Add mock enrichment process

docs/pipeline/diagrams/planned/class.puml

@@ -1,4 +1,4 @@
-@startuml class_diagram
+@startuml
 
 ' ==========================================
 ' CONFIGURATION & STYLING
@@ -8,8 +8,6 @@ skinparam classAttributeFontSize 9
 skinparam defaultFontSize 25
 skinparam titleFontSize 30
 
-title Biergarten Data Pipeline — Class Diagram
-
 package "Domain: Models" {
 
   class Location {
@@ -143,7 +141,7 @@ package "Domain: Models" {
 
   LocationContext *-- Completeness
 }
-
+@startuml
 package "Domain: Application Configuration" {
   class SamplingOptions {
     + temperature: float = 1.0F
@@ -169,10 +167,12 @@ package "Domain: Application Configuration" {
     + pipeline: PipelineOptions
   }
 
+  ' --- Domain Model Relationships ---
   ApplicationOptions *-- GeneratorOptions
   ApplicationOptions *-- PipelineOptions
   GeneratorOptions o-- SamplingOptions
 }
+@endum
 
 package "Domain: Policy" {
 
@@ -297,6 +297,7 @@ package "Infrastructure: Logging" {
     - ToString(phase) : std::string
   }
 
+  ' --- Logging Relationships ---
   LogEntry       *--  LogLevel
   LogEntry       *--  PipelinePhase
   PipelineLogger ..>  LogEntry       : emits
@@ -362,22 +363,6 @@ package "Infrastructure: Enrichment" {
 
 }
 
-package "Infrastructure: Prompting" {
-
-  interface IPromptDirectory <<interface>> {
-    + Load(key : std::string_view) : std::string
-  }
-
-  class PromptDirectory {
-    - prompt_dir_ : std::filesystem::path
-    - cache_ : std::unordered_map<std::string, std::string>
-    + PromptDirectory(prompt_dir : const std::filesystem::path&)
-    + Load(key : std::string_view) : std::string
-  }
-
-  IPromptDirectory <|.. PromptDirectory
-}
-
 package "Infrastructure: Data Generation" {
 
   interface DataGenerator <<interface>> {
@@ -401,7 +386,6 @@ package "Infrastructure: Data Generation" {
     - model_ : ModelHandle
     - context_ : ContextHandle
     - prompt_formatter_ : std::unique_ptr<PromptFormatter>
-    - prompt_directory_ : std::unique_ptr<IPromptDirectory>
     - rng_ : std::mt19937
     + GenerateBrewery(...) : BreweryResult
     + GenerateBeer(...) : BeerResult
@@ -475,6 +459,8 @@ package "Infrastructure: Data Export" {
 
 }
 
+
+
 class BiergartenPipelineOrchestrator {
   - preloader_ : std::unique_ptr<DataPreloader>
   - enrichment_service_ : std::unique_ptr<EnrichmentService>
@@ -545,7 +531,6 @@ DateTimeProvider               <|.. SystemDateTimeProvider
 WikipediaService               *--  WebClient
 WikipediaService               ..>  ContextStrategy
 LlamaGenerator                 *--  PromptFormatter
-LlamaGenerator                 *--  IPromptDirectory
 LlamaGenerator                 ..>  GeneratorOptions
 SqliteExportService            *--  DateTimeProvider
 

tooling/pipeline/CMakeLists.txt

@@ -138,8 +138,7 @@ FetchContent_MakeAvailable(cpp-httplib)
 
 # 5. Executable & Sources
 add_executable(${PROJECT_NAME}
-        includes/services/enrichment/mock_enrichment.h
+        includes/services/enrichment/mock_enrichment.h)
-        includes/json_handling/pretty_print.h)
 
 # --- Entry point ---
 target_sources(${PROJECT_NAME} PRIVATE
@@ -156,13 +155,13 @@ target_sources(${PROJECT_NAME} PRIVATE
         src/application_options/parse_arguments.cc
 )
 
-# --- biergarten_pipeline_orchestrator ---
+# --- biergarten_data_generator ---
 target_sources(${PROJECT_NAME} PRIVATE
-        src/biergarten_pipeline_orchestrator/log_results.cc
+        src/biergarten_data_generator/log_results.cc
-        src/biergarten_pipeline_orchestrator/biergarten_pipeline_orchestrator.cc
+        src/biergarten_data_generator/biergarten_data_generator.cc
-        src/biergarten_pipeline_orchestrator/generate_breweries.cc
+        src/biergarten_data_generator/generate_breweries.cc
-        src/biergarten_pipeline_orchestrator/run.cc
+        src/biergarten_data_generator/run.cc
-        src/biergarten_pipeline_orchestrator/query_cities_with_countries.cc
+        src/biergarten_data_generator/query_cities_with_countries.cc
 )
 
 # --- web_client ---
@@ -211,12 +210,6 @@ target_sources(${PROJECT_NAME} PRIVATE
         src/services/sqlite/helpers/sqlite_statement_helpers.cc
 )
 
-# --- services: logging ---
-target_sources(${PROJECT_NAME} PRIVATE
-	"src/services/logging/log_producer.cc"
-        src/services/logging/log_dispatcher.cc
-)
-
 # --- services (top-level) ---
 target_sources(${PROJECT_NAME} PRIVATE
         src/services/prompt_directory.cc

tooling/pipeline/includes/biergarten_data_generator.h

@@ -1,12 +1,9 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_PIPELINE_ORCHESTRATOR_H_
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_PIPELINE_ORCHESTRATOR_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
 
 /**
- * @file biergarten_pipeline_orchestrator.h
+ * @file biergarten_data_generator.h
- * @brief Orchestration for end-to-end brewery data generation pipeline.
+ * @brief Core orchestration class for pipeline data generation.
- *
- * Intent: Coordinates location loading, enrichment, and generation phases
- * to produce a complete dataset. Coordinates dependencies via composition root.
  */
 
 #include <memory>
@@ -18,27 +15,22 @@
 #include "services/database/export_service.h"
 #include "services/enrichment/enrichment_service.h"
 
-#include "services/logging/logger.h"
-
 /**
  * @brief Main data generator class for the Biergarten pipeline.
  *
  * This class encapsulates the core logic for generating brewery data.
  * It handles location loading, city enrichment, and brewery generation.
  */
-class BiergartenPipelineOrchestrator {
+class BiergartenDataGenerator {
  public:
   /**
-   * @brief Constructs the orchestrator with injected pipeline dependencies.
+   * @brief Construct a BiergartenDataGenerator with injected dependencies.
    *
-   * @param context_service Provides regional context for locations.
+   * @param context_service Context provider for sampled locations.
-   * @param generator Implementation (Llama or Mock) for brewery/user generation.
+   * @param generator Brewery and user data generator.
-   * @param exporter Database backend for persisting generated records.
+   * @param exporter Storage backend for generated brewery data.
-   * @param application_options CLI configuration and paths.
    */
-  BiergartenPipelineOrchestrator(
+  BiergartenDataGenerator(std::unique_ptr<IEnrichmentService> context_service,
-      std::shared_ptr<ILogger> logger,
-      std::unique_ptr<IEnrichmentService> context_service,
                           std::unique_ptr<DataGenerator> generator,
                           std::unique_ptr<IExportService> exporter,
                           const ApplicationOptions& application_options);
@@ -56,9 +48,6 @@ class BiergartenPipelineOrchestrator {
   bool Run();
 
  private:
-  /// @brief Logger instance for emitting pipeline messages.
-  std::shared_ptr<ILogger> logger_;
-
   /// @brief Owning context provider dependency.
   std::unique_ptr<IEnrichmentService> context_service_;
 
@@ -68,8 +57,7 @@ class BiergartenPipelineOrchestrator {
   /// @brief Storage backend for generated brewery records.
   std::unique_ptr<IExportService> exporter_;
 
-  /// @brief CLI configuration: paths, model settings, generation parameters.
+  const ApplicationOptions application_options_;
-  ApplicationOptions application_options_;
 
   /**
    * @brief Load locations from JSON and sample cities.
@@ -93,5 +81,4 @@ class BiergartenPipelineOrchestrator {
   /// @brief Stores generated brewery data.
   std::vector<GeneratedBrewery> generated_breweries_;
 };
-
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_PIPELINE_ORCHESTRATOR_H_

tooling/pipeline/includes/concurrency/bounded_channel.h

@@ -1,73 +0,0 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_CONCURRENCY_BOUNDED_CHANNEL_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_CONCURRENCY_BOUNDED_CHANNEL_H_
-
-#include <condition_variable>
-#include <cstddef>
-#include <mutex>
-#include <optional>
-#include <queue>
-
-/**
- * @file concurrency/bounded_channel.h
- * @brief Thread-safe, bounded multi-producer/multi-consumer synchronous channel.
- *
- * Intent: Enables asynchronous inter-thread communication with backpressure.
- * Models a synchronous channel where producers/consumers block on capacity limits.
- */
-
-/**
- * @class BoundedChannel
- * @brief MPMC channel with fixed capacity and blocking semantics.
- *
- * Producers block when buffer is full; consumers block when empty.
- * Close() unblocks all waiters and signals channel exhaustion.
- */
-template <typename T>
-class BoundedChannel {
-  // -------------------------------------------------------------------------
-  // Internal state — all access must be guarded by mutex_.
-  // -------------------------------------------------------------------------
-
-  std::queue<T> queue_;
-
-  std::mutex mutex_;
-
-  std::condition_variable not_full_;
-
-  std::condition_variable not_empty_;
-
-  std::size_t capacity_;
-
-  bool closed_ = false;
-
- public:
-  /**
-   * @brief Construct a bounded channel with the given capacity.
-   * @param capacity Maximum number of items the channel may hold.
-   */
-  explicit BoundedChannel(std::size_t capacity) : capacity_(capacity) {}
-
-  /**
-   * @brief Send an item into the channel. Blocks when the channel is full.
-   * @param item Move-only item to enqueue.
-   */
-  void Send(T item);
-
-  /**
-   * @brief Receive an item from the channel. Blocks when the channel is
-   * empty.
-   * @return std::optional<T> containing the item, or std::nullopt when the
-   * channel is closed and drained.
-   */
-  std::optional<T> Receive();
-
-  /**
-   * @brief Close the channel and unblock all waiting threads. Idempotent.
-   */
-  void Close();
-};
-
-// Include the template implementation
-#include "bounded_channel.tcc"
-
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_CONCURRENCY_BOUNDED_CHANNEL_H_

tooling/pipeline/includes/concurrency/bounded_channel.tcc

@@ -1,57 +0,0 @@
-#include "bounded_channel.h"
-
-template <typename T>
-void BoundedChannel<T>::Send(T item) {
-  // Acquire exclusive ownership of the mutex; released automatically on scope exit.
-  std::unique_lock lock(mutex_);
-
-  // Block until there is space in the queue or the channel has been closed.
-  // The predicate guards against spurious wakeups.
-  not_full_.wait(lock, [&] { return queue_.size() < capacity_ || closed_; });
-
-  // If the channel was closed while waiting, discard the item and return.
-  if (closed_) return;
-
-  // Move the item into the queue to avoid an unnecessary copy.
-  queue_.push(std::move(item));
-
-  // Wake one blocked Receive() call to signal that data is now available.
-  not_empty_.notify_one();
-}
-
-template <typename T>
-std::optional<T> BoundedChannel<T>::Receive() {
-  // Acquire exclusive ownership of the mutex.
-  std::unique_lock lock(mutex_);
-
-  // Block until the queue is non-empty or the channel has been closed.
-  // The predicate guards against spurious wakeups.
-  not_empty_.wait(lock, [&] { return !queue_.empty() || closed_; });
-
-  // If woken due to closure and no items remain, signal exhaustion via nullopt.
-  if (queue_.empty()) return std::nullopt;
-
-  // Move the front item out of the queue to avoid an unnecessary copy.
-  T item = std::move(queue_.front());
-  queue_.pop();
-
-  // Wake one blocked Send() call to signal that a slot has opened.
-  not_full_.notify_one();
-
-  return item;
-}
-
-template <typename T>
-void BoundedChannel<T>::Close() {
-  // Acquire exclusive ownership of the mutex to ensure visibility of the flag.
-  std::unique_lock lock(mutex_);
-
-  // Mark the channel as closed; subsequent Send() calls will be dropped.
-  closed_ = true;
-
-  // Wake all blocked Send() callers so they can observe the closed flag and exit.
-  not_full_.notify_all();
-
-  // Wake all blocked Receive() callers so they can drain remaining items or return nullopt.
-  not_empty_.notify_all();
-}

tooling/pipeline/includes/data_generation/llama_generator.h

@@ -18,7 +18,6 @@
 #include "data_generation/data_generator.h"
 #include "data_generation/prompt_formatting/prompt_formatter.h"
 #include "data_model/models.h"
-#include "services/logging/logger.h"
 
 struct llama_model;
 struct llama_context;
@@ -39,7 +38,6 @@ class LlamaGenerator final : public DataGenerator {
    */
   LlamaGenerator(const ApplicationOptions& options,
                  const std::string& model_path,
-                 std::shared_ptr<ILogger> logger,
                  std::unique_ptr<IPromptFormatter> prompt_formatter,
                  std::unique_ptr<IPromptDirectory> prompt_directory);
 
@@ -132,7 +130,6 @@ class LlamaGenerator final : public DataGenerator {
   std::mt19937 rng_;
   uint32_t n_ctx_ = kDefaultContextSize;
   int n_gpu_layers_ = 0;
-  std::shared_ptr<ILogger> logger_;
   std::unique_ptr<IPromptFormatter> prompt_formatter_;
   std::unique_ptr<IPromptDirectory> prompt_directory_;
 };

tooling/pipeline/includes/data_generation/prompt_formatting/gemma4_jinja_prompt_formatter.h

@@ -1,11 +1,6 @@
 #ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_GEMMA4_JINJA_PROMPT_FORMATTER_H_
 #define BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_GEMMA4_JINJA_PROMPT_FORMATTER_H_
 
-/**
- * @file data_generation/prompt_formatting/gemma4_jinja_prompt_formatter.h
- * @brief Prompt formatter for Google Gemma 4 model using Jinja2 template syntax.
- */
-
 #include <string>
 #include <string_view>
 

tooling/pipeline/includes/data_generation/prompt_formatting/prompt_formatter.h

@@ -1,11 +1,6 @@
 #ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_PROMPT_FORMATTER_H_
 #define BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_PROMPT_FORMATTER_H_
 
-/**
- * @file data_generation/prompt_formatting/prompt_formatter.h
- * @brief Abstract interface for formatting system and user prompts.
- */
-
 #include <string>
 #include <string_view>
 

tooling/pipeline/includes/data_model/models.h

@@ -10,14 +10,11 @@
 #include <boost/program_options.hpp>
 #include <cstdint>
 #include <filesystem>
-#include <memory>
 #include <optional>
 #include <string>
 #include <string_view>
 #include <vector>
 
-class ILogger;
-
 namespace prog_opts = boost::program_options;
 
 // ============================================================================
@@ -139,7 +136,6 @@ struct ApplicationOptions {
 // Function Declarations
 // ============================================================================
 
-std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv,
+std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv);
-                                                std::shared_ptr<ILogger> logger = nullptr);
 
 #endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_MODELS_H_

tooling/pipeline/includes/json_handling/json_loader.h

@@ -7,19 +7,16 @@
  */
 
 #include <filesystem>
-#include <memory>
 #include <vector>
 
 #include "data_model/models.h"
-#include "services/logging/logger.h"
 
 /// @brief Loads curated world locations from a JSON file into memory.
 class JsonLoader {
  public:
   /// @brief Parses a JSON array file and returns all location records.
   static std::vector<Location> LoadLocations(
-      const std::filesystem::path& filepath,
+      const std::filesystem::path& filepath);
-      std::shared_ptr<ILogger> logger = nullptr);
 };
 
 #endif  // BIERGARTEN_PIPELINE_INCLUDES_JSON_HANDLING_JSON_LOADER_H_

tooling/pipeline/includes/json_handling/pretty_print.h

@@ -1,109 +0,0 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_JSON_HANDLING_PRETTY_PRINT_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_JSON_HANDLING_PRETTY_PRINT_H_
-
-/**
- * @file json_handling/pretty_print.h
- * @brief Pretty-printing utilities for JSON values.
- *
- * Provides formatting capability for boost::json::value with indentation and
- * readable output. Adapted from Boost JSON library examples.
- */
-
-#include <boost/json.hpp>
-#include <ostream>
-#include <string>
-
-/**
- * @brief Pretty-prints a JSON value to an output stream with indentation.
- *
- * Recursively formats JSON objects and arrays with consistent 4-space
- * indentation. Adapted from:
- * https://raw.githubusercontent.com/boostorg/json/refs/heads/develop/example/pretty.cpp
- *
- * @param outstream Output stream to write formatted JSON.
- * @param json_val JSON value to format.
- * @param indent Optional indentation string (managed internally on first call).
- */
-inline void PrettyPrint(std::ostream& outstream,
-                        boost::json::value const& json_val,
-                        std::string* indent = nullptr) {
-  std::string str;
-  if (indent == nullptr) {
-    indent = &str;
-  }
-  switch (json_val.kind()) {
-    case boost::json::kind::object: {
-      outstream << "{\n";
-      indent->append(4, ' ');
-      auto const& obj = json_val.get_object();
-      if (!obj.empty()) {
-        const auto* iter = obj.begin();
-        for (;;) {
-          outstream << *indent << boost::json::serialize(iter->key()) << " : ";
-          PrettyPrint(outstream, iter->value(), indent);
-          iter = std::next(iter);
-          if (iter == obj.end()) {
-            break;
-          }
-
-          outstream << ",\n";
-        }
-      }
-      outstream << "\n";
-      indent->resize(indent->size() - 4);
-      outstream << *indent << "}";
-      break;
-    }
-
-    case boost::json::kind::array: {
-      outstream << "[\n";
-      indent->append(4, ' ');
-      auto const& arr = json_val.get_array();
-      if (!arr.empty()) {
-        const auto* iter = arr.begin();
-        for (;;) {
-          outstream << *indent;
-          PrettyPrint(outstream, *iter, indent);
-          iter = std::next(iter);
-          if (iter == arr.end()) {
-            break;
-          }
-          outstream << ",\n";
-        }
-      }
-      outstream << "\n";
-      indent->resize(indent->size() - 4);
-      outstream << *indent << "]";
-      break;
-    }
-
-    case boost::json::kind::string: {
-      outstream << serialize(json_val.get_string());
-      break;
-    }
-
-    case boost::json::kind::uint64:
-    case boost::json::kind::int64:
-    case boost::json::kind::double_:
-      outstream << json_val;
-      break;
-
-    case boost::json::kind::bool_:
-      if (json_val.get_bool()) {
-        outstream << "true";
-      } else {
-        outstream << "false";
-      }
-      break;
-
-    case boost::json::kind::null:
-      outstream << "null";
-      break;
-  }
-
-  if (indent->empty()) {
-    outstream << "\n";
-  }
-}
-
-#endif

tooling/pipeline/includes/services/database/export_service.h

@@ -2,7 +2,7 @@
 #define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_EXPORT_SERVICE_H_
 
 /**
- * @file services/database/export_service.h
+ * @file services/export_service.h
  * @brief Abstraction for persisting generated brewery data.
  */
 

tooling/pipeline/includes/services/database/sqlite_connection_helpers.h

@@ -2,7 +2,7 @@
 #define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_CONNECTION_HELPERS_H_
 
 /**
- * @file services/database/sqlite_connection_helpers.h
+ * @file services/sqlite_connection_helpers.h
  * @brief Declarations for connection-level SQLite helper functions.
  */
 

tooling/pipeline/includes/services/database/sqlite_export_service.h

@@ -2,7 +2,7 @@
 #define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_EXPORT_SERVICE_H_
 
 /**
- * @file services/database/sqlite_export_service.h
+ * @file services/sqlite_export_service.h
  * @brief SQLite-backed export service for generated brewery data.
  */
 

tooling/pipeline/includes/services/database/sqlite_statement_helpers.h

@@ -2,7 +2,7 @@
 #define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_STATEMENT_HELPERS_H_
 
 /**
- * @file services/database/sqlite_statement_helpers.h
+ * @file services/sqlite_statement_helpers.h
  * @brief Declarations for statement-level SQLite helper functions and
  * constants.
  */

tooling/pipeline/includes/services/datetime/date_time_provider.h

@@ -2,7 +2,7 @@
 #define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATETIME_DATE_TIME_PROVIDER_H_
 
 /**
- * @file services/datetime/date_time_provider.h
+ * @file services/date_time_provider.h
  * @brief Abstraction for UTC timestamp generation.
  */
 

tooling/pipeline/includes/services/datetime/timer.h

@@ -4,7 +4,7 @@
 #include <chrono>
 
 /**
- * @file services/datetime/timer.h
+ * @file services/timer.h
  * @brief Simple timer utility for measuring elapsed time.
  */
 class Timer {

tooling/pipeline/includes/services/enrichment/enrichment_service.h

@@ -2,7 +2,7 @@
 #define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_ENRICHMENT_SERVICE_H_
 
 /**
- * @file services/enrichment/enrichment_service.h
+ * @file services/enrichment_service.h
  * @brief Abstraction for resolving contextual enrichment for a location.
  */
 

tooling/pipeline/includes/services/enrichment/mock_enrichment.h

@@ -1,29 +1,15 @@
+//
+// Created by aaronpo on 13/05/2026.
+//
+
 #ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_MOCK_ENRICHMENT_H_
 #define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_MOCK_ENRICHMENT_H_
-
-/**
- * @file services/enrichment/mock_enrichment.h
- * @brief Mock implementation of enrichment service for testing.
- */
-
 #include <string>
 
 #include "enrichment_service.h"
 
-/**
- * @brief Mock implementation of enrichment service for testing and prototyping.
- *
- * Returns empty context without performing actual web queries or enrichment.
- * Useful for unit tests and development scenarios.
- */
 class MockEnrichmentService final : public IEnrichmentService {
  public:
-  /**
-   * @brief Returns empty location context.
-   *
-   * @param loc Unused location parameter.
-   * @return Empty string (no enrichment performed).
-   */
   std::string GetLocationContext(const Location& /*loc*/) override {
     return {};
   }

tooling/pipeline/includes/services/enrichment/wikipedia_service.h

@@ -2,7 +2,7 @@
 #define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_WIKIPEDIA_SERVICE_H_
 
 /**
- * @file services/enrichment/wikipedia_service.h
+ * @file services/wikipedia_service.h
  * @brief Wikipedia summary retrieval service with in-memory caching.
  */
 
@@ -12,15 +12,13 @@
 #include <unordered_map>
 
 #include "enrichment_service.h"
-#include "services/logging/logger.h"
 #include "web_client/web_client.h"
 
 /// @brief Provides Wikipedia summary lookups backed by cached raw extracts.
 class WikipediaEnrichmentService final : public IEnrichmentService {
  public:
   /// @brief Creates a new Wikipedia service with the provided web client.
-  explicit WikipediaEnrichmentService(std::unique_ptr<WebClient> client,
+  explicit WikipediaEnrichmentService(std::unique_ptr<WebClient> client);
-                                      std::shared_ptr<ILogger> logger);
 
   /// @brief Returns the Wikipedia-derived context for a location.
   [[nodiscard]] std::string GetLocationContext(const Location& loc) override;
@@ -28,7 +26,6 @@ class WikipediaEnrichmentService final : public IEnrichmentService {
  private:
   std::string FetchExtract(std::string_view query);
   std::unique_ptr<WebClient> client_;
-  std::shared_ptr<ILogger> logger_;
   /// @brief Canonical cache for raw Wikipedia query extracts.
   std::unordered_map<std::string, std::string> extract_cache_;
 };

tooling/pipeline/includes/services/logging/log_dispatcher.h

@@ -1,53 +0,0 @@
-/**
- * @file services/logging/log_dispatcher.h
- * @brief Dedicated log dispatcher for asynchronous pipeline logging.
- *
- * The dispatcher drains LogEntry values from a bounded channel and forwards
- * them to spdlog on a dedicated thread.
- */
-
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_DISPATCHER_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_DISPATCHER_H_
-
-#include <spdlog/spdlog.h>
-
-#include "concurrency/bounded_channel.h"
-#include "services/logging/log_entry.h"
-
-/**
- * @class LogDispatcher
- * @brief Consumes log entries from a channel and forwards them to spdlog.
- *
- * Non-copyable and non-movable. Intended to run on its own dedicated thread
- * and exit once the channel has been closed and drained.
- */
-class LogDispatcher {
- public:
-  /**
-   * @brief Construct a log dispatcher.
-   *
-   * @param channel Reference to the bounded channel used for log retrieval.
-   */
-  explicit LogDispatcher(BoundedChannel<LogEntry>& channel);
-
-  LogDispatcher(const LogDispatcher&) = delete;
-  LogDispatcher& operator=(const LogDispatcher&) = delete;
-  LogDispatcher(LogDispatcher&&) = delete;
-  LogDispatcher& operator=(LogDispatcher&&) = delete;
-  ~LogDispatcher() = default;
-
-  /**
-   * @brief Drain the channel and forward entries to spdlog.
-   *
-   * Intended to be called once on a dedicated thread. The loop returns after
-   * the channel has been closed and all queued entries have been processed.
-   */
-  void Run();
-
- private:
-  BoundedChannel<LogEntry>& channel_;
-
-  static spdlog::level::level_enum ToSpdlogLevel(LogLevel level);
-};
-
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_DISPATCHER_H_

tooling/pipeline/includes/services/logging/log_entry.h

@@ -1,69 +0,0 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_ENTRY_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_ENTRY_H_
-
-/**
- * @file services/logging/log_entry.h
- * @brief Structured log record shared by the pipeline logging infra.
- *
- * LogEntry is a lightweight value type that can be passed safely between the
- * logging producer and dispatcher through BoundedChannel<LogEntry>.
- */
-
-
-#include <chrono>
-#include <thread>
-#include <string>
-
-/**
- * @enum LogLevel
- * @brief Severity levels supported by the logging infra.
- */
-enum class LogLevel {
-  Debug,  ///< Development/debugging information.
-  Info,   ///< General informational messages.
-  Warn,   ///< Warning conditions.
-  Error,  ///< Error conditions.
-};
-
-/**
- * @enum PipelinePhase
- * @brief Pipeline execution phases used to tag log records.
- *
- * The phase tag makes it easier to correlate log output with the part of the
- * pipeline that emitted it.
- */
-enum class PipelinePhase {
-  Startup,                   ///< Initialization and validation.
-  UserGeneration,            ///< User profile generation.
-  BreweryAndBeerGeneration,  ///< Brewery and beer data generation.
-  CheckinGeneration,         ///< Checkin (visit) record generation.
-  RatingGeneration,          ///< Rating and review generation.
-  FollowGeneration,          ///< Follow relationship generation.
-  Teardown,                  ///< Finalization and cleanup.
-};
-
-/**
- * @struct LogEntry
- * @brief Single structured log event.
- *
- * All fields are value types, which keeps transfer across the bounded channel
- * simple and avoids shared ownership.
- */
-struct LogEntry {
-  /// @brief Timestamp when the entry was created.
-  std::chrono::system_clock::time_point timestamp =
-      std::chrono::system_clock::now();
-
-
-  /// @brief Severity level of this entry.
-  LogLevel level;
-
-  /// @brief Pipeline phase associated with the entry.
-  PipelinePhase phase;
-
-  /// @brief Log message text.
-  std::string message;
-
-};
-
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_ENTRY_H_

tooling/pipeline/includes/services/logging/log_producer.h

@@ -1,52 +0,0 @@
-/**
- * @file services/logging/log_producer.h
- * @brief Channel-backed log producer for asynchronous pipeline logging.
- *
- * The producer captures log records from application code and forwards them to
- * a bounded channel for later processing by the dispatcher.
- */
-
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_PRODUCER_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_PRODUCER_H_
-
-#include <string_view>
-
-#include "concurrency/bounded_channel.h"
-#include "services/logging/log_entry.h"
-#include "services/logging/logger.h"
-
-/**
- * @class LogProducer
- * @brief ILogger implementation that forwards entries to a bounded channel.
- *
- * Non-copyable and non-movable. The channel reference is non-owning and must
- * remain valid for the lifetime of the producer.
- */
-class LogProducer final : public ILogger {
- public:
-  /**
-   * @brief Construct a channel-backed producer.
-   *
-   * @param channel Reference to the bounded channel used for log transfer.
-   */
-  explicit LogProducer(BoundedChannel<LogEntry>& channel);
-
-  LogProducer(const LogProducer&) = delete;
-  LogProducer& operator=(const LogProducer&) = delete;
-  LogProducer(LogProducer&&) = delete;
-  LogProducer& operator=(LogProducer&&) = delete;
-
-  ~LogProducer() override = default;
-
-  /**
-   * @brief Queue a log message for asynchronous processing.
-   *
-   * Blocks while the channel applies backpressure.
-   */
-  void Log(LogEntry const& entry) override;
-
- private:
-  BoundedChannel<LogEntry>& channel_;
-};
-
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_PRODUCER_H_

tooling/pipeline/includes/services/logging/logger.h

@@ -1,44 +0,0 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_
-
-/**
- * @file services/logging/logger.h
- * @brief Abstract logging interface used by pipeline components.
- *
- * The interface keeps application code independent from the concrete logging
- * transport, buffering, and formatting implementation.
- */
-
-
-#include <optional>
-#include <string>
-#include <string_view>
-
-#include "services/logging/log_entry.h"
-
-/**
- * @class ILogger
- * @brief Minimal interface for submitting structured log messages.
- *
- * Implementations are non-copyable and non-movable. They are typically owned
- * by the composition root and injected into services that emit diagnostics.
- */
-class ILogger {
- public:
-  ILogger() = default;
-  ILogger(const ILogger&) = delete;
-  ILogger& operator=(const ILogger&) = delete;
-  ILogger(ILogger&&) = delete;
-  ILogger& operator=(ILogger&&) = delete;
-  virtual ~ILogger() = default;
-
-  /**
-   * @brief Submit a log message to the logging subsystem.
-   *
-   * @param entry Structured log record containing message and metadata.
-   *
-   */
-  virtual void Log(const LogEntry& entry) = 0;
-};
-
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_

tooling/pipeline/includes/services/prompting/prompt_directory.h

@@ -2,7 +2,7 @@
 #define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_PROMPTING_PROMPT_DIRECTORY_H_
 
 /**
- * @file services/prompting/prompt_directory.h
+ * @file services/prompt_directory.h
  * @brief Interface and filesystem-backed implementation for named prompt
  * loading.
  *
@@ -12,14 +12,11 @@
  */
 
 #include <filesystem>
-#include <memory>
 #include <stdexcept>
 #include <string>
 #include <string_view>
 #include <unordered_map>
 
-#include "services/logging/logger.h"
-
 /**
  * @brief Interface for loading named prompt files.
  */
@@ -59,8 +56,6 @@ class PromptDirectory final : public IPromptDirectory {
    *         directory.
    */
   explicit PromptDirectory(const std::filesystem::path& prompt_dir);
-  PromptDirectory(const std::filesystem::path& prompt_dir,
-                  std::shared_ptr<ILogger> logger);
 
   /**
    * @brief Loads the prompt for @p key, caching the result.
@@ -75,7 +70,6 @@ class PromptDirectory final : public IPromptDirectory {
 
  private:
   std::filesystem::path prompt_dir_;
-  std::shared_ptr<ILogger> logger_;
   std::unordered_map<std::string, std::string> cache_;
 };
 

tooling/pipeline/includes/web_client/http_web_client.h

@@ -1,18 +1,16 @@
 /**
- * @file web_client/http_web_client.h
+* @file web_client/http_web_client.h
- * @brief cpp-httplib implementation of the WebClient interface.
+* @brief cpp-httplib implementation of the WebClient interface.
- */
+*/
 
 #ifndef BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_HTTP_WEB_CLIENT_H_
 #define BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_HTTP_WEB_CLIENT_H_
 
-#include <memory>
-#include <string>
-#include <utility>
 
-#include "services/logging/logger.h"
 #include "web_client/web_client.h"
 
+#include <string>
+
 /**
  * @brief WebClient implementation backed by cpp-httplib.
  *
@@ -25,18 +23,8 @@
  * bound to a single origin at construction time.
  */
 class HttpWebClient final : public WebClient {
- public:
+public:
-  /**
+  HttpWebClient() = default;
-   * @brief Construct an HTTP web client with a logger.
-   *
-   * @param logger Logger instance for diagnostics.
-   */
-  explicit HttpWebClient(std::shared_ptr<ILogger> logger)
-      : logger_(std::move(logger)) {}
-
-  /**
-   * @brief Destructor.
-   */
   ~HttpWebClient() override = default;
 
   /**
@@ -55,9 +43,7 @@ class HttpWebClient final : public WebClient {
    * @return Percent-encoded string safe for use in a URL.
    */
   std::string EncodeURL(const std::string& value) override;
-
- private:
-  std::shared_ptr<ILogger> logger_;
 };
 
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_HTTP_WEB_CLIENT_H_
+
+#endif

tooling/pipeline/src/application_options/parse_arguments.cc

@@ -1,14 +1,12 @@
-#include <chrono>
+#include <spdlog/spdlog.h>
-#include <iostream>
+
 #include <optional>
 #include <sstream>
 #include <string>
 
 #include "data_model/models.h"
-#include "services/logging/logger.h"
 
-std::optional<ApplicationOptions> ParseArguments(
+std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv) {
-    const int argc, char** argv, std::shared_ptr<ILogger> logger) {
   prog_opts::options_description desc("Pipeline Options");
   auto opt = desc.add_options();
 
@@ -63,22 +61,10 @@ std::optional<ApplicationOptions> ParseArguments(
 
   // No flags provided — treat as a help request rather than an error.
   if (argc == 1) {
-    const std::string title = "Biergarten Pipeline";
+    spdlog::info("Biergarten Pipeline");
-    const std::string usage = ([&] {
     std::stringstream usage_stream;
     usage_stream << "\nUsage: biergarten-pipeline [options]\n\n" << desc;
-      return usage_stream.str();
+    spdlog::info(usage_stream.str());
-    })();
-    if (logger) {
-      logger->Log({.level = LogLevel::Info,
-                   .phase = PipelinePhase::Startup,
-                   .message = title});
-      logger->Log({.level = LogLevel::Info,
-                   .phase = PipelinePhase::Startup,
-                   .message = usage});
-    } else {
-      std::cout << title << std::endl << usage << std::endl;
-    }
     return std::nullopt;
   }
 
@@ -90,13 +76,7 @@ std::optional<ApplicationOptions> ParseArguments(
     if (var_map.contains("help")) {
       std::stringstream help_stream;
       help_stream << "\n" << desc;
-      if (logger) {
+      spdlog::info(help_stream.str());
-        logger->Log({.level = LogLevel::Info,
-                     .phase = PipelinePhase::Startup,
-                     .message = help_stream.str()});
-      } else {
-        std::cout << help_stream.str() << std::endl;
-      }
       return std::nullopt;
     }
 
@@ -105,7 +85,8 @@ std::optional<ApplicationOptions> ParseArguments(
     options.pipeline.output_path = var_map["output"].as<std::string>();
     options.pipeline.log_path = var_map["log-path"].as<std::string>();
     options.pipeline.prompt_dir = var_map["prompt-dir"].as<std::string>();
-    options.pipeline.location_count = var_map["location-count"].as<uint32_t>();
+    options.pipeline.location_count =
+      var_map["location-count"].as<uint32_t>();
 
     const bool use_mocked = var_map["mocked"].as<bool>();
     const std::string model_path = var_map["model"].as<std::string>();
@@ -113,43 +94,23 @@ std::optional<ApplicationOptions> ParseArguments(
 
     // Enforce mutual exclusivity before any further configuration is applied.
     if (use_mocked && !model_path.empty()) {
-      const std::string msg =
+      spdlog::error(
-          "Invalid arguments: --mocked and --model are mutually exclusive";
+          "Invalid arguments: --mocked and --model are mutually exclusive");
-      if (logger) {
-        logger->Log({.level = LogLevel::Error,
-                     .phase = PipelinePhase::Startup,
-                     .message = msg});
-      } else {
-        std::cerr << msg << std::endl;
-      }
       return std::nullopt;
     }
 
     if (!use_mocked && model_path.empty()) {
-      const std::string msg =
+      spdlog::error(
-          "Invalid arguments: either --mocked or --model must be specified";
+          "Invalid arguments: either --mocked or --model must be specified");
-      if (logger) {
-        logger->Log({.level = LogLevel::Error,
-                     .phase = PipelinePhase::Startup,
-                     .message = msg});
-      } else {
-        std::cerr << msg << std::endl;
-      }
       return std::nullopt;
     }
 
     // Prompt directory is only meaningful for live inference — the mock
     // generator has no use for it and should not require it to be present.
     if (!use_mocked && options.pipeline.prompt_dir.empty()) {
-      const std::string msg =
+      spdlog::error(
-          "Invalid arguments: --prompt-dir is required when not using --mocked";
+          "Invalid arguments: --prompt-dir is required when not using "
-      if (logger) {
+          "--mocked");
-        logger->Log({.level = LogLevel::Error,
-                     .phase = PipelinePhase::Startup,
-                     .message = msg});
-      } else {
-        std::cerr << msg << std::endl;
-      }
       return std::nullopt;
     }
 
@@ -170,15 +131,7 @@ std::optional<ApplicationOptions> ParseArguments(
       // Warn but do not fail — the run is still valid, the flags are just
       // silently irrelevant when no model is loaded.
       if (use_mocked) {
-        const std::string msg =
+        spdlog::warn("Sampling parameters are ignored when using --mocked");
-            "Sampling parameters are ignored when using --mocked";
-        if (logger) {
-          logger->Log({.level = LogLevel::Warn,
-                       .phase = PipelinePhase::Startup,
-                       .message = msg});
-        } else {
-          std::cerr << msg << std::endl;
-        }
       } else {
         SamplingOptions sampling;
         sampling.temperature = var_map["temperature"].as<float>();
@@ -195,27 +148,11 @@ std::optional<ApplicationOptions> ParseArguments(
     return options;
 
   } catch (const std::exception& exception) {
-    const std::string msg =
+    spdlog::error("Failed to parse command-line arguments: {}",
-        std::string("Failed to parse command-line arguments: ") +
+                  exception.what());
-        exception.what();
-    if (logger) {
-      logger->Log({.level = LogLevel::Error,
-                   .phase = PipelinePhase::Startup,
-                   .message = msg});
-    } else {
-      std::cerr << msg << std::endl;
-    }
     return std::nullopt;
   } catch (...) {
-    const std::string msg =
+    spdlog::error("Failed to parse command-line arguments: unknown error");
-        "Failed to parse command-line arguments: unknown error";
-    if (logger) {
-      logger->Log({.level = LogLevel::Error,
-                   .phase = PipelinePhase::Startup,
-                   .message = msg});
-    } else {
-      std::cerr << msg << std::endl;
-    }
     return std::nullopt;
   }
 }

tooling/pipeline/src/biergarten_data_generator/biergarten_data_generator.cc

@@ -1,20 +1,18 @@
 /**
- * @file biergarten_pipeline_orchestrator/biergarten_pipeline_orchestrator.cc
+ * @file biergarten_data_generator/biergarten_data_generator.cc
  * @brief BiergartenDataGenerator constructor implementation.
  */
 
-#include "biergarten_pipeline_orchestrator.h"
+#include "biergarten_data_generator.h"
 
 #include <utility>
 
-BiergartenPipelineOrchestrator::BiergartenPipelineOrchestrator(
+BiergartenDataGenerator::BiergartenDataGenerator(
-    std::shared_ptr<ILogger> logger,
     std::unique_ptr<IEnrichmentService> context_service,
     std::unique_ptr<DataGenerator> generator,
     std::unique_ptr<IExportService> exporter,
     const ApplicationOptions &app_options)
-    : logger_(std::move(logger)),
+    : context_service_(std::move(context_service)),
-      context_service_(std::move(context_service)),
       generator_(std::move(generator)),
       exporter_(std::move(exporter)),
       application_options_(app_options) {}

tooling/pipeline/src/biergarten_data_generator/generate_breweries.cc

@@ -0,0 +1,58 @@
+/**
+ * @file biergarten_data_generator/generate_breweries.cc
+ * @brief BiergartenDataGenerator::GenerateBreweries() implementation.
+ */
+
+#include <spdlog/spdlog.h>
+
+#include "biergarten_data_generator.h"
+
+void BiergartenDataGenerator::GenerateBreweries(
+    std::span<const EnrichedCity> cities) {
+  spdlog::info("\n=== SAMPLE BREWERY GENERATION ===");
+
+  generated_breweries_.clear();
+  size_t skipped_count = 0;
+  size_t export_failed_count = 0;
+
+  for (const auto& [location, region_context] : cities) {
+    try {
+      const BreweryResult brewery =
+          generator_->GenerateBrewery(location, region_context);
+
+      const GeneratedBrewery gen{.location = location, .brewery = brewery};
+
+      generated_breweries_.push_back(gen);
+
+      try {
+        exporter_->ProcessRecord(gen);
+      } catch (const std::exception& export_exception) {
+        ++export_failed_count;
+
+        spdlog::warn(
+            "[Pipeline] Generated brewery for '{}' ({}) but SQLite export "
+            "failed: {}",
+            location.city, location.country, export_exception.what());
+      }
+    } catch (const std::exception& e) {
+      ++skipped_count;
+
+      spdlog::warn(
+          "[Pipeline] Skipping city '{}' ({}): brewery generation failed: "
+          "{}",
+          location.city, location.country, e.what());
+    }
+  }
+
+  if (skipped_count > 0) {
+    spdlog::warn("[Pipeline] Skipped {} city/cities due to generation errors",
+                 skipped_count);
+  }
+
+  if (export_failed_count > 0) {
+    spdlog::warn(
+        "[Pipeline] Failed to export {} generated brewery/breweries to "
+        "SQLite",
+        export_failed_count);
+  }
+}

tooling/pipeline/src/biergarten_data_generator/log_results.cc

@@ -0,0 +1,26 @@
+/**
+ * @file biergarten_data_generator/log_results.cc
+ * @brief BiergartenDataGenerator::LogResults() implementation.
+ */
+
+#include <spdlog/spdlog.h>
+
+#include "biergarten_data_generator.h"
+
+void BiergartenDataGenerator::LogResults() const {
+  spdlog::info("\n=== GENERATED DATA DUMP ===");
+  size_t index = 1;
+  for (const auto& [location, brewery] : generated_breweries_) {
+    spdlog::info(
+        "{}. city=\"{}\" country=\"{}\" state=\"{}\" "
+        "iso3166_2={} lat={} lon={}",
+        index, location.city, location.country, location.state_province,
+        location.iso3166_2, location.latitude, location.longitude);
+    spdlog::info("   brewery_name_en=\"{}\"", brewery.name_en);
+    spdlog::info("   brewery_description_en=\"{}\"", brewery.description_en);
+    spdlog::info("   brewery_name_local=\"{}\"", brewery.name_local);
+    spdlog::info("   brewery_description_local=\"{}\"",
+                 brewery.description_local);
+    ++index;
+  }
+}

tooling/pipeline/src/biergarten_data_generator/query_cities_with_countries.cc

@@ -0,0 +1,41 @@
+/**
+ * @file biergarten_data_generator/query_cities_with_countries.cc
+ * @brief BiergartenDataGenerator::QueryCitiesWithCountries() implementation.
+ */
+
+#include <spdlog/spdlog.h>
+
+#include <algorithm>
+#include <filesystem>
+#include <iterator>
+#include <random>
+
+#include "biergarten_data_generator.h"
+#include "json_handling/json_loader.h"
+
+std::vector<Location> BiergartenDataGenerator::QueryCitiesWithCountries() {
+  spdlog::info("\n=== GEOGRAPHIC DATA OVERVIEW ===");
+
+  const std::filesystem::path locations_path = "locations.json";
+
+  auto all_locations = JsonLoader::LoadLocations(locations_path);
+  spdlog::info("  Locations available: {}", all_locations.size());
+
+  const size_t sample_count = std::min(
+      static_cast<size_t>(application_options_.pipeline.location_count),
+      all_locations.size());
+
+  const auto sample_count_signed =
+      static_cast<std::iter_difference_t<decltype(all_locations.cbegin())>>(
+          sample_count);
+
+  std::vector<Location> sampled_locations;
+  sampled_locations.reserve(sample_count);
+
+  std::random_device random_generator;
+  std::ranges::sample(all_locations, std::back_inserter(sampled_locations),
+                      sample_count_signed, random_generator);
+
+  spdlog::info("  Sampled locations: {}", sampled_locations.size());
+  return sampled_locations;
+}

tooling/pipeline/src/biergarten_data_generator/run.cc

@@ -0,0 +1,52 @@
+/**
+ * @file biergarten_data_generator/run.cc
+ * @brief BiergartenDataGenerator::Run() implementation.
+ */
+
+#include <spdlog/spdlog.h>
+
+#include <utility>
+
+#include "biergarten_data_generator.h"
+
+bool BiergartenDataGenerator::Run() {
+  try {
+    exporter_->Initialize();
+
+    std::vector<Location> cities = QueryCitiesWithCountries();
+    std::vector<EnrichedCity> enriched;
+    enriched.reserve(cities.size());
+
+    size_t skipped_count = 0;
+    for (auto& city : cities) {
+      try {
+        std::string region_context = context_service_->GetLocationContext(city);
+        // spdlog::debug("[Pipeline] Context for '{}' ({}) gathered:\n{}",
+        //               city.city, city.iso3166_2, region_context);
+
+        enriched.push_back(
+            EnrichedCity{.location = std::move(city),
+                         .region_context = std::move(region_context)});
+      } catch (const std::exception& exception) {
+        ++skipped_count;
+        spdlog::warn(
+            "[Pipeline] Skipping city '{}' ({}): context lookup failed: {}",
+            city.city, city.country, exception.what());
+      }
+    }
+
+    if (skipped_count > 0) {
+      spdlog::warn(
+          "[Pipeline] Skipped {} city/cities due to context lookup errors",
+          skipped_count);
+    }
+
+    this->GenerateBreweries(enriched);
+    exporter_->Finalize();
+    this->LogResults();
+    return true;
+  } catch (const std::exception& e) {
+    spdlog::error("Pipeline execution failed with error: {}", e.what());
+    return false;
+  }
+}

tooling/pipeline/src/biergarten_pipeline_orchestrator/generate_breweries.cc

@@ -1,69 +0,0 @@
-/**
- * @file biergarten_pipeline_orchestrator/generate_breweries.cc
- * @brief BiergartenDataGenerator::GenerateBreweries() implementation.
- */
-
-#include <chrono>
-
-#include "biergarten_pipeline_orchestrator.h"
-#include "services/logging/logger.h"
-
-void BiergartenPipelineOrchestrator::GenerateBreweries(
-    std::span<const EnrichedCity> cities) {
-  logger_->Log({.level = LogLevel::Info,
-                .phase = PipelinePhase::BreweryAndBeerGeneration,
-                .message = "=== SAMPLE BREWERY GENERATION ==="});
-
-  generated_breweries_.clear();
-  size_t skipped_count = 0;
-  size_t export_failed_count = 0;
-
-  for (const auto& [location, region_context] : cities) {
-    try {
-      const BreweryResult brewery =
-          generator_->GenerateBrewery(location, region_context);
-
-      const GeneratedBrewery gen{.location = location, .brewery = brewery};
-
-      generated_breweries_.push_back(gen);
-
-      try {
-        exporter_->ProcessRecord(gen);
-      } catch (const std::exception& export_exception) {
-        ++export_failed_count;
-
-        logger_->Log(
-            {.level = LogLevel::Warn,
-             .phase = PipelinePhase::BreweryAndBeerGeneration,
-             .message =
-                 std::string("[Pipeline] Generated brewery for '") +
-                 location.city + "' (" + location.country +
-                 ") but SQLite export failed: " + export_exception.what()});
-      }
-    } catch (const std::exception& e) {
-      ++skipped_count;
-
-      logger_->Log({.level = LogLevel::Warn,
-                    .phase = PipelinePhase::BreweryAndBeerGeneration,
-                    .message = std::string("[Pipeline] Skipping city '") +
-                               location.city + " (" + location.country +
-                               "): brewery generation failed: " + e.what()});
-    }
-  }
-
-  if (skipped_count > 0) {
-    logger_->Log({.level = LogLevel::Warn,
-                  .phase = PipelinePhase::BreweryAndBeerGeneration,
-                  .message = std::string("[Pipeline] Skipped ") +
-                             std::to_string(skipped_count) +
-                             " city/cities due to generation errors"});
-  }
-
-  if (export_failed_count > 0) {
-    logger_->Log({.level = LogLevel::Warn,
-                  .phase = PipelinePhase::Teardown,
-                  .message = std::string("[Pipeline] Failed to export ") +
-                             std::to_string(export_failed_count) +
-                             " generated brewery/breweries to SQLite"});
-  }
-}

tooling/pipeline/src/biergarten_pipeline_orchestrator/log_results.cc

@@ -1,37 +0,0 @@
-/**
- * @file biergarten_pipeline_orchestrator/log_results.cc
- * @brief BiergartenDataGenerator::LogResults() implementation.
- */
-
-#include <boost/json/array.hpp>
-#include <chrono>
-#include <format>
-
-#include "../../includes/json_handling/pretty_print.h"
-#include "biergarten_pipeline_orchestrator.h"
-#include "services/logging/logger.h"
-void BiergartenPipelineOrchestrator::LogResults() const {
-  boost::json::array output;
-
-  for (const auto& [location, brewery] : generated_breweries_) {
-    output.push_back(boost::json::object{
-        {"name_en", brewery.name_en},
-        {"description_en", brewery.description_en},
-        {"name_local", brewery.name_local},
-        {"description_local", brewery.description_local},
-        {"location", boost::json::object{
-                         {"city", location.city},
-                         {"country", location.country},
-                         {"state_province", location.state_province},
-                         {"iso3166_2", location.iso3166_2},
-                         {"latitude", location.latitude},
-                         {"longitude", location.longitude},
-                     }}});
-  }
-
-  std::ostringstream oss;
-  PrettyPrint(oss, output);
-  logger_->Log({.level = LogLevel::Info,
-                .phase = PipelinePhase::Teardown,
-                .message = oss.str()});
-}

tooling/pipeline/src/biergarten_pipeline_orchestrator/query_cities_with_countries.cc

@@ -1,51 +0,0 @@
-/**
- * @file biergarten_pipeline_orchestrator/query_cities_with_countries.cc
- * @brief BiergartenDataGenerator::QueryCitiesWithCountries() implementation.
- */
-
-#include <algorithm>
-#include <chrono>
-#include <filesystem>
-#include <format>
-#include <iterator>
-#include <random>
-
-#include "biergarten_pipeline_orchestrator.h"
-#include "json_handling/json_loader.h"
-#include "services/logging/logger.h"
-
-std::vector<Location>
-BiergartenPipelineOrchestrator::QueryCitiesWithCountries() {
-  logger_->Log({.level = LogLevel::Info,
-                .phase = PipelinePhase::Startup,
-                .message = "=== GEOGRAPHIC DATA OVERVIEW ==="});
-
-  const std::filesystem::path locations_path = "locations.json";
-
-  auto all_locations = JsonLoader::LoadLocations(locations_path, logger_);
-
-  const size_t sample_count = std::min(
-      static_cast<size_t>(application_options_.pipeline.location_count),
-      all_locations.size());
-
-  const auto sample_count_signed =
-      static_cast<std::iter_difference_t<decltype(all_locations.cbegin())>>(
-          sample_count);
-
-  std::vector<Location> sampled_locations;
-  sampled_locations.reserve(sample_count);
-
-  std::random_device random_generator;
-  std::ranges::sample(all_locations, std::back_inserter(sampled_locations),
-                      sample_count_signed, random_generator);
-
-  logger_->Log({.level = LogLevel::Info,
-                .phase = PipelinePhase::Startup,
-                .message = std::format("  Locations available: {}",
-                                       all_locations.size())});
-  logger_->Log({.level = LogLevel::Info,
-                .phase = PipelinePhase::Startup,
-                .message = std::format("  Sampled locations: {}",
-                                       sampled_locations.size())});
-  return sampled_locations;
-}

tooling/pipeline/src/biergarten_pipeline_orchestrator/run.cc

@@ -1,62 +0,0 @@
-/**
- * @file biergarten_pipeline_orchestrator/run.cc
- * @brief BiergartenDataGenerator::Run() implementation.
- */
-
-#include <chrono>
-#include <utility>
-
-#include "biergarten_pipeline_orchestrator.h"
-#include "services/logging/logger.h"
-
-bool BiergartenPipelineOrchestrator::Run() {
-  try {
-    exporter_->Initialize();
-
-    std::vector<Location> cities = QueryCitiesWithCountries();
-    std::vector<EnrichedCity> enriched;
-    enriched.reserve(cities.size());
-
-    size_t skipped_count = 0;
-    for (auto& city : cities) {
-      try {
-        std::string region_context = context_service_->GetLocationContext(city);
-        // logger_->Log(LogLevel::Debug, PipelinePhase::UserGeneration,
-        //              "[Pipeline] Context for '" + city.city + "' (" +
-        //              city.iso3166_2 + ") gathered:\n" + region_context);
-
-        enriched.push_back(
-            EnrichedCity{.location = std::move(city),
-                         .region_context = std::move(region_context)});
-      } catch (const std::exception& exception) {
-        ++skipped_count;
-        logger_->Log(
-            {.level = LogLevel::Warn,
-             .phase = PipelinePhase::UserGeneration,
-             .message = std::string("[Pipeline] Skipping city '") + city.city +
-                        " (" + city.country +
-                        "): context lookup failed: " + exception.what()});
-      }
-    }
-
-    if (skipped_count > 0) {
-      logger_->Log({.level = LogLevel::Warn,
-                    .phase = PipelinePhase::UserGeneration,
-                    .message = std::string("[Pipeline] Skipped ") +
-                               std::to_string(skipped_count) +
-                               " city/cities due to context lookup errors"});
-    }
-
-    this->GenerateBreweries(enriched);
-    exporter_->Finalize();
-    this->LogResults();
-    return true;
-  } catch (const std::exception& e) {
-    logger_->Log(
-        {.level = LogLevel::Error,
-         .phase = PipelinePhase::Teardown,
-         .message =
-             std::string("Pipeline execution failed with error: ") + e.what()});
-    return false;
-  }
-}

tooling/pipeline/src/data_generation/llama/generate_brewery.cc

@@ -4,7 +4,8 @@
  * inference, and validates structured JSON output for brewery records.
  */
 
-#include <chrono>
+#include <spdlog/spdlog.h>
+
 #include <format>
 #include <optional>
 #include <stdexcept>
@@ -99,13 +100,8 @@ BreweryResult LlamaGenerator::GenerateBrewery(
     // Generate brewery data from LLM
     raw = this->Infer(system_prompt, user_prompt, max_tokens,
                       kBreweryJsonGrammar);
-    if (logger_) {
+    spdlog::debug("LlamaGenerator: raw output (attempt {}): {}", attempt + 1,
-      logger_->Log(
+                  raw);
-          {.level = LogLevel::Debug,
-           .phase = PipelinePhase::BreweryAndBeerGeneration,
-           .message = std::string("LlamaGenerator: raw output (attempt ") +
-                      std::to_string(attempt + 1) + "): " + raw});
-    }
 
     // Validate output: parse JSON and check required fields
 
@@ -116,14 +112,9 @@ BreweryResult LlamaGenerator::GenerateBrewery(
     if (!validation_error.has_value()) {
       // Success: return parsed brewery data
 
-      if (logger_) {
+      spdlog::info(
-        logger_->Log(
+          "LlamaGenerator: successfully generated brewery data on attempt {}",
-            {.level = LogLevel::Info,
+          attempt + 1);
-             .phase = PipelinePhase::BreweryAndBeerGeneration,
-             .message = std::string("LlamaGenerator: successfully generated "
-                                    "brewery data on attempt ") +
-                        std::to_string(attempt + 1)});
-      }
 
       return brewery;
     }
@@ -131,14 +122,8 @@ BreweryResult LlamaGenerator::GenerateBrewery(
     // Validation failed: log error and prepare corrective feedback
 
     last_error = *validation_error;
-    if (logger_) {
+    spdlog::warn("LlamaGenerator: malformed brewery JSON (attempt {}): {}",
-      logger_->Log(
+                 attempt + 1, *validation_error);
-          {.level = LogLevel::Warn,
-           .phase = PipelinePhase::BreweryAndBeerGeneration,
-           .message =
-               std::string("LlamaGenerator: malformed brewery JSON (attempt ") +
-               std::to_string(attempt + 1) + "): " + *validation_error});
-    }
 
     // Update prompt with error details to guide LLM toward correct output.
     user_prompt = std::format(
@@ -155,14 +140,9 @@ BreweryResult LlamaGenerator::GenerateBrewery(
   }
 
   // All retry attempts exhausted: log failure and throw exception
-  if (logger_) {
+  spdlog::error(
-    logger_->Log(
+      "LlamaGenerator: malformed brewery response after {} attempts: "
-        {.level = LogLevel::Error,
+      "{}",
-         .phase = PipelinePhase::BreweryAndBeerGeneration,
+      max_attempts, last_error.empty() ? raw : last_error);
-         .message =
-             std::string("LlamaGenerator: malformed brewery response after ") +
-             std::to_string(max_attempts) +
-             " attempts: " + (last_error.empty() ? raw : last_error)});
-  }
   throw std::runtime_error("LlamaGenerator: malformed brewery response");
 }

tooling/pipeline/src/data_generation/llama/generate_user.cc

@@ -4,7 +4,9 @@
  * retry handling, and output sanitization for downstream parsing.
  */
 
+#include <spdlog/spdlog.h>
 
+#include <stdexcept>
 #include <string>
 
 #include "data_generation/llama_generator.h"

tooling/pipeline/src/data_generation/llama/helpers.cc

@@ -16,11 +16,11 @@
 
 #include "data_generation/llama_generator_helpers.h"
 #include "llama.h"
-namespace {
+
 /**
  * String trimming: removes leading and trailing whitespace
  */
-std::string Trim(std::string_view value) {
+static std::string Trim(std::string_view value) {
   constexpr std::string_view whitespace = " \t\n\r\f\v";
   const size_t first_index = value.find_first_not_of(whitespace);
   if (first_index == std::string_view::npos) {
@@ -35,7 +35,7 @@ std::string Trim(std::string_view value) {
  * Normalize whitespace: collapses multiple spaces/tabs/newlines into single
  * spaces
  */
-std::string CondenseWhitespace(std::string_view text) {
+static std::string CondenseWhitespace(std::string_view text) {
   std::string out;
   out.reserve(text.size());
 
@@ -61,37 +61,7 @@ std::string CondenseWhitespace(std::string_view text) {
 // Guard against truncating in the first half of the string.
 // This preserves the critical opening content and avoids cutting critical
 // context words early in the region description.
-constexpr size_t kTruncationGuardDivisor = 2;
+static constexpr size_t kTruncationGuardDivisor = 2;
-
-bool ReadRequiredTrimmedStringField(const boost::json::object& obj,
-                                    std::string_view key, std::string& out,
-                                    std::string* error_out) {
-  const boost::json::value* field = obj.if_contains(key);
-  if (field == nullptr || !field->is_string()) {
-    return false;
-  }
-
-  const auto& string_value = field->as_string();
-  out = Trim(std::string_view(string_value.data(), string_value.size()));
-  return !out.empty();
-}
-
-bool HasSchemaPlaceholder(const std::array<std::string*, 4>& values) {
-  for (const std::string* value : values) {
-    std::string lowered = *value;
-    std::ranges::transform(lowered, lowered.begin(),
-                           [](const unsigned char character) {
-                             return static_cast<char>(std::tolower(character));
-                           });
-
-    if (lowered == "string") {
-      return true;
-    }
-  }
-
-  return false;
-}
-}  // namespace
 
 /**
  * Truncate region context to fit within max length while preserving word
@@ -151,6 +121,47 @@ void AppendTokenPiece(const llama_vocab* vocab, llama_token token,
       "LlamaGenerator: failed to decode sampled token piece");
 }
 
+static bool ReadRequiredTrimmedStringField(const boost::json::object& obj,
+                                           std::string_view key,
+                                           std::string& out,
+                                           std::string* error_out) {
+  const boost::json::value* field = obj.if_contains(key);
+  if (field == nullptr || !field->is_string()) {
+    if (error_out != nullptr) {
+      *error_out =
+          "JSON field '" + std::string(key) + "' is missing or not a string";
+    }
+    return false;
+  }
+
+  const auto& string_value = field->as_string();
+  out = Trim(std::string_view(string_value.data(), string_value.size()));
+  if (out.empty()) {
+    if (error_out != nullptr) {
+      *error_out = "JSON field '" + std::string(key) + "' must not be empty";
+    }
+    return false;
+  }
+
+  return true;
+}
+
+static bool HasSchemaPlaceholder(const std::array<std::string*, 4>& values) {
+  for (const std::string* value : values) {
+    std::string lowered = *value;
+    std::ranges::transform(lowered, lowered.begin(),
+                           [](unsigned char character) {
+                             return static_cast<char>(std::tolower(character));
+                           });
+
+    if (lowered == "string") {
+      return true;
+    }
+  }
+
+  return false;
+}
+
 std::optional<std::string> ValidateBreweryJson(const std::string& raw,
                                                BreweryResult& brewery_out) {
   boost::system::error_code error_code;
@@ -198,7 +209,7 @@ std::optional<std::string> ValidateBreweryJson(const std::string& raw,
     return validation_error;
   }
 
-  const std::array schema_placeholders = {
+  const std::array<std::string*, 4> schema_placeholders = {
       &brewery_out.name_en, &brewery_out.description_en,
       &brewery_out.name_local, &brewery_out.description_local};
   if (HasSchemaPlaceholder(schema_placeholders)) {

tooling/pipeline/src/data_generation/llama/infer.cc

@@ -5,9 +5,9 @@
  * output tokens back to text for system+user chat prompts.
  */
 
+#include <spdlog/spdlog.h>
+
 #include <algorithm>
-#include <chrono>
-#include <format>
 #include <memory>
 #include <stdexcept>
 #include <string>
@@ -107,7 +107,7 @@ std::string LlamaGenerator::InferFormatted(const std::string& formatted_prompt,
       .top_p = sampling_top_p_,
       .seed = static_cast<uint32_t>(rng_()),
   };
-  const auto sampler = MakeSamplerChain(vocab, sampler_config, grammar);
+  auto sampler = MakeSamplerChain(vocab, sampler_config, grammar);
 
   /**
    * Clear KV cache to ensure clean inference state (no residual context)
@@ -171,14 +171,10 @@ std::string LlamaGenerator::InferFormatted(const std::string& formatted_prompt,
    */
   prompt_tokens.resize(static_cast<size_t>(token_count));
   if (token_count > prompt_budget) {
-    if (logger_) {
+    spdlog::warn(
-      logger_->Log({.level = LogLevel::Warn,
+        "LlamaGenerator: prompt too long ({} tokens), truncating to {} "
-                    .phase = PipelinePhase::BreweryAndBeerGeneration,
+        "tokens to fit n_batch/n_ctx limits",
-                    .message = std::format(
+        token_count, prompt_budget);
-                        "LlamaGenerator: prompt too long ({} tokens), "
-                        "truncating to {} tokens to fit n_batch/n_ctx limits",
-                        token_count, prompt_budget)});
-    }
     prompt_tokens.resize(static_cast<size_t>(prompt_budget));
     token_count = prompt_budget;
   }

tooling/pipeline/src/data_generation/llama/llama_generator.cc

@@ -32,11 +32,9 @@ void LlamaGenerator::ContextDeleter::operator()(
 
 LlamaGenerator::LlamaGenerator(
     const ApplicationOptions& options, const std::string& model_path,
-    std::shared_ptr<ILogger> logger,
     std::unique_ptr<IPromptFormatter> prompt_formatter,
     std::unique_ptr<IPromptDirectory> prompt_directory)
     : rng_(std::random_device{}()),
-      logger_(std::move(logger)),
       prompt_formatter_(std::move(prompt_formatter)),
       prompt_directory_(std::move(prompt_directory)) {
   if (model_path.empty()) {
@@ -53,46 +51,45 @@ LlamaGenerator::LlamaGenerator(
         "LlamaGenerator: prompt directory dependency must not be null");
   }
 
-  const auto [temperature, top_p, top_k, n_ctx, seed, n_gpu_layers] =
+  const auto sampling = options.generator.sampling.value_or(SamplingOptions{});
-      options.generator.sampling.value_or(SamplingOptions{});
 
-  if (temperature < 0.0F) {
+  if (sampling.temperature < 0.0F) {
     throw std::runtime_error(
         "LlamaGenerator: sampling temperature must be >= 0");
   }
 
-  if (top_p <= 0.0F || top_p > 1.0F) {
+  if (sampling.top_p <= 0.0F || sampling.top_p > 1.0F) {
     throw std::runtime_error(
         "LlamaGenerator: sampling top-p must be in (0, 1]");
   }
 
-  if (top_k == 0U) {
+  if (sampling.top_k == 0U) {
     throw std::runtime_error("LlamaGenerator: sampling top-k must be > 0");
   }
 
-  if (seed < -1) {
+  if (sampling.seed < -1) {
     throw std::runtime_error(
         "LlamaGenerator: seed must be >= 0, or -1 for random");
   }
 
-  if (n_ctx == 0 || n_ctx > kMaxContextSize) {
+  if (sampling.n_ctx == 0 || sampling.n_ctx > kMaxContextSize) {
     throw std::runtime_error(
         "LlamaGenerator: context size must be in range [1, 32768]");
   }
 
-  sampling_temperature_ = temperature;
+  sampling_temperature_ = sampling.temperature;
-  sampling_top_p_ = top_p;
+  sampling_top_p_ = sampling.top_p;
-  sampling_top_k_ = top_k;
+  sampling_top_k_ = sampling.top_k;
 
-  if (seed == -1) {
+  if (sampling.seed == -1) {
     std::random_device random_device;
     rng_.seed(random_device());
   } else {
-    rng_.seed(static_cast<uint32_t>(seed));
+    rng_.seed(static_cast<uint32_t>(sampling.seed));
   }
 
-  n_ctx_ = n_ctx;
+  n_ctx_ = sampling.n_ctx;
-  n_gpu_layers_ = n_gpu_layers;
+  n_gpu_layers_ = sampling.n_gpu_layers;
 
   this->Load(model_path);
 }

tooling/pipeline/src/data_generation/llama/load.cc

@@ -4,8 +4,9 @@
  * context, and resets prior resources during model initialization.
  */
 
+#include <spdlog/spdlog.h>
+
 #include <algorithm>
-#include <chrono>
 #include <stdexcept>
 #include <string>
 #include <utility>
@@ -28,10 +29,8 @@ void LlamaGenerator::Load(const std::string& model_path) {
 
   llama_model_params model_params = llama_model_default_params();
   model_params.n_gpu_layers = n_gpu_layers_;
-
+  LlamaGenerator::ModelHandle loaded_model(
-  ModelHandle loaded_model(
       llama_model_load_from_file(model_path.c_str(), model_params));
-
   if (!loaded_model) {
     throw std::runtime_error(
         "LlamaGenerator: failed to load model from path: " + model_path);
@@ -41,9 +40,8 @@ void LlamaGenerator::Load(const std::string& model_path) {
   context_params.n_ctx = n_ctx_;
   context_params.n_batch = std::min(n_ctx_, kMaxBatchSize);
 
-  ContextHandle loaded_context(
+  LlamaGenerator::ContextHandle loaded_context(
       llama_init_from_model(loaded_model.get(), context_params));
-
   if (!loaded_context) {
     throw std::runtime_error("LlamaGenerator: failed to create context");
   }
@@ -51,10 +49,5 @@ void LlamaGenerator::Load(const std::string& model_path) {
   model_ = std::move(loaded_model);
   context_ = std::move(loaded_context);
 
-  if (logger_) {
+  spdlog::info("[LlamaGenerator] Loaded model: {}", model_path);
-    logger_->Log({.level = LogLevel::Info,
-                  .phase = PipelinePhase::Startup,
-                  .message = std::format("[LlamaGenerator] Loaded model: {} ",
-                                         model_path)});
-  }
 }

tooling/pipeline/src/json_handling/json_loader.cc

@@ -6,8 +6,7 @@
 
 #include "json_handling/json_loader.h"
 
-#include "services/logging/logger.h"
+#include <spdlog/spdlog.h>
-#include <iostream>
 
 #include <boost/json.hpp>
 #include <fstream>
@@ -59,7 +58,7 @@ static std::vector<std::string> ReadRequiredStringArray(
 }
 
 std::vector<Location> JsonLoader::LoadLocations(
-    const std::filesystem::path& filepath, std::shared_ptr<ILogger> logger) {
+    const std::filesystem::path& filepath) {
   std::ifstream input(filepath);
   if (!input.is_open()) {
     throw std::runtime_error("Failed to open locations file: " +
@@ -105,5 +104,7 @@ std::vector<Location> JsonLoader::LoadLocations(
     });
   }
 
+  spdlog::info("[JsonLoader] Loaded {} locations from {}", locations.size(),
+               filepath.string());
   return locations;
 }

tooling/pipeline/src/main.cc

@@ -4,22 +4,16 @@
  * initializes shared infrastructure, and executes the pipeline entry flow.
  */
 
-#include <spdlog/fmt/fmt.h>
 #include <spdlog/spdlog.h>
 
 #include <boost/di.hpp>
 #include <boost/program_options.hpp>
-#include <chrono>
 #include <exception>
-#include <format>
-#include <iostream>
 #include <memory>
 #include <optional>
 #include <string>
-#include <thread>
 
-#include "biergarten_pipeline_orchestrator.h"
+#include "biergarten_data_generator.h"
-#include "concurrency/bounded_channel.h"
 #include "data_generation/llama_generator.h"
 #include "data_generation/mock_generator.h"
 #include "data_generation/prompt_formatting/gemma4_jinja_prompt_formatter.h"
@@ -31,50 +25,28 @@
 #include "services/enrichment/enrichment_service.h"
 #include "services/enrichment/mock_enrichment.h"
 #include "services/enrichment/wikipedia_service.h"
-#include "services/logging/log_dispatcher.h"
-#include "services/logging/log_entry.h"
-#include "services/logging/log_producer.h"
-#include "services/logging/logger.h"
 #include "services/prompting/prompt_directory.h"
 #include "web_client/http_web_client.h"
 
 namespace di = boost::di;
 
-static constexpr size_t kLogMaxCount = 512;
-
 int main(const int argc, char** argv) {
-  spdlog::set_level(spdlog::level::debug);
-  spdlog::set_pattern("│ %Y-%m-%d %H:%M:%S.%e │ %^%-7l%$ │ %v");
-  BoundedChannel<LogEntry> log_channel(kLogMaxCount);
-
-  auto log_dispatcher =  //
-      std::make_unique<LogDispatcher>(log_channel);
-  std::shared_ptr<ILogger> log_producer =
-      std::make_shared<LogProducer>(log_channel);
-
-  std::thread log_thread([&log_dispatcher] { log_dispatcher->Run(); });
-  auto shutdown = [&](const int exit_code) {
-    log_channel.Close();
-    log_thread.join();
-    return exit_code;
-  };
-
   try {
     Timer timer;
+    spdlog::set_pattern("[%Y-%m-%d %H:%M:%S.%e] [%^%l%$] %v");
 
 #ifndef BIERGARTEN_MOCK_ONLY
     const LlamaBackendState llama_backend_state;
 #endif
-
+#ifdef DEBUG
-    log_producer->Log({.level = LogLevel::Info,
+    spdlog::set_level(spdlog::level::debug);
-                       .phase = PipelinePhase::Startup,
+#endif
-                       .message = "STARTING PIPELINE"});
 
     const std::optional<ApplicationOptions> parsed_options =
-        ParseArguments(argc, argv, log_producer);
+        ParseArguments(argc, argv);
 
     if (!parsed_options.has_value()) {
-      return shutdown(EXIT_FAILURE);
+      return 0;
     }
 
     const auto options = *parsed_options;
@@ -83,136 +55,65 @@ int main(const int argc, char** argv) {
         options.generator.sampling.value_or(SamplingOptions{});
 
     std::unique_ptr<IPromptDirectory> prompt_directory;
-
     if (!options.generator.use_mocked) {
       try {
-        prompt_directory = std::make_unique<PromptDirectory>(
+        prompt_directory =
-            options.pipeline.prompt_dir, log_producer);
+            std::make_unique<PromptDirectory>(options.pipeline.prompt_dir);
       } catch (const std::exception& dir_error) {
-        log_producer->Log({.level = LogLevel::Error,
+        spdlog::error("[Startup] Invalid --prompt-dir: {}", dir_error.what());
-                           .phase = PipelinePhase::Startup,
+        return 1;
-                           .message = std::format("Invalid --prompt-dir: {}",
-                                                  dir_error.what())});
-
-        return shutdown(EXIT_FAILURE);
       }
     }
 
     const auto injector = di::make_injector(
-        di::bind<ILogger>().to(log_producer),
         di::bind<ApplicationOptions>().to(options),
         di::bind<std::string>().to(model_path),
+        di::bind<WebClient>().to<HttpWebClient>(),
         di::bind<IExportService>().to<SqliteExportService>(),
-        di::bind<IPromptFormatter>().to([options, log_producer] {
+        di::bind<IPromptFormatter>().to<Gemma4JinjaPromptFormatter>(),
-          if (options.generator.use_mocked) {
-            {
-              log_producer->Log(
-                  {.level = LogLevel::Info,
-                   .phase = PipelinePhase::Startup,
-                   .message = "Prompt formatter: none (mock mode)"});
-            }
-            return std::unique_ptr<IPromptFormatter>(nullptr);
-          }
-          {
-            log_producer->Log(
-                {.level = LogLevel::Info,
-                 .phase = PipelinePhase::Startup,
-                 .message = "Prompt formatter: Gemma4JinjaPromptFormatter"});
-          }
-          return std::unique_ptr<IPromptFormatter>(
-              std::make_unique<Gemma4JinjaPromptFormatter>());
-        }),
-        di::bind<WebClient>().to([options, log_producer] {
-          if (options.generator.use_mocked) {
-            {
-              log_producer->Log({.level = LogLevel::Info,
-                                 .phase = PipelinePhase::Startup,
-                                 .message = "Web client: none (mock mode)"});
-            }
-            return std::unique_ptr<WebClient>(nullptr);
-          }
-          {
-            log_producer->Log({.level = LogLevel::Info,
-                               .phase = PipelinePhase::Startup,
-                               .message = "Web client: HttpWebClient"});
-          }
-          return std::unique_ptr<WebClient>(
-              std::make_unique<HttpWebClient>(log_producer));
-        }),
         di::bind<IEnrichmentService>().to(
-            [options, &log_producer](
+            [options](const auto& inj) -> std::unique_ptr<IEnrichmentService> {
-                const auto& inj) -> std::unique_ptr<IEnrichmentService> {
               if (options.generator.use_mocked) {
-                {
-                  log_producer->Log({.level = LogLevel::Info,
-                                     .phase = PipelinePhase::Startup,
-                                     .message = "Enrichment: mock"});
-                }
                 return std::make_unique<MockEnrichmentService>();
               }
-              {
+
-                log_producer->Log({.level = LogLevel::Info,
-                                   .phase = PipelinePhase::Startup,
-                                   .message = "Enrichment: Wikipedia"});
-              }
               return std::make_unique<WikipediaEnrichmentService>(
-                  inj.template create<std::unique_ptr<WebClient>>(),
+                  inj.template create<std::unique_ptr<WebClient>>());
-                  log_producer);
             }),
         di::bind<DataGenerator>().to(
-            [&options, &model_path, &sampling, &prompt_directory,
+            [options, model_path, sampling, &prompt_directory](
-             &log_producer](const auto& inj) -> std::unique_ptr<DataGenerator> {
+                const auto& inj) -> std::unique_ptr<DataGenerator> {
               if (options.generator.use_mocked) {
-                {
+                spdlog::info(
-                  log_producer->Log({.level = LogLevel::Info,
+                    "[Generator] Using MockGenerator (no model path provided)");
-                                     .phase = PipelinePhase::Startup,
-                                     .message = "Generator: mock"});
-                }
                 return std::make_unique<MockGenerator>();
               }
-              {
+
-                log_producer->Log(
+              spdlog::info(
-                    {.level = LogLevel::Info,
+                  "[Generator] Using LlamaGenerator: {} (temperature={}, "
-                     .phase = PipelinePhase::Startup,
+                  "top-p={}, top-k={}, n_ctx={}, seed={})",
-                     .message = std::format(
-                         "Generator: LlamaGenerator | model={} | temp={:.2f} "
-                         "top_p={:.2f} top_k={} n_ctx={} seed={}",
                   model_path, sampling.temperature, sampling.top_p,
-                         sampling.top_k, sampling.n_ctx, sampling.seed)});
+                  sampling.top_k, sampling.n_ctx, sampling.seed);
-              }
               return std::make_unique<LlamaGenerator>(
-                  options, model_path, log_producer,
+                  options, model_path,
                   inj.template create<std::unique_ptr<IPromptFormatter>>(),
                   std::move(prompt_directory));
-            }));
+            })
 
-    const auto orchestrator =
+    );
-        injector.create<std::unique_ptr<BiergartenPipelineOrchestrator>>();
 
-    if (!orchestrator->Run()) {
+    const auto generator =
-      log_producer->Log({.level = LogLevel::Error,
+        injector.create<std::unique_ptr<BiergartenDataGenerator>>();
-                         .phase = PipelinePhase::Teardown,
+
-                         .message = "Pipeline execution failed"});
+    if (!generator->Run()) {
-      return shutdown(EXIT_FAILURE);
+      spdlog::error("Pipeline execution failed");
+      return 1;
     }
 
-    log_producer->Log({.level = LogLevel::Info,
+    spdlog::info("Pipeline executed successfully in {} ms", timer.Elapsed());
-                       .phase = PipelinePhase::Teardown,
+    return 0;
-                       .message = std::format("Pipeline complete in {} ms",
-                                              timer.Elapsed())});
-
-    return shutdown(EXIT_SUCCESS);
-
   } catch (const std::exception& exception) {
-    const LogEntry log_entry{.level = LogLevel::Error,
+    spdlog::critical("Unhandled fatal error in main: {}", exception.what());
-                             .phase = PipelinePhase::Teardown,
+    return 1;
-                             .message = exception.what()};
-    if (log_producer) {
-      log_producer->Log(log_entry);
-    } else {
-      std::cerr << log_entry.message << std::endl;
-    }
-
-    return shutdown(EXIT_FAILURE);
   }
 }

tooling/pipeline/src/services/enrichment/wikipedia/fetch_extract.cc

@@ -2,6 +2,8 @@
  * @file wikipedia/fetch_extract.cc
  */
 
+#include <spdlog/spdlog.h>
+
 #include <boost/json.hpp>
 #include <chrono>
 #include <format>
@@ -14,17 +16,13 @@
 using namespace boost;
 
 std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
+
   const std::string cache_key(query);
 
   // 1. Cache Lookup
   if (const auto cache_it = this->extract_cache_.find(cache_key);
       cache_it != this->extract_cache_.end()) {
-    if (logger_) {
+    spdlog::debug("Wikipedia: Cache hit for {}!", cache_key);
-      logger_->Log({.level = LogLevel::Debug,
-                    .phase = PipelinePhase::UserGeneration,
-                    .message = std::string("Wikipedia: Cache hit for ") +
-                               cache_key + "!"});
-    }
     return cache_it->second;
   }
 
@@ -34,6 +32,7 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
       "api.php?action=query&titles={}&prop=extracts&explaintext=1&format=json",
       encoded);
 
+
   const std::string body = this->client_->Get(url);
   {
     using namespace std::literals::chrono_literals;
@@ -45,27 +44,15 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
   json::value doc = json::parse(body, ec);
 
   if (ec) {
-    if (logger_) {
+    spdlog::warn("WikipediaService: JSON parse error for '{}': {}", query,
-      logger_->Log(
+                 ec.message());
-          {.level = LogLevel::Warn,
-           .phase = PipelinePhase::UserGeneration,
-           .message = std::string("WikipediaService: JSON parse error for '") +
-                      std::string(query) + "': " + ec.message()});
-    }
     return {};
   }
 
   // 3. Safe Extraction
   const json::object* obj = doc.if_object();
   if (obj == nullptr) {
-    if (logger_) {
+    spdlog::warn("WikipediaService: Expected root object for '{}'", query);
-      logger_->Log(
-          {.level = LogLevel::Warn,
-           .phase = PipelinePhase::UserGeneration,
-           .message =
-               std::string("WikipediaService: Expected root object for '") +
-               std::string(query) + "'"});
-    }
     return {};
   }
 
@@ -76,27 +63,14 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
           : nullptr;
 
   if ((pages_ptr == nullptr) || !pages_ptr->is_object()) {
-    if (logger_) {
+    spdlog::warn("WikipediaService: Missing query.pages for '{}'", query);
-      logger_->Log(
-          {.level = LogLevel::Warn,
-           .phase = PipelinePhase::UserGeneration,
-           .message =
-               std::string("WikipediaService: Missing query.pages for '") +
-               std::string(query) + "'"});
-    }
     return {};
   }
 
   const json::object& pages = pages_ptr->get_object();
 
   if (pages.empty()) {
-    if (logger_) {
+    spdlog::warn("WikipediaService: No pages returned for '{}'", query);
-      logger_->Log(
-          {.level = LogLevel::Warn,
-           .phase = PipelinePhase::UserGeneration,
-           .message = std::string("WikipediaService: No pages returned for '") +
-                      std::string(query) + "'"});
-    }
     this->extract_cache_.emplace(cache_key, "");
     return {};
   }
@@ -106,14 +80,7 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
   const json::value& page_val = pages.begin()->value();
 
   if (!page_val.is_object()) {
-    if (logger_) {
+    spdlog::warn("WikipediaService: Unexpected page format for '{}'", query);
-      logger_->Log(
-          {.level = LogLevel::Warn,
-           .phase = PipelinePhase::UserGeneration,
-           .message =
-               std::string("WikipediaService: Unexpected page format for '") +
-               std::string(query) + "'"});
-    }
     return {};
   }
 
@@ -121,12 +88,7 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
 
   // Handle 404/Missing status
   if (page.contains("missing")) {
-    if (logger_) {
+    spdlog::warn("WikipediaService: Page '{}' does not exist", query);
-      logger_->Log({.level = LogLevel::Warn,
-                    .phase = PipelinePhase::UserGeneration,
-                    .message = std::string("WikipediaService: Page '") +
-                               std::string(query) + "' does not exist"});
-    }
     this->extract_cache_.emplace(cache_key, "");
     return {};
   }
@@ -134,27 +96,15 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
   const json::value* extract_ptr = page.if_contains("extract");
 
   if ((extract_ptr == nullptr) || !extract_ptr->is_string()) {
-    if (logger_) {
+    spdlog::warn("WikipediaService: No extract string found for '{}'", query);
-      logger_->Log(
-          {.level = LogLevel::Warn,
-           .phase = PipelinePhase::UserGeneration,
-           .message =
-               std::string("WikipediaService: No extract string found for '") +
-               std::string(query) + "'"});
-    }
     this->extract_cache_.emplace(cache_key, "");
     return {};
   }
 
   // 4. Success
   std::string extract(extract_ptr->as_string());
-  if (logger_) {
+  spdlog::info("WikipediaService: Fetched {} chars for '{}'", extract.size(),
-    logger_->Log({.level = LogLevel::Info,
+                query);
-                  .phase = PipelinePhase::UserGeneration,
-                  .message = std::string("WikipediaService: Fetched ") +
-                             std::to_string(extract.size()) + " chars for '" +
-                             std::string(query) + "'"});
-  }
 
   this->extract_cache_.insert_or_assign(cache_key, extract);
 

tooling/pipeline/src/services/enrichment/wikipedia/get_summary.cc

@@ -3,6 +3,8 @@
  * @brief WikipediaService::GetLocationContext() implementation.
  */
 
+#include <spdlog/spdlog.h>
+
 #include <chrono>
 #include <format>
 #include <string>
@@ -10,15 +12,10 @@
 
 #include "services/enrichment/wikipedia_service.h"
 
-std::string WikipediaEnrichmentService::GetLocationContext(
+std::string WikipediaEnrichmentService::GetLocationContext(const Location& loc) {
-    const Location& loc) {
   using namespace std::literals::chrono_literals;
   if (!this->client_) {
-    if (logger_) {
+    spdlog::warn("Client is nullptr.");
-      logger_->Log({.level = LogLevel::Warn,
-                    .phase = PipelinePhase::UserGeneration,
-                    .message = "Wikipedia client is nullptr."});
-    }
     return {};
   }
 
@@ -49,22 +46,13 @@ std::string WikipediaEnrichmentService::GetLocationContext(
   try {
     append_extract(FetchExtract(brewing_query));
     append_extract(FetchExtract(beer_query));
-    if (logger_) {
+    spdlog::info("Done fetching for {}. Sleeping for 10 seconds.",
-      logger_->Log({.level = LogLevel::Info,
+                 location_query);
-                    .phase = PipelinePhase::UserGeneration,
-                    .message = std::string("Done fetching for ") +
-                               location_query + ". Sleeping for 10 seconds."});
-    }
     std::this_thread::sleep_for(10s);
 
   } catch (const std::runtime_error& e) {
-    if (logger_) {
+    spdlog::debug("WikipediaService lookup failed for '{}': {}", location_query,
-      logger_->Log(
+                  e.what());
-          {.level = LogLevel::Debug,
-           .phase = PipelinePhase::UserGeneration,
-           .message = std::string("WikipediaService lookup failed for '") +
-                      location_query + "': " + e.what()});
-    }
   }
   return result;
 }

tooling/pipeline/src/services/enrichment/wikipedia/wikipedia_service.cc

@@ -8,5 +8,5 @@
 #include <utility>
 
 WikipediaEnrichmentService::WikipediaEnrichmentService(
-    std::unique_ptr<WebClient> client, std::shared_ptr<ILogger> logger)
+    std::unique_ptr<WebClient> client)
-    : client_(std::move(client)), logger_(std::move(logger)) {}
+    : client_(std::move(client)) {}

tooling/pipeline/src/services/logging/log_dispatcher.cc

@@ -1,47 +0,0 @@
-/**
- * @brief LogDispatcher implementation for asynchronous pipeline logging.
- *
- * LogDispatcher drains LogEntry items from a BoundedChannel and forwards them
- * to spdlog for final output.
- */
-#include "services/logging/log_dispatcher.h"
-
-#include <spdlog/spdlog.h>
-
-#include <string>
-
-#include "concurrency/bounded_channel.h"
-#include "services/logging/log_entry.h"
-
-LogDispatcher::LogDispatcher(BoundedChannel<LogEntry>& channel)
-    : channel_(channel) {}
-
-void LogDispatcher::Run() {
-  auto logger = spdlog::default_logger();
-
-  while (true) {
-    auto entry = channel_.Receive();
-    if (!entry.has_value()) {
-      // Channel is closed and drained.
-      break;
-    }
-
-    const auto& log = entry.value();
-
-    logger->log(ToSpdlogLevel(log.level), log.message);
-  }
-}
-
-spdlog::level::level_enum LogDispatcher::ToSpdlogLevel(LogLevel level) {
-  switch (level) {
-    case LogLevel::Debug:
-      return spdlog::level::debug;
-    case LogLevel::Info:
-      return spdlog::level::info;
-    case LogLevel::Warn:
-      return spdlog::level::warn;
-    case LogLevel::Error:
-      return spdlog::level::err;
-  }
-  return spdlog::level::info;
-}

tooling/pipeline/src/services/logging/log_producer.cc

@@ -1,19 +0,0 @@
-/**
- * @file src/services/logging/log_producer.cc
- * @brief LogProducer implementation for asynchronous pipeline logging.
- */
-
-#include "services/logging/log_producer.h"
-
-#include <chrono>
-#include <optional>
-#include <string>
-#include <string_view>
-
-#include "concurrency/bounded_channel.h"
-#include "services/logging/log_entry.h"
-
-LogProducer::LogProducer(BoundedChannel<LogEntry>& channel)
-    : channel_(channel) {}
-
-void LogProducer::Log(const LogEntry& entry) { channel_.Send(entry); }

tooling/pipeline/src/services/prompt_directory.cc

@@ -6,24 +6,20 @@
 
 #include "services/prompting/prompt_directory.h"
 
-#include <chrono>
+#include <spdlog/spdlog.h>
+
 #include <filesystem>
 #include <fstream>
 #include <stdexcept>
 #include <string>
 #include <string_view>
-#include <utility>
 
 // ---------------------------------------------------------------------------
 // PromptDirectory
 // ---------------------------------------------------------------------------
 
 PromptDirectory::PromptDirectory(const std::filesystem::path& prompt_dir)
-    : PromptDirectory(prompt_dir, nullptr) {}
+    : prompt_dir_(prompt_dir) {
-
-PromptDirectory::PromptDirectory(const std::filesystem::path& prompt_dir,
-                                 std::shared_ptr<ILogger> logger)
-    : prompt_dir_(prompt_dir), logger_(std::move(logger)) {
   std::error_code ec;
 
   // Scenario 4: directory must exist.
@@ -48,14 +44,8 @@ PromptDirectory::PromptDirectory(const std::filesystem::path& prompt_dir,
         prompt_dir_.string() + " (" + ec.message() + ")");
   }
 
-  if (logger_) {
+  spdlog::info("[PromptDirectory] Resolved prompt directory: {}",
-    logger_->Log(
+               prompt_dir_.string());
-        {.level = LogLevel::Info,
-         .phase = PipelinePhase::Startup,
-         .message =
-             std::string("[PromptDirectory] Resolved prompt directory: ") +
-             prompt_dir_.string()});
-  }
 }
 
 std::string PromptDirectory::Load(std::string_view key) {
@@ -87,13 +77,8 @@ std::string PromptDirectory::Load(std::string_view key) {
                              key_str + "' is empty: " + file_path.string());
   }
 
-  if (logger_) {
+  spdlog::info("[PromptDirectory] Loaded prompt '{}' from '{}' ({} chars)",
-    logger_->Log({.level = LogLevel::Info,
+               key_str, file_path.string(), content.size());
-                  .phase = PipelinePhase::Startup,
-                  .message = std::string("[PromptDirectory] Loaded prompt '") +
-                             key_str + "' from '" + file_path.string() + "' (" +
-                             std::to_string(content.size()) + " chars)"});
-  }
 
   cache_.emplace(key_str, content);
   return content;

tooling/pipeline/src/web_client/http_web_client.cc

@@ -1,5 +1,5 @@
 /**
- * @file web_client/http_web_client.cc
+* @file web_client/http_web_client.cc
  * @brief cpp-httplib implementation of WebClient.
  */
 
@@ -7,13 +7,12 @@
 
 #include <httplib.h>
 
-#include <chrono>
 #include <regex>
 #include <stdexcept>
 #include <string>
 #include <utility>
 
-#include "services/logging/logger.h"
+#include "spdlog/spdlog.h"
 
 namespace {
 constexpr time_t kConnectionTimeoutSeconds = 5;
@@ -41,26 +40,23 @@ std::string HttpWebClient::Get(const std::string& url) {
   client.set_follow_location(true);
   client.set_connection_timeout(kConnectionTimeoutSeconds);
   client.set_read_timeout(kReadTimeoutSeconds);
-  client.set_default_headers({{"Accept", "application/json"},
+  client.set_default_headers({
-                              {"User-Agent", "biergarten-pipeline/1.0"}});
+     {"Accept", "application/json"},
+     {"User-Agent", "biergarten-pipeline/1.0"}
+ });
 
   const httplib::Result result = client.Get(path);
 
   if (!result) {
-    throw std::runtime_error("[HttpWebClient] Request failed for URL: " + url +
+    throw std::runtime_error(
+        "[HttpWebClient] Request failed for URL: " + url +
         " — " + httplib::to_string(result.error()));
   }
 
   if (result->status < kSuccessMin || result->status >= kSuccessMax) {
-    if (logger_) {
+    spdlog::error("[HttpWebClient] Request failed for URL: " + url);
-      logger_->Log(
+    throw std::runtime_error(
-          {.level = LogLevel::Error,
+        "[HttpWebClient] HTTP " + std::to_string(result->status) +
-           .phase = PipelinePhase::UserGeneration,
-           .message =
-               std::string("[HttpWebClient] Request failed for URL: ") + url});
-    }
-    throw std::runtime_error("[HttpWebClient] HTTP " +
-                             std::to_string(result->status) +
         " for URL: " + url);
   }