Create .dockerignore

Co-authored-by: Copilot <copilot@github.com>

.gitattributes

@@ -1 +1 @@
-archive/** linguist-vendored
+archive/* linguist-vendored

docs/pipeline/diagrams/current/class.puml

@@ -26,7 +26,6 @@ skinparam note {
 title The Biergarten Data Pipeline - Class Diagram
 
 class BiergartenDataGenerator {
-  - logger_ : std::shared_ptr<ILogger>
   - context_service_ : std::unique_ptr<IEnrichmentService>
   - generator_ : std::unique_ptr<DataGenerator>
   - exporter_ : std::unique_ptr<IExportService>
@@ -37,46 +36,6 @@ class BiergartenDataGenerator {
   - LogResults() : void
 }
 
-class LogLevel <<enumeration>> {
-  Debug
-  Info
-  Warn
-  Error
-}
-
-class PipelinePhase <<enumeration>> {
-  Startup
-  UserGeneration
-  BreweryAndBeerGeneration
-  CheckinGeneration
-  RatingGeneration
-  FollowGeneration
-  Teardown
-}
-
-struct LogEntry {
-  + timestamp : std::chrono::system_clock::time_point
-  + level : LogLevel
-  + phase : PipelinePhase
-  + message : std::string
-  + worker : std::optional<std::string>
-}
-
-interface ILogger <<interface>> {
-  + Log(entry : const LogEntry&) : void
-}
-
-class LogProducer {
-  - channel_ : BoundedChannel<LogEntry>&
-  + Log(entry : const LogEntry&) : void
-}
-
-class LogDispatcher {
-  - channel_ : BoundedChannel<LogEntry>&
-  + Run() : void
-  - ToSpdlogLevel(level) : spdlog::level::level_enum
-}
-
 interface IEnrichmentService <<interface>> {
   + GetLocationContext(loc : const Location&) : std::string
 }
@@ -164,17 +123,10 @@ class SystemDateTimeProvider {
 }
 
 ' Structural Relationships / Dependency Injection
-BiergartenDataGenerator *-- ILogger : owns
 BiergartenDataGenerator *-- IEnrichmentService : owns
 BiergartenDataGenerator *-- DataGenerator : owns
 BiergartenDataGenerator *-- IExportService : owns
 
-LogEntry *-- LogLevel
-LogEntry *-- PipelinePhase
-ILogger <|.. LogProducer : implements
-LogProducer ..> LogEntry : emits
-LogDispatcher ..> LogEntry : consumes
-
 IEnrichmentService <|.. WikipediaService : implements
 WikipediaService *-- WebClient : owns
 

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" {
 
@@ -275,29 +275,33 @@ package "Infrastructure: Logging" {
     + level : LogLevel
     + phase : PipelinePhase
     + message : std::string
+    + city : std::optional<std::string>
+    + entity_id : std::optional<std::string>
     + worker : std::optional<std::string>
   }
 
-  interface ILogger <<interface>> {
+  interface Logger <<interface>> {
-    + Log(entry : const LogEntry&) : void
+    + Log(level, phase, message,\n  city, entity_id, worker) : void
   }
 
-  class LogProducer {
+  class PipelineLogger {
-    - channel_ : BoundedChannel<LogEntry>&
+    - log_ch_ : BoundedChannel<LogEntry>&
-    + Log(entry : const LogEntry&) : void
+    + Log(level, phase, message,\n  city, entity_id, worker) : void
   }
 
-  class LogDispatcher {
+  class LogWorker {
-    - channel_ : BoundedChannel<LogEntry>&
+    - log_ch_ : BoundedChannel<LogEntry>&
     + Run() : void
+    - FormatTimestamp(tp) : std::string
     - ToSpdlogLevel(level) : spdlog::level::level_enum
+    - ToString(phase) : std::string
   }
 
+  ' --- Logging Relationships ---
   LogEntry       *--  LogLevel
   LogEntry       *--  PipelinePhase
-  ILogger        <|.. LogProducer
+  PipelineLogger ..>  LogEntry       : emits
-  LogProducer    ..>  LogEntry       : emits
+  LogWorker      ..>  LogEntry       : consumes
-  LogDispatcher  ..>  LogEntry       : consumes
 }
 
 package "Infrastructure: Pipeline Channel" {
@@ -359,22 +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>> {
@@ -398,7 +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
@@ -472,6 +459,8 @@ package "Infrastructure: Data Export" {
 
 }
 
+
+
 class BiergartenPipelineOrchestrator {
   - preloader_ : std::unique_ptr<DataPreloader>
   - enrichment_service_ : std::unique_ptr<EnrichmentService>
@@ -542,7 +531,6 @@ DateTimeProvider               <|.. SystemDateTimeProvider
 WikipediaService               *--  WebClient
 WikipediaService               ..>  ContextStrategy
 LlamaGenerator                 *--  PromptFormatter
-LlamaGenerator                 *--  IPromptDirectory
 LlamaGenerator                 ..>  GeneratorOptions
 SqliteExportService            *--  DateTimeProvider
 

tooling/pipeline/CMakeLists.txt

@@ -137,9 +137,7 @@ set(HTTPLIB_REQUIRE_OPENSSL ON CACHE BOOL "Require OpenSSL for cpp-httplib" FORC
 FetchContent_MakeAvailable(cpp-httplib)
 
 # 5. Executable & Sources
-add_executable(${PROJECT_NAME}
+add_executable(${PROJECT_NAME})
-        includes/services/enrichment/mock_enrichment.h
-        includes/json_handling/pretty_print.h)
 
 # --- Entry point ---
 target_sources(${PROJECT_NAME} PRIVATE
@@ -156,13 +154,13 @@ target_sources(${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 ---
@@ -196,30 +194,24 @@ endif()
 
 # --- services: wikipedia ---
 target_sources(${PROJECT_NAME} PRIVATE
-        src/services/enrichment/wikipedia/wikipedia_service.cc
+        src/services/wikipedia/wikipedia_service.cc
-        src/services/enrichment/wikipedia/fetch_extract.cc
+        src/services/wikipedia/fetch_extract.cc
-        src/services/enrichment/wikipedia/get_summary.cc
+        src/services/wikipedia/get_summary.cc
 )
 
 # --- services: sqlite ---
 target_sources(${PROJECT_NAME} PRIVATE
-	src/services/sqlite/process_record.cc
+        src/services/sqlite/process_record.cc
-	src/services/sqlite/sqlite_export_service.cc
+        src/services/sqlite/sqlite_export_service.cc
-	src/services/sqlite/finalize.cc
+        src/services/sqlite/finalize.cc
-	src/services/sqlite/initialize.cc
+        src/services/sqlite/initialize.cc
-	src/services/sqlite/helpers/sqlite_connection_helpers.cc
+        src/services/sqlite/helpers/sqlite_connection_helpers.cc
-	src/services/sqlite/helpers/sqlite_statement_helpers.cc
+        src/services/sqlite/helpers/sqlite_statement_helpers.cc
-)
-
-# --- services: logging ---
-target_sources(${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
+        src/services/prompt_directory.cc
 )
 
 # 6. Include Directories, Link Libraries & Compile Definitions
@@ -249,11 +241,6 @@ target_compile_definitions(${PROJECT_NAME} PRIVATE
         $<$<CONFIG:Debug>:DEBUG>
 )
 
-target_compile_options(biergarten-pipeline PRIVATE
-   -fmacro-prefix-map=${CMAKE_SOURCE_DIR}/tooling/pipeline/src/=
-)
-
-
 # 7. Runtime Assets
 configure_file(
         ${CMAKE_SOURCE_DIR}/locations.json
@@ -265,4 +252,3 @@ add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD
         ${CMAKE_SOURCE_DIR}/prompts
         ${CMAKE_BINARY_DIR}/prompts
 )
-

tooling/pipeline/includes/biergarten_data_generator.h

@@ -3,10 +3,7 @@
 
 /**
  * @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>
@@ -15,10 +12,8 @@
 
 #include "data_generation/data_generator.h"
 #include "data_model/generated_models.h"
-#include "services/database/export_service.h"
 #include "services/enrichment/enrichment_service.h"
-
+#include "services/database/export_service.h"
-#include "services/logging/logger.h"
 
 /**
  * @brief Main data generator class for the Biergarten pipeline.
@@ -26,22 +21,18 @@
  * 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.
+   */
- */
+  BiergartenDataGenerator(std::unique_ptr<IEnrichmentService> context_service,
-  BiergartenPipelineOrchestrator(
+                          std::unique_ptr<DataGenerator> generator,
-      std::shared_ptr<ILogger> logger,
+                          std::unique_ptr<IExportService> exporter);
-      std::unique_ptr<IEnrichmentService> context_service,
-      std::unique_ptr<DataGenerator> generator,
-      std::unique_ptr<IExportService> exporter,
-      const ApplicationOptions& application_options);
 
   /**
    * @brief Run the data generation pipeline.
@@ -51,38 +42,26 @@ class BiergartenPipelineOrchestrator {
    * 2. Resolve context for each city using the injected context service
    * 3. Generate brewery data for sampled cities
    *
-   * @note STRUCTURAL CONCURRENCY REQUIREMENT:
-   * When transitioned to a multithreaded design, this method MUST structurally
-   * enforce that all deployed worker threads are joined before returning (e.g.
-   * by using std::jthread or a structured concurrency primitive). This ensures
-   * workers do not attempt to log to a closed channel during application teardown.
-   *
    * @return true if successful, false if not
    */
   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_;
 
   /// @brief Generator dependency selected in the composition root.
   std::unique_ptr<DataGenerator> generator_;
 
-   /// @brief Storage backend for generated brewery records.
+  /// @brief Storage backend for generated brewery records.
-   std::unique_ptr<IExportService> exporter_;
+  std::unique_ptr<IExportService> exporter_;
-
-   /// @brief CLI configuration: paths, model settings, generation parameters.
-   ApplicationOptions application_options_;
 
   /**
    * @brief Load locations from JSON and sample cities.
    *
    * @return Vector of sampled locations capped at 50 entries.
    */
-  std::vector<Location> QueryCitiesWithCountries();
+  static std::vector<Location> QueryCitiesWithCountries();
 
   /**
    * @brief Generate breweries for enriched cities.

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 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;
@@ -38,7 +37,7 @@ class LlamaGenerator final : public DataGenerator {
    * @param prompt_directory Directory service for loading named prompt files.
    */
   LlamaGenerator(const ApplicationOptions& options,
-                 const std::string& model_path, std::shared_ptr<ILogger> logger,
+                 const std::string& model_path,
                  std::unique_ptr<IPromptFormatter> prompt_formatter,
                  std::unique_ptr<IPromptDirectory> prompt_directory);
 
@@ -131,7 +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_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;
 
 // ============================================================================
@@ -86,9 +83,6 @@ struct SamplingOptions {
 
   /// @brief Random seed (-1 for random, otherwise non-negative).
   int seed = -1;
-
-  /// @brief Number of layers to offload to GPU.
-  int n_gpu_layers = 0;
 };
 
 /**
@@ -101,7 +95,8 @@ struct GeneratorOptions {
   /// @brief Use mocked generator instead of actual LLM inference.
   bool use_mocked = false;
 
-
+  /// @brief Number of layers to offload to GPU.
+  int n_gpu_layers = 0;
 
   /// @brief Specific sampling parameters for this generator.
   /// If nullopt, the application should use global defaults.
@@ -121,10 +116,6 @@ struct PipelineOptions {
 
   /// @brief Path for application logs.
   std::filesystem::path log_path;
-
-  /// @brief Number of locations to sample from the dataset
-  /// More locations -> more users/more breweries
-  uint32_t location_count;
 };
 
 /**
@@ -139,7 +130,6 @@ 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/enrichment/mock_enrichment.h

@@ -1,17 +0,0 @@
-//
-// 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_
-#include <string>
-
-#include "enrichment_service.h"
-
-class MockEnrichmentService final : public IEnrichmentService {
- public:
-  std::string GetLocationContext(const Location& /*loc*/) override {
-    return {};
-  }
-};
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_MOCK_ENRICHMENT_H_

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

@@ -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 {
+class WikipediaService final : public IEnrichmentService {
  public:
   /// @brief Creates a new Wikipedia service with the provided web client.
-  explicit WikipediaEnrichmentService(std::unique_ptr<WebClient> client,
+  explicit WikipediaService(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

@@ -1,88 +0,0 @@
-/**
- * @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>.
- */
-
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_ENTRY_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_ENTRY_H_
-
-#include <chrono>
-#include <source_location>
-#include <string>
-#include <thread>
-#include <vector>
-
-/**
- * @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 LogDTO
- * @brief User-provided subset of log fields. Used to capture call-site info transparently.
- */
-struct LogDTO {
-  LogLevel level;
-  PipelinePhase phase;
-  std::string message;
-};
-
-/**
- * @struct LogEntry
- * @brief Single structured log event.
- *
- * All fields are value types, which keeps transfer across the bounded channel
- * simple and avoids shared ownership.
- *
- * NOTE: timestamp, thread_id, and origin must be populated by ILogger::Log()
- * before the entry is dispatched.
- */
-struct LogEntry {
-  /// @brief Timestamp when the entry was created.
-  std::chrono::system_clock::time_point timestamp{};
-
-  /// @brief Source location where the log call was made.
-  std::source_location origin{};
-
-  /// @brief Thread responsible for emitting the log.
-  std::thread::id thread_id{};
-
-
-  /// @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

@@ -1,53 +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_CHANNEL_LOGGER_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_CHANNEL_LOGGER_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. This blocking behavior
-   * under heavy load is an accepted trade-off for simplicity.
-   */
-  void DoLog(LogEntry log_entry) override;
-
- private:
-  BoundedChannel<LogEntry>& channel_;
-};
-
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_CHANNEL_LOGGER_H_

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

@@ -1,64 +0,0 @@
-/**
- * @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.
- */
-
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_
-
-#include <source_location>
-#include <string>
-#include <utility>
-
-#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 payload User-provided log data (level, phase, message).
-   * @param origin Auto-captured source location of the call site.
-   */
-  void Log(LogDTO payload,
-           std::source_location origin = std::source_location::current(),
-           std::chrono::system_clock::time_point timestamp = std::chrono::system_clock::now(),
-           std::thread::id thread_id = std::this_thread::get_id()) {
-    LogEntry entry;
-    entry.timestamp = timestamp;
-    entry.thread_id = thread_id;
-    entry.level = payload.level;
-    entry.phase = payload.phase;
-    entry.message = std::move(payload.message);
-    entry.origin = origin;
-    DoLog(std::move(entry));
-  }
-
- protected:
-  /**
-   * @brief Underlying implementation to transport the log entry.
-   *
-   * Implementations must be thread-safe as DoLog can be called concurrently
-   * from multiple worker threads.
-   */
-  virtual void DoLog(LogEntry log_entry) = 0;
-};
-
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_

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

@@ -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

@@ -8,11 +8,8 @@
 
 
 #include "web_client/web_client.h"
-#include "services/logging/logger.h"
 
-#include <memory>
 #include <string>
-#include <utility>
 
 /**
  * @brief WebClient implementation backed by cpp-httplib.
@@ -27,8 +24,7 @@
  */
 class HttpWebClient final : public WebClient {
 public:
-  explicit HttpWebClient(std::shared_ptr<ILogger> logger)
+  HttpWebClient() = default;
-      : logger_(std::move(logger)) {}
   ~HttpWebClient() override = default;
 
   /**
@@ -46,10 +42,7 @@ public:
    * @param value Raw string to encode.
    * @return Percent-encoded string safe for use in a URL.
    */
-  std::string EncodeURL(const std::string& value) override;
+  std::string UrlEncode(const std::string& value) override;
-
- private:
-  std::shared_ptr<ILogger> logger_;
 };
 
 

tooling/pipeline/includes/web_client/web_client.h

@@ -30,7 +30,7 @@ class WebClient {
    * @param value Raw string value.
    * @return Encoded value safe for URL usage.
    */
-  virtual std::string EncodeURL(const std::string& value) = 0;
+  virtual std::string UrlEncode(const std::string& value) = 0;
 };
 
 #endif  // BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_WEB_CLIENT_H_

tooling/pipeline/src/application_options/parse_arguments.cc

@@ -1,15 +1,12 @@
-#include <chrono>
+#include <spdlog/spdlog.h>
-#include <format>
+
-#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();
 
@@ -33,8 +30,6 @@ std::optional<ApplicationOptions> ParseArguments(
         "Context window size in tokens");
     opt("seed", prog_opts::value<int>()->default_value(sampling_defaults.seed),
         "Sampler seed: -1 for random, otherwise non-negative integer");
-    opt("n-gpu-layers", prog_opts::value<int>()->default_value(0),
-        "Number of layers to offload to GPU");
   };
 
   // --mocked and --model are mutually exclusive; validation is enforced below
@@ -55,7 +50,8 @@ std::optional<ApplicationOptions> ParseArguments(
     opt("prompt-dir", prog_opts::value<std::string>()->default_value(""),
         "Directory containing named prompt files (e.g. BREWERY_GENERATION.md)."
         " Required when not using --mocked.");
-    opt("location-count", prog_opts::value<uint32_t>()->default_value(10));
+    opt("n-gpu-layers", prog_opts::value<int>()->default_value(0),
+        "Number of layers to offload to GPU");
   };
 
   add_sampling_options();
@@ -64,20 +60,10 @@ 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;
-      std::stringstream usage_stream;
+    usage_stream << "\nUsage: biergarten-pipeline [options]\n\n" << desc;
-      usage_stream << "\nUsage: biergarten-pipeline [options]\n\n" << desc;
+    spdlog::info(usage_stream.str());
-      return usage_stream.str();
-    })();
-    if (logger) {
-      logger->Log(LogDTO{.level = LogLevel::Info,
-                   .phase = PipelinePhase::Startup,
-                   .message = title});
-      logger->Log(LogDTO{.level = LogLevel::Info,
-                   .phase = PipelinePhase::Startup,
-                   .message = usage});
-    }
     return std::nullopt;
   }
 
@@ -89,11 +75,7 @@ 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(LogDTO{.level = LogLevel::Info,
-                     .phase = PipelinePhase::Startup,
-                     .message = help_stream.str()});
-      }
       return std::nullopt;
     }
 
@@ -102,7 +84,6 @@ 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>();
 
     const bool use_mocked = var_map["mocked"].as<bool>();
     const std::string model_path = var_map["model"].as<std::string>();
@@ -110,49 +91,29 @@ 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(LogDTO{.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(LogDTO{.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;
     }
 
     options.generator.use_mocked = use_mocked;
     options.generator.model_path = model_path;
-    // options.generator.n_gpu_layers = n_gpu_layers;
+    options.generator.n_gpu_layers = n_gpu_layers;
 
     // Only populate sampling config when the user explicitly overrides at
     // least one value. Leaving it as std::nullopt lets LlamaGenerator fall
@@ -161,21 +122,13 @@ std::optional<ApplicationOptions> ParseArguments(
     const bool user_provided_sampling =
         !var_map["temperature"].defaulted() || !var_map["top-p"].defaulted() ||
         !var_map["top-k"].defaulted() || !var_map["n-ctx"].defaulted() ||
-        !var_map["seed"].defaulted() || !var_map["n_gpu_layers"].defaulted();
+        !var_map["seed"].defaulted();
 
     if (user_provided_sampling) {
       // 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(LogDTO{.level = LogLevel::Warn,
-                       .phase = PipelinePhase::Startup,
-                       .message = msg});
-        } else {
-          std::cerr << msg << std::endl;
-        }
       } else {
         SamplingOptions sampling;
         sampling.temperature = var_map["temperature"].as<float>();
@@ -183,7 +136,6 @@ std::optional<ApplicationOptions> ParseArguments(
         sampling.top_k = var_map["top-k"].as<uint32_t>();
         sampling.n_ctx = var_map["n-ctx"].as<uint32_t>();
         sampling.seed = var_map["seed"].as<int>();
-        sampling.n_gpu_layers = var_map["n-gpu-layers"].as<int>();
 
         options.generator.sampling = sampling;
       }
@@ -192,23 +144,11 @@ 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(LogDTO{.level = LogLevel::Error,
-                   .phase = PipelinePhase::Startup,
-                   .message = msg});
-    }
     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(LogDTO{.level = LogLevel::Error,
-                   .phase = PipelinePhase::Startup,
-                   .message = msg});
-    }
     return std::nullopt;
   }
 }

tooling/pipeline/src/biergarten_data_generator/biergarten_data_generator.cc

@@ -0,0 +1,16 @@
+/**
+ * @file biergarten_data_generator/biergarten_data_generator.cc
+ * @brief BiergartenDataGenerator constructor implementation.
+ */
+
+#include "biergarten_data_generator.h"
+
+#include <utility>
+
+BiergartenDataGenerator::BiergartenDataGenerator(
+    std::unique_ptr<IEnrichmentService> context_service,
+    std::unique_ptr<DataGenerator> generator,
+    std::unique_ptr<IExportService> exporter)
+    : context_service_(std::move(context_service)),
+      generator_(std::move(generator)),
+      exporter_(std::move(exporter)) {}

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"
+
+static constexpr size_t kBreweryAmount = 50;
+
+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(kBreweryAmount, 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.country, 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/biergarten_pipeline_orchestrator.cc

@@ -1,20 +0,0 @@
-/**
- * @file biergarten_pipeline_orchestrator/biergarten_pipeline_orchestrator.cc
- * @brief BiergartenDataGenerator constructor implementation.
- */
-
-#include "biergarten_pipeline_orchestrator.h"
-
-#include <utility>
-
-BiergartenPipelineOrchestrator::BiergartenPipelineOrchestrator(
-    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)),
-      generator_(std::move(generator)),
-      exporter_(std::move(exporter)),
-      application_options_(app_options) {}

tooling/pipeline/src/biergarten_pipeline_orchestrator/generate_breweries.cc

@@ -1,68 +0,0 @@
-/**
- * @file biergarten_pipeline_orchestrator/generate_breweries.cc
- * @brief BiergartenDataGenerator::GenerateBreweries() implementation.
- */
-
-#include <chrono>
-#include <format>
-
-#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::format("[Pipeline] Generated brewery for '{}' ({}) but SQLite export failed: {}",
-                 location.city, location.country, export_exception.what())});
-      }
-    } catch (const std::exception& e) {
-      ++skipped_count;
-
-      logger_->Log({.level = LogLevel::Warn,
-                    .phase = PipelinePhase::BreweryAndBeerGeneration,
-                    .message = std::format("[Pipeline] Skipping city '{}' ({}): brewery generation failed: {}",
-                               location.city, location.country, e.what())});
-    }
-  }
-
-  if (skipped_count > 0) {
-    logger_->Log({.level = LogLevel::Warn,
-                  .phase = PipelinePhase::BreweryAndBeerGeneration,
-                  .message = std::format(
-                      "[Pipeline] Skipped {} city/cities due to generation errors",
-                      skipped_count)});
-  }
-
-  if (export_failed_count > 0) {
-    logger_->Log({.level = LogLevel::Warn,
-                  .phase = PipelinePhase::Teardown,
-                  .message = std::format(
-                      "[Pipeline] Failed to export {} generated brewery/breweries to SQLite",
-                      export_failed_count)});
-  }
-}

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

@@ -1,63 +0,0 @@
-/**
- * @file biergarten_pipeline_orchestrator/run.cc
- * @brief BiergartenDataGenerator::Run() implementation.
- */
-
-#include <chrono>
-#include <format>
-#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::format(
-                 "[Pipeline] Skipping city '{}' ({}): context lookup failed: {}",
-                 city.city, city.country, exception.what())});
-      }
-    }
-
-    if (skipped_count > 0) {
-      logger_->Log({.level = LogLevel::Warn,
-                    .phase = PipelinePhase::UserGeneration,
-                    .message = std::format(
-                        "[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) {
-    logger_->Log(
-        {.level = LogLevel::Error,
-         .phase = PipelinePhase::Teardown,
-         .message =
-             std::format("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::format("LlamaGenerator: raw output (attempt {}): {}",
-                      attempt + 1, raw)});
-    }
 
     // Validate output: parse JSON and check required fields
 
@@ -116,13 +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::format("LlamaGenerator: successfully generated brewery data on attempt {}",
-                        attempt + 1)});
-      }
 
       return brewery;
     }
@@ -130,14 +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::format("LlamaGenerator: malformed brewery JSON (attempt {}): {}",
-               attempt + 1, *validation_error)});
-    }
 
     // Update prompt with error details to guide LLM toward correct output.
     user_prompt = std::format(
@@ -154,13 +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::format(
-         "LlamaGenerator: malformed brewery response after {} attempts: {}",
-         max_attempts, last_error.empty() ? raw : last_error)});
-  }
   throw std::runtime_error("LlamaGenerator: malformed brewery response");
 }

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

@@ -4,8 +4,9 @@
  * retry handling, and output sanitization for downstream parsing.
  */
 
+#include <spdlog/spdlog.h>
 
-#include <format>
+#include <stdexcept>
 #include <string>
 
 #include "data_generation/llama_generator.h"
@@ -20,5 +21,5 @@
 // 4. Return locale-aware username and biography
 UserResult LlamaGenerator::GenerateUser(const std::string& locale) {
   return {.username = "test_user",
-          .bio = std::format("This is a test user profile from {}.", locale)};
+          .bio = "This is a test user profile from " + locale + "."};
 }

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()) {
@@ -91,7 +89,7 @@ LlamaGenerator::LlamaGenerator(
   }
 
   n_ctx_ = sampling.n_ctx;
-  n_gpu_layers_ = sampling.n_gpu_layers;
+  n_gpu_layers_ = options.generator.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

@@ -6,9 +6,7 @@
 
 #include "json_handling/json_loader.h"
 
-#include <format>
+#include <spdlog/spdlog.h>
-#include "services/logging/logger.h"
-#include <iostream>
 
 #include <boost/json.hpp>
 #include <fstream>
@@ -21,8 +19,8 @@ static std::string ReadRequiredString(const boost::json::object& object,
                                       const char* key) {
   const boost::json::value* value = object.if_contains(key);
   if (value == nullptr || !value->is_string()) {
-    throw std::runtime_error(
+    throw std::runtime_error(std::string("Missing or invalid string field: ") +
-        std::format("Missing or invalid string field: {}", key));
+                             key);
   }
   const std::string_view text = value->as_string();
   return std::string(text);
@@ -32,8 +30,8 @@ static double ReadRequiredNumber(const boost::json::object& object,
                                  const char* key) {
   const boost::json::value* value = object.if_contains(key);
   if (value == nullptr || !value->is_number()) {
-    throw std::runtime_error(
+    throw std::runtime_error(std::string("Missing or invalid numeric field: ") +
-        std::format("Missing or invalid numeric field: {}", key));
+                             key);
   }
   return value->to_number<double>();
 }
@@ -43,7 +41,7 @@ static std::vector<std::string> ReadRequiredStringArray(
   const boost::json::value* value = object.if_contains(key);
   if (value == nullptr || !value->is_array()) {
     throw std::runtime_error(
-      std::format("Missing or invalid string array field: {}", key));
+        std::string("Missing or invalid string array field: ") + key);
   }
 
   const auto& array = value->as_array();
@@ -52,7 +50,7 @@ static std::vector<std::string> ReadRequiredStringArray(
   for (const auto& item : array) {
     if (!item.is_string()) {
       throw std::runtime_error(
-          std::format("Missing or invalid string array field: {}", key));
+          std::string("Missing or invalid string array field: ") + key);
     }
     items.emplace_back(item.as_string());
   }
@@ -60,7 +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: " +
@@ -106,5 +104,7 @@ std::vector<Location> JsonLoader::LoadLocations(
     });
   }
 
+  spdlog::info("[JsonLoader] Loaded {} locations from {}", locations.size(),
+               filepath.string());
   return locations;
 }

tooling/pipeline/src/main.cc

@@ -4,77 +4,48 @@
  * 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 <string>
-#include "concurrency/bounded_channel.h"
+
+#include "biergarten_data_generator.h"
 #include "data_generation/llama_generator.h"
 #include "data_generation/mock_generator.h"
 #include "data_generation/prompt_formatting/gemma4_jinja_prompt_formatter.h"
 #include "data_model/models.h"
 #include "llama_backend_state.h"
+#include "services/enrichment/enrichment_service.h"
 #include "services/database/export_service.h"
+#include "services/prompting/prompt_directory.h"
 #include "services/database/sqlite_export_service.h"
 #include "services/datetime/timer.h"
-#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
+    spdlog::set_level(spdlog::level::debug);
+#endif
 
-    log_producer->Log({.level   = LogLevel::Info,
+    const auto parsed_options = ParseArguments(argc, argv);
-                       .phase   = PipelinePhase::Startup,
-                       .message = "STARTING PIPELINE"});
-
-    const std::optional<ApplicationOptions> parsed_options =
-        ParseArguments(argc, argv, log_producer);
-
     if (!parsed_options.has_value()) {
-      return shutdown(EXIT_FAILURE);
+      return 0;
     }
 
     const auto options = *parsed_options;
@@ -83,136 +54,55 @@ 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<WebClient>().to<HttpWebClient>(),
         di::bind<ApplicationOptions>().to(options),
-        di::bind<std::string>().to(model_path),
+        di::bind<IEnrichmentService>().to<WikipediaService>(),
         di::bind<IExportService>().to<SqliteExportService>(),
-        di::bind<IPromptFormatter>().to([options, log_producer] {
+        di::bind<IPromptFormatter>().to<Gemma4JinjaPromptFormatter>(),
-          if (options.generator.use_mocked) {
+        di::bind<std::string>().to(model_path),
-            {
-              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](
-                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>>(),
-                  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(
+                  model_path, sampling.temperature, sampling.top_p,
-                         "Generator: LlamaGenerator | model={} | temp={:.2f} "
+                  sampling.top_k, sampling.n_ctx, sampling.seed);
-                         "top_p={:.2f} top_k={} n_ctx={} seed={}",
-                         model_path, sampling.temperature, sampling.top_p,
-                         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 =
+    auto generator =
-        injector.create<std::unique_ptr<BiergartenPipelineOrchestrator>>();
+        injector.create<std::unique_ptr<BiergartenDataGenerator>>();
 
-    if (!orchestrator->Run()) {
+    if (!generator->Run()) {
-      log_producer->Log({.level   = LogLevel::Error,
+      spdlog::error("Pipeline execution failed");
-                         .phase   = PipelinePhase::Teardown,
+      return 1;
-                         .message = "Pipeline execution failed"});
-      return shutdown(EXIT_FAILURE);
     }
 
-    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 LogDTO 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

@@ -1,160 +0,0 @@
-/**
- * @file wikipedia/fetch_extract.cc
- */
-
-#include <boost/json.hpp>
-#include <chrono>
-#include <format>
-#include <string>
-#include <string_view>
-#include <thread>
-
-#include "services/enrichment/wikipedia_service.h"
-
-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_) {
-      logger_->Log({.level = LogLevel::Debug,
-                    .phase = PipelinePhase::UserGeneration,
-                    .message = std::format("Wikipedia: Cache hit for {}!", cache_key)});
-    }
-    return cache_it->second;
-  }
-
-  const std::string encoded = this->client_->EncodeURL(cache_key);
-  const std::string url = std::format(
-      "https://en.wikipedia.org/w/"
-      "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;
-    std::this_thread::sleep_for(1s);
-  }
-
-  // 2. Parse JSON
-  system::error_code ec;
-  json::value doc = json::parse(body, ec);
-
-  if (ec) {
-    if (logger_) {
-      logger_->Log(
-          {.level = LogLevel::Warn,
-           .phase = PipelinePhase::UserGeneration,
-           .message = std::format("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_) {
-      logger_->Log(
-          {.level = LogLevel::Warn,
-           .phase = PipelinePhase::UserGeneration,
-           .message =
-               std::format("WikipediaService: Expected root object for '{}'",
-               std::string(query))});
-    }
-    return {};
-  }
-
-  const json::value* query_ptr = obj->if_contains("query");
-  const json::value* pages_ptr =
-      ((query_ptr != nullptr) && query_ptr->is_object())
-          ? query_ptr->get_object().if_contains("pages")
-          : nullptr;
-
-  if ((pages_ptr == nullptr) || !pages_ptr->is_object()) {
-    if (logger_) {
-      logger_->Log(
-          {.level = LogLevel::Warn,
-           .phase = PipelinePhase::UserGeneration,
-           .message =
-               std::format("WikipediaService: Missing query.pages for '{}'",
-               std::string(query))});
-    }
-    return {};
-  }
-
-  const json::object& pages = pages_ptr->get_object();
-
-  if (pages.empty()) {
-    if (logger_) {
-      logger_->Log(
-          {.level = LogLevel::Warn,
-           .phase = PipelinePhase::UserGeneration,
-           .message = std::format("WikipediaService: No pages returned for '{}'",
-                      std::string(query))});
-    }
-    this->extract_cache_.emplace(cache_key, "");
-    return {};
-  }
-
-  // Wikipedia returns the page under a dynamic ID key; we just want the first
-  // one
-  const json::value& page_val = pages.begin()->value();
-
-  if (!page_val.is_object()) {
-    if (logger_) {
-      logger_->Log(
-          {.level = LogLevel::Warn,
-           .phase = PipelinePhase::UserGeneration,
-           .message =
-               std::format("WikipediaService: Unexpected page format for '{}'",
-               std::string(query))});
-    }
-    return {};
-  }
-
-  const json::object& page = page_val.get_object();
-
-  // Handle 404/Missing status
-  if (page.contains("missing")) {
-    if (logger_) {
-      logger_->Log({.level = LogLevel::Warn,
-                    .phase = PipelinePhase::UserGeneration,
-                    .message = std::format("WikipediaService: Page '{}' does not exist",
-                               std::string(query))});
-    }
-    this->extract_cache_.emplace(cache_key, "");
-    return {};
-  }
-
-  const json::value* extract_ptr = page.if_contains("extract");
-
-  if ((extract_ptr == nullptr) || !extract_ptr->is_string()) {
-    if (logger_) {
-      logger_->Log(
-          {.level = LogLevel::Warn,
-           .phase = PipelinePhase::UserGeneration,
-           .message =
-               std::format("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_) {
-    logger_->Log({.level = LogLevel::Info,
-                  .phase = PipelinePhase::UserGeneration,
-                  .message = std::format("WikipediaService: Fetched {} chars for '{}'",
-                             extract.size(), std::string(query))});
-  }
-
-  this->extract_cache_.insert_or_assign(cache_key, extract);
-
-  return extract;
-}

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

@@ -1,70 +0,0 @@
-/**
- * @file wikipedia/get_summary.cc
- * @brief WikipediaService::GetLocationContext() implementation.
- */
-
-#include <chrono>
-#include <format>
-#include <string>
-#include <thread>
-
-#include "services/enrichment/wikipedia_service.h"
-
-std::string WikipediaEnrichmentService::GetLocationContext(
-    const Location& loc) {
-  using namespace std::literals::chrono_literals;
-  if (!this->client_) {
-    if (logger_) {
-      logger_->Log({.level = LogLevel::Warn,
-                    .phase = PipelinePhase::UserGeneration,
-                    .message = "Wikipedia client is nullptr."});
-    }
-    return {};
-  }
-
-  std::string result;
-
-  // std::string region_query(loc.city);
-  // if (!loc.country.empty()) {
-  //   region_query += loc.state_province,
-  //   region_query += ", ";
-  //   region_query += loc.country;
-  // }
-
-  constexpr std::string_view brewing_query = "brewing";
-  const std::string location_query =
-      std::format("{}, {}", loc.city, loc.iso3166_2);
-  const std::string beer_query = std::format("beer in {}", loc.country);
-
-  auto append_extract = [&result](const std::string& extract) -> void {
-    if (extract.empty()) {
-      return;
-    }
-    if (!result.empty()) {
-      result += "\n\n";
-    }
-    result += extract;
-  };
-
-  try {
-    append_extract(FetchExtract(brewing_query));
-    append_extract(FetchExtract(beer_query));
-    if (logger_) {
-      logger_->Log({.level = LogLevel::Info,
-                    .phase = PipelinePhase::UserGeneration,
-                    .message = std::format("Done fetching for {}. Sleeping for 10 seconds.",
-                               location_query)});
-    }
-    std::this_thread::sleep_for(10s);
-
-  } catch (const std::runtime_error& e) {
-    if (logger_) {
-      logger_->Log(
-          {.level = LogLevel::Debug,
-           .phase = PipelinePhase::UserGeneration,
-           .message = std::format("WikipediaService lookup failed for '{}': {}",
-                      location_query, e.what())});
-    }
-  }
-  return result;
-}

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

@@ -1,12 +0,0 @@
-/**
- * @file services/wikipedia/wikipedia_service.cc
- * @brief WikipediaService constructor implementation.
- */
-
-#include "services/enrichment/wikipedia_service.h"
-
-#include <utility>
-
-WikipediaEnrichmentService::WikipediaEnrichmentService(
-    std::unique_ptr<WebClient> client, std::shared_ptr<ILogger> logger)
-    : client_(std::move(client)), logger_(std::move(logger)) {}

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

@@ -1,74 +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"
-
-namespace {
-[[nodiscard]] constexpr std::string_view PipelinePhaseToString(
-    PipelinePhase phase) {
-  switch (phase) {
-    case PipelinePhase::Startup:
-      return "Startup";
-    case PipelinePhase::UserGeneration:
-      return "User Generation";
-    case PipelinePhase::BreweryAndBeerGeneration:
-      return "Brewery & Beer Gen";
-    case PipelinePhase::CheckinGeneration:
-      return "Checkin Gen";
-    case PipelinePhase::RatingGeneration:
-      return "Rating Gen";
-    case PipelinePhase::FollowGeneration:
-      return "Follow Gen";
-    case PipelinePhase::Teardown:
-      return "Teardown";
-  }
-  return "Unknown";
-}
-}  // namespace
-
-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),
-                "{:<20} │ thread: {:016x} │ [{}:{}] │ {}",
-                PipelinePhaseToString(log.phase),
-                std::hash<std::thread::id>{}(log.thread_id),
-                log.origin.file_name(), log.origin.line(), 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::DoLog(LogEntry entry) { channel_.Send(std::move(entry)); }

tooling/pipeline/src/services/prompt_directory.cc

@@ -6,25 +6,20 @@
 
 #include "services/prompting/prompt_directory.h"
 
-#include <chrono>
+#include <spdlog/spdlog.h>
+
 #include <filesystem>
-#include <format>
 #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.
@@ -45,18 +40,12 @@ PromptDirectory::PromptDirectory(const std::filesystem::path& prompt_dir,
   std::filesystem::directory_iterator probe(prompt_dir_, ec);
   if (ec) {
     throw std::runtime_error(
-        std::format("PromptDirectory: prompt directory is not readable: {} ({})",
+        "PromptDirectory: prompt directory is not readable: " +
-        prompt_dir_.string(), ec.message()));
+        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) {
@@ -70,13 +59,13 @@ std::string PromptDirectory::Load(std::string_view key) {
 
   // Scenario 3: resolve <prompt_dir>/<key>.md and require it to exist.
   const std::filesystem::path file_path =
-      prompt_dir_ / std::filesystem::path(std::format("{}.md", key_str));
+      prompt_dir_ / std::filesystem::path(key_str + ".md");
 
   std::ifstream file(file_path);
   if (!file.is_open()) {
     throw std::runtime_error(
-        std::format("PromptDirectory: prompt file not found for key '{}': {}",
+        "PromptDirectory: prompt file not found for key '" + key_str +
-        key_str, file_path.string()));
+        "': " + file_path.string());
   }
 
   std::string content((std::istreambuf_iterator<char>(file)),
@@ -84,16 +73,12 @@ std::string PromptDirectory::Load(std::string_view key) {
   file.close();
 
   if (content.empty()) {
-    throw std::runtime_error(std::format("PromptDirectory: prompt file for key '{}' is empty: {}",
+    throw std::runtime_error("PromptDirectory: prompt file for key '" +
-                             key_str, file_path.string()));
+                             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::format("[PromptDirectory] Loaded prompt '{}' from '{}' ({} chars)",
-                             key_str, file_path.string(), content.size())});
-  }
 
   cache_.emplace(key_str, content);
   return content;

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

@@ -1,6 +1,5 @@
 #include "services/database/sqlite_connection_helpers.h"
 
-#include <format>
 #include <stdexcept>
 
 namespace sqlite_export_service_internal {
@@ -21,7 +20,7 @@ void SqliteStatementDeleter::operator()(
 void ThrowSqliteError(sqlite3* db_handle, std::string_view action) {
   const std::string message =
       db_handle != nullptr ? sqlite3_errmsg(db_handle) : "unknown SQLite error";
-  throw std::runtime_error(std::format("{}: {}", action, message));
+  throw std::runtime_error(std::string(action) + ": " + message);
 }
 
 SqliteDatabaseHandle OpenDatabase(const std::filesystem::path& path) {
@@ -51,7 +50,7 @@ void ExecSql(const SqliteDatabaseHandle& db_handle, std::string_view sql,
                                     ? error_message
                                     : sqlite3_errmsg(db_handle.get());
     sqlite3_free(error_message);
-    throw std::runtime_error(std::format("{}: {}", action, message));
+    throw std::runtime_error(std::string(action) + ": " + message);
   }
 }
 

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

@@ -4,7 +4,6 @@
  */
 
 #include <filesystem>
-#include <format>
 #include <memory>
 #include <stdexcept>
 #include <string>
@@ -19,8 +18,8 @@ std::filesystem::path SqliteExportService::BuildDatabasePath() const {
 
   for (int suffix = 1; std::filesystem::exists(candidate); ++suffix) {
     candidate = output_path_ /
-                std::filesystem::path(std::format("biergarten_seed_{}-{}.sqlite",
+                std::filesystem::path("biergarten_seed_" + run_timestamp_utc_ +
-                                      run_timestamp_utc_, suffix));
+                                      "-" + std::to_string(suffix) + ".sqlite");
   }
 
   return candidate;

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

@@ -0,0 +1,61 @@
+/**
+ * @file wikipedia/fetch_extract.cc
+ * @brief WikipediaService::FetchExtract() implementation.
+ */
+
+#include <spdlog/spdlog.h>
+
+#include <boost/json.hpp>
+#include <string>
+#include <string_view>
+
+#include "services/enrichment/wikipedia_service.h"
+
+std::string WikipediaService::FetchExtract(std::string_view query) {
+  const std::string cache_key(query);
+  const auto cache_it = this->extract_cache_.find(cache_key);
+  if (cache_it != this->extract_cache_.end()) {
+    return cache_it->second;
+  }
+
+  const std::string encoded = this->client_->UrlEncode(cache_key);
+  const std::string url =
+      "https://en.wikipedia.org/w/api.php?action=query&titles=" + encoded +
+      "&prop=extracts&explaintext=1&format=json";
+
+  const std::string body = this->client_->Get(url);
+
+  boost::system::error_code parse_error;
+  boost::json::value doc = boost::json::parse(body, parse_error);
+
+  if (!parse_error && doc.is_object()) {
+    try {
+      auto& pages = doc.at("query").at("pages").get_object();
+      if (!pages.empty()) {
+        auto& page = pages.begin()->value().get_object();
+        if (page.contains("extract") && page.at("extract").is_string()) {
+          const std::string_view extract_view = page.at("extract").as_string();
+          std::string extract(extract_view);
+
+          spdlog::debug("WikipediaService fetched {} chars for '{}'",
+                        extract.size(), query);
+
+          this->extract_cache_.emplace(cache_key, extract);
+          return extract;
+        }
+      }
+      this->extract_cache_.emplace(cache_key, std::string{});
+    } catch (const std::exception& e) {
+      spdlog::warn(
+          "WikipediaService: failed to parse response structure for '{}': "
+          "{}",
+          query, e.what());
+      return {};
+    }
+  } else if (parse_error) {
+    spdlog::warn("WikipediaService: JSON parse error for '{}': {}", query,
+                 parse_error.message());
+  }
+
+  return {};
+}

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

@@ -0,0 +1,47 @@
+/**
+ * @file wikipedia/get_summary.cc
+ * @brief WikipediaService::GetLocationContext() implementation.
+ */
+
+#include <spdlog/spdlog.h>
+
+#include <string>
+
+#include "services/enrichment/wikipedia_service.h"
+
+std::string WikipediaService::GetLocationContext(const Location& loc) {
+  if (!client_) {
+    return {};
+  }
+
+  std::string result;
+
+  std::string region_query(loc.city);
+  if (!loc.country.empty()) {
+    region_query += ", ";
+    region_query += loc.country;
+  }
+
+  const std::string beer_query = "beer in " + loc.country;
+  const std::string city_beer_query = "beer in " + loc.city;
+
+  auto append_extract = [&result](const std::string& extract) -> void {
+    if (extract.empty()) {
+      return;
+    }
+    if (!result.empty()) {
+      result += "\n\n";
+    }
+    result += extract;
+  };
+
+  try {
+    append_extract(FetchExtract(region_query));
+    append_extract(FetchExtract(beer_query));
+    append_extract(FetchExtract(city_beer_query));
+  } catch (const std::runtime_error& e) {
+    spdlog::debug("WikipediaService lookup failed for '{}': {}", region_query,
+                  e.what());
+  }
+  return result;
+}

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

@@ -0,0 +1,11 @@
+/**
+ * @file services/wikipedia/wikipedia_service.cc
+ * @brief WikipediaService constructor implementation.
+ */
+
+#include "services/enrichment/wikipedia_service.h"
+
+#include <utility>
+
+WikipediaService::WikipediaService(std::unique_ptr<WebClient> client)
+    : client_(std::move(client)) {}

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.
  */
 
@@ -7,15 +7,11 @@
 
 #include <httplib.h>
 
-#include <chrono>
-#include <format>
 #include <regex>
 #include <stdexcept>
 #include <string>
 #include <utility>
 
-#include "services/logging/logger.h"
-
 namespace {
 constexpr time_t kConnectionTimeoutSeconds = 5;
 constexpr time_t kReadTimeoutSeconds = 10;
@@ -33,7 +29,7 @@ std::pair<std::string, std::string> SplitUrl(const std::string& url) {
 
   return {match[1].str(), match[2].matched ? match[2].str() : "/"};
 }
-}  // namespace
+} // namespace
 
 std::string HttpWebClient::Get(const std::string& url) {
   const auto [origin, path] = SplitUrl(url);
@@ -42,32 +38,24 @@ 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"},
-                              {"User-Agent", "biergarten-pipeline/1.0"}});
 
-  const httplib::Result result = client.Get(path);
+  const auto result = client.Get(path);
 
   if (!result) {
-    throw std::runtime_error(std::format(
+    throw std::runtime_error(
-        "[HttpWebClient] Request failed for URL: {} — {}", url,
+        "[HttpWebClient] Request failed for URL: " + url +
-        httplib::to_string(result.error())));
+        " — " + httplib::to_string(result.error()));
   }
 
   if (result->status < kSuccessMin || result->status >= kSuccessMax) {
-    if (logger_) {
+    throw std::runtime_error(
-      logger_->Log(
+        "[HttpWebClient] HTTP " + std::to_string(result->status) +
-          {.level = LogLevel::Error,
+        " for URL: " + url);
-           .phase = PipelinePhase::UserGeneration,
-         .message =
-           std::format("[HttpWebClient] Request failed for URL: {}", url)});
-    }
-    throw std::runtime_error(std::format("[HttpWebClient] HTTP {} for URL: {}",
-                       result->status, url));
   }
 
   return result->body;
 }
 
-std::string HttpWebClient::EncodeURL(const std::string& value) {
+std::string HttpWebClient::UrlEncode(const std::string& value) {
   return httplib::encode_uri_component(value);
 }