser = entity.UseHeadlessBrowser
UseHeadlessBrowser = entity.UseHeadlessBrowser,
RequireKeywordInAnchor = entity.RequireKeywordInAnchor
};
}
+1 -21
View File
@@ -2,8 +2,7 @@
"Serilog": {
"Using": [
"Serilog.Sinks.Console",
"Serilog.Sinks.File",
"Serilog.Sinks.Email"
"Serilog.Sinks.File"
],
"MinimumLevel": {
"Default": "Information",
@@ -30,25 +29,6 @@
"retainedFileCountLimit": 30,
"outputTemplate": "{Timestamp:yyyy-MM-dd HH:mm:ss.fff zzz} [{Level:u3}] {SourceContext}: {Message:lj}{NewLine}{Exception}"
}
},
{
"Name": "Email",
"Args": {
"restrictedToMinimumLevel": "Error",
"fromEmail": "",
"toEmail": "",
"mailServer": "",
"networkCredential": {
"userName": "",
"password": ""
},
"port": 587,
"enableSsl": true,
"emailSubject": "[mihes.ro API] Error Alert",
"outputTemplate": "{Timestamp:yyyy-MM-dd HH:mm:ss.fff zzz} [{Level:u3}] {SourceContext}{NewLine}{Message:lj}{NewLine}{Exception}",
"batchPostingLimit": 10,
"period": "0.00:05:00"
}
}
],
"Enrich": [
@@ -0,0 +1,130 @@
// <auto-generated />
using System;
using CvMatcher.Data;
using Microsoft.EntityFrameworkCore;
using Microsoft.EntityFrameworkCore.Infrastructure;
using Microsoft.EntityFrameworkCore.Metadata;
using Microsoft.EntityFrameworkCore.Migrations;
using Microsoft.EntityFrameworkCore.Storage.ValueConversion;
#nullable disable
namespace CvMatcher.Data.Migrations
{
[DbContext(typeof(CvMatcherDbContext))]
[Migration("20260608124331_ImproveKeywordsAndAddLocation")]
partial class ImproveKeywordsAndAddLocation
{
/// <inheritdoc />
protected override void BuildTargetModel(ModelBuilder modelBuilder)
{
#pragma warning disable 612, 618
modelBuilder
.HasDefaultSchema("cvMatcher")
.HasAnnotation("ProductVersion", "10.0.7")
.HasAnnotation("Relational:MaxIdentifierLength", 128);
SqlServerModelBuilderExtensions.UseIdentityColumns(modelBuilder);
modelBuilder.Entity("CvMatcher.Data.Entities.AiPromptEntity", b =>
{
b.Property<string>("Key")
.HasMaxLength(128)
.HasColumnType("nvarchar(128)");
b.Property<string>("Language")
.HasMaxLength(8)
.HasColumnType("nvarchar(8)");
b.Property<string>("Description")
.IsRequired()
.ValueGeneratedOnAdd()
.HasMaxLength(500)
.HasColumnType("nvarchar(500)")
.HasDefaultValue("");
b.Property<DateTime>("UpdatedAt")
.ValueGeneratedOnAdd()
.HasColumnType("datetime2")
.HasDefaultValueSql("SYSUTCDATETIME()");
b.Property<string>("Value")
.IsRequired()
.HasColumnType("nvarchar(max)");
b.HasKey("Key", "Language");
b.ToTable("AiPrompts", "cvMatcher");
});
modelBuilder.Entity("CvMatcher.Data.Entities.CvMatchResultEntity", b =>
{
b.Property<string>("Id")
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.Property<DateTime>("CreatedAt")
.ValueGeneratedOnAdd()
.HasColumnType("datetime2")
.HasDefaultValueSql("SYSUTCDATETIME()");
b.Property<string>("CvDocumentId")
.IsRequired()
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.Property<string>("JobDocumentId")
.IsRequired()
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.Property<string>("Language")
.IsRequired()
.HasColumnType("nvarchar(450)");
b.Property<string>("ResultJson")
.IsRequired()
.HasColumnType("nvarchar(max)");
b.Property<int>("Score")
.HasColumnType("int");
b.HasKey("Id");
b.HasIndex("CvDocumentId", "JobDocumentId", "Language")
.IsUnique();
b.ToTable("Results", "cvMatcher");
});
modelBuilder.Entity("CvMatcher.Data.Entities.CvMatcherChatCacheEntity", b =>
{
b.Property<string>("CacheKey")
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.Property<DateTime>("CreatedAt")
.ValueGeneratedOnAdd()
.HasColumnType("datetime2")
.HasDefaultValueSql("SYSUTCDATETIME()");
b.Property<string>("Model")
.IsRequired()
.HasMaxLength(120)
.HasColumnType("nvarchar(120)");
b.Property<string>("ResponseText")
.IsRequired()
.HasColumnType("nvarchar(max)");
b.Property<decimal>("Temperature")
.HasColumnType("decimal(4,2)");
b.HasKey("CacheKey");
b.ToTable("ChatCache", "cvMatcher");
});
#pragma warning restore 612, 618
}
}
}
@@ -0,0 +1,65 @@
using Microsoft.EntityFrameworkCore.Migrations;
#nullable disable
namespace CvMatcher.Data.Migrations
{
/// <inheritdoc />
public partial class ImproveKeywordsAndAddLocation : Migration
{
/// <inheritdoc />
protected override void Up(MigrationBuilder migrationBuilder)
{
// Update English prompt: tighter keywords instruction (job-board search terms, not abstract
// concepts) and add location field so the LLM extracts the candidate's city/country.
migrationBuilder.UpdateData(
schema: MigrationConstants.SchemaName,
table: "AiPrompts",
keyColumns: ["Key", "Language"],
keyValues: ["ai.cv-match.system-prompt", "en"],
columns: ["Value", "Description"],
values: [
"You are a strict CV-to-job matching engine. Return JSON only. Score realistically from 0 to 100. Penalize missing required skills. Do not invent experience. Use concise business language. All text fields in the JSON response must be in English.\nJSON shape: {\"score\":number,\"summary\":\"one-line summary in English\",\"strengths\":[\"strength 1 in English\"],\"gaps\":[\"gap 1 in English\"],\"recommendations\":[\"recommendation 1 in English\"],\"evidence\":[\"evidence 1 in English\"],\"keywords\":[\"Senior .NET Developer\",\"C#\",\"Azure\"],\"location\":\"City, Country\"}.\nFor 'keywords': extract 2-4 short, concrete terms a recruiter would search for on a job board — the candidate's primary role title and key technologies (e.g. 'Senior .NET Developer', 'C#', 'Azure'). Avoid abstract concepts like 'leadership', 'cloud', or 'microservices'.\nFor 'location': extract the candidate's city and country from the CV (e.g. 'Cluj-Napoca, Romania'). Use an empty string if not found.",
"System prompt for CV-to-job matching in English. Extracts job-board-friendly keywords (role title + key tech) and candidate location."
]);
// Update Romanian prompt: same improvements.
migrationBuilder.UpdateData(
schema: MigrationConstants.SchemaName,
table: "AiPrompts",
keyColumns: ["Key", "Language"],
keyValues: ["ai.cv-match.system-prompt", "ro"],
columns: ["Value", "Description"],
values: [
"Ești un motor strict de potrivire CV-job. Returnează doar JSON. Punctează realist între 0 și 100. Penalizează abilitățile lipsă necesare. Nu inventa experiență. Folosește limbaj profesional concis. Toate câmpurile text din răspunsul JSON trebuie să fie în limba română.\nJSON shape: {\"score\":number,\"summary\":\"rezumat pe o linie în română\",\"strengths\":[\"punct forte 1 în română\"],\"gaps\":[\"lipsă 1 în română\"],\"recommendations\":[\"recomandare 1 în română\"],\"evidence\":[\"dovadă 1 în română\"],\"keywords\":[\"Senior .NET Developer\",\"C#\",\"Azure\"],\"location\":\"Oraș, Țară\"}.\nPentru 'keywords': extrage 2-4 termeni scurți și concreți pe care un recrutor i-ar căuta pe un site de joburi — titlul principal al rolului și tehnologiile cheie (ex. 'Senior .NET Developer', 'C#', 'Azure'). Evită concepte abstracte precum 'leadership', 'cloud' sau 'microservicii'.\nPentru 'location': extrage orașul și țara candidatului din CV (ex. 'Cluj-Napoca, România'). Folosește string gol dacă nu se găsește.",
"System prompt pentru potrivire CV-job în limba română. Extrage cuvinte cheie prietenoase pentru site-uri de joburi (titlu rol + tehnologii cheie) și locația candidatului."
]);
}
/// <inheritdoc />
protected override void Down(MigrationBuilder migrationBuilder)
{
migrationBuilder.UpdateData(
schema: MigrationConstants.SchemaName,
table: "AiPrompts",
keyColumns: ["Key", "Language"],
keyValues: ["ai.cv-match.system-prompt", "en"],
columns: ["Value", "Description"],
values: [
"You are a strict CV-to-job matching engine. Return JSON only. Score realistically from 0 to 100. Penalize missing required skills. Do not invent experience. Use concise business language. All text fields in the JSON response must be in English.\nJSON shape: {\"score\":number,\"summary\":\"one-line summary in English\",\"strengths\":[\"strength 1 in English\"],\"gaps\":[\"gap 1 in English\"],\"recommendations\":[\"recommendation 1 in English\"],\"evidence\":[\"evidence 1 in English\"],\"keywords\":[\"keyword1\",\"keyword2\",\"keyword3\"]}",
"System prompt for CV-to-job matching in English. Instructs LLM to return JSON with CV strengths, gaps, and recommendations relative to the job."
]);
migrationBuilder.UpdateData(
schema: MigrationConstants.SchemaName,
table: "AiPrompts",
keyColumns: ["Key", "Language"],
keyValues: ["ai.cv-match.system-prompt", "ro"],
columns: ["Value", "Description"],
values: [
"Ești un motor strict de potrivire CV-job. Returnează doar JSON. Punctează realist între 0 și 100. Penalizează abilitățile lipsă necesare. Nu inventa experiență. Folosește limbaj profesional concis. Toate câmpurile text din răspunsul JSON trebuie să fie în limba română.\nJSON shape: {\"score\":number,\"summary\":\"rezumat pe o linie în română\",\"strengths\":[\"punct forte 1 în română\"],\"gaps\":[\"lipsă 1 în română\"],\"recommendations\":[\"recomandare 1 în română\"],\"evidence\":[\"dovadă 1 în română\"],\"keywords\":[\"cuvant1\",\"cuvant2\",\"cuvant3\"]}",
"System prompt pentru potrivire CV-job în limba română. Instruiește LLM-ul să returneze JSON cu punctele forte ale CV-ului, lacunele și recomandări relative la job."
]);
}
}
}
@@ -33,4 +33,10 @@ public sealed class JobProviderEntity
/// <summary>When true, the scraper renders the page with headless Chromium instead of a plain HTTP GET.</summary>
public bool UseHeadlessBrowser { get; set; }
/// <summary>
/// When false, the Stage 2 anchor-text keyword filter is skipped.
/// Set to false for providers whose search URL already filters by relevance server-side (ejobs.ro, bestjobs.eu).
/// </summary>
public bool RequireKeywordInAnchor { get; set; } = true;
}
@@ -9,6 +9,7 @@ public sealed class JobSearchSessionEntity : BaseEntity
public string Email { get; set; } = string.Empty;
public string Status { get; set; } = JobSearchStatus.Pending;
public string Keywords { get; set; } = string.Empty;
public string? Location { get; set; }
public string? ProviderConfigJson { get; set; }
public string Language { get; set; } = "en";
}
@@ -10,4 +10,5 @@ public sealed class JobSearchTokenEntity : BaseEntity
public DateTime ExpiresAt { get; set; }
public bool Used { get; set; }
public string Keywords { get; set; } = string.Empty;
public string? Location { get; set; }
}
@@ -0,0 +1,243 @@
// <auto-generated />
using System;
using CvSearch.Data;
using Microsoft.EntityFrameworkCore;
using Microsoft.EntityFrameworkCore.Infrastructure;
using Microsoft.EntityFrameworkCore.Metadata;
using Microsoft.EntityFrameworkCore.Migrations;
using Microsoft.EntityFrameworkCore.Storage.ValueConversion;
#nullable disable
namespace CvSearch.Data.Migrations
{
[DbContext(typeof(CvSearchDbContext))]
[Migration("20260608124304_AddRequireKeywordInAnchorAndLocation")]
partial class AddRequireKeywordInAnchorAndLocation
{
/// <inheritdoc />
protected override void BuildTargetModel(ModelBuilder modelBuilder)
{
#pragma warning disable 612, 618
modelBuilder
.HasDefaultSchema("cvSearch")
.HasAnnotation("ProductVersion", "10.0.7")
.HasAnnotation("Relational:MaxIdentifierLength", 128);
SqlServerModelBuilderExtensions.UseIdentityColumns(modelBuilder);
modelBuilder.Entity("CvSearch.Data.Entities.JobProviderEntity", b =>
{
b.Property<int>("Id")
.ValueGeneratedOnAdd()
.HasColumnType("int");
SqlServerPropertyBuilderExtensions.UseIdentityColumn(b.Property<int>("Id"));
b.Property<int>("DisplayOrder")
.ValueGeneratedOnAdd()
.HasColumnType("int")
.HasDefaultValue(0);
b.Property<bool>("Enabled")
.HasColumnType("bit");
b.Property<string>("InitialKeywordsJson")
.IsRequired()
.ValueGeneratedOnAdd()
.HasMaxLength(2000)
.HasColumnType("nvarchar(2000)")
.HasDefaultValue("[]");
b.Property<string>("JobLinkContains")
.IsRequired()
.HasMaxLength(256)
.HasColumnType("nvarchar(256)");
b.Property<int>("MaxResults")
.ValueGeneratedOnAdd()
.HasColumnType("int")
.HasDefaultValue(20);
b.Property<string>("Name")
.IsRequired()
.HasMaxLength(128)
.HasColumnType("nvarchar(128)");
b.Property<bool>("RequireKeywordInAnchor")
.HasColumnType("bit");
b.Property<string>("SearchUrlTemplate")
.IsRequired()
.HasMaxLength(1024)
.HasColumnType("nvarchar(1024)");
b.Property<bool>("UseHeadlessBrowser")
.ValueGeneratedOnAdd()
.HasColumnType("bit")
.HasDefaultValue(false);
b.HasKey("Id");
b.ToTable("JobProviders", "cvSearch");
});
modelBuilder.Entity("CvSearch.Data.Entities.JobSearchResultEntity", b =>
{
b.Property<string>("Id")
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.Property<DateTime>("CreatedAt")
.ValueGeneratedOnAdd()
.HasColumnType("datetime2")
.HasDefaultValueSql("SYSUTCDATETIME()");
b.Property<string>("JobText")
.IsRequired()
.HasColumnType("nvarchar(max)");
b.Property<string>("JobTitle")
.IsRequired()
.HasMaxLength(512)
.HasColumnType("nvarchar(512)");
b.Property<string>("JobUrl")
.IsRequired()
.HasMaxLength(2048)
.HasColumnType("nvarchar(2048)");
b.Property<string>("ProviderName")
.IsRequired()
.HasMaxLength(128)
.HasColumnType("nvarchar(128)");
b.Property<string>("ResultJson")
.IsRequired()
.HasColumnType("nvarchar(max)");
b.Property<int>("Score")
.HasColumnType("int");
b.Property<string>("SessionId")
.IsRequired()
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.HasKey("Id");
b.HasIndex("SessionId");
b.ToTable("JobSearchResults", "cvSearch");
});
modelBuilder.Entity("CvSearch.Data.Entities.JobSearchSessionEntity", b =>
{
b.Property<string>("Id")
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.Property<DateTime>("CreatedAt")
.ValueGeneratedOnAdd()
.HasColumnType("datetime2")
.HasDefaultValueSql("SYSUTCDATETIME()");
b.Property<string>("CvDocumentId")
.IsRequired()
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.Property<string>("Email")
.IsRequired()
.HasMaxLength(256)
.HasColumnType("nvarchar(256)");
b.Property<string>("Keywords")
.IsRequired()
.HasMaxLength(1000)
.HasColumnType("nvarchar(1000)");
b.Property<string>("Language")
.IsRequired()
.ValueGeneratedOnAdd()
.HasMaxLength(8)
.HasColumnType("nvarchar(8)")
.HasDefaultValue("en");
b.Property<string>("Location")
.HasColumnType("nvarchar(max)");
b.Property<string>("ProviderConfigJson")
.HasColumnType("nvarchar(max)");
b.Property<string>("Status")
.IsRequired()
.HasMaxLength(32)
.HasColumnType("nvarchar(32)");
b.Property<string>("TokenId")
.IsRequired()
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.HasKey("Id");
b.HasIndex("Status");
b.ToTable("JobSearchSessions", "cvSearch");
});
modelBuilder.Entity("CvSearch.Data.Entities.JobSearchTokenEntity", b =>
{
b.Property<string>("Id")
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.Property<DateTime>("CreatedAt")
.ValueGeneratedOnAdd()
.HasColumnType("datetime2")
.HasDefaultValueSql("SYSUTCDATETIME()");
b.Property<string>("CvDocumentId")
.IsRequired()
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.Property<string>("Email")
.IsRequired()
.HasMaxLength(256)
.HasColumnType("nvarchar(256)");
b.Property<DateTime>("ExpiresAt")
.HasColumnType("datetime2");
b.Property<string>("Keywords")
.IsRequired()
.ValueGeneratedOnAdd()
.HasMaxLength(1000)
.HasColumnType("nvarchar(1000)")
.HasDefaultValue("");
b.Property<string>("Language")
.IsRequired()
.ValueGeneratedOnAdd()
.HasMaxLength(8)
.HasColumnType("nvarchar(8)")
.HasDefaultValue("en");
b.Property<string>("Location")
.HasColumnType("nvarchar(max)");
b.Property<bool>("Used")
.ValueGeneratedOnAdd()
.HasColumnType("bit")
.HasDefaultValue(false);
b.HasKey("Id");
b.ToTable("JobSearchTokens", "cvSearch");
});
#pragma warning restore 612, 618
}
}
}
@@ -0,0 +1,74 @@
using Microsoft.EntityFrameworkCore.Migrations;
#nullable disable
namespace CvSearch.Data.Migrations
{
/// <inheritdoc />
public partial class AddRequireKeywordInAnchorAndLocation : Migration
{
/// <inheritdoc />
protected override void Up(MigrationBuilder migrationBuilder)
{
migrationBuilder.AddColumn<string>(
name: "Location",
schema: "cvSearch",
table: "JobSearchTokens",
type: "nvarchar(max)",
nullable: true);
migrationBuilder.AddColumn<string>(
name: "Location",
schema: "cvSearch",
table: "JobSearchSessions",
type: "nvarchar(max)",
nullable: true);
migrationBuilder.AddColumn<bool>(
name: "RequireKeywordInAnchor",
schema: "cvSearch",
table: "JobProviders",
type: "bit",
nullable: false,
defaultValue: true);
// ejobs.ro (Id=1) and bestjobs.eu (Id=2) do server-side keyword filtering via their
// search URL — the Stage 2 anchor-text filter rejects all Romanian job titles because
// they rarely contain abstract LLM keywords.
migrationBuilder.UpdateData(
schema: "cvSearch",
table: "JobProviders",
keyColumn: "Id",
keyValue: 1,
column: "RequireKeywordInAnchor",
value: false);
migrationBuilder.UpdateData(
schema: "cvSearch",
table: "JobProviders",
keyColumn: "Id",
keyValue: 2,
column: "RequireKeywordInAnchor",
value: false);
}
/// <inheritdoc />
protected override void Down(MigrationBuilder migrationBuilder)
{
migrationBuilder.DropColumn(
name: "Location",
schema: "cvSearch",
table: "JobSearchTokens");
migrationBuilder.DropColumn(
name: "Location",
schema: "cvSearch",
table: "JobSearchSessions");
migrationBuilder.DropColumn(
name: "RequireKeywordInAnchor",
schema: "cvSearch",
table: "JobProviders");
}
}
}
@@ -0,0 +1,243 @@
// <auto-generated />
using System;
using CvSearch.Data;
using Microsoft.EntityFrameworkCore;
using Microsoft.EntityFrameworkCore.Infrastructure;
using Microsoft.EntityFrameworkCore.Metadata;
using Microsoft.EntityFrameworkCore.Migrations;
using Microsoft.EntityFrameworkCore.Storage.ValueConversion;
#nullable disable
namespace CvSearch.Data.Migrations
{
[DbContext(typeof(CvSearchDbContext))]
[Migration("20260608124452_AddLocationToProviders")]
partial class AddLocationToProviders
{
/// <inheritdoc />
protected override void BuildTargetModel(ModelBuilder modelBuilder)
{
#pragma warning disable 612, 618
modelBuilder
.HasDefaultSchema("cvSearch")
.HasAnnotation("ProductVersion", "10.0.7")
.HasAnnotation("Relational:MaxIdentifierLength", 128);
SqlServerModelBuilderExtensions.UseIdentityColumns(modelBuilder);
modelBuilder.Entity("CvSearch.Data.Entities.JobProviderEntity", b =>
{
b.Property<int>("Id")
.ValueGeneratedOnAdd()
.HasColumnType("int");
SqlServerPropertyBuilderExtensions.UseIdentityColumn(b.Property<int>("Id"));
b.Property<int>("DisplayOrder")
.ValueGeneratedOnAdd()
.HasColumnType("int")
.HasDefaultValue(0);
b.Property<bool>("Enabled")
.HasColumnType("bit");
b.Property<string>("InitialKeywordsJson")
.IsRequired()
.ValueGeneratedOnAdd()
.HasMaxLength(2000)
.HasColumnType("nvarchar(2000)")
.HasDefaultValue("[]");
b.Property<string>("JobLinkContains")
.IsRequired()
.HasMaxLength(256)
.HasColumnType("nvarchar(256)");
b.Property<int>("MaxResults")
.ValueGeneratedOnAdd()
.HasColumnType("int")
.HasDefaultValue(20);
b.Property<string>("Name")
.IsRequired()
.HasMaxLength(128)
.HasColumnType("nvarchar(128)");
b.Property<bool>("RequireKeywordInAnchor")
.HasColumnType("bit");
b.Property<string>("SearchUrlTemplate")
.IsRequired()
.HasMaxLength(1024)
.HasColumnType("nvarchar(1024)");
b.Property<bool>("UseHeadlessBrowser")
.ValueGeneratedOnAdd()
.HasColumnType("bit")
.HasDefaultValue(false);
b.HasKey("Id");
b.ToTable("JobProviders", "cvSearch");
});
modelBuilder.Entity("CvSearch.Data.Entities.JobSearchResultEntity", b =>
{
b.Property<string>("Id")
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.Property<DateTime>("CreatedAt")
.ValueGeneratedOnAdd()
.HasColumnType("datetime2")
.HasDefaultValueSql("SYSUTCDATETIME()");
b.Property<string>("JobText")
.IsRequired()
.HasColumnType("nvarchar(max)");
b.Property<string>("JobTitle")
.IsRequired()
.HasMaxLength(512)
.HasColumnType("nvarchar(512)");
b.Property<string>("JobUrl")
.IsRequired()
.HasMaxLength(2048)
.HasColumnType("nvarchar(2048)");
b.Property<string>("ProviderName")
.IsRequired()
.HasMaxLength(128)
.HasColumnType("nvarchar(128)");
b.Property<string>("ResultJson")
.IsRequired()
.HasColumnType("nvarchar(max)");
b.Property<int>("Score")
.HasColumnType("int");
b.Property<string>("SessionId")
.IsRequired()
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.HasKey("Id");
b.HasIndex("SessionId");
b.ToTable("JobSearchResults", "cvSearch");
});
modelBuilder.Entity("CvSearch.Data.Entities.JobSearchSessionEntity", b =>
{
b.Property<string>("Id")
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.Property<DateTime>("CreatedAt")
.ValueGeneratedOnAdd()
.HasColumnType("datetime2")
.HasDefaultValueSql("SYSUTCDATETIME()");
b.Property<string>("CvDocumentId")
.IsRequired()
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.Property<string>("Email")
.IsRequired()
.HasMaxLength(256)
.HasColumnType("nvarchar(256)");
b.Property<string>("Keywords")
.IsRequired()
.HasMaxLength(1000)
.HasColumnType("nvarchar(1000)");
b.Property<string>("Language")
.IsRequired()
.ValueGeneratedOnAdd()
.HasMaxLength(8)
.HasColumnType("nvarchar(8)")
.HasDefaultValue("en");
b.Property<string>("Location")
.HasColumnType("nvarchar(max)");
b.Property<string>("ProviderConfigJson")
.HasColumnType("nvarchar(max)");
b.Property<string>("Status")
.IsRequired()
.HasMaxLength(32)
.HasColumnType("nvarchar(32)");
b.Property<string>("TokenId")
.IsRequired()
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.HasKey("Id");
b.HasIndex("Status");
b.ToTable("JobSearchSessions", "cvSearch");
});
modelBuilder.Entity("CvSearch.Data.Entities.JobSearchTokenEntity", b =>
{
b.Property<string>("Id")
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.Property<DateTime>("CreatedAt")
.ValueGeneratedOnAdd()
.HasColumnType("datetime2")
.HasDefaultValueSql("SYSUTCDATETIME()");
b.Property<string>("CvDocumentId")
.IsRequired()
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.Property<string>("Email")
.IsRequired()
.HasMaxLength(256)
.HasColumnType("nvarchar(256)");
b.Property<DateTime>("ExpiresAt")
.HasColumnType("datetime2");
b.Property<string>("Keywords")
.IsRequired()
.ValueGeneratedOnAdd()
.HasMaxLength(1000)
.HasColumnType("nvarchar(1000)")
.HasDefaultValue("");
b.Property<string>("Language")
.IsRequired()
.ValueGeneratedOnAdd()
.HasMaxLength(8)
.HasColumnType("nvarchar(8)")
.HasDefaultValue("en");
b.Property<string>("Location")
.HasColumnType("nvarchar(max)");
b.Property<bool>("Used")
.ValueGeneratedOnAdd()
.HasColumnType("bit")
.HasDefaultValue(false);
b.HasKey("Id");
b.ToTable("JobSearchTokens", "cvSearch");
});
#pragma warning restore 612, 618
}
}
}
@@ -0,0 +1,71 @@
using Microsoft.EntityFrameworkCore.Migrations;
#nullable disable
namespace CvSearch.Data.Migrations
{
/// <inheritdoc />
public partial class AddLocationToProviders : Migration
{
/// <inheritdoc />
protected override void Up(MigrationBuilder migrationBuilder)
{
// ejobs.ro (Id=1): location in URL path as slug, keywords via q= param.
// Verified URL structure: /locuri-de-munca/{location-slug}?q={keywords}
migrationBuilder.UpdateData(
schema: MigrationConstants.SchemaName,
table: "JobProviders",
keyColumn: "Id",
keyValue: 1,
column: "SearchUrlTemplate",
value: "https://www.ejobs.ro/locuri-de-munca/{location-slug}?q={keywords}");
// bestjobs.eu (Id=2): location in URL path as slug, keywords via query param.
// Verified URL structure: /ro/locuri-de-munca-in-{location-slug}?keywords={keywords}
migrationBuilder.UpdateData(
schema: MigrationConstants.SchemaName,
table: "JobProviders",
keyColumn: "Id",
keyValue: 2,
column: "SearchUrlTemplate",
value: "https://bestjobs.eu/ro/locuri-de-munca-in-{location-slug}?keywords={keywords}");
// linkedin.com (Id=3): location as query parameter.
migrationBuilder.UpdateData(
schema: MigrationConstants.SchemaName,
table: "JobProviders",
keyColumn: "Id",
keyValue: 3,
column: "SearchUrlTemplate",
value: "https://www.linkedin.com/jobs/search/?keywords={keywords}&location={location}");
}
/// <inheritdoc />
protected override void Down(MigrationBuilder migrationBuilder)
{
migrationBuilder.UpdateData(
schema: MigrationConstants.SchemaName,
table: "JobProviders",
keyColumn: "Id",
keyValue: 1,
column: "SearchUrlTemplate",
value: "https://www.ejobs.ro/locuri-de-munca?q={keywords}");
migrationBuilder.UpdateData(
schema: MigrationConstants.SchemaName,
table: "JobProviders",
keyColumn: "Id",
keyValue: 2,
column: "SearchUrlTemplate",
value: "https://www.bestjobs.eu/ro/locuri-de-munca?keywords={keywords}");
migrationBuilder.UpdateData(
schema: MigrationConstants.SchemaName,
table: "JobProviders",
keyColumn: "Id",
keyValue: 3,
column: "SearchUrlTemplate",
value: "https://www.linkedin.com/jobs/search/?keywords={keywords}");
}
}
}
@@ -61,6 +61,9 @@ namespace CvSearch.Data.Migrations
.HasMaxLength(128)
.HasColumnType("nvarchar(128)");
b.Property<bool>("RequireKeywordInAnchor")
.HasColumnType("bit");
b.Property<string>("SearchUrlTemplate")
.IsRequired()
.HasMaxLength(1024)
@@ -158,6 +161,9 @@ namespace CvSearch.Data.Migrations
.HasColumnType("nvarchar(8)")
.HasDefaultValue("en");
b.Property<string>("Location")
.HasColumnType("nvarchar(max)");
b.Property<string>("ProviderConfigJson")
.HasColumnType("nvarchar(max)");
@@ -216,6 +222,9 @@ namespace CvSearch.Data.Migrations
.HasColumnType("nvarchar(8)")
.HasDefaultValue("en");
b.Property<string>("Location")
.HasColumnType("nvarchar(max)");
b.Property<bool>("Used")
.ValueGeneratedOnAdd()
.HasColumnType("bit")
+2
View File
@@ -4,6 +4,7 @@ WORKDIR /src
COPY Apis/email-api/email-api.csproj Apis/email-api/
COPY Apis/email-data/email-data.csproj Apis/email-data/
COPY Apis/shared-data/shared-data.csproj Apis/shared-data/
COPY Apis/email-api-models/email-api-models.csproj Apis/email-api-models/
COPY Apis/api-models/api-models.csproj Apis/api-models/
COPY Apis/common/common.csproj Apis/common/
@@ -15,6 +16,7 @@ RUN dotnet restore Apis/email-api/email-api.csproj
COPY Apis/email-api/ Apis/email-api/
COPY Apis/email-data/ Apis/email-data/
COPY Apis/shared-data/ Apis/shared-data/
COPY Apis/email-api-models/ Apis/email-api-models/
COPY Apis/api-models/ Apis/api-models/
COPY Apis/common/ Apis/common/
+1 -2
View File
@@ -50,9 +50,8 @@ try
app.UseDefaultSerilogRequestLogging();
app.UseJsonExceptionHandler(ServiceName);
app.UseSwaggerInDevelopment("Email API", "EmailAPI");
app.UseInternalApiKeyProtection();
app.UseSwaggerInDevelopment("Email API", "EmailAPI");
app.UseRouting();
app.UseAuthorization();
+1 -21
View File
@@ -2,8 +2,7 @@
"Serilog": {
"Using": [
"Serilog.Sinks.Console",
"Serilog.Sinks.File",
"Serilog.Sinks.Email"
"Serilog.Sinks.File"
],
"MinimumLevel": {
"Default": "Information",
@@ -30,25 +29,6 @@
"retainedFileCountLimit": 30,
"outputTemplate": "{Timestamp:yyyy-MM-dd HH:mm:ss.fff zzz} [{Level:u3}] {SourceContext}: {Message:lj}{NewLine}{Exception}"
}
},
{
"Name": "Email",
"Args": {
"restrictedToMinimumLevel": "Error",
"fromEmail": "",
"toEmail": "",
"mailServer": "",
"networkCredential": {
"userName": "",
"password": ""
},
"port": 587,
"enableSsl": true,
"emailSubject": "[myAi] Email API Error Alert",
"outputTemplate": "{Timestamp:yyyy-MM-dd HH:mm:ss.fff zzz} [{Level:u3}] {SourceContext}{NewLine}{Message:lj}{NewLine}{Exception}",
"batchPostingLimit": 10,
"period": "0.00:05:00"
}
}
],
"Enrich": [
+1 -21
View File
@@ -2,8 +2,7 @@
"Serilog": {
"Using": [
"Serilog.Sinks.Console",
"Serilog.Sinks.File",
"Serilog.Sinks.Email"
"Serilog.Sinks.File"
],
"MinimumLevel": {
"Default": "Information",
@@ -30,25 +29,6 @@
"retainedFileCountLimit": 30,
"outputTemplate": "{Timestamp:yyyy-MM-dd HH:mm:ss.fff zzz} [{Level:u3}] {SourceContext}: {Message:lj}{NewLine}{Exception}"
}
},
{
"Name": "Email",
"Args": {
"restrictedToMinimumLevel": "Error",
"fromEmail": "",
"toEmail": "",
"mailServer": "",
"networkCredential": {
"userName": "",
"password": ""
},
"port": 587,
"enableSsl": true,
"emailSubject": "[mihes.ro API] Error Alert",
"outputTemplate": "{Timestamp:yyyy-MM-dd HH:mm:ss.fff zzz} [{Level:u3}] {SourceContext}{NewLine}{Message:lj}{NewLine}{Exception}",
"batchPostingLimit": 10,
"period": "0.00:05:00"
}
}
],
"Enrich": [
@@ -1,5 +1,7 @@
using System.Net;
using System.Reflection;
using Azure.Identity;
using MailKit.Security;
using Microsoft.AspNetCore.Builder;
using Microsoft.AspNetCore.Diagnostics;
using Microsoft.AspNetCore.Http;
@@ -9,6 +11,7 @@ using Microsoft.Extensions.DependencyInjection;
using Microsoft.Extensions.Hosting;
using Microsoft.Extensions.Logging;
using Serilog;
using Serilog.Events;
using Swashbuckle.AspNetCore.SwaggerGen;
using Swashbuckle.AspNetCore.Annotations;
@@ -41,6 +44,8 @@ public static class StartupExtensions
.Enrich.WithProperty("Service", serviceName)
.Enrich.WithProperty("AppVersion", appVersion)
.WriteTo.Console(new Serilog.Formatting.Json.JsonFormatter());
AddEmailSinkIfConfigured(configuration, context.Configuration, serviceName);
});
}
@@ -57,9 +62,40 @@ public static class StartupExtensions
.Enrich.WithProperty("Service", serviceName)
.Enrich.WithProperty("AppVersion", appVersion)
.WriteTo.Console(new Serilog.Formatting.Json.JsonFormatter());
AddEmailSinkIfConfigured(configuration, builder.Configuration, serviceName);
});
}
private static void AddEmailSinkIfConfigured(LoggerConfiguration loggerConfig, IConfiguration appConfig, string serviceName)
{
var from = appConfig["SerilogEmail:From"];
var to = appConfig["SerilogEmail:To"];
var host = appConfig["SerilogEmail:Host"];
if (string.IsNullOrWhiteSpace(from) || string.IsNullOrWhiteSpace(to) || string.IsNullOrWhiteSpace(host))
return;
var port = appConfig.GetValue("SerilogEmail:Port", 587);
var userName = appConfig["SerilogEmail:UserName"];
var password = appConfig["SerilogEmail:Password"];
NetworkCredential? credentials = null;
if (!string.IsNullOrWhiteSpace(userName))
credentials = new NetworkCredential(userName, password);
loggerConfig.WriteTo.Email(
from: from,
to: to,
host: host,
port: port,
connectionSecurity: SecureSocketOptions.StartTls,
credentials: credentials,
subject: $"[myAi {serviceName}] Error Alert",
body: "{Timestamp:yyyy-MM-dd HH:mm:ss.fff zzz} [{Level:u3}] {SourceContext}{NewLine}{Message:lj}{NewLine}{Exception}",
restrictedToMinimumLevel: LogEventLevel.Error);
}
public static void AddAzureKeyVaultIfConfigured(this WebApplicationBuilder builder)
{
var keyVaultUri = builder.Configuration["KeyVault:VaultUri"];
+1 -21
View File
@@ -2,8 +2,7 @@
"Serilog": {
"Using": [
"Serilog.Sinks.Console",
"Serilog.Sinks.File",
"Serilog.Sinks.Email"
"Serilog.Sinks.File"
],
"MinimumLevel": {
"Default": "Information",
@@ -31,25 +30,6 @@
"retainedFileCountLimit": 30,
"outputTemplate": "{Timestamp:yyyy-MM-dd HH:mm:ss.fff zzz} [{Level:u3}] {SourceContext}: {Message:lj}{NewLine}{Exception}"
}
},
{
"Name": "Email",
"Args": {
"restrictedToMinimumLevel": "Error",
"fromEmail": "",
"toEmail": "",
"mailServer": "",
"networkCredential": {
"userName": "",
"password": ""
},
"port": 587,
"enableSsl": true,
"emailSubject": "[mihes.ro CV cleanup job] Error Alert",
"outputTemplate": "{Timestamp:yyyy-MM-dd HH:mm:ss.fff zzz} [{Level:u3}] {SourceContext}{NewLine}{Message:lj}{NewLine}{Exception}",
"batchPostingLimit": 10,
"period": "0.00:05:00"
}
}
],
"Enrich": [
+18 -6
View File
@@ -33,6 +33,7 @@ public sealed class HtmlJobSearcher
public async Task<IReadOnlyList<string>> SearchJobUrlsAsync(
JobProviderConfig provider,
IReadOnlyList<string> cvKeywords,
string? location,
CancellationToken ct)
{
var allKeywords = provider.InitialKeywords
@@ -48,13 +49,23 @@ public sealed class HtmlJobSearcher
}
var keywordsEncoded = HttpUtility.UrlEncode(string.Join(" ", allKeywords));
var searchUrl = provider.SearchUrlTemplate.Replace("{keywords}", keywordsEncoded);
var locationEncoded = HttpUtility.UrlEncode(location ?? string.Empty);
var locationSlug = (location ?? string.Empty)
.ToLowerInvariant()
.Replace(",", "")
.Replace(" ", "-")
.Trim('-');
var searchUrl = provider.SearchUrlTemplate
.Replace("{keywords}", keywordsEncoded)
.Replace("{location}", locationEncoded)
.Replace("{location-slug}", locationSlug);
_logger.LogInformation(
"Provider {Provider}: fetching {Url} [{Mode}] | CV keywords: [{Keywords}]",
"Provider {Provider}: fetching {Url} [{Mode}] | CV keywords: [{Keywords}] | Location: {Location}",
provider.Name, searchUrl,
provider.UseHeadlessBrowser ? "headless" : "http",
string.Join(", ", cvKeywords));
string.Join(", ", cvKeywords),
location ?? "(none)");
string? html;
if (provider.UseHeadlessBrowser)
@@ -89,7 +100,8 @@ public sealed class HtmlJobSearcher
stage1Pass++;
if (!cvKeywords.Any(k => anchorText.Contains(k, StringComparison.OrdinalIgnoreCase)))
if (provider.RequireKeywordInAnchor &&
!cvKeywords.Any(k => anchorText.Contains(k, StringComparison.OrdinalIgnoreCase)))
{
_logger.LogDebug(
"Provider {Provider}: stage-2 reject | href={Href} | text={Text}",
@@ -125,7 +137,7 @@ public sealed class HtmlJobSearcher
}
catch (Exception ex)
{
_logger.LogWarning(ex, "Provider {Provider}: HTTP fetch failed for {Url}", providerName, url);
_logger.LogError(ex, "Provider {Provider}: HTTP fetch failed for {Url}", providerName, url);
return null;
}
}
@@ -169,7 +181,7 @@ public sealed class HtmlJobSearcher
}
catch (Exception ex)
{
_logger.LogWarning(ex, "Provider {Provider}: Playwright fetch failed for {Url}", providerName, url);
_logger.LogError(ex, "Provider {Provider}: Playwright fetch failed for {Url}", providerName, url);
return null;
}
}
+1 -1
View File
@@ -141,7 +141,7 @@ public sealed class CvSearchJobTask : IJobTask
foreach (var provider in providers)
{
var urls = await _searcher.SearchJobUrlsAsync(provider, cvKeywords, ct);
var urls = await _searcher.SearchJobUrlsAsync(provider, cvKeywords, session.Location, ct);
_logger.LogInformation("Session {SessionId}: provider {Provider} returned {Count} URLs", session.Id, provider.Name, urls.Count);
foreach (var url in urls) jobUrls.Add(url);
}
+1 -21
View File
@@ -13,8 +13,7 @@
"Serilog": {
"Using": [
"Serilog.Sinks.Console",
"Serilog.Sinks.File",
"Serilog.Sinks.Email"
"Serilog.Sinks.File"
],
"MinimumLevel": {
"Default": "Information",
@@ -42,25 +41,6 @@
"retainedFileCountLimit": 30,
"outputTemplate": "{Timestamp:yyyy-MM-dd HH:mm:ss.fff zzz} [{Level:u3}] {SourceContext}: {Message:lj}{NewLine}{Exception}"
}
},
{
"Name": "Email",
"Args": {
"restrictedToMinimumLevel": "Error",
"fromEmail": "",
"toEmail": "",
"mailServer": "",
"networkCredential": {
"userName": "",
"password": ""
},
"port": 587,
"enableSsl": true,
"emailSubject": "[mihes.ro CV search job] Error Alert",
"outputTemplate": "{Timestamp:yyyy-MM-dd HH:mm:ss.fff zzz} [{Level:u3}] {SourceContext}{NewLine}{Message:lj}{NewLine}{Exception}",
"batchPostingLimit": 10,
"period": "0.00:05:00"
}
}
],
"Enrich": [
+3
View File
@@ -147,3 +147,6 @@ RateLimiting__Policies__contact__QueueLimit=0
RateLimiting__Policies__cvMatcher__PermitLimit=10
RateLimiting__Policies__cvMatcher__Window=00:10:00
RateLimiting__Policies__cvMatcher__QueueLimit=0
RateLimiting__Policies__download__PermitLimit=5
RateLimiting__Policies__download__Window=00:01:00
RateLimiting__Policies__download__QueueLimit=0
+39 -42
View File
@@ -35,13 +35,12 @@ services:
- Ai__Ollama__EmbeddingModel=${Ai__Ollama__EmbeddingModel:-nomic-embed-text}
- Ai__Ollama__TimeoutSeconds=${Ai__Ollama__TimeoutSeconds:-180}
- Serilog__WriteTo__2__Args__fromEmail=${Serilog__WriteTo__2__Args__fromEmail:-}
- Serilog__WriteTo__2__Args__toEmail=${Serilog__WriteTo__2__Args__toEmail:-}
- Serilog__WriteTo__2__Args__mailServer=${Serilog__WriteTo__2__Args__mailServer:-}
- Serilog__WriteTo__2__Args__networkCredential__userName=${Serilog__WriteTo__2__Args__networkCredential__userName:-}
- Serilog__WriteTo__2__Args__networkCredential__password=${Serilog__WriteTo__2__Args__networkCredential__password:-}
- Serilog__WriteTo__2__Args__port=${Serilog__WriteTo__2__Args__port:-587}
- Serilog__WriteTo__2__Args__enableSsl=${Serilog__WriteTo__2__Args__enableSsl:-true}
- SerilogEmail__From=${SerilogEmail__From:-}
- SerilogEmail__To=${SerilogEmail__To:-}
- SerilogEmail__Host=${SerilogEmail__Host:-}
- SerilogEmail__Port=${SerilogEmail__Port:-587}
- SerilogEmail__UserName=${SerilogEmail__UserName:-}
- SerilogEmail__Password=${SerilogEmail__Password:-}
volumes:
- ${LOGS_PATH:-/opt/myai/logs}/rag-api:/app/logs
networks:
@@ -85,13 +84,12 @@ services:
- Matcher__DeepScoreTopN=${Matcher__DeepScoreTopN:-5}
- Matcher__MaxJobTextChars=${Matcher__MaxJobTextChars:-60000}
- Serilog__WriteTo__2__Args__fromEmail=${Serilog__WriteTo__2__Args__fromEmail:-}
- Serilog__WriteTo__2__Args__toEmail=${Serilog__WriteTo__2__Args__toEmail:-}
- Serilog__WriteTo__2__Args__mailServer=${Serilog__WriteTo__2__Args__mailServer:-}
- Serilog__WriteTo__2__Args__networkCredential__userName=${Serilog__WriteTo__2__Args__networkCredential__userName:-}
- Serilog__WriteTo__2__Args__networkCredential__password=${Serilog__WriteTo__2__Args__networkCredential__password:-}
- Serilog__WriteTo__2__Args__port=${Serilog__WriteTo__2__Args__port:-587}
- Serilog__WriteTo__2__Args__enableSsl=${Serilog__WriteTo__2__Args__enableSsl:-true}
- SerilogEmail__From=${SerilogEmail__From:-}
- SerilogEmail__To=${SerilogEmail__To:-}
- SerilogEmail__Host=${SerilogEmail__Host:-}
- SerilogEmail__Port=${SerilogEmail__Port:-587}
- SerilogEmail__UserName=${SerilogEmail__UserName:-}
- SerilogEmail__Password=${SerilogEmail__Password:-}
volumes:
- ${LOGS_PATH:-/opt/myai/logs}/cv-matcher-api:/app/logs
networks:
@@ -126,13 +124,12 @@ services:
- FileStorage__Path=${FileStorage__Path:-Files}
- Serilog__WriteTo__2__Args__fromEmail=${Serilog__WriteTo__2__Args__fromEmail:-}
- Serilog__WriteTo__2__Args__toEmail=${Serilog__WriteTo__2__Args__toEmail:-}
- Serilog__WriteTo__2__Args__mailServer=${Serilog__WriteTo__2__Args__mailServer:-}
- Serilog__WriteTo__2__Args__networkCredential__userName=${Serilog__WriteTo__2__Args__networkCredential__userName:-}
- Serilog__WriteTo__2__Args__networkCredential__password=${Serilog__WriteTo__2__Args__networkCredential__password:-}
- Serilog__WriteTo__2__Args__port=${Serilog__WriteTo__2__Args__port:-587}
- Serilog__WriteTo__2__Args__enableSsl=${Serilog__WriteTo__2__Args__enableSsl:-true}
- SerilogEmail__From=${SerilogEmail__From:-}
- SerilogEmail__To=${SerilogEmail__To:-}
- SerilogEmail__Host=${SerilogEmail__Host:-}
- SerilogEmail__Port=${SerilogEmail__Port:-587}
- SerilogEmail__UserName=${SerilogEmail__UserName:-}
- SerilogEmail__Password=${SerilogEmail__Password:-}
volumes:
- ${LOGS_PATH:-/opt/myai/logs}/email-api:/app/logs
- ${FILES_PATH:-/opt/myai/files}:/app/Files
@@ -194,17 +191,19 @@ services:
- RateLimiting__Policies__cvMatcher__PermitLimit=${RateLimiting__Policies__cvMatcher__PermitLimit:-10}
- RateLimiting__Policies__cvMatcher__Window=${RateLimiting__Policies__cvMatcher__Window:-00:10:00}
- RateLimiting__Policies__cvMatcher__QueueLimit=${RateLimiting__Policies__cvMatcher__QueueLimit:-0}
- RateLimiting__Policies__download__PermitLimit=${RateLimiting__Policies__download__PermitLimit:-5}
- RateLimiting__Policies__download__Window=${RateLimiting__Policies__download__Window:-00:01:00}
- RateLimiting__Policies__download__QueueLimit=${RateLimiting__Policies__download__QueueLimit:-0}
- Cors__AllowedOrigins__0=${Cors__AllowedOrigins__0:-}
- Cors__AllowedOrigins__1=${Cors__AllowedOrigins__1:-}
- Serilog__WriteTo__2__Args__fromEmail=${Serilog__WriteTo__2__Args__fromEmail:-}
- Serilog__WriteTo__2__Args__toEmail=${Serilog__WriteTo__2__Args__toEmail:-}
- Serilog__WriteTo__2__Args__mailServer=${Serilog__WriteTo__2__Args__mailServer:-}
- Serilog__WriteTo__2__Args__networkCredential__userName=${Serilog__WriteTo__2__Args__networkCredential__userName:-}
- Serilog__WriteTo__2__Args__networkCredential__password=${Serilog__WriteTo__2__Args__networkCredential__password:-}
- Serilog__WriteTo__2__Args__port=${Serilog__WriteTo__2__Args__port:-587}
- Serilog__WriteTo__2__Args__enableSsl=${Serilog__WriteTo__2__Args__enableSsl:-true}
- SerilogEmail__From=${SerilogEmail__From:-}
- SerilogEmail__To=${SerilogEmail__To:-}
- SerilogEmail__Host=${SerilogEmail__Host:-}
- SerilogEmail__Port=${SerilogEmail__Port:-587}
- SerilogEmail__UserName=${SerilogEmail__UserName:-}
- SerilogEmail__Password=${SerilogEmail__Password:-}
volumes:
- ${LOGS_PATH:-/opt/myai/logs}/api:/app/logs
- ${FILES_PATH:-/opt/myai/files}:/app/Files
@@ -229,13 +228,12 @@ services:
- Jobs__Tasks__0__Interval=${Jobs__CvStorageCleanupInterval:-01:00:00}
- Jobs__Tasks__0__Parameters__MaxTotalSizeMegabytes=${Jobs__CvStorageMaxTotalSizeMegabytes:-40}
- Serilog__WriteTo__2__Args__fromEmail=${Serilog__WriteTo__2__Args__fromEmail:-}
- Serilog__WriteTo__2__Args__toEmail=${Serilog__WriteTo__2__Args__toEmail:-}
- Serilog__WriteTo__2__Args__mailServer=${Serilog__WriteTo__2__Args__mailServer:-}
- Serilog__WriteTo__2__Args__networkCredential__userName=${Serilog__WriteTo__2__Args__networkCredential__userName:-}
- Serilog__WriteTo__2__Args__networkCredential__password=${Serilog__WriteTo__2__Args__networkCredential__password:-}
- Serilog__WriteTo__2__Args__port=${Serilog__WriteTo__2__Args__port:-587}
- Serilog__WriteTo__2__Args__enableSsl=${Serilog__WriteTo__2__Args__enableSsl:-true}
- SerilogEmail__From=${SerilogEmail__From:-}
- SerilogEmail__To=${SerilogEmail__To:-}
- SerilogEmail__Host=${SerilogEmail__Host:-}
- SerilogEmail__Port=${SerilogEmail__Port:-587}
- SerilogEmail__UserName=${SerilogEmail__UserName:-}
- SerilogEmail__Password=${SerilogEmail__Password:-}
volumes:
- ${LOGS_PATH:-/opt/myai/logs}/cv-cleanup-job:/app/logs
- ${FILES_PATH:-/opt/myai/files}:/app/Files
@@ -280,13 +278,12 @@ services:
- Jobs__Tasks__0__Enabled=${Jobs__CvSearchEnabled:-true}
- Jobs__Tasks__0__Interval=${Jobs__CvSearchInterval:-00:00:30}
- Serilog__WriteTo__2__Args__fromEmail=${Serilog__WriteTo__2__Args__fromEmail:-}
- Serilog__WriteTo__2__Args__toEmail=${Serilog__WriteTo__2__Args__toEmail:-}
- Serilog__WriteTo__2__Args__mailServer=${Serilog__WriteTo__2__Args__mailServer:-}
- Serilog__WriteTo__2__Args__networkCredential__userName=${Serilog__WriteTo__2__Args__networkCredential__userName:-}
- Serilog__WriteTo__2__Args__networkCredential__password=${Serilog__WriteTo__2__Args__networkCredential__password:-}
- Serilog__WriteTo__2__Args__port=${Serilog__WriteTo__2__Args__port:-587}
- Serilog__WriteTo__2__Args__enableSsl=${Serilog__WriteTo__2__Args__enableSsl:-true}
- SerilogEmail__From=${SerilogEmail__From:-}
- SerilogEmail__To=${SerilogEmail__To:-}
- SerilogEmail__Host=${SerilogEmail__Host:-}
- SerilogEmail__Port=${SerilogEmail__Port:-587}
- SerilogEmail__UserName=${SerilogEmail__UserName:-}
- SerilogEmail__Password=${SerilogEmail__Password:-}
volumes:
- ${LOGS_PATH:-/opt/myai/logs}/cv-search-job:/app/logs
- ${FILES_PATH:-/opt/myai/files}:/app/Files