logging updates

* Add timeout for enrichment, refactor json deserialization

* Add location count to application options and as a cli arg

* Add mock enrichment process

docs/pipeline/diagrams/planned/class.puml

@@ -1,4 +1,4 @@
-@startuml
+@startuml class_diagram
 
 ' ==========================================
 ' CONFIGURATION & STYLING
@@ -8,6 +8,8 @@ skinparam classAttributeFontSize 9
 skinparam defaultFontSize 25
 skinparam titleFontSize 30
 
+title Biergarten Data Pipeline — Class Diagram
+
 package "Domain: Models" {
 
   class Location {
@@ -141,7 +143,7 @@ package "Domain: Models" {
 
   LocationContext *-- Completeness
 }
-@startuml
+
 package "Domain: Application Configuration" {
   class SamplingOptions {
     + temperature: float = 1.0F
@@ -167,12 +169,10 @@ package "Domain: Application Configuration" {
     + pipeline: PipelineOptions
   }
 
-  ' --- Domain Model Relationships ---
   ApplicationOptions *-- GeneratorOptions
   ApplicationOptions *-- PipelineOptions
   GeneratorOptions o-- SamplingOptions
 }
-@endum
 
 package "Domain: Policy" {
 
@@ -297,7 +297,6 @@ package "Infrastructure: Logging" {
     - ToString(phase) : std::string
   }
 
-  ' --- Logging Relationships ---
   LogEntry       *--  LogLevel
   LogEntry       *--  PipelinePhase
   PipelineLogger ..>  LogEntry       : emits
@@ -363,6 +362,22 @@ 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>> {
@@ -386,6 +401,7 @@ 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
@@ -459,8 +475,6 @@ package "Infrastructure: Data Export" {
 
 }
 
-
-
 class BiergartenPipelineOrchestrator {
   - preloader_ : std::unique_ptr<DataPreloader>
   - enrichment_service_ : std::unique_ptr<EnrichmentService>
@@ -531,6 +545,7 @@ DateTimeProvider               <|.. SystemDateTimeProvider
 WikipediaService               *--  WebClient
 WikipediaService               ..>  ContextStrategy
 LlamaGenerator                 *--  PromptFormatter
+LlamaGenerator                 *--  IPromptDirectory
 LlamaGenerator                 ..>  GeneratorOptions
 SqliteExportService            *--  DateTimeProvider
 

tooling/pipeline/CMakeLists.txt

@@ -137,7 +137,9 @@ 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(${PROJECT_NAME} PRIVATE
@@ -154,13 +156,13 @@ target_sources(${PROJECT_NAME} PRIVATE
         src/application_options/parse_arguments.cc
 )
 
-# --- biergarten_data_generator ---
+# --- biergarten_pipeline_orchestrator ---
 target_sources(${PROJECT_NAME} PRIVATE
-        src/biergarten_data_generator/log_results.cc
-        src/biergarten_data_generator/biergarten_data_generator.cc
-        src/biergarten_data_generator/generate_breweries.cc
-        src/biergarten_data_generator/run.cc
-        src/biergarten_data_generator/query_cities_with_countries.cc
+        src/biergarten_pipeline_orchestrator/log_results.cc
+        src/biergarten_pipeline_orchestrator/biergarten_pipeline_orchestrator.cc
+        src/biergarten_pipeline_orchestrator/generate_breweries.cc
+        src/biergarten_pipeline_orchestrator/run.cc
+        src/biergarten_pipeline_orchestrator/query_cities_with_countries.cc
 )
 
 # --- web_client ---
@@ -194,24 +196,30 @@ endif()
 
 # --- services: wikipedia ---
 target_sources(${PROJECT_NAME} PRIVATE
-        src/services/wikipedia/wikipedia_service.cc
-        src/services/wikipedia/fetch_extract.cc
-        src/services/wikipedia/get_summary.cc
+        src/services/enrichment/wikipedia/wikipedia_service.cc
+        src/services/enrichment/wikipedia/fetch_extract.cc
+        src/services/enrichment/wikipedia/get_summary.cc
 )
 
 # --- services: sqlite ---
 target_sources(${PROJECT_NAME} PRIVATE
-        src/services/sqlite/process_record.cc
-        src/services/sqlite/sqlite_export_service.cc
-        src/services/sqlite/finalize.cc
-        src/services/sqlite/initialize.cc
-        src/services/sqlite/helpers/sqlite_connection_helpers.cc
-        src/services/sqlite/helpers/sqlite_statement_helpers.cc
+	src/services/sqlite/process_record.cc
+	src/services/sqlite/sqlite_export_service.cc
+	src/services/sqlite/finalize.cc
+	src/services/sqlite/initialize.cc
+	src/services/sqlite/helpers/sqlite_connection_helpers.cc
+	src/services/sqlite/helpers/sqlite_statement_helpers.cc
+)
+
+# --- services: logging ---
+target_sources(${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

tooling/pipeline/includes/biergarten_pipeline_orchestrator.h

@@ -1,9 +1,12 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_PIPELINE_ORCHESTRATOR_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_PIPELINE_ORCHESTRATOR_H_
 
 /**
- * @file biergarten_data_generator.h
- * @brief Core orchestration class for pipeline data generation.
+ * @file biergarten_pipeline_orchestrator.h
+ * @brief Orchestration for end-to-end brewery data generation pipeline.
+ *
+ * Intent: Coordinates location loading, enrichment, and generation phases
+ * to produce a complete dataset. Coordinates dependencies via composition root.
  */
 
 #include <memory>
@@ -12,8 +15,10 @@
 
 #include "data_generation/data_generator.h"
 #include "data_model/generated_models.h"
-#include "services/enrichment/enrichment_service.h"
 #include "services/database/export_service.h"
+#include "services/enrichment/enrichment_service.h"
+
+#include "services/logging/logger.h"
 
 /**
  * @brief Main data generator class for the Biergarten pipeline.
@@ -21,18 +26,22 @@
  * This class encapsulates the core logic for generating brewery data.
  * It handles location loading, city enrichment, and brewery generation.
  */
-class BiergartenDataGenerator {
+class BiergartenPipelineOrchestrator {
  public:
   /**
-   * @brief Construct a BiergartenDataGenerator with injected dependencies.
+   * @brief Constructs the orchestrator with injected pipeline dependencies.
    *
-   * @param context_service Context provider for sampled locations.
-   * @param generator Brewery and user data generator.
-   * @param exporter Storage backend for generated brewery data.
+   * @param context_service Provides regional context for locations.
+   * @param generator Implementation (Llama or Mock) for brewery/user generation.
+   * @param exporter Database backend for persisting generated records.
+   * @param application_options CLI configuration and paths.
    */
-  BiergartenDataGenerator(std::unique_ptr<IEnrichmentService> context_service,
-                          std::unique_ptr<DataGenerator> generator,
-                          std::unique_ptr<IExportService> exporter);
+  BiergartenPipelineOrchestrator(
+      std::shared_ptr<ILogger> logger,
+      std::unique_ptr<IEnrichmentService> context_service,
+      std::unique_ptr<DataGenerator> generator,
+      std::unique_ptr<IExportService> exporter,
+      const ApplicationOptions& application_options);
 
   /**
    * @brief Run the data generation pipeline.
@@ -47,6 +56,9 @@ class BiergartenDataGenerator {
   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_;
 
@@ -56,12 +68,15 @@ class BiergartenDataGenerator {
   /// @brief Storage backend for generated brewery records.
   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.
    */
-  static std::vector<Location> QueryCitiesWithCountries();
+  std::vector<Location> QueryCitiesWithCountries();
 
   /**
    * @brief Generate breweries for enriched cities.
@@ -78,4 +93,5 @@ class BiergartenDataGenerator {
   /// @brief Stores generated brewery data.
   std::vector<GeneratedBrewery> generated_breweries_;
 };
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
+
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_PIPELINE_ORCHESTRATOR_H_

tooling/pipeline/includes/concurrency/bounded_channel.h

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

tooling/pipeline/includes/concurrency/bounded_channel.tcc

@@ -0,0 +1,57 @@
+#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

@@ -18,6 +18,7 @@
 #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;
@@ -38,6 +39,7 @@ class LlamaGenerator final : public DataGenerator {
    */
   LlamaGenerator(const ApplicationOptions& options,
                  const std::string& model_path,
+                 std::shared_ptr<ILogger> logger,
                  std::unique_ptr<IPromptFormatter> prompt_formatter,
                  std::unique_ptr<IPromptDirectory> prompt_directory);
 
@@ -130,6 +132,7 @@ class LlamaGenerator final : public DataGenerator {
   std::mt19937 rng_;
   uint32_t n_ctx_ = kDefaultContextSize;
   int n_gpu_layers_ = 0;
+  std::shared_ptr<ILogger> logger_;
   std::unique_ptr<IPromptFormatter> prompt_formatter_;
   std::unique_ptr<IPromptDirectory> prompt_directory_;
 };

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

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

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

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

tooling/pipeline/includes/data_model/models.h

@@ -10,11 +10,14 @@
 #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;
 
 // ============================================================================
@@ -83,6 +86,9 @@ 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;
 };
 
 /**
@@ -95,8 +101,7 @@ 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.
@@ -116,6 +121,10 @@ 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;
 };
 
 /**
@@ -130,6 +139,7 @@ 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

@@ -7,16 +7,19 @@
  */
 
 #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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

@@ -0,0 +1,31 @@
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_MOCK_ENRICHMENT_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_MOCK_ENRICHMENT_H_
+
+/**
+ * @file services/enrichment/mock_enrichment.h
+ * @brief Mock implementation of enrichment service for testing.
+ */
+
+#include <string>
+
+#include "enrichment_service.h"
+
+/**
+ * @brief Mock implementation of enrichment service for testing and prototyping.
+ *
+ * Returns empty context without performing actual web queries or enrichment.
+ * Useful for unit tests and development scenarios.
+ */
+class MockEnrichmentService final : public IEnrichmentService {
+ public:
+  /**
+   * @brief Returns empty location context.
+   *
+   * @param loc Unused location parameter.
+   * @return Empty string (no enrichment performed).
+   */
+  std::string GetLocationContext(const Location& /*loc*/) override {
+    return {};
+  }
+};
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_MOCK_ENRICHMENT_H_

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

@@ -2,7 +2,7 @@
 #define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_WIKIPEDIA_SERVICE_H_
 
 /**
- * @file services/wikipedia_service.h
+ * @file services/enrichment/wikipedia_service.h
  * @brief Wikipedia summary retrieval service with in-memory caching.
  */
 
@@ -12,13 +12,15 @@
 #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 WikipediaService final : public IEnrichmentService {
+class WikipediaEnrichmentService final : public IEnrichmentService {
  public:
   /// @brief Creates a new Wikipedia service with the provided web client.
-  explicit WikipediaService(std::unique_ptr<WebClient> client);
+  explicit WikipediaEnrichmentService(std::unique_ptr<WebClient> client,
+                                      std::shared_ptr<ILogger> logger);
 
   /// @brief Returns the Wikipedia-derived context for a location.
   [[nodiscard]] std::string GetLocationContext(const Location& loc) override;
@@ -26,6 +28,7 @@ class WikipediaService 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

@@ -0,0 +1,53 @@
+/**
+ * @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

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

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

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

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

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

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

@@ -2,7 +2,7 @@
 #define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_PROMPTING_PROMPT_DIRECTORY_H_
 
 /**
- * @file services/prompt_directory.h
+ * @file services/prompting/prompt_directory.h
  * @brief Interface and filesystem-backed implementation for named prompt
  * loading.
  *
@@ -12,11 +12,14 @@
  */
 
 #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.
  */
@@ -56,6 +59,8 @@ 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.
@@ -70,6 +75,7 @@ class PromptDirectory final : public IPromptDirectory {
 
  private:
   std::filesystem::path prompt_dir_;
+  std::shared_ptr<ILogger> logger_;
   std::unordered_map<std::string, std::string> cache_;
 };
 

tooling/pipeline/includes/web_client/http_web_client.h

@@ -1,15 +1,17 @@
 /**
-* @file web_client/http_web_client.h
-* @brief cpp-httplib implementation of the WebClient interface.
-*/
+ * @file web_client/http_web_client.h
+ * @brief cpp-httplib implementation of the WebClient interface.
+ */
 
 #ifndef BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_HTTP_WEB_CLIENT_H_
 #define BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_HTTP_WEB_CLIENT_H_
 
-
-#include "web_client/web_client.h"
-
+#include <memory>
 #include <string>
+#include <utility>
+
+#include "services/logging/logger.h"
+#include "web_client/web_client.h"
 
 /**
  * @brief WebClient implementation backed by cpp-httplib.
@@ -23,8 +25,18 @@
  * bound to a single origin at construction time.
  */
 class HttpWebClient final : public WebClient {
-public:
-  HttpWebClient() = default;
+ public:
+  /**
+   * @brief Construct an HTTP web client with a logger.
+   *
+   * @param logger Logger instance for diagnostics.
+   */
+  explicit HttpWebClient(std::shared_ptr<ILogger> logger)
+      : logger_(std::move(logger)) {}
+
+  /**
+   * @brief Destructor.
+   */
   ~HttpWebClient() override = default;
 
   /**
@@ -42,8 +54,10 @@ public:
    * @param value Raw string to encode.
    * @return Percent-encoded string safe for use in a URL.
    */
-  std::string UrlEncode(const std::string& value) override;
+  std::string EncodeURL(const std::string& value) override;
+
+ private:
+  std::shared_ptr<ILogger> logger_;
 };
 
-
-#endif
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_HTTP_WEB_CLIENT_H_

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 UrlEncode(const std::string& value) = 0;
+  virtual std::string EncodeURL(const std::string& value) = 0;
 };
 
 #endif  // BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_WEB_CLIENT_H_

tooling/pipeline/src/application_options/parse_arguments.cc

@@ -1,12 +1,14 @@
-#include <spdlog/spdlog.h>
-
+#include <chrono>
+#include <iostream>
 #include <optional>
 #include <sstream>
 #include <string>
 
 #include "data_model/models.h"
+#include "services/logging/logger.h"
 
-std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv) {
+std::optional<ApplicationOptions> ParseArguments(
+    const int argc, char** argv, std::shared_ptr<ILogger> logger) {
   prog_opts::options_description desc("Pipeline Options");
   auto opt = desc.add_options();
 
@@ -30,6 +32,8 @@ std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv) {
         "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
@@ -50,8 +54,7 @@ std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv) {
     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("n-gpu-layers", prog_opts::value<int>()->default_value(0),
-        "Number of layers to offload to GPU");
+    opt("location-count", prog_opts::value<uint32_t>()->default_value(10));
   };
 
   add_sampling_options();
@@ -60,10 +63,22 @@ std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv) {
 
   // No flags provided — treat as a help request rather than an error.
   if (argc == 1) {
-    spdlog::info("Biergarten Pipeline");
-    std::stringstream usage_stream;
-    usage_stream << "\nUsage: biergarten-pipeline [options]\n\n" << desc;
-    spdlog::info(usage_stream.str());
+    const std::string title = "Biergarten Pipeline";
+    const std::string usage = ([&] {
+      std::stringstream usage_stream;
+      usage_stream << "\nUsage: biergarten-pipeline [options]\n\n" << desc;
+      return usage_stream.str();
+    })();
+    if (logger) {
+      logger->Log({.level = LogLevel::Info,
+                   .phase = PipelinePhase::Startup,
+                   .message = title});
+      logger->Log({.level = LogLevel::Info,
+                   .phase = PipelinePhase::Startup,
+                   .message = usage});
+    } else {
+      std::cout << title << std::endl << usage << std::endl;
+    }
     return std::nullopt;
   }
 
@@ -75,7 +90,13 @@ std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv) {
     if (var_map.contains("help")) {
       std::stringstream help_stream;
       help_stream << "\n" << desc;
-      spdlog::info(help_stream.str());
+      if (logger) {
+        logger->Log({.level = LogLevel::Info,
+                     .phase = PipelinePhase::Startup,
+                     .message = help_stream.str()});
+      } else {
+        std::cout << help_stream.str() << std::endl;
+      }
       return std::nullopt;
     }
 
@@ -84,6 +105,7 @@ std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv) {
     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>();
@@ -91,29 +113,49 @@ std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv) {
 
     // Enforce mutual exclusivity before any further configuration is applied.
     if (use_mocked && !model_path.empty()) {
-      spdlog::error(
-          "Invalid arguments: --mocked and --model are mutually exclusive");
+      const std::string msg =
+          "Invalid arguments: --mocked and --model are mutually exclusive";
+      if (logger) {
+        logger->Log({.level = LogLevel::Error,
+                     .phase = PipelinePhase::Startup,
+                     .message = msg});
+      } else {
+        std::cerr << msg << std::endl;
+      }
       return std::nullopt;
     }
 
     if (!use_mocked && model_path.empty()) {
-      spdlog::error(
-          "Invalid arguments: either --mocked or --model must be specified");
+      const std::string msg =
+          "Invalid arguments: either --mocked or --model must be specified";
+      if (logger) {
+        logger->Log({.level = LogLevel::Error,
+                     .phase = PipelinePhase::Startup,
+                     .message = msg});
+      } else {
+        std::cerr << msg << std::endl;
+      }
       return std::nullopt;
     }
 
     // Prompt directory is only meaningful for live inference — the mock
     // generator has no use for it and should not require it to be present.
     if (!use_mocked && options.pipeline.prompt_dir.empty()) {
-      spdlog::error(
-          "Invalid arguments: --prompt-dir is required when not using "
-          "--mocked");
+      const std::string msg =
+          "Invalid arguments: --prompt-dir is required when not using --mocked";
+      if (logger) {
+        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
@@ -122,13 +164,21 @@ std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv) {
     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["seed"].defaulted() || !var_map["n_gpu_layers"].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) {
-        spdlog::warn("Sampling parameters are ignored when using --mocked");
+        const std::string msg =
+            "Sampling parameters are ignored when using --mocked";
+        if (logger) {
+          logger->Log({.level = LogLevel::Warn,
+                       .phase = PipelinePhase::Startup,
+                       .message = msg});
+        } else {
+          std::cerr << msg << std::endl;
+        }
       } else {
         SamplingOptions sampling;
         sampling.temperature = var_map["temperature"].as<float>();
@@ -136,6 +186,7 @@ std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv) {
         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;
       }
@@ -144,11 +195,27 @@ std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv) {
     return options;
 
   } catch (const std::exception& exception) {
-    spdlog::error("Failed to parse command-line arguments: {}",
-                  exception.what());
+    const std::string msg =
+        std::string("Failed to parse command-line arguments: ") +
+        exception.what();
+    if (logger) {
+      logger->Log({.level = LogLevel::Error,
+                   .phase = PipelinePhase::Startup,
+                   .message = msg});
+    } else {
+      std::cerr << msg << std::endl;
+    }
     return std::nullopt;
   } catch (...) {
-    spdlog::error("Failed to parse command-line arguments: unknown error");
+    const std::string msg =
+        "Failed to parse command-line arguments: unknown error";
+    if (logger) {
+      logger->Log({.level = LogLevel::Error,
+                   .phase = PipelinePhase::Startup,
+                   .message = msg});
+    } else {
+      std::cerr << msg << std::endl;
+    }
     return std::nullopt;
   }
 }

tooling/pipeline/src/biergarten_data_generator/biergarten_data_generator.cc

@@ -1,16 +0,0 @@
-/**
- * @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

@@ -1,58 +0,0 @@
-/**
- * @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

@@ -1,26 +0,0 @@
-/**
- * @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

@@ -1,41 +0,0 @@
-/**
- * @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

@@ -1,52 +0,0 @@
-/**
- * @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

@@ -0,0 +1,20 @@
+/**
+ * @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

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

tooling/pipeline/src/biergarten_pipeline_orchestrator/log_results.cc

@@ -0,0 +1,37 @@
+/**
+ * @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

@@ -0,0 +1,51 @@
+/**
+ * @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

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

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

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

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

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

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

@@ -16,11 +16,11 @@
 
 #include "data_generation/llama_generator_helpers.h"
 #include "llama.h"
-
+namespace {
 /**
  * String trimming: removes leading and trailing whitespace
  */
-static std::string Trim(std::string_view value) {
+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 @@ static std::string Trim(std::string_view value) {
  * Normalize whitespace: collapses multiple spaces/tabs/newlines into single
  * spaces
  */
-static std::string CondenseWhitespace(std::string_view text) {
+std::string CondenseWhitespace(std::string_view text) {
   std::string out;
   out.reserve(text.size());
 
@@ -61,7 +61,37 @@ static 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.
-static constexpr size_t kTruncationGuardDivisor = 2;
+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
@@ -121,47 +151,6 @@ 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;
@@ -209,7 +198,7 @@ std::optional<std::string> ValidateBreweryJson(const std::string& raw,
     return validation_error;
   }
 
-  const std::array<std::string*, 4> schema_placeholders = {
+  const std::array 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_()),
   };
-  auto sampler = MakeSamplerChain(vocab, sampler_config, grammar);
+  const auto sampler = MakeSamplerChain(vocab, sampler_config, grammar);
 
   /**
    * Clear KV cache to ensure clean inference state (no residual context)
@@ -171,10 +171,14 @@ std::string LlamaGenerator::InferFormatted(const std::string& formatted_prompt,
    */
   prompt_tokens.resize(static_cast<size_t>(token_count));
   if (token_count > prompt_budget) {
-    spdlog::warn(
-        "LlamaGenerator: prompt too long ({} tokens), truncating to {} "
-        "tokens to fit n_batch/n_ctx limits",
-        token_count, prompt_budget);
+    if (logger_) {
+      logger_->Log({.level = LogLevel::Warn,
+                    .phase = PipelinePhase::BreweryAndBeerGeneration,
+                    .message = std::format(
+                        "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

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

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

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

tooling/pipeline/src/json_handling/json_loader.cc

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

tooling/pipeline/src/main.cc

@@ -4,48 +4,77 @@
  * 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_data_generator.h"
+#include "biergarten_pipeline_orchestrator.h"
+#include "concurrency/bounded_channel.h"
 #include "data_generation/llama_generator.h"
 #include "data_generation/mock_generator.h"
 #include "data_generation/prompt_formatting/gemma4_jinja_prompt_formatter.h"
 #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
 
-    const auto parsed_options = ParseArguments(argc, argv);
+    log_producer->Log({.level = LogLevel::Info,
+                       .phase = PipelinePhase::Startup,
+                       .message = "STARTING PIPELINE"});
+
+    const std::optional<ApplicationOptions> parsed_options =
+        ParseArguments(argc, argv, log_producer);
+
     if (!parsed_options.has_value()) {
-      return 0;
+      return shutdown(EXIT_FAILURE);
     }
 
     const auto options = *parsed_options;
@@ -54,55 +83,136 @@ 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>(options.pipeline.prompt_dir);
+        prompt_directory = std::make_unique<PromptDirectory>(
+            options.pipeline.prompt_dir, log_producer);
       } catch (const std::exception& dir_error) {
-        spdlog::error("[Startup] Invalid --prompt-dir: {}", dir_error.what());
-        return 1;
+        log_producer->Log({.level = LogLevel::Error,
+                           .phase = PipelinePhase::Startup,
+                           .message = std::format("Invalid --prompt-dir: {}",
+                                                  dir_error.what())});
+
+        return shutdown(EXIT_FAILURE);
       }
     }
 
     const auto injector = di::make_injector(
-        di::bind<WebClient>().to<HttpWebClient>(),
+        di::bind<ILogger>().to(log_producer),
         di::bind<ApplicationOptions>().to(options),
-        di::bind<IEnrichmentService>().to<WikipediaService>(),
-        di::bind<IExportService>().to<SqliteExportService>(),
-        di::bind<IPromptFormatter>().to<Gemma4JinjaPromptFormatter>(),
         di::bind<std::string>().to(model_path),
-        di::bind<DataGenerator>().to(
-            [options, model_path, sampling, &prompt_directory](
-            const auto& inj) -> std::unique_ptr<DataGenerator> {
+        di::bind<IExportService>().to<SqliteExportService>(),
+        di::bind<IPromptFormatter>().to([options, log_producer] {
+          if (options.generator.use_mocked) {
+            {
+              log_producer->Log(
+                  {.level = LogLevel::Info,
+                   .phase = PipelinePhase::Startup,
+                   .message = "Prompt formatter: none (mock mode)"});
+            }
+            return std::unique_ptr<IPromptFormatter>(nullptr);
+          }
+          {
+            log_producer->Log(
+                {.level = LogLevel::Info,
+                 .phase = PipelinePhase::Startup,
+                 .message = "Prompt formatter: Gemma4JinjaPromptFormatter"});
+          }
+          return std::unique_ptr<IPromptFormatter>(
+              std::make_unique<Gemma4JinjaPromptFormatter>());
+        }),
+        di::bind<WebClient>().to([options, log_producer] {
+          if (options.generator.use_mocked) {
+            {
+              log_producer->Log({.level = LogLevel::Info,
+                                 .phase = PipelinePhase::Startup,
+                                 .message = "Web client: none (mock mode)"});
+            }
+            return std::unique_ptr<WebClient>(nullptr);
+          }
+          {
+            log_producer->Log({.level = LogLevel::Info,
+                               .phase = PipelinePhase::Startup,
+                               .message = "Web client: HttpWebClient"});
+          }
+          return std::unique_ptr<WebClient>(
+              std::make_unique<HttpWebClient>(log_producer));
+        }),
+        di::bind<IEnrichmentService>().to(
+            [options, &log_producer](
+                const auto& inj) -> std::unique_ptr<IEnrichmentService> {
               if (options.generator.use_mocked) {
-                spdlog::info(
-                    "[Generator] Using MockGenerator (no model path provided)");
+                {
+                  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,
+             &log_producer](const auto& inj) -> std::unique_ptr<DataGenerator> {
+              if (options.generator.use_mocked) {
+                {
+                  log_producer->Log({.level = LogLevel::Info,
+                                     .phase = PipelinePhase::Startup,
+                                     .message = "Generator: mock"});
+                }
                 return std::make_unique<MockGenerator>();
               }
-
-              spdlog::info(
-                  "[Generator] Using LlamaGenerator: {} (temperature={}, "
-                  "top-p={}, top-k={}, n_ctx={}, seed={})",
-                  model_path, sampling.temperature, sampling.top_p,
-                  sampling.top_k, sampling.n_ctx, sampling.seed);
+              {
+                log_producer->Log(
+                    {.level = LogLevel::Info,
+                     .phase = PipelinePhase::Startup,
+                     .message = std::format(
+                         "Generator: LlamaGenerator | model={} | temp={:.2f} "
+                         "top_p={:.2f} top_k={} n_ctx={} seed={}",
+                         model_path, sampling.temperature, sampling.top_p,
+                         sampling.top_k, sampling.n_ctx, sampling.seed)});
+              }
               return std::make_unique<LlamaGenerator>(
-                  options, model_path,
+                  options, model_path, log_producer,
                   inj.template create<std::unique_ptr<IPromptFormatter>>(),
                   std::move(prompt_directory));
             }));
 
-    auto generator =
-        injector.create<std::unique_ptr<BiergartenDataGenerator>>();
+    const auto orchestrator =
+        injector.create<std::unique_ptr<BiergartenPipelineOrchestrator>>();
 
-    if (!generator->Run()) {
-      spdlog::error("Pipeline execution failed");
-      return 1;
+    if (!orchestrator->Run()) {
+      log_producer->Log({.level = LogLevel::Error,
+                         .phase = PipelinePhase::Teardown,
+                         .message = "Pipeline execution failed"});
+      return shutdown(EXIT_FAILURE);
     }
 
-    spdlog::info("Pipeline executed successfully in {} ms", timer.Elapsed());
-    return 0;
+    log_producer->Log({.level = LogLevel::Info,
+                       .phase = PipelinePhase::Teardown,
+                       .message = std::format("Pipeline complete in {} ms",
+                                              timer.Elapsed())});
+
+    return shutdown(EXIT_SUCCESS);
+
   } catch (const std::exception& exception) {
-    spdlog::critical("Unhandled fatal error in main: {}", exception.what());
-    return 1;
+    const LogEntry log_entry{.level = LogLevel::Error,
+                             .phase = PipelinePhase::Teardown,
+                             .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

@@ -0,0 +1,162 @@
+/**
+ * @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::string("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::string("WikipediaService: JSON parse error for '") +
+                      std::string(query) + "': " + ec.message()});
+    }
+    return {};
+  }
+
+  // 3. Safe Extraction
+  const json::object* obj = doc.if_object();
+  if (obj == nullptr) {
+    if (logger_) {
+      logger_->Log(
+          {.level = LogLevel::Warn,
+           .phase = PipelinePhase::UserGeneration,
+           .message =
+               std::string("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::string("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::string("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::string("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::string("WikipediaService: Page '") +
+                               std::string(query) + "' does not exist"});
+    }
+    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::string("WikipediaService: No extract string found for '") +
+               std::string(query) + "'"});
+    }
+    this->extract_cache_.emplace(cache_key, "");
+    return {};
+  }
+
+  // 4. Success
+  std::string extract(extract_ptr->as_string());
+  if (logger_) {
+    logger_->Log({.level = LogLevel::Info,
+                  .phase = PipelinePhase::UserGeneration,
+                  .message = std::string("WikipediaService: Fetched ") +
+                             std::to_string(extract.size()) + " chars for '" +
+                             std::string(query) + "'"});
+  }
+
+  this->extract_cache_.insert_or_assign(cache_key, extract);
+
+  return extract;
+}

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

@@ -0,0 +1,70 @@
+/**
+ * @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::string("Done fetching for ") +
+                               location_query + ". Sleeping for 10 seconds."});
+    }
+    std::this_thread::sleep_for(10s);
+
+  } catch (const std::runtime_error& e) {
+    if (logger_) {
+      logger_->Log(
+          {.level = LogLevel::Debug,
+           .phase = PipelinePhase::UserGeneration,
+           .message = std::string("WikipediaService lookup failed for '") +
+                      location_query + "': " + e.what()});
+    }
+  }
+  return result;
+}

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

@@ -0,0 +1,12 @@
+/**
+ * @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

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

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

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

tooling/pipeline/src/services/prompt_directory.cc

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

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

@@ -1,61 +0,0 @@
-/**
- * @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

@@ -1,47 +0,0 @@
-/**
- * @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

@@ -1,11 +0,0 @@
-/**
- * @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.
  */
 
@@ -7,11 +7,14 @@
 
 #include <httplib.h>
 
+#include <chrono>
 #include <regex>
 #include <stdexcept>
 #include <string>
 #include <utility>
 
+#include "services/logging/logger.h"
+
 namespace {
 constexpr time_t kConnectionTimeoutSeconds = 5;
 constexpr time_t kReadTimeoutSeconds = 10;
@@ -29,7 +32,7 @@ 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);
@@ -38,24 +41,32 @@ 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 auto result = client.Get(path);
+  const httplib::Result result = client.Get(path);
 
   if (!result) {
-    throw std::runtime_error(
-        "[HttpWebClient] Request failed for URL: " + url +
-        " — " + httplib::to_string(result.error()));
+    throw std::runtime_error("[HttpWebClient] Request failed for URL: " + url +
+                             " — " + httplib::to_string(result.error()));
   }
 
   if (result->status < kSuccessMin || result->status >= kSuccessMax) {
-    throw std::runtime_error(
-        "[HttpWebClient] HTTP " + std::to_string(result->status) +
-        " for URL: " + url);
+    if (logger_) {
+      logger_->Log(
+          {.level = LogLevel::Error,
+           .phase = PipelinePhase::UserGeneration,
+           .message =
+               std::string("[HttpWebClient] Request failed for URL: ") + url});
+    }
+    throw std::runtime_error("[HttpWebClient] HTTP " +
+                             std::to_string(result->status) +
+                             " for URL: " + url);
   }
 
   return result->body;
 }
 
-std::string HttpWebClient::UrlEncode(const std::string& value) {
+std::string HttpWebClient::EncodeURL(const std::string& value) {
   return httplib::encode_uri_component(value);
-}
+}