refactor(pipeline): restructure config, add PromptDirectory, consolidate SQLite layer (#217)

* Refactor ApplicationOptions to separate config concerns

* add prompt dir app option

* readability updates: remove magic numbers, update comments

* codebase formatting

* Update docs

* Extract argument parsing, timer out of

tooling/pipeline/src/services/prompt_directory.cc

@@ -0,0 +1,85 @@
+/**
+ * @file services/prompt_directory.cc
+ * @brief PromptDirectory implementation: validates the directory at
+ * construction and loads named prompt files on demand with in-process caching.
+ */
+
+#include "services/prompt_directory.h"
+
+#include <spdlog/spdlog.h>
+
+#include <filesystem>
+#include <fstream>
+#include <stdexcept>
+#include <string>
+#include <string_view>
+
+// ---------------------------------------------------------------------------
+// PromptDirectory
+// ---------------------------------------------------------------------------
+
+PromptDirectory::PromptDirectory(const std::filesystem::path& prompt_dir)
+    : prompt_dir_(prompt_dir) {
+  std::error_code ec;
+
+  // Scenario 4: directory must exist.
+  if (!std::filesystem::exists(prompt_dir_, ec) || ec) {
+    throw std::runtime_error(
+        "PromptDirectory: prompt directory does not exist: " +
+        prompt_dir_.string());
+  }
+
+  // Scenario 4: path must be a directory, not a file.
+  if (!std::filesystem::is_directory(prompt_dir_, ec) || ec) {
+    throw std::runtime_error(
+        "PromptDirectory: prompt directory path is not a directory: " +
+        prompt_dir_.string());
+  }
+
+  // Scenario 4: directory must be readable (probe with directory_iterator).
+  std::filesystem::directory_iterator probe(prompt_dir_, ec);
+  if (ec) {
+    throw std::runtime_error(
+        "PromptDirectory: prompt directory is not readable: " +
+        prompt_dir_.string() + " (" + ec.message() + ")");
+  }
+
+  spdlog::info("[PromptDirectory] Resolved prompt directory: {}",
+               prompt_dir_.string());
+}
+
+std::string PromptDirectory::Load(std::string_view key) {
+  const std::string key_str(key);
+
+  // Return cached content if already loaded during this run.
+  const auto cache_it = cache_.find(key_str);
+  if (cache_it != cache_.end()) {
+    return cache_it->second;
+  }
+
+  // Scenario 3: resolve <prompt_dir>/<key>.md and require it to exist.
+  const std::filesystem::path file_path =
+      prompt_dir_ / std::filesystem::path(key_str + ".md");
+
+  std::ifstream file(file_path);
+  if (!file.is_open()) {
+    throw std::runtime_error(
+        "PromptDirectory: prompt file not found for key '" + key_str +
+        "': " + file_path.string());
+  }
+
+  std::string content((std::istreambuf_iterator<char>(file)),
+                      std::istreambuf_iterator<char>());
+  file.close();
+
+  if (content.empty()) {
+    throw std::runtime_error("PromptDirectory: prompt file for key '" +
+                             key_str + "' is empty: " + file_path.string());
+  }
+
+  spdlog::info("[PromptDirectory] Loaded prompt '{}' from '{}' ({} chars)",
+               key_str, file_path.string(), content.size());
+
+  cache_.emplace(key_str, content);
+  return content;
+}

tooling/pipeline/src/services/sqlite/build_database_path.cc

@@ -1,24 +0,0 @@
-/**
- * @file services/sqlite/build_database_path.cc
- * @brief SqliteExportService::BuildDatabasePath() implementation.
- */
-
-#include <filesystem>
-#include <string>
-
-#include "services/sqlite_export_service.h"
-
-std::filesystem::path SqliteExportService::BuildDatabasePath() const {
-  std::filesystem::path base_filename("biergarten_seed_" + run_timestamp_utc_ +
-                                      ".sqlite");
-  std::filesystem::path candidate =
-      std::filesystem::current_path() / base_filename;
-
-  for (int suffix = 1; std::filesystem::exists(candidate); ++suffix) {
-    candidate = std::filesystem::current_path() /
-                std::filesystem::path("biergarten_seed_" + run_timestamp_utc_ +
-                                      "-" + std::to_string(suffix) + ".sqlite");
-  }
-
-  return candidate;
-}

tooling/pipeline/src/services/sqlite/finalize.cc

@@ -8,7 +8,6 @@
 #include "services/sqlite_export_service.h"
 #include "services/sqlite_export_service_helpers.h"
 
-
 void SqliteExportService::Finalize() {
   if (db_handle_ == nullptr) {
     return;

tooling/pipeline/src/services/sqlite/helpers/sqlite_connection_helpers.cc

@@ -10,7 +10,8 @@ void SqliteDatabaseDeleter::operator()(sqlite3* handle) const noexcept {
   }
 }
 
-void SqliteStatementDeleter::operator()(sqlite3_stmt* statement) const noexcept {
+void SqliteStatementDeleter::operator()(
+    sqlite3_stmt* statement) const noexcept {
   if (statement != nullptr) {
     sqlite3_finalize(statement);
   }
@@ -23,7 +24,6 @@ void ThrowSqliteError(sqlite3* db_handle, std::string_view action) {
 }
 
 SqliteDatabaseHandle OpenDatabase(const std::filesystem::path& path) {
-
   sqlite3* raw_handle = nullptr;
   const int result = sqlite3_open(path.string().c_str(), &raw_handle);
 
@@ -54,7 +54,8 @@ void ExecSql(const SqliteDatabaseHandle& db_handle, std::string_view sql,
   }
 }
 
-void RollbackTransactionNoThrow(const SqliteDatabaseHandle& db_handle) noexcept {
+void RollbackTransactionNoThrow(
+    const SqliteDatabaseHandle& db_handle) noexcept {
   if (!db_handle) {
     return;
   }
@@ -63,4 +64,3 @@ void RollbackTransactionNoThrow(const SqliteDatabaseHandle& db_handle) noexcept
 }
 
 }  // namespace sqlite_export_service_internal
-

tooling/pipeline/src/services/sqlite/helpers/sqlite_statement_helpers.cc

@@ -1,11 +1,12 @@
 #include "services/sqlite_statement_helpers.h"
-#include "services/sqlite_connection_helpers.h"
 
-#include <cstring>
-#include <memory>
-#include <limits>
-#include <stdexcept>
 #include <boost/json.hpp>
+#include <cstring>
+#include <limits>
+#include <memory>
+#include <stdexcept>
+
+#include "services/sqlite_connection_helpers.h"
 
 namespace sqlite_export_service_internal {
 
@@ -86,16 +87,6 @@ sqlite3_int64 LastInsertRowId(const SqliteDatabaseHandle& db_handle) {
   return sqlite3_last_insert_rowid(db_handle.get());
 }
 
-std::string SerializeLocalLanguages(
-    const std::vector<std::string>& local_languages) {
-  boost::json::array array;
-  array.reserve(local_languages.size());
-  for (const auto& language : local_languages) {
-    array.emplace_back(language);
-  }
-  return boost::json::serialize(array);
-}
-
 std::string SerializeVector(const std::vector<std::string>& str_vec) {
   boost::json::array array(str_vec.size());
   for (const auto& s : str_vec) {
@@ -105,4 +96,3 @@ std::string SerializeVector(const std::vector<std::string>& str_vec) {
 }
 
 }  // namespace sqlite_export_service_internal
-

tooling/pipeline/src/services/sqlite/initialize.cc

@@ -11,6 +11,19 @@
 #include "services/sqlite_export_service.h"
 #include "services/sqlite_export_service_helpers.h"
 
+std::filesystem::path SqliteExportService::BuildDatabasePath() const {
+  std::filesystem::path base_filename("biergarten_seed_" + run_timestamp_utc_ +
+                                      ".sqlite");
+  std::filesystem::path candidate = output_path_ / base_filename;
+
+  for (int suffix = 1; std::filesystem::exists(candidate); ++suffix) {
+    candidate = output_path_ /
+                std::filesystem::path("biergarten_seed_" + run_timestamp_utc_ +
+                                      "-" + std::to_string(suffix) + ".sqlite");
+  }
+
+  return candidate;
+}
 
 void SqliteExportService::InitializeSchema() const {
   sqlite_export_service_internal::ExecSql(
@@ -46,7 +59,6 @@ void SqliteExportService::RollbackAndCloseNoThrow() noexcept {
   location_cache_.clear();
 }
 
-
 void SqliteExportService::Initialize() {
   if (db_handle_ != nullptr) {
     throw std::runtime_error("SQLite export service is already initialized");

tooling/pipeline/src/services/sqlite/process_record.cc

@@ -3,6 +3,8 @@
  * @brief SqliteExportService::ProcessRecord() implementation.
  */
 
+#include <iomanip>
+#include <sstream>
 #include <stdexcept>
 #include <string>
 

tooling/pipeline/src/services/sqlite/sqlite_export_service.cc

@@ -7,11 +7,12 @@
 
 #include <memory>
 
-SqliteExportService::SqliteExportService()
-    : date_time_provider_(std::make_unique<SystemDateTimeProvider>()) {}
+SqliteExportService::SqliteExportService(const ApplicationOptions& options)
+    : date_time_provider_(std::make_unique<SystemDateTimeProvider>()),
+      output_path_(options.pipeline.output_path) {}
 
 SqliteExportService::~SqliteExportService() {
   if (db_handle_ != nullptr) {
     RollbackAndCloseNoThrow();
   }
-}
+}