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

@@ -155,13 +155,13 @@ 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 ---
@@ -210,6 +210,12 @@ target_sources(${PROJECT_NAME} PRIVATE
 	src/services/sqlite/helpers/sqlite_statement_helpers.cc
 )
 
+# --- services: logging ---
+target_sources(${PROJECT_NAME} PRIVATE
+	"src/services/logging/log_producer.cc"
+        src/services/logging/log_dispatcher.cc
+)
+
 # --- services (top-level) ---
 target_sources(${PROJECT_NAME} PRIVATE
 	src/services/prompt_directory.cc

tooling/pipeline/includes/biergarten_pipeline_orchestrator.h

@@ -3,7 +3,10 @@
 
 /**
  * @file biergarten_data_generator.h
- * @brief Core orchestration class for pipeline data generation.
+ * @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>
@@ -15,22 +18,27 @@
 #include "services/database/export_service.h"
 #include "services/enrichment/enrichment_service.h"
 
+#include "services/logging/logger.h"
+
 /**
  * @brief Main data generator class for the Biergarten pipeline.
  *
  * This class encapsulates the core logic for generating brewery data.
  * It handles location loading, city enrichment, and brewery generation.
  */
-class 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,
+  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);
@@ -48,6 +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_;
 
@@ -57,7 +68,8 @@ class BiergartenDataGenerator {
    /// @brief Storage backend for generated brewery records.
    std::unique_ptr<IExportService> exporter_;
 
-  const ApplicationOptions application_options_;
+   /// @brief CLI configuration: paths, model settings, generation parameters.
+   ApplicationOptions application_options_;
 
   /**
    * @brief Load locations from JSON and sample cities.

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 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_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;
 
 // ============================================================================
@@ -136,6 +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/services/enrichment/wikipedia_service.h

@@ -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 WikipediaEnrichmentService final : public IEnrichmentService {
  public:
   /// @brief Creates a new Wikipedia service with the provided web client.
-  explicit WikipediaEnrichmentService(std::unique_ptr<WebClient> client);
+  explicit WikipediaEnrichmentService(std::unique_ptr<WebClient> client,
+                                      std::shared_ptr<ILogger> logger);
 
   /// @brief Returns the Wikipedia-derived context for a location.
   [[nodiscard]] std::string GetLocationContext(const Location& loc) override;
@@ -26,6 +28,7 @@ class WikipediaEnrichmentService final : public IEnrichmentService {
  private:
   std::string FetchExtract(std::string_view query);
   std::unique_ptr<WebClient> client_;
+  std::shared_ptr<ILogger> logger_;
   /// @brief Canonical cache for raw Wikipedia query extracts.
   std::unordered_map<std::string, std::string> extract_cache_;
 };

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

@@ -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_CONSUMER_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_CONSUMER_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_CONSUMER_H_

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

@@ -0,0 +1,68 @@
+/**
+ * @file services/logging/log_entry.h
+ * @brief Structured log record shared by the pipeline logging infra.
+ *
+ * LogEntry is a lightweight value type that can be passed safely between the
+ * logging producer and dispatcher through BoundedChannel<LogEntry>.
+ */
+
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_ENTRY_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_ENTRY_H_
+
+#include <chrono>
+#include <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 +1,53 @@
+/**
+ * @file services/logging/log_producer.h
+ * @brief Channel-backed log producer for asynchronous pipeline logging.
+ *
+ * The producer captures log records from application code and forwards them to
+ * a bounded channel for later processing by the dispatcher.
+ */
+
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_CHANNEL_LOGGER_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_CHANNEL_LOGGER_H_
+
+#include <string_view>
+
+#include "concurrency/bounded_channel.h"
+#include "services/logging/log_entry.h"
+#include "services/logging/logger.h"
+
+/**
+ * @class LogProducer
+ * @brief ILogger implementation that forwards entries to a bounded channel.
+ *
+ * Non-copyable and non-movable. The channel reference is non-owning and must
+ * remain valid for the lifetime of the producer.
+ */
+class LogProducer final : public ILogger {
+ public:
+   /**
+     * @brief Construct a channel-backed producer.
+    *
+     * @param channel Reference to the bounded channel used for log transfer.
+    */
+   explicit LogProducer(BoundedChannel<LogEntry>& channel);
+
+   LogProducer(const LogProducer&) = delete;
+   LogProducer& operator=(const LogProducer&) = delete;
+   LogProducer(LogProducer&&) = delete;
+   LogProducer& operator=(LogProducer&&) = delete;
+
+   ~LogProducer() override = default;
+
+   /**
+     * @brief Queue a log message for asynchronous processing.
+    *
+     * Blocks while the channel applies backpressure.
+    */
+   void Log(LogLevel level, PipelinePhase phase,
+            std::string_view message) override;
+
+ private:
+   BoundedChannel<LogEntry>& channel_;
+};
+
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_CHANNEL_LOGGER_H_

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

@@ -0,0 +1,45 @@
+/**
+ * @file services/logging/logger.h
+ * @brief Abstract logging interface used by pipeline components.
+ *
+ * The interface keeps application code independent from the concrete logging
+ * transport, buffering, and formatting implementation.
+ */
+
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_
+
+#include <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 level Severity of the message.
+     * @param phase Pipeline execution phase associated with the message.
+     * @param message Log message text.
+    */
+   virtual void Log(LogLevel level, PipelinePhase phase,
+                    std::string_view message) = 0;
+};
+
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_

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

@@ -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

@@ -8,8 +8,11 @@
 
 
 #include "web_client/web_client.h"
+#include "services/logging/logger.h"
 
+#include <memory>
 #include <string>
+#include <utility>
 
 /**
  * @brief WebClient implementation backed by cpp-httplib.
@@ -24,7 +27,8 @@
  */
 class HttpWebClient final : public WebClient {
 public:
-  HttpWebClient() = default;
+  explicit HttpWebClient(std::shared_ptr<ILogger> logger)
+      : logger_(std::move(logger)) {}
   ~HttpWebClient() override = default;
 
   /**
@@ -43,6 +47,9 @@ public:
    * @return Percent-encoded string safe for use in a URL.
    */
   std::string EncodeURL(const std::string& value) override;
+
+ private:
+  std::shared_ptr<ILogger> logger_;
 };
 
 

tooling/pipeline/src/application_options/parse_arguments.cc

@@ -1,4 +1,5 @@
-#include <spdlog/spdlog.h>
+#include "services/logging/logger.h"
+#include <iostream>
 
 #include <optional>
 #include <sstream>
@@ -6,7 +7,8 @@
 
 #include "data_model/models.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();
 
@@ -61,10 +63,18 @@ 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");
+    const std::string title = "Biergarten Pipeline";
+    const std::string usage = ([&] {
       std::stringstream usage_stream;
       usage_stream << "\nUsage: biergarten-pipeline [options]\n\n" << desc;
-    spdlog::info(usage_stream.str());
+      return usage_stream.str();
+    })();
+    if (logger) {
+      logger->Log(LogLevel::Info, PipelinePhase::Startup, title);
+      logger->Log(LogLevel::Info, PipelinePhase::Startup, usage);
+    } else {
+      std::cout << title << std::endl << usage << std::endl;
+    }
     return std::nullopt;
   }
 
@@ -76,7 +86,11 @@ 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(LogLevel::Info, PipelinePhase::Startup, help_stream.str());
+      } else {
+        std::cout << help_stream.str() << std::endl;
+      }
       return std::nullopt;
     }
 
@@ -94,23 +108,37 @@ 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(LogLevel::Error, PipelinePhase::Startup, 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(LogLevel::Error, PipelinePhase::Startup, 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(LogLevel::Error, PipelinePhase::Startup, msg);
+      } else {
+        std::cerr << msg << std::endl;
+      }
       return std::nullopt;
     }
 
@@ -131,7 +159,13 @@ std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv) {
       // 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(LogLevel::Warn, PipelinePhase::Startup, msg);
+        } else {
+          std::cerr << msg << std::endl;
+        }
       } else {
         SamplingOptions sampling;
         sampling.temperature = var_map["temperature"].as<float>();
@@ -148,11 +182,22 @@ 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(LogLevel::Error, PipelinePhase::Startup, 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(LogLevel::Error, PipelinePhase::Startup, msg);
+    } else {
+      std::cerr << msg << std::endl;
+    }
     return std::nullopt;
   }
 }

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/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.iso3166_2, region_context);
-
-        enriched.push_back(
-            EnrichedCity{.location = std::move(city),
-                         .region_context = std::move(region_context)});
-      } catch (const std::exception& exception) {
-        ++skipped_count;
-        spdlog::warn(
-            "[Pipeline] Skipping city '{}' ({}): context lookup failed: {}",
-            city.city, city.country, exception.what());
-      }
-    }
-
-    if (skipped_count > 0) {
-      spdlog::warn(
-          "[Pipeline] Skipped {} city/cities due to context lookup errors",
-          skipped_count);
-    }
-
-    this->GenerateBreweries(enriched);
-    exporter_->Finalize();
-    this->LogResults();
-    return true;
-  } catch (const std::exception& e) {
-    spdlog::error("Pipeline execution failed with error: {}", e.what());
-    return false;
-  }
-}

tooling/pipeline/src/biergarten_pipeline_orchestrator/biergarten_pipeline_orchestrator.cc

@@ -1,18 +1,20 @@
 /**
- * @file biergarten_data_generator/biergarten_data_generator.cc
+ * @file biergarten_pipeline_orchestrator/biergarten_pipeline_orchestrator.cc
  * @brief BiergartenDataGenerator constructor implementation.
  */
 
-#include "biergarten_data_generator.h"
+#include "biergarten_pipeline_orchestrator.h"
 
 #include <utility>
 
-BiergartenDataGenerator::BiergartenDataGenerator(
+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)
-    : context_service_(std::move(context_service)),
+    : 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 +1,61 @@
+/**
+ * @file biergarten_pipeline_orchestrator/generate_breweries.cc
+ * @brief BiergartenDataGenerator::GenerateBreweries() implementation.
+ */
+
+#include "services/logging/logger.h"
+#include "biergarten_pipeline_orchestrator.h"
+
+void BiergartenPipelineOrchestrator::GenerateBreweries(
+    std::span<const EnrichedCity> cities) {
+  logger_->Log(LogLevel::Info, PipelinePhase::BreweryAndBeerGeneration,
+               "=== 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(LogLevel::Warn, PipelinePhase::BreweryAndBeerGeneration,
+                     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(LogLevel::Warn, PipelinePhase::BreweryAndBeerGeneration,
+                   std::string("[Pipeline] Skipping city '") + location.city +
+                       " (" + location.country + "): brewery generation failed: " +
+                       e.what());
+    }
+  }
+
+  if (skipped_count > 0) {
+    logger_->Log(LogLevel::Warn, PipelinePhase::BreweryAndBeerGeneration,
+                 std::string("[Pipeline] Skipped ") +
+                     std::to_string(skipped_count) +
+                     " city/cities due to generation errors");
+  }
+
+  if (export_failed_count > 0) {
+    logger_->Log(LogLevel::Warn, PipelinePhase::Teardown,
+                 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 +1,31 @@
+/**
+ * @file biergarten_pipeline_orchestrator/log_results.cc
+ * @brief BiergartenDataGenerator::LogResults() implementation.
+ */
+
+#include "services/logging/logger.h"
+
+#include "biergarten_pipeline_orchestrator.h"
+#include <sstream>
+
+void BiergartenPipelineOrchestrator::LogResults() const {
+  std::ostringstream msg;
+  msg << "GENERATED DATA DUMP\n";
+  size_t index = 1;
+  for (const auto& [location, brewery] : generated_breweries_) {
+    msg << index << ". city=\"" << location.city << "\" country=\""
+        << location.country << "\" state=\"" << location.state_province
+        << "\" iso3166_2=" << location.iso3166_2 << " lat="
+        << location.latitude << " lon=" << location.longitude << "\n";
+
+    msg << "   brewery_name_en=\"" << brewery.name_en << "\"\n";
+    msg << "   brewery_description_en=\"" << brewery.description_en
+        << "\"\n";
+    msg << "   brewery_name_local=\"" << brewery.name_local << "\"\n";
+    msg << "   brewery_description_local=\"" << brewery.description_local
+        << "\"\n";
+    ++index;
+  }
+
+  logger_->Log(LogLevel::Debug, PipelinePhase::Teardown, msg.str());
+}

tooling/pipeline/src/biergarten_pipeline_orchestrator/query_cities_with_countries.cc

@@ -1,25 +1,27 @@
 /**
- * @file biergarten_data_generator/query_cities_with_countries.cc
+ * @file biergarten_pipeline_orchestrator/query_cities_with_countries.cc
  * @brief BiergartenDataGenerator::QueryCitiesWithCountries() implementation.
  */
 
-#include <spdlog/spdlog.h>
+#include "services/logging/logger.h"
 
 #include <algorithm>
 #include <filesystem>
+#include <format>
 #include <iterator>
 #include <random>
 
-#include "biergarten_data_generator.h"
+#include "biergarten_pipeline_orchestrator.h"
 #include "json_handling/json_loader.h"
 
-std::vector<Location> BiergartenDataGenerator::QueryCitiesWithCountries() {
-  spdlog::info("\n=== GEOGRAPHIC DATA OVERVIEW ===");
+std::vector<Location> BiergartenPipelineOrchestrator::QueryCitiesWithCountries() {
+  logger_->Log(LogLevel::Info, PipelinePhase::Startup,
+               "=== 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());
+  auto all_locations = JsonLoader::LoadLocations(locations_path, logger_);
+
 
   const size_t sample_count = std::min(
       static_cast<size_t>(application_options_.pipeline.location_count),
@@ -36,6 +38,9 @@ std::vector<Location> BiergartenDataGenerator::QueryCitiesWithCountries() {
   std::ranges::sample(all_locations, std::back_inserter(sampled_locations),
                       sample_count_signed, random_generator);
 
-  spdlog::info("  Sampled locations: {}", sampled_locations.size());
+  logger_->Log(LogLevel::Info, PipelinePhase::Startup,
+               std::format("  Locations available: {}", all_locations.size()));
+  logger_->Log(LogLevel::Info, PipelinePhase::Startup,
+               std::format("  Sampled locations: {}", sampled_locations.size()));
   return sampled_locations;
 }

tooling/pipeline/src/biergarten_pipeline_orchestrator/run.cc

@@ -0,0 +1,57 @@
+/**
+ * @file biergarten_pipeline_orchestrator/run.cc
+ * @brief BiergartenDataGenerator::Run() implementation.
+ */
+
+#include "services/logging/logger.h"
+
+#include <utility>
+
+#include "biergarten_pipeline_orchestrator.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(LogLevel::Warn, PipelinePhase::UserGeneration,
+                     std::string("[Pipeline] Skipping city '") + city.city +
+                         " (" + city.country + "): context lookup failed: " +
+                         exception.what());
+      }
+    }
+
+    if (skipped_count > 0) {
+      logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
+                   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(LogLevel::Error, PipelinePhase::Teardown,
+                 std::string("Pipeline execution failed with error: ") +
+                     e.what());
+    return false;
+  }
+}

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

@@ -4,8 +4,6 @@
  * inference, and validates structured JSON output for brewery records.
  */
 
-#include <spdlog/spdlog.h>
-
 #include <format>
 #include <optional>
 #include <stdexcept>
@@ -100,8 +98,11 @@ 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(LogLevel::Debug, PipelinePhase::BreweryAndBeerGeneration,
+                   std::string("LlamaGenerator: raw output (attempt ") +
+                       std::to_string(attempt + 1) + "): " + raw);
+    }
 
     // Validate output: parse JSON and check required fields
 
@@ -112,9 +113,12 @@ 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(LogLevel::Info, PipelinePhase::BreweryAndBeerGeneration,
+                     std::string(
+                         "LlamaGenerator: successfully generated brewery data on attempt ") +
+                         std::to_string(attempt + 1));
+      }
 
       return brewery;
     }
@@ -122,8 +126,11 @@ 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(LogLevel::Warn, PipelinePhase::BreweryAndBeerGeneration,
+                   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 +147,11 @@ 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(LogLevel::Error, PipelinePhase::BreweryAndBeerGeneration,
+                 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/infer.cc

@@ -5,8 +5,6 @@
  * output tokens back to text for system+user chat prompts.
  */
 
-#include <spdlog/spdlog.h>
-
 #include <algorithm>
 #include <memory>
 #include <stdexcept>
@@ -171,10 +169,14 @@ 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(
+          LogLevel::Warn, PipelinePhase::BreweryAndBeerGeneration,
+          std::string("LlamaGenerator: prompt too long (") +
+              std::to_string(token_count) + ") tokens, truncating to " +
+              std::to_string(prompt_budget) +
+              " tokens to fit n_batch/n_ctx limits");
+    }
     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()) {

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

@@ -4,8 +4,6 @@
  * context, and resets prior resources during model initialization.
  */
 
-#include <spdlog/spdlog.h>
-
 #include <algorithm>
 #include <stdexcept>
 #include <string>
@@ -49,5 +47,8 @@ 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(LogLevel::Info, PipelinePhase::Startup,
+                 std::string("[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

@@ -12,8 +12,10 @@
 #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"
@@ -25,27 +27,41 @@
 #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::thread log_thread([&log_dispatcher] { log_dispatcher->Run(); });
+
+  std::shared_ptr<ILogger> log_producer =
+      std::make_shared<LogProducer>(log_channel);
   try {
     Timer timer;
-    spdlog::set_pattern("[%Y-%m-%d %H:%M:%S.%e] [%^%l%$] %v");
 
 #ifndef BIERGARTEN_MOCK_ONLY
     const LlamaBackendState llama_backend_state;
 #endif
-#ifdef DEBUG
-    spdlog::set_level(spdlog::level::debug);
-#endif
 
+    log_producer->Log(LogLevel::Info, PipelinePhase::Startup,
+                      "STARTING PIPELINE");
     const std::optional<ApplicationOptions> parsed_options =
-        ParseArguments(argc, argv);
+        ParseArguments(argc, argv, log_producer);
 
     if (!parsed_options.has_value()) {
+      log_channel.Close();
+      log_thread.join();
       return 0;
     }
 
@@ -54,66 +70,100 @@ int main(const int argc, char** argv) {
     const auto sampling =
         options.generator.sampling.value_or(SamplingOptions{});
 
+    // -----------------------------------------------------------------------
+    // Prompt directory
+    // Conditionally constructed before the injector; moved into LlamaGenerator.
+    // -----------------------------------------------------------------------
     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());
+        log_producer->Log(
+            LogLevel::Error, PipelinePhase::Startup,
+            std::string("Invalid --prompt-dir: ") + dir_error.what());
+        log_channel.Close();
+        log_thread.join();
         return 1;
       }
     }
 
+    // -----------------------------------------------------------------------
+    // Dependency injection
+    // -----------------------------------------------------------------------
     const auto injector = di::make_injector(
+        di::bind<ILogger>().to(log_producer),
         di::bind<ApplicationOptions>().to(options),
         di::bind<std::string>().to(model_path),
         di::bind<WebClient>().to<HttpWebClient>(),
         di::bind<IExportService>().to<SqliteExportService>(),
         di::bind<IPromptFormatter>().to<Gemma4JinjaPromptFormatter>(),
         di::bind<IEnrichmentService>().to(
-            [options](const auto& inj) -> std::unique_ptr<IEnrichmentService> {
-              if (options.generator.use_mocked) {
-                return std::make_unique<MockEnrichmentService>();
-              }
-
+            [options, &log_producer](
+                const auto& inj) -> std::unique_ptr<IEnrichmentService> {
+              // if (options.generator.use_mocked) {
+              //   return std::make_unique<MockEnrichmentService>();
+              // }
               return std::make_unique<WikipediaEnrichmentService>(
-                  inj.template create<std::unique_ptr<WebClient>>());
+                  inj.template create<std::unique_ptr<WebClient>>(),
+                  log_producer);
             }),
         di::bind<DataGenerator>().to(
-            [options, model_path, sampling, &prompt_directory](
-                const auto& inj) -> std::unique_ptr<DataGenerator> {
+            [&options, &model_path, &sampling, &prompt_directory,
+             &log_producer](const auto& inj) -> std::unique_ptr<DataGenerator> {
               if (options.generator.use_mocked) {
-                spdlog::info(
-                    "[Generator] Using MockGenerator (no model path provided)");
+                log_producer->Log(
+                    LogLevel::Info, PipelinePhase::Startup,
+                    "Using MockGenerator (no model path provided)");
                 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(
+                  LogLevel::Info, PipelinePhase::Startup,
+                  "Using LlamaGenerator: " + model_path +
+                      " (temperature=" + std::to_string(sampling.temperature) +
+                      ", top-p=" + std::to_string(sampling.top_p) +
+                      ", top-k=" + std::to_string(sampling.top_k) +
+                      ", n_ctx=" + std::to_string(sampling.n_ctx) +
+                      ", seed=" + std::to_string(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));
-            })
+            }));
 
-    );
+    // -----------------------------------------------------------------------
+    // Pipeline execution
+    // -----------------------------------------------------------------------
+    const auto orchestrator =
+        injector.create<std::unique_ptr<BiergartenPipelineOrchestrator>>();
 
-    const auto generator =
-        injector.create<std::unique_ptr<BiergartenDataGenerator>>();
-
-    if (!generator->Run()) {
-      spdlog::error("Pipeline execution failed");
+    if (!orchestrator->Run()) {
+      log_producer->Log(LogLevel::Error, PipelinePhase::Teardown,
+                        "Pipeline execution failed");
+      log_channel.Close();
+      log_thread.join();
       return 1;
     }
 
-    spdlog::info("Pipeline executed successfully in {} ms", timer.Elapsed());
+    log_producer->Log(LogLevel::Info, PipelinePhase::Teardown,
+                      "Pipeline executed successfully in " +
+                          std::to_string(timer.Elapsed()) + " ms");
+
+    log_channel.Close();
+    log_thread.join();
     return 0;
+
   } catch (const std::exception& exception) {
-    spdlog::critical("Unhandled fatal error in main: {}", exception.what());
+    // Attempt to use the logging infrastructure; if channel/dispatcher are
+    // compromised this is a best-effort fallback.
+    if (log_producer) {
+      log_producer->Log(
+          LogLevel::Error, PipelinePhase::Teardown,
+          std::string("Unhandled fatal error in main: ") + exception.what());
+    }
+    log_channel.Close();
+    log_thread.join();
     return 1;
   }
 }

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

@@ -2,8 +2,6 @@
  * @file wikipedia/fetch_extract.cc
  */
 
-#include <spdlog/spdlog.h>
-
 #include <boost/json.hpp>
 #include <chrono>
 #include <format>
@@ -22,7 +20,10 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
   // 1. Cache Lookup
   if (const auto cache_it = this->extract_cache_.find(cache_key);
       cache_it != this->extract_cache_.end()) {
-    spdlog::debug("Wikipedia: Cache hit for {}!", cache_key);
+    if (logger_) {
+      logger_->Log(LogLevel::Debug, PipelinePhase::UserGeneration,
+                   std::string("Wikipedia: Cache hit for ") + cache_key + "!");
+    }
     return cache_it->second;
   }
 
@@ -44,15 +45,22 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
   json::value doc = json::parse(body, ec);
 
   if (ec) {
-    spdlog::warn("WikipediaService: JSON parse error for '{}': {}", query,
-                 ec.message());
+    if (logger_) {
+      logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
+                   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) {
-    spdlog::warn("WikipediaService: Expected root object for '{}'", query);
+    if (logger_) {
+      logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
+                   std::string("WikipediaService: Expected root object for '") +
+                       std::string(query) + "'");
+    }
     return {};
   }
 
@@ -63,14 +71,22 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
           : nullptr;
 
   if ((pages_ptr == nullptr) || !pages_ptr->is_object()) {
-    spdlog::warn("WikipediaService: Missing query.pages for '{}'", query);
+    if (logger_) {
+      logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
+                   std::string("WikipediaService: Missing query.pages for '") +
+                       std::string(query) + "'");
+    }
     return {};
   }
 
   const json::object& pages = pages_ptr->get_object();
 
   if (pages.empty()) {
-    spdlog::warn("WikipediaService: No pages returned for '{}'", query);
+    if (logger_) {
+      logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
+                   std::string("WikipediaService: No pages returned for '") +
+                       std::string(query) + "'");
+    }
     this->extract_cache_.emplace(cache_key, "");
     return {};
   }
@@ -80,7 +96,11 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
   const json::value& page_val = pages.begin()->value();
 
   if (!page_val.is_object()) {
-    spdlog::warn("WikipediaService: Unexpected page format for '{}'", query);
+    if (logger_) {
+      logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
+                   std::string("WikipediaService: Unexpected page format for '") +
+                       std::string(query) + "'");
+    }
     return {};
   }
 
@@ -88,7 +108,11 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
 
   // Handle 404/Missing status
   if (page.contains("missing")) {
-    spdlog::warn("WikipediaService: Page '{}' does not exist", query);
+    if (logger_) {
+      logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
+                   std::string("WikipediaService: Page '") + std::string(query) +
+                       "' does not exist");
+    }
     this->extract_cache_.emplace(cache_key, "");
     return {};
   }
@@ -96,15 +120,23 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
   const json::value* extract_ptr = page.if_contains("extract");
 
   if ((extract_ptr == nullptr) || !extract_ptr->is_string()) {
-    spdlog::warn("WikipediaService: No extract string found for '{}'", query);
+    if (logger_) {
+      logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
+                   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());
-  spdlog::info("WikipediaService: Fetched {} chars for '{}'", extract.size(),
-                query);
+  if (logger_) {
+    logger_->Log(LogLevel::Info, PipelinePhase::UserGeneration,
+                 std::string("WikipediaService: Fetched ") +
+                     std::to_string(extract.size()) + " chars for '" +
+                     std::string(query) + "'");
+  }
 
   this->extract_cache_.insert_or_assign(cache_key, extract);
 

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

@@ -3,8 +3,6 @@
  * @brief WikipediaService::GetLocationContext() implementation.
  */
 
-#include <spdlog/spdlog.h>
-
 #include <chrono>
 #include <format>
 #include <string>
@@ -15,7 +13,10 @@
 std::string WikipediaEnrichmentService::GetLocationContext(const Location& loc) {
   using namespace std::literals::chrono_literals;
   if (!this->client_) {
-    spdlog::warn("Client is nullptr.");
+    if (logger_) {
+      logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
+                   "Wikipedia client is nullptr.");
+    }
     return {};
   }
 
@@ -46,13 +47,19 @@ std::string WikipediaEnrichmentService::GetLocationContext(const Location& loc)
   try {
     append_extract(FetchExtract(brewing_query));
     append_extract(FetchExtract(beer_query));
-    spdlog::info("Done fetching for {}. Sleeping for 10 seconds.",
-                 location_query);
+    if (logger_) {
+      logger_->Log(LogLevel::Info, PipelinePhase::UserGeneration,
+                   std::string("Done fetching for ") + location_query +
+                       ". Sleeping for 10 seconds.");
+    }
     std::this_thread::sleep_for(10s);
 
   } catch (const std::runtime_error& e) {
-    spdlog::debug("WikipediaService lookup failed for '{}': {}", location_query,
-                  e.what());
+    if (logger_) {
+      logger_->Log(LogLevel::Debug, PipelinePhase::UserGeneration,
+                   std::string("WikipediaService lookup failed for '") +
+                       location_query + "': " + e.what());
+    }
   }
   return result;
 }

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

@@ -8,5 +8,5 @@
 #include <utility>
 
 WikipediaEnrichmentService::WikipediaEnrichmentService(
-    std::unique_ptr<WebClient> client)
-    : client_(std::move(client)) {}
+    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 +1,25 @@
+/**
+ * @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(LogLevel level, PipelinePhase phase,
+                      const std::string_view message) {
+  channel_.Send(LogEntry{.timestamp = std::chrono::system_clock::now(),
+                         .level = level,
+                         .phase = phase,
+                         .message = std::string(message)});
+}

tooling/pipeline/src/services/prompt_directory.cc

@@ -6,20 +6,23 @@
 
 #include "services/prompting/prompt_directory.h"
 
-#include <spdlog/spdlog.h>
-
 #include <filesystem>
 #include <fstream>
 #include <stdexcept>
 #include <string>
 #include <string_view>
+#include <utility>
 
 // ---------------------------------------------------------------------------
 // PromptDirectory
 // ---------------------------------------------------------------------------
 
 PromptDirectory::PromptDirectory(const std::filesystem::path& prompt_dir)
-    : 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 +47,11 @@ PromptDirectory::PromptDirectory(const std::filesystem::path& prompt_dir)
         prompt_dir_.string() + " (" + ec.message() + ")");
   }
 
-  spdlog::info("[PromptDirectory] Resolved prompt directory: {}",
+  if (logger_) {
+    logger_->Log(LogLevel::Info, PipelinePhase::Startup,
+                 std::string("[PromptDirectory] Resolved prompt directory: ") +
                      prompt_dir_.string());
+  }
 }
 
 std::string PromptDirectory::Load(std::string_view key) {
@@ -77,8 +83,12 @@ 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(LogLevel::Info, PipelinePhase::Startup,
+                 std::string("[PromptDirectory] Loaded prompt '") + key_str +
+                     "' from '" + file_path.string() + "' (" +
+                     std::to_string(content.size()) + " chars)");
+  }
 
   cache_.emplace(key_str, content);
   return content;

tooling/pipeline/src/web_client/http_web_client.cc

@@ -12,7 +12,7 @@
 #include <string>
 #include <utility>
 
-#include "spdlog/spdlog.h"
+#include "services/logging/logger.h"
 
 namespace {
 constexpr time_t kConnectionTimeoutSeconds = 5;
@@ -54,7 +54,11 @@ std::string HttpWebClient::Get(const std::string& url) {
   }
 
   if (result->status < kSuccessMin || result->status >= kSuccessMax) {
-    spdlog::error("[HttpWebClient] Request failed for URL: " + url);
+    if (logger_) {
+      logger_->Log(LogLevel::Error, PipelinePhase::UserGeneration,
+                   std::string("[HttpWebClient] Request failed for URL: ") +
+                       url);
+    }
     throw std::runtime_error(
         "[HttpWebClient] HTTP " + std::to_string(result->status) +
         " for URL: " + url);