fixes

add pretty print log

.gitattributes

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

docs/pipeline/README.md

@@ -18,6 +18,7 @@ descriptions via a local GGUF model or a deterministic mock.
   - [Build](#build)
   - [Model](#model)
   - [Run](#run)
+- [Docker / RunPod](#docker--runpod)
 - [Architecture](#architecture)
   - [Pipeline Stages](#pipeline-stages)
   - [Key Components](#key-components)
@@ -51,7 +52,7 @@ step.
 
 ### Build
 
-Requirements: C++20 compiler, CMake 3.24+, libcurl, Boost (JSON and
+Requirements: C++20 compiler, CMake 3.31+, OpenSSL, Boost (JSON and
 ProgramOptions). SQLite is fetched from the upstream amalgamation, so no system
 SQLite package is required.
 
@@ -60,6 +61,16 @@ cmake -S . -B build
 cmake --build build
 ```
 
+CMake automatically detects whether a compatible llama.cpp installation is
+present on the system (`libllama`, `libggml`, `libggml-base`, and `llama.h`
+visible on the default search paths). If found, it links against those
+libraries and skips the FetchContent build. If not found, it fetches and builds
+llama.cpp from source at tag `b9012`. No additional flags are required in
+either case.
+
+Metal is enabled automatically on Apple Silicon. CUDA or HIP/ROCm is detected
+automatically on Linux when the relevant toolkit is present.
+
 ### Model
 
 > Skip this step if you only need `--mocked`.
@@ -74,20 +85,27 @@ curl -L \
 ### Run
 
 Run from `build/` so the copied `locations.json` and `prompts/` are available.
-Each run also writes a fresh dated SQLite file such as
+Each run writes a fresh dated SQLite file such as
 `biergarten_seed_2026-04-19T15-30-45.123456Z.sqlite` into the working directory.
 
 ```bash
 ./biergarten-pipeline --mocked
-./biergarten-pipeline --model models/google_gemma-4-E4B-it-Q6_K.gguf --temperature 1.0 --top-p 0.95 --top-k 64 --n-ctx 8192 --seed -1
+
+./biergarten-pipeline \
+  --model ../models/google_gemma-4-E4B-it-Q6_K.gguf \
+  --prompt-dir prompts \
+  --temperature 1.0 --top-p 0.95 --top-k 64 --n-ctx 8192 --seed -1
 ```
 
 #### CLI Flags
 
 | Flag            | Purpose                                                                                              |
-| --------------- | ------------------------------------------------------- |
+| --------------- | ---------------------------------------------------------------------------------------------------- |
 | `--mocked`      | Deterministic mock generator, no model required.                                                     |
 | `--model, -m`   | Path to a GGUF file. Required unless `--mocked` is set.                                              |
+| `--prompt-dir`  | Directory containing prompt files (e.g. `BREWERY_GENERATION.md`). Required unless `--mocked` is set. |
+| `--output, -o`  | Directory for generated SQLite artifacts. Default: `output`.                                         |
+| `--log-path`    | Path for application logs. Default: `pipeline.log`.                                                  |
 | `--temperature` | Sampling temperature. Default: `1.0`.                                                                |
 | `--top-p`       | Nucleus sampling. Default: `0.95`.                                                                   |
 | `--top-k`       | Top-k sampling. Default: `64`.                                                                       |
@@ -100,7 +118,91 @@ error before the pipeline starts. Sampling flags are ignored when `--mocked` is
 set.
 
 The post-build step copies `prompts/` into `build/prompts/`. Rebuild after
-editing `prompts/system.md`.
+editing any prompt file.
+
+---
+
+## Docker / RunPod
+
+The `tooling/pipeline/runpod/` directory contains a GPU-ready container
+configuration for running the pipeline on RunPod or any Docker host with an
+NVIDIA GPU.
+
+### How it works
+
+The container uses a two-stage build. The first stage pulls prebuilt
+`libllama`, `libggml`, and backend plugin libraries (including `libggml-cuda.so`
+and the CPU variant plugins) from `ghcr.io/ggml-org/llama.cpp:full-cuda`. The
+second stage copies those libraries into `/usr/local/lib` and runs `ldconfig` so
+the dynamic linker and `dlopen` calls from `ggml_backend_load_all()` can resolve
+the CUDA backend plugin at runtime. llama.cpp headers are cloned at the matching
+tag and installed into `/usr/local/include`. CMake auto-detects both and skips
+the FetchContent source build entirely, keeping image build times short.
+
+`GGML_BACKEND_PATH` is set to `/usr/local/lib` so llama.cpp knows where to scan
+for backend plugins.
+
+### Build the image
+
+Run from the `tooling/pipeline/` directory (the CMake project root), not from
+inside `runpod/`, so the `COPY . .` step picks up the full project context.
+
+```bash
+docker build -t biergarten-pipeline:latest -f runpod/Dockerfile .
+```
+
+To monitor the full build output and confirm CMake selects the system llama.cpp:
+
+```bash
+docker build \
+  --progress=plain \
+  --no-cache \
+  -t biergarten-pipeline:latest \
+  -f runpod/Dockerfile \
+  . 2>&1 | tee build.log
+```
+
+Look for `[biergarten] Found system llama.cpp — skipping FetchContent` in the
+output to confirm the fast path was taken.
+
+### Run in mocked mode
+
+No model or GPU required. Useful for validating the pipeline logic and SQLite
+export path.
+
+```bash
+docker run --rm \
+  -e BIERGARTEN_MODE=mocked \
+  -v "$PWD/output:/workspace/output" \
+  -v "$PWD/logs:/workspace/logs" \
+  biergarten-pipeline:latest
+```
+
+### Run in live mode
+
+Mount your GGUF model before starting. The container validates the model path
+before launching the binary.
+
+```bash
+docker run --rm \
+  --runtime=nvidia \
+  -e BIERGARTEN_MODE=live \
+  -e GGML_BACKEND_PATH="/usr/local/lib/libggml-cuda.so" \
+  -v "$PWD/models:/workspace/models" \
+  -v "$PWD/output:/workspace/output" \
+  -v "$PWD/logs:/workspace/logs" \
+  biergarten-pipeline:latest
+```
+
+The model must be present at `./models/google_gemma-4-E4B-it-Q6_K.gguf` on the
+host. See [Model](#model) above for the download command.
+
+### RunPod deployment
+
+Use a GPU pod template. Mount persistent storage for `/workspace/models`,
+`/workspace/output`, and `/workspace/logs`. Set `BIERGARTEN_MODE=live` in the
+template environment. See `tooling/pipeline/runpod/pod-template.yaml` for a
+starter template.
 
 ---
 
@@ -197,16 +299,18 @@ code, latitude, and longitude for each entry.
 ## Tech Stack
 
 - C++20
-- CMake 3.24+
+- CMake 3.31+
 - Boost.JSON, Boost.ProgramOptions, Boost.DI
 - spdlog
-- libcurl
+- cpp-httplib (with OpenSSL)
 - SQLite amalgamation fetched and compiled via CMake FetchContent
-- llama.cpp
+- llama.cpp (auto-detected from system install or fetched via FetchContent)
+- Docker with NVIDIA CUDA 12.6 base image for GPU container builds
+- RunPod for cloud GPU inference
 
-The build fetches Boost.DI, spdlog, llama.cpp, and SQLite via CMake. Metal is
-enabled on Apple Silicon; CUDA or HIP/ROCm is detected on Linux when the toolkit
-is present.
+The build fetches Boost.DI, spdlog, and SQLite via CMake. llama.cpp is fetched
+only when a system installation is not detected. Metal is enabled on Apple
+Silicon; CUDA or HIP/ROCm is detected on Linux when the toolkit is present.
 
 > **Code Style:** Modern C++20 throughout — RAII for ownership,
 > `std::unique_ptr` for injected dependencies, `std::optional` for parse
@@ -218,7 +322,7 @@ is present.
 
 ## Tested Hardware
 
-### ARM macOS - M1 Pro
+### ARM macOS — M1 Pro
 
 |           |                                   |
 | --------- | --------------------------------- |
@@ -229,7 +333,7 @@ is present.
 | Model     | Gemma 4 E4B                       |
 | Inference | llama.cpp with Metal              |
 
-### x86_64 Linux - NVIDIA RTX 2000
+### x86_64 Linux — NVIDIA RTX 2000
 
 |           |                                |
 | --------- | ------------------------------ |
@@ -240,6 +344,15 @@ is present.
 | Model     | Gemma 4 E4B                    |
 | Inference | llama.cpp with CUDA 12.x       |
 
+### x86_64 Linux — Docker / RunPod (NVIDIA CUDA)
+
+|           |                                             |
+| --------- | ------------------------------------------- |
+| Host      | RunPod GPU pod                              |
+| Base      | nvidia/cuda:12.6.3-devel-ubuntu24.04        |
+| Model     | Gemma 4 E4B Q6_K                            |
+| Inference | llama.cpp prebuilt CUDA backends via dlopen |
+
 ---
 
 ## Fixture Strategy
@@ -260,8 +373,9 @@ is present.
 | `includes/`                  | Public headers and shared models.                  |
 | `src/`                       | Implementation files.                              |
 | `locations.json`             | Curated city input copied into the build tree.     |
-| `prompts/`                   | System prompt used by the model-backed path.       |
+| `prompts/`                   | System prompts used by the model-backed path.      |
 | `diagrams/`                  | Architecture and pipeline diagrams.                |
+| `tooling/pipeline/runpod/`   | Dockerfile, launcher, and RunPod pod template.     |
 | `ETHICS-AND-KNOWN-ISSUES.md` | Ethics, bias, hallucination analysis, mitigations. |
 
 ---
@@ -276,6 +390,7 @@ is present.
 - `src/data_generation/llama/` — local inference, prompt loading, output
   validation.
 - `src/data_generation/mock/` — deterministic fallback.
+- `tooling/pipeline/runpod/` — container build and runtime launcher.
 
 ---
 

docs/pipeline/diagrams/current/activity.puml

@@ -29,7 +29,7 @@ if (Are arguments valid?) then (no)
 else (yes)
 endif
 
-:Init CurlGlobalState & LlamaBackendState;
+:Init OpenSSL global state & LlamaBackendState;
 :di::make_injector(...);
 :injector.create<std::unique_ptr<BiergartenDataGenerator>>();
 :BiergartenDataGenerator::Run();

docs/pipeline/diagrams/current/class.puml

@@ -26,6 +26,7 @@ skinparam note {
 title The Biergarten Data Pipeline - Class Diagram
 
 class BiergartenDataGenerator {
+  - logger_ : std::shared_ptr<ILogger>
   - context_service_ : std::unique_ptr<IEnrichmentService>
   - generator_ : std::unique_ptr<DataGenerator>
   - exporter_ : std::unique_ptr<IExportService>
@@ -36,6 +37,46 @@ class BiergartenDataGenerator {
   - LogResults() : void
 }
 
+class LogLevel <<enumeration>> {
+  Debug
+  Info
+  Warn
+  Error
+}
+
+class PipelinePhase <<enumeration>> {
+  Startup
+  UserGeneration
+  BreweryAndBeerGeneration
+  CheckinGeneration
+  RatingGeneration
+  FollowGeneration
+  Teardown
+}
+
+struct LogEntry {
+  + timestamp : std::chrono::system_clock::time_point
+  + level : LogLevel
+  + phase : PipelinePhase
+  + message : std::string
+  + worker : std::optional<std::string>
+}
+
+interface ILogger <<interface>> {
+  + Log(entry : const LogEntry&) : void
+}
+
+class LogProducer {
+  - channel_ : BoundedChannel<LogEntry>&
+  + Log(entry : const LogEntry&) : void
+}
+
+class LogDispatcher {
+  - channel_ : BoundedChannel<LogEntry>&
+  + Run() : void
+  - ToSpdlogLevel(level) : spdlog::level::level_enum
+}
+
 interface IEnrichmentService <<interface>> {
   + GetLocationContext(loc : const Location&) : std::string
 }
@@ -52,7 +93,7 @@ interface WebClient <<interface>> {
   + UrlEncode(value : const std::string&) : std::string
 }
 
-class CURLWebClient {
+class HttpWebClient {
   + Get(url : const std::string&) : std::string
   + UrlEncode(value : const std::string&) : std::string
 }
@@ -123,14 +164,21 @@ class SystemDateTimeProvider {
 }
 
 ' Structural Relationships / Dependency Injection
+BiergartenDataGenerator *-- ILogger : owns
 BiergartenDataGenerator *-- IEnrichmentService : owns
 BiergartenDataGenerator *-- DataGenerator : owns
 BiergartenDataGenerator *-- IExportService : owns
 
+LogEntry *-- LogLevel
+LogEntry *-- PipelinePhase
+ILogger <|.. LogProducer : implements
+LogProducer ..> LogEntry : emits
+LogDispatcher ..> LogEntry : consumes
+
 IEnrichmentService <|.. WikipediaService : implements
 WikipediaService *-- WebClient : owns
 
-WebClient <|.. CURLWebClient : implements
+WebClient <|.. HttpWebClient : implements
 
 DataGenerator <|.. MockGenerator : implements
 DataGenerator <|.. LlamaGenerator : implements

docs/pipeline/diagrams/planned/activity.puml

@@ -13,7 +13,7 @@ if (Invalid args?) then (yes)
   stop
 else (no)
 endif
-:Init CurlGlobalState & LlamaBackendState;
+:Init OpenSSL global state & LlamaBackendState;
 :Build DI injector;
 
 :Initialize SqliteExportService;

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 {
@@ -154,7 +156,7 @@ package "Domain: Application Configuration"{
   class GeneratorOptions {
     + model_path: std::filesystem::path
     + use_mocked: bool = false
-    + sampling : SamplingOptions
+    + sampling: std::optional<SamplingOptions>
   }
 
   class PipelineOptions {
@@ -167,10 +169,9 @@ package "Domain: Application Configuration"{
     + pipeline: PipelineOptions
   }
 
-  ' --- Domain Model Relationships ---
   ApplicationOptions *-- GeneratorOptions
   ApplicationOptions *-- PipelineOptions
-  GeneratorOptions   *-- SamplingOptions
+  GeneratorOptions o-- SamplingOptions
 }
 
 package "Domain: Policy" {
@@ -274,33 +275,29 @@ package "Infrastructure: Logging" {
     + level : LogLevel
     + phase : PipelinePhase
     + message : std::string
-    + city : std::optional<std::string>
-    + entity_id : std::optional<std::string>
     + worker : std::optional<std::string>
   }
 
-  interface Logger <<interface>> {
-    + Log(level, phase, message,\n  city, entity_id, worker) : void
+  interface ILogger <<interface>> {
+    + Log(entry : const LogEntry&) : void
   }
 
-  class PipelineLogger {
-    - log_ch_ : BoundedChannel<LogEntry>&
-    + Log(level, phase, message,\n  city, entity_id, worker) : void
+  class LogProducer {
+    - channel_ : BoundedChannel<LogEntry>&
+    + Log(entry : const LogEntry&) : void
   }
 
-  class LogWorker {
-    - log_ch_ : BoundedChannel<LogEntry>&
+  class LogDispatcher {
+    - channel_ : BoundedChannel<LogEntry>&
     + Run() : void
-    - FormatTimestamp(tp) : std::string
     - ToSpdlogLevel(level) : spdlog::level::level_enum
-    - ToString(phase) : std::string
   }
 
-  ' --- Logging Relationships ---
   LogEntry       *--  LogLevel
   LogEntry       *--  PipelinePhase
-  PipelineLogger ..>  LogEntry       : emits
-  LogWorker      ..>  LogEntry       : consumes
+  ILogger        <|.. LogProducer
+  LogProducer    ..>  LogEntry       : emits
+  LogDispatcher  ..>  LogEntry       : consumes
 }
 
 package "Infrastructure: Pipeline Channel" {
@@ -355,13 +352,29 @@ package "Infrastructure: Enrichment" {
     + UrlEncode(value : const std::string&) : std::string
   }
 
-  class CURLWebClient {
+  class HttpWebClient {
     + Get(url : const std::string&) : std::string
     + UrlEncode(value : const std::string&) : std::string
   }
 
 }
 
+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>> {
@@ -385,6 +398,7 @@ 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
@@ -458,8 +472,6 @@ package "Infrastructure: Data Export" {
 
 }
 
-
-
 class BiergartenPipelineOrchestrator {
   - preloader_ : std::unique_ptr<DataPreloader>
   - enrichment_service_ : std::unique_ptr<EnrichmentService>
@@ -519,7 +531,7 @@ CheckinDistributionStrategy    <|.. RandomCheckinStrategy
 FollowGenerationStrategy       <|.. RandomFollowStrategy
 FollowGenerationStrategy       <|.. ActivityWeightedFollowStrategy
 EnrichmentService              <|.. WikipediaService
-WebClient                      <|.. CURLWebClient
+WebClient                      <|.. HttpWebClient
 DataGenerator                  <|.. MockGenerator
 DataGenerator                  <|.. LlamaGenerator
 PromptFormatter                <|.. Gemma4JinjaPromptFormatter
@@ -530,6 +542,7 @@ DateTimeProvider               <|.. SystemDateTimeProvider
 WikipediaService               *--  WebClient
 WikipediaService               ..>  ContextStrategy
 LlamaGenerator                 *--  PromptFormatter
+LlamaGenerator                 *--  IPromptDirectory
 LlamaGenerator                 ..>  GeneratorOptions
 SqliteExportService            *--  DateTimeProvider
 

tooling/pipeline/.dockerignore

@@ -0,0 +1,9 @@
+build/
+cmake-build-debug/
+.git/
+.idea/
+**/*.sqlite
+**/*.log
+**/*.sqlite3
+**/*.db
+

tooling/pipeline/.gitignore

@@ -6,3 +6,4 @@ data
 models
 *.gguf
 BiergartenPipeline.png
+output

tooling/pipeline/CMakeLists.txt

@@ -1,13 +1,20 @@
-cmake_minimum_required(VERSION 3.24)
+cmake_minimum_required(VERSION 3.31)
 project(biergarten-pipeline)
 
-set(CMAKE_POLICY_VERSION_MINIMUM 3.5 CACHE STRING "" FORCE)
+# Set policy to allow FetchContent_Populate for header-only libraries
+# that have outdated CMakeLists.txt files
+cmake_policy(SET CMP0169 OLD)
 
-# =============================================================================
-# 1. Platform & GPU Detection
-# =============================================================================
-if(WIN32)
-    message(FATAL_ERROR "[biergarten] Windows is currently not supported. Please use Linux (Fedora 43) or macOS (M1 Pro).")
+# 1. Build Options
+
+option(BIERGARTEN_MOCK_ONLY "Build with mock data generators only — skips llama.cpp" OFF)
+if(BIERGARTEN_MOCK_ONLY)
+        message(STATUS "[biergarten] MOCK_ONLY build — llama.cpp will not be compiled.")
+endif()
+
+# 2. Platform & GPU Detection
+if(NOT UNIX)
+        message(FATAL_ERROR "[biergarten] Windows is not supported. Please use Linux (Fedora 43) or macOS (M1 Pro).")
 endif()
 
 if(APPLE)
@@ -18,15 +25,15 @@ if(APPLE)
                 message(STATUS "[biergarten] Intel Mac detected — using CPU / Accelerate framework.")
                 set(GGML_METAL OFF CACHE BOOL "Disable Metal for Intel Macs" FORCE)
         endif()
-elseif(UNIX AND NOT APPLE)
+else()
         find_package(CUDAToolkit QUIET)
-    find_package(HIP QUIET)
+        find_package(hip CONFIG QUIET)
 
         if(CUDAToolkit_FOUND)
                 message(STATUS "[biergarten] NVIDIA GPU detected — enabling CUDA acceleration.")
                 set(GGML_CUDA ON CACHE BOOL "Enable CUDA for NVIDIA GPUs" FORCE)
                 set(CMAKE_CUDA_ARCHITECTURES native)
-    elseif(HIP_FOUND OR EXISTS "/opt/rocm")
+        elseif(hip_FOUND OR DEFINED ENV{ROCM_PATH} OR EXISTS "/opt/rocm")
                 message(STATUS "[biergarten] AMD GPU detected — enabling HIP/ROCm acceleration.")
                 set(GGML_HIPBLAS ON CACHE BOOL "Enable HIP for AMD GPUs" FORCE)
         else()
@@ -34,71 +41,79 @@ elseif(UNIX AND NOT APPLE)
         endif()
 endif()
 
-# =============================================================================
-# 2. Project-wide Settings (Standard & Optimization)
-# =============================================================================
-
+# 3. Project-wide Settings
 set(CMAKE_CXX_STANDARD 20)
 set(CMAKE_CXX_STANDARD_REQUIRED ON)
 set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
-
-# Release Build Optimization: Aggressive (-O3), Arch-specific, and LTO
 set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -O3 -march=native -flto")
-
 set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -Og -g")
 
-# =============================================================================
-# 3. Dependencies
-# =============================================================================
+# 4. Dependencies
 include(FetchContent)
 
-find_package(CURL QUIET)
-if(NOT CURL_FOUND)
-    message(FATAL_ERROR "[biergarten] libcurl not found. Install it (e.g. 'sudo dnf install libcurl-devel').")
-endif()
-
-# Require system Boost for JSON and Program Options to speed up build times
+# Boost (system install — via dnf/brew)
 find_package(Boost REQUIRED COMPONENTS json program_options)
 
-FetchContent_Declare(
-    sqlite_amalgamation
-    URL https://www.sqlite.org/2026/sqlite-amalgamation-3530000.zip
-    URL_HASH SHA3_256=c2325c53b3b41761469f91cfb078e96882ac5d85bac10c11b0bd8f253b031e5b
-)
-FetchContent_GetProperties(sqlite_amalgamation)
-if(NOT sqlite_amalgamation_POPULATED)
-    FetchContent_Populate(sqlite_amalgamation)
-endif()
-
-if(NOT TARGET sqlite3)
-    add_library(sqlite3 STATIC
-        ${sqlite_amalgamation_SOURCE_DIR}/sqlite3.c
-    )
-    target_include_directories(sqlite3 PUBLIC
-        ${sqlite_amalgamation_SOURCE_DIR}
-    )
-    target_compile_definitions(sqlite3 PUBLIC
-        SQLITE_THREADSAFE=1
-    )
-endif()
-
-FetchContent_Declare(
-    llama-cpp
-    GIT_REPOSITORY https://github.com/ggml-org/llama.cpp.git
-    GIT_TAG        b8742
-)
-FetchContent_MakeAvailable(llama-cpp)
-
+# Boost.DI (unofficial Boost extension, must declare separately from main Boost dependency)
+# Header-only library, so we only fetch without invoking its CMakeLists.txt
 FetchContent_Declare(
         boost-di
         GIT_REPOSITORY https://github.com/boost-ext/di.git
         GIT_TAG v1.3.0
+        GIT_SHALLOW TRUE
 )
-FetchContent_MakeAvailable(boost-di)
-if(TARGET Boost.DI AND NOT TARGET boost::di)
-    add_library(boost::di ALIAS Boost.DI)
+FetchContent_GetProperties(boost-di)
+if(NOT boost-di_POPULATED)
+        FetchContent_Populate(boost-di)
 endif()
 
+add_library(boost_di INTERFACE)
+add_library(boost::di ALIAS boost_di)
+target_include_directories(boost_di INTERFACE
+        $<BUILD_INTERFACE:${boost-di_SOURCE_DIR}/include>
+)
+# SQLite amalgamation
+FetchContent_Declare(
+        sqlite_amalgamation
+        URL https://www.sqlite.org/2026/sqlite-amalgamation-3530000.zip
+        URL_HASH SHA3_256=c2325c53b3b41761469f91cfb078e96882ac5d85bac10c11b0bd8f253b031e5b
+        EXCLUDE_FROM_ALL
+)
+FetchContent_MakeAvailable(sqlite_amalgamation)
+if(NOT TARGET sqlite3)
+        add_library(sqlite3 STATIC ${sqlite_amalgamation_SOURCE_DIR}/sqlite3.c)
+        target_include_directories(sqlite3 PUBLIC ${sqlite_amalgamation_SOURCE_DIR})
+        target_compile_definitions(sqlite3 PUBLIC SQLITE_THREADSAFE=1)
+endif()
+
+# llama.cpp — skipped for mock-only builds
+if(NOT BIERGARTEN_MOCK_ONLY)
+        find_library(LLAMA_LIB NAMES llama)
+        find_library(GGML_LIB NAMES ggml)
+        find_library(GGML_BASE_LIB NAMES ggml-base)
+        find_path(LLAMA_INC_DIR NAMES llama.h PATH_SUFFIXES include)
+
+        if(LLAMA_LIB AND GGML_LIB AND GGML_BASE_LIB AND LLAMA_INC_DIR)
+                message(STATUS "[biergarten] Found system llama.cpp — skipping FetchContent")
+
+                add_library(llama SHARED IMPORTED)
+                set_target_properties(llama PROPERTIES
+                        IMPORTED_LOCATION "${LLAMA_LIB}"
+                        INTERFACE_INCLUDE_DIRECTORIES "${LLAMA_INC_DIR}"
+                        INTERFACE_LINK_LIBRARIES "${GGML_LIB};${GGML_BASE_LIB}"
+                )
+        else()
+                message(STATUS "[biergarten] System llama.cpp not found — fetching via FetchContent")
+                FetchContent_Declare(
+                        llama-cpp
+                        GIT_REPOSITORY https://github.com/ggml-org/llama.cpp.git
+                        GIT_TAG b9012
+                )
+                FetchContent_MakeAvailable(llama-cpp)
+        endif()
+endif()
+
+# spdlog
 FetchContent_Declare(
         spdlog
         GIT_REPOSITORY https://github.com/gabime/spdlog.git
@@ -106,73 +121,148 @@ FetchContent_Declare(
 )
 FetchContent_MakeAvailable(spdlog)
 
-# =============================================================================
-# 4. Sources
-# =============================================================================
-set(SOURCES
+# cpp-httplib — header-only HTTP/HTTPS client replacing libcurl.
+# OpenSSL is required for HTTPS (Wikipedia API). find_package locates
+# libssl/libcrypto; HTTPLIB_REQUIRE_OPENSSL causes a hard build failure
+# if OpenSSL is absent rather than silently producing an HTTP-only binary.
+find_package(OpenSSL REQUIRED)
+FetchContent_Declare(
+        cpp-httplib
+        GIT_REPOSITORY https://github.com/yhirose/cpp-httplib.git
+        GIT_TAG v0.43.2
+        GIT_SHALLOW TRUE
+        SYSTEM
+)
+set(HTTPLIB_REQUIRE_OPENSSL ON CACHE BOOL "Require OpenSSL for cpp-httplib" FORCE)
+FetchContent_MakeAvailable(cpp-httplib)
+
+# 5. Executable & Sources
+add_executable(${PROJECT_NAME}
+        includes/services/enrichment/mock_enrichment.h
+        includes/json_handling/pretty_print.h)
+
+# --- Entry point ---
+target_sources(${PROJECT_NAME} PRIVATE
         src/main.cc
-    src/biergarten_data_generator/biergarten_data_generator.cc
-    src/biergarten_data_generator/run.cc
-    src/biergarten_data_generator/query_cities_with_countries.cc
-    src/biergarten_data_generator/generate_breweries.cc
-    src/biergarten_data_generator/log_results.cc
-    src/services/wikipedia/wikipedia_service.cc
-    src/services/wikipedia/get_summary.cc
-    src/services/wikipedia/fetch_extract.cc
-    src/services/sqlite/sqlite_export_service.cc
-    src/services/sqlite/build_database_path.cc
-        src/services/sqlite/process_record.cc
-        src/services/sqlite/initialize.cc
-    src/services/sqlite/finalize.cc
-    src/web_client/curl_global_state.cc
-    src/web_client/curl_web_client_get.cc
-    src/web_client/curl_web_client_url_encode.cc
-    src/data_generation/llama/llama_generator.cc
-    src/data_generation/llama/generate_brewery.cc
-    src/data_generation/llama/generate_user.cc
-    src/data_generation/llama/helpers.cc
-    src/data_generation/llama/infer.cc
-    src/data_generation/llama/load.cc
-    src/data_generation/llama/load_brewery_prompt.cc
-    src/data_generation/prompt_formatting/gemma4_jinja_prompt_formatter.cc
-    src/data_generation/mock/deterministic_hash.cc
-    src/data_generation/mock/generate_brewery.cc
-    src/data_generation/mock/generate_user.cc
-    src/json_handling/json_loader.cc
-        src/services/sqlite/helpers/sqlite_connection_helpers.cpp
-        src/services/sqlite/helpers/sqlite_statement_helpers.cpp
 )
 
-# =============================================================================
-# 5. Target
-# =============================================================================
-add_executable(${PROJECT_NAME} ${SOURCES})
+# --- json_handling ---
+target_sources(${PROJECT_NAME} PRIVATE
+        src/json_handling/json_loader.cc
+)
+
+# --- application_options ---
+target_sources(${PROJECT_NAME} PRIVATE
+        src/application_options/parse_arguments.cc
+)
+
+# --- biergarten_pipeline_orchestrator ---
+target_sources(${PROJECT_NAME} PRIVATE
+        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 ---
+target_sources(${PROJECT_NAME} PRIVATE
+        src/web_client/http_web_client.cc
+)
+
+# --- data_generation: prompt_formatting ---
+target_sources(${PROJECT_NAME} PRIVATE
+        src/data_generation/prompt_formatting/gemma4_jinja_prompt_formatter.cc
+)
+
+# --- data_generation: mock ---
+target_sources(${PROJECT_NAME} PRIVATE
+        src/data_generation/mock/generate_brewery.cc
+        src/data_generation/mock/generate_user.cc
+        src/data_generation/mock/deterministic_hash.cc
+)
+
+# --- data_generation: llama (skipped for mock-only builds) ---
+if(NOT BIERGARTEN_MOCK_ONLY)
+        target_sources(${PROJECT_NAME} PRIVATE
+                src/data_generation/llama/load.cc
+                src/data_generation/llama/helpers.cc
+                src/data_generation/llama/generate_brewery.cc
+                src/data_generation/llama/infer.cc
+                src/data_generation/llama/llama_generator.cc
+                src/data_generation/llama/generate_user.cc
+        )
+endif()
+
+# --- services: wikipedia ---
+target_sources(${PROJECT_NAME} PRIVATE
+        src/services/enrichment/wikipedia/wikipedia_service.cc
+        src/services/enrichment/wikipedia/fetch_extract.cc
+        src/services/enrichment/wikipedia/get_summary.cc
+)
+
+# --- services: sqlite ---
+target_sources(${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
+)
+
+# --- 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
+)
+
+# 6. Include Directories, Link Libraries & Compile Definitions
 target_include_directories(${PROJECT_NAME} PRIVATE
         includes
-    ${llama-cpp_SOURCE_DIR}/include
-    ${llama-cpp_SOURCE_DIR}/common
 )
+
 target_link_libraries(${PROJECT_NAME} PRIVATE
-    llama
+        $<$<NOT:$<BOOL:${BIERGARTEN_MOCK_ONLY}>>:llama>
         boost::di
         Boost::json
         Boost::program_options
         spdlog::spdlog
         sqlite3
-    CURL::libcurl
+        httplib::httplib
+        OpenSSL::SSL
+        OpenSSL::Crypto
 )
 
-# =============================================================================
-# 6. Runtime Assets
-# =============================================================================
+target_compile_definitions(${PROJECT_NAME} PRIVATE
+        # Defined when -DBIERGARTEN_MOCK_ONLY=ON — skips llama.cpp entirely.
+        # Use #ifdef BIERGARTEN_MOCK_ONLY in source to guard llama-specific code.
+        $<$<BOOL:${BIERGARTEN_MOCK_ONLY}>:BIERGARTEN_MOCK_ONLY>
+
+        # Defined for Debug configuration builds.
+        # Use #ifdef DEBUG in source to enable debug-only behaviour (e.g. verbose logging).
+        $<$<CONFIG:Debug>:DEBUG>
+)
+
+target_compile_options(biergarten-pipeline PRIVATE
+   -fmacro-prefix-map=${CMAKE_SOURCE_DIR}/tooling/pipeline/src/=
+)
+
+
+# 7. Runtime Assets
 configure_file(
         ${CMAKE_SOURCE_DIR}/locations.json
         ${CMAKE_BINARY_DIR}/locations.json
         COPYONLY
 )
-
 add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD
         COMMAND ${CMAKE_COMMAND} -E copy_directory
         ${CMAKE_SOURCE_DIR}/prompts
         ${CMAKE_BINARY_DIR}/prompts
 )
+

tooling/pipeline/includes/biergarten_data_generator.h

@@ -1,83 +0,0 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
-
-/**
- * @file biergarten_data_generator.h
- * @brief Core orchestration class for pipeline data generation.
- */
-
-#include <memory>
-#include <span>
-#include <vector>
-
-#include "data_generation/data_generator.h"
-#include "data_model/enriched_city.h"
-#include "data_model/generated_brewery.h"
-#include "data_model/location.h"
-#include "services/enrichment_service.h"
-#include "services/export_service.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 {
- public:
-  /**
-   * @brief Construct a BiergartenDataGenerator with injected dependencies.
-   *
-   * @param context_service Context provider for sampled locations.
-   * @param generator Brewery and user data generator.
-   * @param exporter Storage backend for generated brewery data.
-   */
-  BiergartenDataGenerator(std::unique_ptr<IEnrichmentService> context_service,
-                          std::unique_ptr<DataGenerator> generator,
-                          std::unique_ptr<IExportService> exporter);
-
-  /**
-   * @brief Run the data generation pipeline.
-   *
-   * Performs the following steps:
-   * 1. Load curated locations from JSON
-   * 2. Resolve context for each city using the injected context service
-   * 3. Generate brewery data for sampled cities
-   *
-   * @return true if successful, false if not
-   */
-  bool Run();
-
- private:
-  /// @brief Owning context provider dependency.
-  std::unique_ptr<IEnrichmentService> context_service_;
-
-  /// @brief Generator dependency selected in the composition root.
-  std::unique_ptr<DataGenerator> generator_;
-
-  /// @brief Storage backend for generated brewery records.
-  std::unique_ptr<IExportService> exporter_;
-
-  /**
-   * @brief Load locations from JSON and sample cities.
-   *
-   * @return Vector of sampled locations capped at 50 entries.
-   */
-  static std::vector<Location> QueryCitiesWithCountries();
-
-  /**
-   * @brief Generate breweries for enriched cities.
-   *
-   * @param cities Span of enriched city data.
-   */
-  void GenerateBreweries(std::span<const EnrichedCity> cities);
-
-  /**
-   * @brief Log the generated brewery results.
-   */
-  void LogResults() const;
-
-  /// @brief Stores generated brewery data.
-  std::vector<GeneratedBrewery> generated_breweries_;
-};
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_

tooling/pipeline/includes/biergarten_pipeline_orchestrator.h

@@ -0,0 +1,102 @@
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
+
+/**
+ * @file biergarten_data_generator.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>
+#include <span>
+#include <vector>
+
+#include "data_generation/data_generator.h"
+#include "data_model/generated_models.h"
+#include "services/database/export_service.h"
+#include "services/enrichment/enrichment_service.h"
+
+#include "services/logging/logger.h"
+
+/**
+ * @brief Main data generator class for the Biergarten pipeline.
+ *
+ * This class encapsulates the core logic for generating brewery data.
+ * It handles location loading, city enrichment, and brewery generation.
+ */
+class BiergartenPipelineOrchestrator {
+ public:
+/**
+ * @brief Constructs the orchestrator with injected pipeline dependencies.
+ *
+ * @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.
+ */
+  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.
+   *
+   * Performs the following steps:
+   * 1. Load curated locations from JSON
+   * 2. Resolve context for each city using the injected context service
+   * 3. Generate brewery data for sampled cities
+   *
+   * @note STRUCTURAL CONCURRENCY REQUIREMENT:
+   * When transitioned to a multithreaded design, this method MUST structurally
+   * enforce that all deployed worker threads are joined before returning (e.g.
+   * by using std::jthread or a structured concurrency primitive). This ensures
+   * workers do not attempt to log to a closed channel during application teardown.
+   *
+   * @return true if successful, false if not
+   */
+  bool Run();
+
+ private:
+  /// @brief Logger instance for emitting pipeline messages.
+  std::shared_ptr<ILogger> logger_;
+
+  /// @brief Owning context provider dependency.
+  std::unique_ptr<IEnrichmentService> context_service_;
+
+  /// @brief Generator dependency selected in the composition root.
+  std::unique_ptr<DataGenerator> generator_;
+
+   /// @brief Storage backend for generated brewery records.
+   std::unique_ptr<IExportService> exporter_;
+
+   /// @brief CLI configuration: paths, model settings, generation parameters.
+   ApplicationOptions application_options_;
+
+  /**
+   * @brief Load locations from JSON and sample cities.
+   *
+   * @return Vector of sampled locations capped at 50 entries.
+   */
+  std::vector<Location> QueryCitiesWithCountries();
+
+  /**
+   * @brief Generate breweries for enriched cities.
+   *
+   * @param cities Span of enriched city data.
+   */
+  void GenerateBreweries(std::span<const EnrichedCity> cities);
+
+  /**
+   * @brief Log the generated brewery results.
+   */
+  void LogResults() const;
+
+  /// @brief Stores generated brewery data.
+  std::vector<GeneratedBrewery> generated_breweries_;
+};
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_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 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/data_generator.h

@@ -8,9 +8,7 @@
 
 #include <string>
 
-#include "data_model/brewery_result.h"
-#include "data_model/location.h"
-#include "data_model/user_result.h"
+#include "data_model/generated_models.h"
 
 /**
  * @brief Interface for data generator implementations.

tooling/pipeline/includes/data_generation/llama_generator.h

@@ -14,9 +14,11 @@
 #include <string>
 #include <string_view>
 
+#include "../services/prompting/prompt_directory.h"
 #include "data_generation/data_generator.h"
 #include "data_generation/prompt_formatting/prompt_formatter.h"
-#include "data_model/application_options.h"
+#include "data_model/models.h"
+#include "services/logging/logger.h"
 
 struct llama_model;
 struct llama_context;
@@ -33,10 +35,12 @@ class LlamaGenerator final : public DataGenerator {
    * @param options Parsed application options.
    * @param model_path Filesystem path to GGUF model assets.
    * @param prompt_formatter Formatter that produces model-specific prompts.
+   * @param prompt_directory Directory service for loading named prompt files.
    */
   LlamaGenerator(const ApplicationOptions& options,
-                 const std::string& model_path,
-                 std::unique_ptr<IPromptFormatter> prompt_formatter);
+                 const std::string& model_path, std::shared_ptr<ILogger> logger,
+                 std::unique_ptr<IPromptFormatter> prompt_formatter,
+                 std::unique_ptr<IPromptDirectory> prompt_directory);
 
   ~LlamaGenerator() override;
 
@@ -119,15 +123,6 @@ class LlamaGenerator final : public DataGenerator {
                              int max_tokens = kDefaultMaxTokens,
                              std::string_view grammar = {});
 
-  /**
-   * @brief Loads the brewery system prompt from disk.
-   *
-   * @param prompt_file_path Prompt file path to try first.
-   * @return Loaded prompt text.
-   */
-  std::string LoadBrewerySystemPrompt(
-      const std::filesystem::path& prompt_file_path);
-
   ModelHandle model_;
   ContextHandle context_;
   float sampling_temperature_ = 1.0F;
@@ -135,8 +130,10 @@ class LlamaGenerator final : public DataGenerator {
   uint32_t sampling_top_k_ = kDefaultSamplingTopK;
   std::mt19937 rng_;
   uint32_t n_ctx_ = kDefaultContextSize;
-  std::string brewery_system_prompt_;
+  int n_gpu_layers_ = 0;
+  std::shared_ptr<ILogger> logger_;
   std::unique_ptr<IPromptFormatter> prompt_formatter_;
+  std::unique_ptr<IPromptDirectory> prompt_directory_;
 };
 
 #endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_LLAMA_GENERATOR_H_

tooling/pipeline/includes/data_generation/llama_generator_helpers.h

@@ -12,7 +12,7 @@
 #include <string>
 #include <string_view>
 
-#include "data_model/brewery_result.h"
+#include "data_model/generated_models.h"
 
 struct llama_vocab;
 using llama_token = int32_t;

tooling/pipeline/includes/data_generation/mock_generator.h

@@ -44,6 +44,13 @@ class MockGenerator final : public DataGenerator {
    */
   static size_t DeterministicHash(const Location& location);
 
+  // Hash stride constants for deterministic distribution across fixed-size
+  // arrays. These coprime strides spread hash values uniformly without
+  // clustering, ensuring diverse output across different hash inputs.
+  static constexpr size_t kNounHashStride = 7;
+  static constexpr size_t kDescriptionHashStride = 13;
+  static constexpr size_t kBioHashStride = 11;
+
   static constexpr std::array<std::string_view, 18> kBreweryAdjectives = {
       "Craft",      "Heritage", "Local",  "Artisan",  "Pioneer",    "Golden",
       "Modern",     "Classic",  "Summit", "Northern", "Riverstone", "Barrel",

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

@@ -1,4 +1,5 @@
-#pragma once
+#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_
 
 #include <string>
 #include <string_view>
@@ -13,3 +14,5 @@ class Gemma4JinjaPromptFormatter final : public IPromptFormatter {
   [[nodiscard]] std::string Format(std::string_view system_prompt,
                                    std::string_view user_prompt) const override;
 };
+
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_GEMMA4_JINJA_PROMPT_FORMATTER_H_

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

@@ -1,4 +1,5 @@
-#pragma once
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_PROMPT_FORMATTER_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_PROMPT_FORMATTER_H_
 
 #include <string>
 #include <string_view>
@@ -15,3 +16,5 @@ class IPromptFormatter {
   [[nodiscard]] virtual std::string Format(
       std::string_view system_prompt, std::string_view user_prompt) const = 0;
 };
+
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_PROMPT_FORMATTER_H_

tooling/pipeline/includes/data_model/application_options.h

@@ -1,42 +0,0 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_APPLICATION_OPTIONS_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_APPLICATION_OPTIONS_H_
-
-/**
- * @file data_model/application_options.h
- * @brief Program options for the Biergarten pipeline application.
- */
-
-#include <cstdint>
-#include <string>
-
-/**
- * @brief Program options for the Biergarten pipeline application.
- */
-struct ApplicationOptions {
-  /// @brief Path to the LLM model file (gguf format); mutually exclusive with
-  /// use_mocked.
-  std::string model_path;
-
-  /// @brief Use mocked generator instead of LLM; mutually exclusive with
-  /// model_path.
-  bool use_mocked = false;
-
-  /// @brief LLM sampling temperature (0.0 to 1.0, higher = more random).
-  float temperature = 1.0F;
-
-  /// @brief LLM nucleus sampling top-p parameter (0.0 to 1.0, higher = more
-  /// random).
-  float top_p = 0.95F;
-
-  /// @brief LLM top-k sampling parameter.
-  uint32_t top_k = 64;
-
-  /// @brief Context window size (tokens) for LLM inference. Higher values
-  /// support longer prompts but use more memory.
-  uint32_t n_ctx = 8192;
-
-  /// @brief Random seed for sampling (-1 for random, otherwise non-negative).
-  int seed = -1;
-};
-
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_APPLICATION_OPTIONS_H_

tooling/pipeline/includes/data_model/brewery_location.h

@@ -1,22 +0,0 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_BREWERY_LOCATION_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_BREWERY_LOCATION_H_
-
-/**
- * @file data_model/brewery_location.h
- * @brief Non-owning brewery location input.
- */
-
-#include <string_view>
-
-/**
- * @brief Non-owning brewery location input.
- */
-struct BreweryLocation {
-  /// @brief City name.
-  std::string_view city_name;
-
-  /// @brief Country name.
-  std::string_view country_name;
-};
-
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_BREWERY_LOCATION_H_

tooling/pipeline/includes/data_model/brewery_result.h

@@ -1,28 +0,0 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_BREWERY_RESULT_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_BREWERY_RESULT_H_
-
-/**
- * @file data_model/brewery_result.h
- * @brief Generated brewery payload.
- */
-
-#include <string>
-
-/**
- * @brief Generated brewery payload.
- */
-struct BreweryResult {
-  /// @brief Brewery display name in English.
-  std::string name_en;
-
-  /// @brief Brewery description text in English.
-  std::string description_en;
-
-  /// @brief Brewery display name in the local language.
-  std::string name_local;
-
-  /// @brief Brewery description text in the local language.
-  std::string description_local;
-};
-
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_BREWERY_RESULT_H_

tooling/pipeline/includes/data_model/enriched_city.h

@@ -1,21 +0,0 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_ENRICHED_CITY_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_ENRICHED_CITY_H_
-
-/**
- * @file data_model/enriched_city.h
- * @brief Enriched city data with Wikipedia context.
- */
-
-#include <string>
-
-#include "data_model/location.h"
-
-/**
- * @brief Enriched city data with Wikipedia context.
- */
-struct EnrichedCity {
-  Location location;
-  std::string region_context{};
-};
-
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_ENRICHED_CITY_H_

tooling/pipeline/includes/data_model/generated_brewery.h

@@ -1,20 +0,0 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATED_BREWERY_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATED_BREWERY_H_
-
-/**
- * @file data_model/generated_brewery.h
- * @brief Helper struct to store generated brewery data.
- */
-
-#include "data_model/brewery_result.h"
-#include "data_model/location.h"
-
-/**
- * @brief Helper struct to store generated brewery data.
- */
-struct GeneratedBrewery {
-  Location location;
-  BreweryResult brewery;
-};
-
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATED_BREWERY_H_

tooling/pipeline/includes/data_model/generated_models.h

@@ -0,0 +1,66 @@
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATED_MODELS_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATED_MODELS_H_
+
+/**
+ * @file data_model/generated_models.h
+ * @brief Generated output models from the pipeline: brewery/user results, enriched data,
+ * and complete generation results.
+ */
+
+#include <string>
+
+#include "data_model/models.h"
+
+// ============================================================================
+// Generation Output Models
+// ============================================================================
+
+/**
+ * @brief Generated brewery payload.
+ */
+struct BreweryResult {
+  /// @brief Brewery display name in English.
+  std::string name_en;
+
+  /// @brief Brewery description text in English.
+  std::string description_en;
+
+  /// @brief Brewery display name in the local language.
+  std::string name_local;
+
+  /// @brief Brewery description text in the local language.
+  std::string description_local;
+};
+
+/**
+ * @brief Generated user profile payload.
+ */
+struct UserResult {
+  /// @brief Username handle.
+  std::string username{};
+
+  /// @brief Short user biography.
+  std::string bio{};
+};
+
+// ============================================================================
+// Pipeline Data Models
+// ============================================================================
+
+/**
+ * @brief Enriched city data with Wikipedia context.
+ */
+struct EnrichedCity {
+  Location location;
+  std::string region_context{};
+};
+
+/**
+ * @brief Helper struct to store generated brewery data.
+ */
+struct GeneratedBrewery {
+  Location location;
+  BreweryResult brewery;
+};
+
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATED_MODELS_H_

tooling/pipeline/includes/data_model/generation_models.h

@@ -1,13 +0,0 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATION_MODELS_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATION_MODELS_H_
-
-/**
- * @file data_model/generation_models.h
- * @brief Convenience include for shared generation payload models.
- */
-
-#include "data_model/brewery_location.h"
-#include "data_model/brewery_result.h"
-#include "data_model/user_result.h"
-
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATION_MODELS_H_

tooling/pipeline/includes/data_model/location.h

@@ -1,41 +0,0 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_LOCATION_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_LOCATION_H_
-
-/**
- * @file data_model/location.h
- * @brief Location data model used throughout generation pipeline.
- */
-
-#include <string>
-#include <vector>
-
-/**
- * @brief Canonical location record for city-level generation.
- */
-struct Location {
-  /// @brief City name.
-  std::string city{};
-
-  /// @brief State or province name.
-  std::string state_province{};
-
-  /// @brief ISO 3166-2 subdivision code.
-  std::string iso3166_2{};
-
-  /// @brief Country name.
-  std::string country{};
-
-  /// @brief ISO 3166-1 country code.
-  std::string iso3166_1{};
-
-  /// @brief Local language codes in priority order.
-  std::vector<std::string> local_languages{};
-
-  /// @brief Latitude in decimal degrees.
-  double latitude{};
-
-  /// @brief Longitude in decimal degrees.
-  double longitude{};
-};
-
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_LOCATION_H_

tooling/pipeline/includes/data_model/models.h

@@ -0,0 +1,145 @@
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_MODELS_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_MODELS_H_
+
+/**
+ * @file data_model/models.h
+ * @brief Core data models: locations, application configuration, and generation
+ * inputs.
+ */
+
+#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;
+
+// ============================================================================
+// Location Models
+// ============================================================================
+
+/**
+ * @brief Canonical location record for city-level generation.
+ */
+struct Location {
+  /// @brief City name.
+  std::string city{};
+
+  /// @brief State or province name.
+  std::string state_province{};
+
+  /// @brief ISO 3166-2 subdivision code.
+  std::string iso3166_2{};
+
+  /// @brief Country name.
+  std::string country{};
+
+  /// @brief ISO 3166-1 country code.
+  std::string iso3166_1{};
+
+  /// @brief Local language codes in priority order.
+  std::vector<std::string> local_languages{};
+
+  /// @brief Latitude in decimal degrees.
+  double latitude{};
+
+  /// @brief Longitude in decimal degrees.
+  double longitude{};
+};
+
+/**
+ * @brief Non-owning brewery location input.
+ */
+struct BreweryLocation {
+  /// @brief City name.
+  std::string_view city_name;
+
+  /// @brief Country name.
+  std::string_view country_name;
+};
+
+// ============================================================================
+// Configuration Models
+// ============================================================================
+
+/**
+ * @brief LLM sampling parameters.
+ */
+struct SamplingOptions {
+  /// @brief LLM sampling temperature (0.0 to 1.0, higher = more random).
+  float temperature = 1.0F;
+
+  /// @brief LLM nucleus sampling top-p parameter.
+  float top_p = 0.95F;
+
+  /// @brief LLM top-k sampling parameter.
+  uint32_t top_k = 64;
+
+  /// @brief Context window size (tokens).
+  uint32_t n_ctx = 8192;
+
+  /// @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;
+};
+
+/**
+ * @brief Configuration for the LLM generator component.
+ */
+struct GeneratorOptions {
+  /// @brief Path to the LLM model file (gguf format).
+  std::filesystem::path model_path;
+
+  /// @brief Use mocked generator instead of actual LLM inference.
+  bool use_mocked = false;
+
+
+
+  /// @brief Specific sampling parameters for this generator.
+  /// If nullopt, the application should use global defaults.
+  std::optional<SamplingOptions> sampling;
+};
+
+/**
+ * @brief Configuration for the pipeline execution and output.
+ */
+struct PipelineOptions {
+  /// @brief Directory for generated artifacts.
+  std::filesystem::path output_path;
+
+  /// @brief Directory that contains named prompt files (e.g.
+  /// BREWERY_GENERATION.md).
+  std::filesystem::path prompt_dir;
+
+  /// @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;
+};
+
+/**
+ * @brief Root configuration object for the Biergarten pipeline.
+ */
+struct ApplicationOptions {
+  GeneratorOptions generator;
+  PipelineOptions pipeline;
+};
+
+// ============================================================================
+// Function Declarations
+// ============================================================================
+
+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/data_model/pipeline_models.h

@@ -1,12 +0,0 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_PIPELINE_MODELS_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_PIPELINE_MODELS_H_
-
-/**
- * @file data_model/pipeline_models.h
- * @brief Convenience include for pipeline-specific data models.
- */
-
-#include "data_model/enriched_city.h"
-#include "data_model/generated_brewery.h"
-
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_PIPELINE_MODELS_H_

tooling/pipeline/includes/data_model/user_result.h

@@ -1,22 +0,0 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_USER_RESULT_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_USER_RESULT_H_
-
-/**
- * @file data_model/user_result.h
- * @brief Generated user profile payload.
- */
-
-#include <string>
-
-/**
- * @brief Generated user profile payload.
- */
-struct UserResult {
-  /// @brief Username handle.
-  std::string username{};
-
-  /// @brief Short user biography.
-  std::string bio{};
-};
-
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_USER_RESULT_H_

tooling/pipeline/includes/json_handling/json_loader.h

@@ -7,16 +7,19 @@
  */
 
 #include <filesystem>
+#include <memory>
 #include <vector>
 
-#include "data_model/location.h"
+#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

@@ -1,12 +1,14 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_EXPORT_SERVICE_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_EXPORT_SERVICE_H_
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_EXPORT_SERVICE_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_EXPORT_SERVICE_H_
 
 /**
  * @file services/export_service.h
  * @brief Abstraction for persisting generated brewery data.
  */
 
-#include "data_model/generated_brewery.h"
+#include <cstdint>
+
+#include "data_model/generated_models.h"
 
 /**
  * @brief Interface for services that persist generated brewery records.
@@ -37,4 +39,4 @@ class IExportService {
   virtual void Finalize() = 0;
 };
 
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_EXPORT_SERVICE_H_
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_EXPORT_SERVICE_H_

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

@@ -1,5 +1,5 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_CONNECTION_HELPERS_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_CONNECTION_HELPERS_H_
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_CONNECTION_HELPERS_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_CONNECTION_HELPERS_H_
 
 /**
  * @file services/sqlite_connection_helpers.h
@@ -7,11 +7,12 @@
  */
 
 #include <sqlite3.h>
+
 #include <filesystem>
 #include <string>
 #include <string_view>
 
-#include "services/sqlite_handle_types.h"
+#include "sqlite_handle_types.h"
 
 namespace sqlite_export_service_internal {
 
@@ -26,6 +27,4 @@ void RollbackTransactionNoThrow(const SqliteDatabaseHandle& db_handle) noexcept;
 
 }  // namespace sqlite_export_service_internal
 
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_CONNECTION_HELPERS_H_
-
-
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_CONNECTION_HELPERS_H_

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

@@ -1,5 +1,5 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_EXPORT_SERVICE_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_EXPORT_SERVICE_H_
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_EXPORT_SERVICE_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_EXPORT_SERVICE_H_
 
 /**
  * @file services/sqlite_export_service.h
@@ -11,16 +11,17 @@
 #include <string>
 #include <unordered_map>
 
-#include "services/date_time_provider.h"
-#include "services/export_service.h"
-#include "services/sqlite_export_service_helpers.h"
+#include "data_model/models.h"
+#include "../datetime/date_time_provider.h"
+#include "export_service.h"
+#include "sqlite_export_service_helpers.h"
 
 /**
  * @brief Persists generated brewery records into a fresh SQLite database.
  */
 class SqliteExportService final : public IExportService {
  public:
-  SqliteExportService();
+  explicit SqliteExportService(const ApplicationOptions& options);
   ~SqliteExportService() override;
 
   SqliteExportService(const SqliteExportService&) = delete;
@@ -41,12 +42,12 @@ class SqliteExportService final : public IExportService {
   void InitializeSchema() const;
   void PrepareStatements();
   void RollbackAndCloseNoThrow() noexcept;
-  void FinalizeStatements() noexcept;
 
   [[nodiscard]] std::filesystem::path BuildDatabasePath() const;
   [[nodiscard]] static std::string BuildLocationKey(const Location& location);
 
   std::unique_ptr<IDateTimeProvider> date_time_provider_;
+  std::filesystem::path output_path_;
   std::string run_timestamp_utc_;
   std::filesystem::path database_path_;
   SqliteDatabaseHandle db_handle_;
@@ -56,4 +57,4 @@ class SqliteExportService final : public IExportService {
   std::unordered_map<std::string, sqlite3_int64> location_cache_;
 };
 
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_EXPORT_SERVICE_H_
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_EXPORT_SERVICE_H_

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

@@ -0,0 +1,10 @@
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_EXPORT_SERVICE_HELPERS_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_EXPORT_SERVICE_HELPERS_H_
+
+/* Umbrella header for backward compatibility. */
+
+#include "sqlite_connection_helpers.h"
+#include "sqlite_handle_types.h"
+#include "sqlite_statement_helpers.h"
+
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_EXPORT_SERVICE_HELPERS_H_

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

@@ -1,11 +1,12 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_HANDLE_TYPES_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_HANDLE_TYPES_H_
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_HANDLE_TYPES_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_HANDLE_TYPES_H_
 
 /**
  * Shared handle and parameter type declarations used by SQLite helper units.
  */
 
 #include <sqlite3.h>
+
 #include <memory>
 #include <string_view>
 
@@ -32,5 +33,4 @@ struct BindParam {
 
 }  // namespace sqlite_export_service_internal
 
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_HANDLE_TYPES_H_
-
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_HANDLE_TYPES_H_

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

@@ -1,17 +1,19 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_STATEMENT_HELPERS_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_STATEMENT_HELPERS_H_
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_STATEMENT_HELPERS_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_STATEMENT_HELPERS_H_
 
 /**
  * @file services/sqlite_statement_helpers.h
- * @brief Declarations for statement-level SQLite helper functions and constants.
+ * @brief Declarations for statement-level SQLite helper functions and
+ * constants.
  */
 
 #include <sqlite3.h>
+
 #include <string>
 #include <string_view>
 #include <vector>
 
-#include "services/sqlite_handle_types.h"
+#include "sqlite_handle_types.h"
 
 namespace sqlite_export_service_internal {
 
@@ -107,10 +109,8 @@ void StepStatement(const SqliteDatabaseHandle& db_handle,
 
 sqlite3_int64 LastInsertRowId(const SqliteDatabaseHandle& db_handle);
 
-std::string SerializeLocalLanguages(const std::vector<std::string>& local_languages);
 std::string SerializeVector(const std::vector<std::string>& str_vec);
 
 }  // namespace sqlite_export_service_internal
 
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_STATEMENT_HELPERS_H_
-
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_STATEMENT_HELPERS_H_

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

@@ -1,5 +1,5 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATE_TIME_PROVIDER_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATE_TIME_PROVIDER_H_
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATETIME_DATE_TIME_PROVIDER_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATETIME_DATE_TIME_PROVIDER_H_
 
 /**
  * @file services/date_time_provider.h
@@ -63,4 +63,4 @@ class SystemDateTimeProvider final : public IDateTimeProvider {
   }
 };
 
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATE_TIME_PROVIDER_H_
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATETIME_DATE_TIME_PROVIDER_H_

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

@@ -0,0 +1,35 @@
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATETIME_TIMER_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATETIME_TIMER_H_
+
+#include <chrono>
+
+/**
+ * @file services/timer.h
+ * @brief Simple timer utility for measuring elapsed time.
+ */
+class Timer {
+  std::chrono::steady_clock::time_point start_time =
+      std::chrono::steady_clock::now();
+
+ public:
+  Timer(const Timer&) = delete;
+  Timer& operator=(const Timer&) = delete;
+  Timer(Timer&&) = delete;
+  Timer& operator=(Timer&&) = delete;
+  Timer() = default;
+  ~Timer() = default;
+
+  [[nodiscard]] int64_t Elapsed() const {
+    return std::chrono::duration_cast<std::chrono::milliseconds>(
+               std::chrono::steady_clock::now() - start_time)
+        .count();
+  }
+
+  [[nodiscard]] int64_t Reset() {
+    auto previous_elapsed = Elapsed();
+    start_time = std::chrono::steady_clock::now();
+    return previous_elapsed;
+  }
+};
+
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATETIME_TIMER_H_

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

@@ -1,5 +1,5 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_SERVICE_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_SERVICE_H_
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_ENRICHMENT_SERVICE_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_ENRICHMENT_SERVICE_H_
 
 /**
  * @file services/enrichment_service.h
@@ -8,7 +8,7 @@
 
 #include <string>
 
-#include "data_model/location.h"
+#include "data_model/models.h"
 
 /**
  * @brief Interface for services that can enrich a location with context.
@@ -27,4 +27,4 @@ class IEnrichmentService {
   virtual std::string GetLocationContext(const Location& loc) = 0;
 };
 
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_SERVICE_H_
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_ENRICHMENT_SERVICE_H_

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

@@ -0,0 +1,17 @@
+//
+// Created by aaronpo on 13/05/2026.
+//
+
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_MOCK_ENRICHMENT_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_MOCK_ENRICHMENT_H_
+#include <string>
+
+#include "enrichment_service.h"
+
+class MockEnrichmentService final : public IEnrichmentService {
+ public:
+  std::string GetLocationContext(const Location& /*loc*/) override {
+    return {};
+  }
+};
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_MOCK_ENRICHMENT_H_

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

@@ -1,5 +1,5 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_WIKIPEDIA_SERVICE_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_WIKIPEDIA_SERVICE_H_
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_WIKIPEDIA_SERVICE_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_WIKIPEDIA_SERVICE_H_
 
 /**
  * @file services/wikipedia_service.h
@@ -11,14 +11,16 @@
 #include <string_view>
 #include <unordered_map>
 
-#include "services/enrichment_service.h"
+#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;
@@ -26,8 +28,9 @@ 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_;
 };
 
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_WIKIPEDIA_SERVICE_H_
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_WIKIPEDIA_SERVICE_H_

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 +1,88 @@
+/**
+ * @file services/logging/log_entry.h
+ * @brief Structured log record shared by the pipeline logging infra.
+ *
+ * LogEntry is a lightweight value type that can be passed safely between the
+ * logging producer and dispatcher through BoundedChannel<LogEntry>.
+ */
+
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_ENTRY_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_ENTRY_H_
+
+#include <chrono>
+#include <source_location>
+#include <string>
+#include <thread>
+#include <vector>
+
+/**
+ * @enum LogLevel
+ * @brief Severity levels supported by the logging infra.
+ */
+enum class LogLevel {
+  Debug,  ///< Development/debugging information.
+  Info,   ///< General informational messages.
+  Warn,   ///< Warning conditions.
+  Error,  ///< Error conditions.
+};
+
+/**
+ * @enum PipelinePhase
+ * @brief Pipeline execution phases used to tag log records.
+ *
+ * The phase tag makes it easier to correlate log output with the part of the
+ * pipeline that emitted it.
+ */
+enum class PipelinePhase {
+  Startup,                   ///< Initialization and validation.
+  UserGeneration,            ///< User profile generation.
+  BreweryAndBeerGeneration,  ///< Brewery and beer data generation.
+  CheckinGeneration,         ///< Checkin (visit) record generation.
+  RatingGeneration,          ///< Rating and review generation.
+  FollowGeneration,          ///< Follow relationship generation.
+  Teardown,                  ///< Finalization and cleanup.
+};
+
+/**
+ * @struct LogDTO
+ * @brief User-provided subset of log fields. Used to capture call-site info transparently.
+ */
+struct LogDTO {
+  LogLevel level;
+  PipelinePhase phase;
+  std::string message;
+};
+
+/**
+ * @struct LogEntry
+ * @brief Single structured log event.
+ *
+ * All fields are value types, which keeps transfer across the bounded channel
+ * simple and avoids shared ownership.
+ *
+ * NOTE: timestamp, thread_id, and origin must be populated by ILogger::Log()
+ * before the entry is dispatched.
+ */
+struct LogEntry {
+  /// @brief Timestamp when the entry was created.
+  std::chrono::system_clock::time_point timestamp{};
+
+  /// @brief Source location where the log call was made.
+  std::source_location origin{};
+
+  /// @brief Thread responsible for emitting the log.
+  std::thread::id thread_id{};
+
+
+  /// @brief Severity level of this entry.
+  LogLevel level;
+
+  /// @brief Pipeline phase associated with the entry.
+  PipelinePhase phase;
+
+  /// @brief Log message text.
+  std::string message;
+
+};
+
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_ENTRY_H_

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

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

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

@@ -0,0 +1,64 @@
+/**
+ * @file services/logging/logger.h
+ * @brief Abstract logging interface used by pipeline components.
+ *
+ * The interface keeps application code independent from the concrete logging
+ * transport, buffering, and formatting implementation.
+ */
+
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_
+
+#include <source_location>
+#include <string>
+#include <utility>
+
+#include "services/logging/log_entry.h"
+
+/**
+ * @class ILogger
+ * @brief Minimal interface for submitting structured log messages.
+ *
+ * Implementations are non-copyable and non-movable. They are typically owned
+ * by the composition root and injected into services that emit diagnostics.
+ */
+class ILogger {
+ public:
+  ILogger() = default;
+  ILogger(const ILogger&) = delete;
+  ILogger& operator=(const ILogger&) = delete;
+  ILogger(ILogger&&) = delete;
+  ILogger& operator=(ILogger&&) = delete;
+  virtual ~ILogger() = default;
+
+  /**
+   * @brief Submit a log message to the logging subsystem.
+   *
+   * @param payload User-provided log data (level, phase, message).
+   * @param origin Auto-captured source location of the call site.
+   */
+  void Log(LogDTO payload,
+           std::source_location origin = std::source_location::current(),
+           std::chrono::system_clock::time_point timestamp = std::chrono::system_clock::now(),
+           std::thread::id thread_id = std::this_thread::get_id()) {
+    LogEntry entry;
+    entry.timestamp = timestamp;
+    entry.thread_id = thread_id;
+    entry.level = payload.level;
+    entry.phase = payload.phase;
+    entry.message = std::move(payload.message);
+    entry.origin = origin;
+    DoLog(std::move(entry));
+  }
+
+ protected:
+  /**
+   * @brief Underlying implementation to transport the log entry.
+   *
+   * Implementations must be thread-safe as DoLog can be called concurrently
+   * from multiple worker threads.
+   */
+  virtual void DoLog(LogEntry log_entry) = 0;
+};
+
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_

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

@@ -0,0 +1,82 @@
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_PROMPTING_PROMPT_DIRECTORY_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_PROMPTING_PROMPT_DIRECTORY_H_
+
+/**
+ * @file services/prompt_directory.h
+ * @brief Interface and filesystem-backed implementation for named prompt
+ * loading.
+ *
+ * Prompt files are resolved by key: a key of "BREWERY_GENERATION" maps to the
+ * file <prompt_dir>/BREWERY_GENERATION.md.  The interface is kept intentionally
+ * narrow so test doubles can be injected without touching the filesystem.
+ */
+
+#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.
+ */
+class IPromptDirectory {
+ public:
+  IPromptDirectory() = default;
+  IPromptDirectory(const IPromptDirectory&) = delete;
+  IPromptDirectory& operator=(const IPromptDirectory&) = delete;
+  IPromptDirectory(IPromptDirectory&&) = delete;
+  IPromptDirectory& operator=(IPromptDirectory&&) = delete;
+  virtual ~IPromptDirectory() = default;
+
+  /**
+   * @brief Loads the prompt associated with @p key.
+   *
+   * @param key Logical prompt key, e.g. "BREWERY_GENERATION".
+   * @return Prompt text.
+   * @throws std::runtime_error if the prompt file cannot be found or read.
+   */
+  [[nodiscard]] virtual std::string Load(std::string_view key) = 0;
+};
+
+/**
+ * @brief Filesystem-backed IPromptDirectory implementation.
+ *
+ * Each call to Load() checks an in-process cache first, then reads
+ * <prompt_dir>/<key>.md from disk.  The directory must exist and be readable
+ * at construction time; individual file absence is reported lazily at Load().
+ */
+class PromptDirectory final : public IPromptDirectory {
+ public:
+  /**
+   * @brief Constructs a PromptDirectory rooted at @p prompt_dir.
+   *
+   * @param prompt_dir Absolute or relative path to the prompt directory.
+   * @throws std::runtime_error if @p prompt_dir does not exist or is not a
+   *         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.
+   *
+   * Maps @p key → <prompt_dir>/<key>.md.
+   *
+   * @param key Logical prompt key.
+   * @return Prompt text.
+   * @throws std::runtime_error if the file does not exist or is empty.
+   */
+  [[nodiscard]] std::string Load(std::string_view key) override;
+
+ private:
+  std::filesystem::path prompt_dir_;
+  std::shared_ptr<ILogger> logger_;
+  std::unordered_map<std::string, std::string> cache_;
+};
+
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_PROMPTING_PROMPT_DIRECTORY_H_

tooling/pipeline/includes/services/sqlite_export_service_helpers.h

@@ -1,10 +0,0 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_EXPORT_SERVICE_HELPERS_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_EXPORT_SERVICE_HELPERS_H_
-
-/* Umbrella header for backward compatibility. */
-
-#include "services/sqlite_handle_types.h"
-#include "services/sqlite_connection_helpers.h"
-#include "services/sqlite_statement_helpers.h"
-
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_EXPORT_SERVICE_HELPERS_H_

tooling/pipeline/includes/web_client/curl_web_client.h

@@ -1,54 +0,0 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_CURL_WEB_CLIENT_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_CURL_WEB_CLIENT_H_
-
-/**
- * @file web_client/curl_web_client.h
- * @brief libcurl-based WebClient implementation.
- */
-
-#include "web_client/web_client.h"
-
-/**
- * @brief RAII wrapper for curl_global_init and curl_global_cleanup.
- *
- * Create one instance in application startup before using libcurl and keep it
- * alive for application lifetime.
- */
-class CurlGlobalState {
- public:
-  /// @brief Initializes global libcurl state.
-  CurlGlobalState();
-
-  /// @brief Cleans up global libcurl state.
-  ~CurlGlobalState();
-
-  /// @brief Non-copyable type.
-  CurlGlobalState(const CurlGlobalState&) = delete;
-
-  /// @brief Non-copyable type.
-  CurlGlobalState& operator=(const CurlGlobalState&) = delete;
-};
-
-/**
- * @brief WebClient implementation backed by libcurl.
- */
-class CURLWebClient : public WebClient {
- public:
-  /**
-   * @brief Executes an HTTP GET request.
-   *
-   * @param url Request URL.
-   * @return Response body.
-   */
-  std::string Get(const std::string& url) override;
-
-  /**
-   * @brief URL-encodes a string value.
-   *
-   * @param value Raw value.
-   * @return URL-encoded string.
-   */
-  std::string UrlEncode(const std::string& value) override;
-};
-
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_CURL_WEB_CLIENT_H_

tooling/pipeline/includes/web_client/http_web_client.h

@@ -0,0 +1,56 @@
+/**
+* @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 "services/logging/logger.h"
+
+#include <memory>
+#include <string>
+#include <utility>
+
+/**
+ * @brief WebClient implementation backed by cpp-httplib.
+ *
+ * Supports HTTP and HTTPS (requires OpenSSL; see HTTPLIB_REQUIRE_OPENSSL
+ * in CMakeLists.txt).
+ *
+ * URL parsing splits a full URL into origin (scheme://host[:port]) and
+ * path + query so that httplib::Client can be constructed correctly.
+ * A new client instance is created per request because the client is
+ * bound to a single origin at construction time.
+ */
+class HttpWebClient final : public WebClient {
+public:
+  explicit HttpWebClient(std::shared_ptr<ILogger> logger)
+      : logger_(std::move(logger)) {}
+  ~HttpWebClient() override = default;
+
+  /**
+   * @brief Executes a blocking HTTP/HTTPS GET request against a full URL.
+   *
+   * @param url Fully-qualified URL, e.g. "https://en.wikipedia.org/api/rest_v1/page/summary/Berlin"
+   * @return Response body on HTTP 2xx; throws std::runtime_error otherwise.
+   */
+  std::string Get(const std::string& url) override;
+
+  /**
+   * @brief Percent-encodes a single URI component (query parameter value or
+   *        path segment). Delegates to httplib::encode_uri_component().
+   *
+   * @param value Raw string to encode.
+   * @return Percent-encoded string safe for use in a URL.
+   */
+  std::string EncodeURL(const std::string& value) override;
+
+ private:
+  std::shared_ptr<ILogger> logger_;
+};
+
+
+#endif

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/runpod/.dockerignore

@@ -0,0 +1,9 @@
+# Ignore model files!
+*.gguf
+*.bin
+models/
+weights/
+
+# Ignore local build folders
+build/
+.git/

tooling/pipeline/runpod/Dockerfile

@@ -0,0 +1,72 @@
+# --- Stage 1: Build Environment (The "Heavy" Stage) ---
+FROM nvidia/cuda:12.6.3-devel-ubuntu24.04 AS builder
+
+ENV DEBIAN_FRONTEND=noninteractive \
+  CMAKE_GENERATOR=Ninja
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+  build-essential ca-certificates curl git libboost-json-dev \
+  libboost-program-options-dev libssl-dev ninja-build pkg-config zlib1g-dev \
+  && rm -rf /var/lib/apt/lists/*
+
+# Install modern CMake
+RUN curl -L https://github.com/Kitware/CMake/releases/download/v3.31.0/cmake-3.31.0-linux-x86_64.sh -o cmake.sh && \
+  sh cmake.sh --skip-license --prefix=/usr/local && rm cmake.sh
+
+# Get headers for C++ build
+RUN curl -L https://github.com/ggml-org/llama.cpp/archive/refs/tags/b9012.tar.gz -o /tmp/llama-src.tar.gz && \
+  tar -xzf /tmp/llama-src.tar.gz -C /tmp && \
+  cp -r /tmp/llama.cpp-b9012/include/* /usr/local/include/ && \
+  cp -r /tmp/llama.cpp-b9012/ggml/include/* /usr/local/include/
+
+# Pull llama.cpp binaries to use during build if needed
+COPY --from=ghcr.io/ggml-org/llama.cpp:full-cuda /app/lib*.so* /usr/local/lib/
+
+WORKDIR /app
+COPY . .
+
+# Build the C++ pipeline
+RUN cmake -S . -B build -G Ninja -DCMAKE_BUILD_TYPE=Release && \
+  cmake --build build -j$(nproc)
+
+# --- Stage 2: Runtime Environment (The "Slim" Stage) ---
+FROM nvidia/cuda:12.6.3-runtime-ubuntu24.04 AS runtime
+
+# Install only necessary runtime shared libraries
+RUN apt-get update && apt-get install -y --no-install-recommends \
+  curl \
+  ca-certificates \
+  libboost-json1.83.0 \
+  libboost-program-options1.83.0 \
+  libgomp1 \
+  libssl3 \
+  zlib1g \
+  && rm -rf /var/lib/apt/lists/*
+
+ENV APP_ROOT=/app \
+  LD_LIBRARY_PATH="/usr/local/lib:${LD_LIBRARY_PATH}"
+
+WORKDIR /app/build
+
+# Copy only the compiled binaries from the builder
+COPY --from=builder /app/build/biergarten-pipeline ./
+
+# Copy required config files
+COPY locations.json /app/build/
+COPY beer-styles.json /app/build/
+
+# Copy prompt templates
+COPY prompts /app/prompts
+
+# Copy only the necessary shared libraries from builder/llama-bin
+COPY --from=ghcr.io/ggml-org/llama.cpp:full-cuda /app/lib*.so* /usr/local/lib/
+
+# Co-locate plugins
+RUN cp /usr/local/lib/libggml-cuda.so . 2>/dev/null || true && \
+  cp /usr/local/lib/libggml-cpu*.so . 2>/dev/null || true
+
+# Setup Start Script
+COPY ./runpod/start.sh /usr/local/bin/biergarten-start
+RUN chmod +x /usr/local/bin/biergarten-start
+
+ENTRYPOINT ["/usr/local/bin/biergarten-start"]

tooling/pipeline/runpod/README.md

@@ -0,0 +1,8 @@
+```bash
+touch runpod/start.sh
+docker build \
+ --progress=plain \
+ -t biergarten-pipeline:latest \
+ -f runpod/Dockerfile \
+ . 2>&1 | tee build.log
+```

tooling/pipeline/runpod/pod-template.yaml

@@ -0,0 +1,22 @@
+name: biergarten-pipeline-live
+imageName: biergarten-pipeline:latest
+category: NVIDIA
+containerDiskInGb: 50
+volumeInGb: 50
+volumeMountPath: /workspace
+dockerEntrypoint:
+  - /usr/local/bin/biergarten-start
+dockerStartCmd: []
+isPublic: false
+isServerless: false
+env:
+  BIERGARTEN_MODE: live
+  BIERGARTEN_MODEL_PATH: /workspace/models/google_gemma-4-E4B-it-Q6_K.gguf
+  BIERGARTEN_PROMPT_DIR: /workspace/app/build/prompts
+  BIERGARTEN_OUTPUT_DIR: /workspace/output
+  BIERGARTEN_LOG_PATH: /workspace/logs/pipeline.log
+  BIERGARTEN_TEMPERATURE: "1.0"
+  BIERGARTEN_TOP_P: "0.95"
+  BIERGARTEN_TOP_K: "64"
+  BIERGARTEN_N_CTX: "8192"
+  BIERGARTEN_SEED: "-1"

tooling/pipeline/runpod/start.sh

@@ -0,0 +1,58 @@
+#!/bin/bash
+set -e
+
+MODEL_PATH="${BIERGARTEN_MODEL_PATH:-/workspace/models/google_gemma-4-E4B-it-Q6_K.gguf}"
+OUTPUT_DIR="${BIERGARTEN_OUTPUT_DIR:-/workspace/output}"
+LOG_PATH="${BIERGARTEN_LOG_PATH:-/workspace/logs/pipeline.log}"
+EXECUTABLE="/app/build/biergarten-pipeline"
+PROMPT_DIR="/app/prompts"
+
+echo "--- Starting Biergarten Pipeline Environment Check ---"
+
+# Ensure directories exist
+mkdir -p "$OUTPUT_DIR"
+mkdir -p "$(dirname "$LOG_PATH")"
+mkdir -p "$(dirname "$MODEL_PATH")"
+
+# Download model if missing
+if [ ! -f "$MODEL_PATH" ]; then
+    echo "Model not found. Downloading (this may take a while)..."
+
+    curl -L -C - \
+      -o "$MODEL_PATH" \
+      "https://huggingface.co/bartowski/google_gemma-4-E4B-it-GGUF/resolve/main/google_gemma-4-E4B-it-Q6_K.gguf?download=true"
+
+    echo "Download complete."
+fi
+
+# Verify model exists
+if [ ! -f "$MODEL_PATH" ]; then
+    echo "ERROR: Model still not found after download attempt."
+    exit 1
+fi
+
+# Default GPU layers
+GL_LAYERS="${BIERGARTEN_GL_LAYERS:-40}"
+
+# Build args
+ARGS=(
+    "--model"      "$MODEL_PATH"
+    "--prompt-dir" "$PROMPT_DIR"
+    "--output"     "$OUTPUT_DIR"
+    "--log-path"   "$LOG_PATH"
+    "--n-gpu-layers" "$GL_LAYERS"
+)
+
+# Optional params
+[[ -n "$BIERGARTEN_TEMPERATURE" ]] && ARGS+=("--temperature"  "$BIERGARTEN_TEMPERATURE")
+[[ -n "$BIERGARTEN_TOP_P" ]]       && ARGS+=("--top-p"        "$BIERGARTEN_TOP_P")
+[[ -n "$BIERGARTEN_TOP_K" ]]       && ARGS+=("--top-k"        "$BIERGARTEN_TOP_K")
+[[ -n "$BIERGARTEN_N_CTX" ]]       && ARGS+=("--n-ctx"        "$BIERGARTEN_N_CTX")
+[[ -n "$BIERGARTEN_SEED" ]]        && ARGS+=("--seed"         "$BIERGARTEN_SEED")
+
+# Extra args
+[[ -n "$BIERGARTEN_EXTRA_ARGS" ]] && ARGS+=($BIERGARTEN_EXTRA_ARGS)
+
+echo "--- Executing: $EXECUTABLE ${ARGS[*]} ---"
+
+exec "$EXECUTABLE" "${ARGS[@]}"

tooling/pipeline/src/application_options/parse_arguments.cc

@@ -0,0 +1,214 @@
+#include <chrono>
+#include <format>
+#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::shared_ptr<ILogger> logger) {
+  prog_opts::options_description desc("Pipeline Options");
+  auto opt = desc.add_options();
+
+  opt("help,h", "Produce help message");
+
+  // Defaults sourced from SamplingOptions{} so the CLI and LlamaGenerator
+  // share a single source of truth — changing the struct updates both.
+  auto add_sampling_options = [&]() -> void {
+    const SamplingOptions sampling_defaults{};
+    opt("temperature",
+        prog_opts::value<float>()->default_value(sampling_defaults.temperature),
+        "Sampling temperature (higher = more random)");
+    opt("top-p",
+        prog_opts::value<float>()->default_value(sampling_defaults.top_p),
+        "Nucleus sampling top-p in (0,1] (higher = more random)");
+    opt("top-k",
+        prog_opts::value<uint32_t>()->default_value(sampling_defaults.top_k),
+        "Top-k sampling parameter (higher = more candidate tokens)");
+    opt("n-ctx",
+        prog_opts::value<uint32_t>()->default_value(sampling_defaults.n_ctx),
+        "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
+  // rather than at registration to produce a clear diagnostic message.
+  auto add_generator_options = [&]() -> void {
+    opt("mocked", prog_opts::bool_switch(),
+        "Use mocked generator for brewery/user data");
+    opt("model,m", prog_opts::value<std::string>()->default_value(""),
+        "Path to LLM model (gguf)");
+  };
+
+  auto add_pipeline_options = [&]() -> void {
+    opt("output,o", prog_opts::value<std::string>()->default_value("output"),
+        "Directory for generated artifacts");
+    opt("log-path",
+        prog_opts::value<std::string>()->default_value("pipeline.log"),
+        "Path for application logs");
+    opt("prompt-dir", prog_opts::value<std::string>()->default_value(""),
+        "Directory containing named prompt files (e.g. BREWERY_GENERATION.md)."
+        " Required when not using --mocked.");
+    opt("location-count", prog_opts::value<uint32_t>()->default_value(10));
+  };
+
+  add_sampling_options();
+  add_generator_options();
+  add_pipeline_options();
+
+  // No flags provided — treat as a help request rather than an error.
+  if (argc == 1) {
+    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(LogDTO{.level = LogLevel::Info,
+                   .phase = PipelinePhase::Startup,
+                   .message = title});
+      logger->Log(LogDTO{.level = LogLevel::Info,
+                   .phase = PipelinePhase::Startup,
+                   .message = usage});
+    }
+    return std::nullopt;
+  }
+
+  try {
+    prog_opts::variables_map var_map;
+    prog_opts::store(prog_opts::parse_command_line(argc, argv, desc), var_map);
+    prog_opts::notify(var_map);
+
+    if (var_map.contains("help")) {
+      std::stringstream help_stream;
+      help_stream << "\n" << desc;
+      if (logger) {
+        logger->Log(LogDTO{.level = LogLevel::Info,
+                     .phase = PipelinePhase::Startup,
+                     .message = help_stream.str()});
+      }
+      return std::nullopt;
+    }
+
+    ApplicationOptions options;
+
+    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>();
+    const int n_gpu_layers = var_map["n-gpu-layers"].as<int>();
+
+    // Enforce mutual exclusivity before any further configuration is applied.
+    if (use_mocked && !model_path.empty()) {
+      const std::string msg =
+          "Invalid arguments: --mocked and --model are mutually exclusive";
+      if (logger) {
+        logger->Log(LogDTO{.level = LogLevel::Error,
+                     .phase = PipelinePhase::Startup,
+                     .message = msg});
+      } else {
+        std::cerr << msg << std::endl;
+      }
+      return std::nullopt;
+    }
+
+    if (!use_mocked && model_path.empty()) {
+      const std::string msg =
+          "Invalid arguments: either --mocked or --model must be specified";
+      if (logger) {
+        logger->Log(LogDTO{.level = LogLevel::Error,
+                     .phase = PipelinePhase::Startup,
+                     .message = msg});
+      } else {
+        std::cerr << msg << std::endl;
+      }
+      return std::nullopt;
+    }
+
+    // Prompt directory is only meaningful for live inference — the mock
+    // generator has no use for it and should not require it to be present.
+    if (!use_mocked && options.pipeline.prompt_dir.empty()) {
+      const std::string msg =
+          "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;
+
+    // Only populate sampling config when the user explicitly overrides at
+    // least one value. Leaving it as std::nullopt lets LlamaGenerator fall
+    // back to its own SamplingOptions{} defaults, keeping the two paths
+    // consistent without redundant copies.
+    const bool user_provided_sampling =
+        !var_map["temperature"].defaulted() || !var_map["top-p"].defaulted() ||
+        !var_map["top-k"].defaulted() || !var_map["n-ctx"].defaulted() ||
+        !var_map["seed"].defaulted() || !var_map["n_gpu_layers"].defaulted();
+
+    if (user_provided_sampling) {
+      // Warn but do not fail — the run is still valid, the flags are just
+      // silently irrelevant when no model is loaded.
+      if (use_mocked) {
+        const std::string msg =
+            "Sampling parameters are ignored when using --mocked";
+        if (logger) {
+          logger->Log(LogDTO{.level = LogLevel::Warn,
+                       .phase = PipelinePhase::Startup,
+                       .message = msg});
+        } else {
+          std::cerr << msg << std::endl;
+        }
+      } else {
+        SamplingOptions sampling;
+        sampling.temperature = var_map["temperature"].as<float>();
+        sampling.top_p = var_map["top-p"].as<float>();
+        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;
+      }
+    }
+
+    return options;
+
+  } catch (const std::exception& exception) {
+    const std::string msg =
+        std::string("Failed to parse command-line arguments: ") +
+        exception.what();
+    if (logger) {
+      logger->Log(LogDTO{.level = LogLevel::Error,
+                   .phase = PipelinePhase::Startup,
+                   .message = msg});
+    }
+    return std::nullopt;
+  } catch (...) {
+    const std::string msg =
+        "Failed to parse command-line arguments: unknown error";
+    if (logger) {
+      logger->Log(LogDTO{.level = LogLevel::Error,
+                   .phase = PipelinePhase::Startup,
+                   .message = msg});
+    }
+    return std::nullopt;
+  }
+}

tooling/pipeline/src/biergarten_data_generator/biergarten_data_generator.cc

@@ -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 +1,68 @@
+/**
+ * @file biergarten_pipeline_orchestrator/generate_breweries.cc
+ * @brief BiergartenDataGenerator::GenerateBreweries() implementation.
+ */
+
+#include <chrono>
+#include <format>
+
+#include "biergarten_pipeline_orchestrator.h"
+#include "services/logging/logger.h"
+
+void BiergartenPipelineOrchestrator::GenerateBreweries(
+    std::span<const EnrichedCity> cities) {
+  logger_->Log({.level = LogLevel::Info,
+                .phase = PipelinePhase::BreweryAndBeerGeneration,
+                .message = "=== SAMPLE BREWERY GENERATION ==="});
+
+  generated_breweries_.clear();
+  size_t skipped_count = 0;
+  size_t export_failed_count = 0;
+
+  for (const auto& [location, region_context] : cities) {
+    try {
+      const BreweryResult brewery =
+          generator_->GenerateBrewery(location, region_context);
+
+      const GeneratedBrewery gen{.location = location, .brewery = brewery};
+
+      generated_breweries_.push_back(gen);
+
+      try {
+        exporter_->ProcessRecord(gen);
+      } catch (const std::exception& export_exception) {
+        ++export_failed_count;
+
+        logger_->Log(
+            {.level = LogLevel::Warn,
+             .phase = PipelinePhase::BreweryAndBeerGeneration,
+             .message =
+                 std::format("[Pipeline] Generated brewery for '{}' ({}) but SQLite export failed: {}",
+                 location.city, location.country, export_exception.what())});
+      }
+    } catch (const std::exception& e) {
+      ++skipped_count;
+
+      logger_->Log({.level = LogLevel::Warn,
+                    .phase = PipelinePhase::BreweryAndBeerGeneration,
+                    .message = std::format("[Pipeline] Skipping city '{}' ({}): brewery generation failed: {}",
+                               location.city, location.country, e.what())});
+    }
+  }
+
+  if (skipped_count > 0) {
+    logger_->Log({.level = LogLevel::Warn,
+                  .phase = PipelinePhase::BreweryAndBeerGeneration,
+                  .message = std::format(
+                      "[Pipeline] Skipped {} city/cities due to generation errors",
+                      skipped_count)});
+  }
+
+  if (export_failed_count > 0) {
+    logger_->Log({.level = LogLevel::Warn,
+                  .phase = PipelinePhase::Teardown,
+                  .message = std::format(
+                      "[Pipeline] Failed to export {} generated brewery/breweries to SQLite",
+                      export_failed_count)});
+  }
+}

tooling/pipeline/src/biergarten_pipeline_orchestrator/log_results.cc

@@ -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 +1,63 @@
+/**
+ * @file biergarten_pipeline_orchestrator/run.cc
+ * @brief BiergartenDataGenerator::Run() implementation.
+ */
+
+#include <chrono>
+#include <format>
+#include <utility>
+
+#include "biergarten_pipeline_orchestrator.h"
+#include "services/logging/logger.h"
+
+bool BiergartenPipelineOrchestrator::Run() {
+  try {
+    exporter_->Initialize();
+
+    std::vector<Location> cities = QueryCitiesWithCountries();
+    std::vector<EnrichedCity> enriched;
+    enriched.reserve(cities.size());
+
+    size_t skipped_count = 0;
+    for (auto& city : cities) {
+      try {
+        std::string region_context = context_service_->GetLocationContext(city);
+        // logger_->Log(LogLevel::Debug, PipelinePhase::UserGeneration,
+        //              "[Pipeline] Context for '" + city.city + "' (" +
+        //              city.iso3166_2 + ") gathered:\n" + region_context);
+
+        enriched.push_back(
+            EnrichedCity{.location = std::move(city),
+                         .region_context = std::move(region_context)});
+      } catch (const std::exception& exception) {
+        ++skipped_count;
+        logger_->Log(
+            {.level = LogLevel::Warn,
+             .phase = PipelinePhase::UserGeneration,
+             .message = std::format(
+                 "[Pipeline] Skipping city '{}' ({}): context lookup failed: {}",
+                 city.city, city.country, exception.what())});
+      }
+    }
+
+    if (skipped_count > 0) {
+      logger_->Log({.level = LogLevel::Warn,
+                    .phase = PipelinePhase::UserGeneration,
+                    .message = std::format(
+                        "[Pipeline] Skipped {} city/cities due to context lookup errors",
+                        skipped_count)});
+    }
+
+    this->GenerateBreweries(enriched);
+    exporter_->Finalize();
+    this->LogResults();
+    return true;
+  } catch (const std::exception& e) {
+    logger_->Log(
+        {.level = LogLevel::Error,
+         .phase = PipelinePhase::Teardown,
+         .message =
+             std::format("Pipeline execution failed with error: {}", e.what())});
+    return false;
+  }
+}

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

@@ -4,8 +4,7 @@
  * inference, and validates structured JSON output for brewery records.
  */
 
-#include <spdlog/spdlog.h>
-
+#include <chrono>
 #include <format>
 #include <optional>
 #include <stdexcept>
@@ -33,6 +32,9 @@ static std::string FormatLocalLanguageCodes(
   return formatted;
 }
 
+// GBNF grammar for structured brewery JSON output.
+// @TODO move to a separate gbnf file if it grows in complexity or is shared
+// across modules.
 static constexpr std::string_view kBreweryJsonGrammar = R"json_brewery(
 root ::= thought-block "{" ws "\"name_en\"" ws ":" ws string ws "," ws "\"description_en\"" ws ":" ws string ws "," ws "\"name_local\"" ws ":" ws string ws "," ws "\"description_local\"" ws ":" ws string ws "}" ws
 thought-block ::= [^{]*
@@ -59,11 +61,12 @@ BreweryResult LlamaGenerator::GenerateBrewery(
       location.country.empty() ? std::string{}
                                : std::format(", {}", location.country);
   /**
-   * Load brewery system prompt from file
-   * Falls back to minimal inline prompt if file not found
+   * Load brewery system prompt via the injected prompt directory.
+   * The key "BREWERY_GENERATION" resolves to BREWERY_GENERATION.md inside
+   * the configured --prompt-dir.  Throws on missing or empty file.
    */
   const std::string system_prompt =
-      LoadBrewerySystemPrompt("prompts/system.md");
+      prompt_directory_->Load("BREWERY_GENERATION");
 
   std::string user_prompt = std::format(
       "## CITY:\n{}\n\n## COUNTRY:\n{}\n\n## LOCAL LANGUAGE CODES:\n{}\n\n## "
@@ -96,8 +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::format("LlamaGenerator: raw output (attempt {}): {}",
+                      attempt + 1, raw)});
+    }
 
     // Validate output: parse JSON and check required fields
 
@@ -108,9 +116,13 @@ 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::format("LlamaGenerator: successfully generated brewery data on attempt {}",
+                        attempt + 1)});
+      }
 
       return brewery;
     }
@@ -118,8 +130,14 @@ 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::format("LlamaGenerator: malformed brewery JSON (attempt {}): {}",
+               attempt + 1, *validation_error)});
+    }
 
     // Update prompt with error details to guide LLM toward correct output.
     user_prompt = std::format(
@@ -136,9 +154,13 @@ 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::format(
+         "LlamaGenerator: malformed brewery response after {} attempts: {}",
+         max_attempts, last_error.empty() ? raw : last_error)});
+  }
   throw std::runtime_error("LlamaGenerator: malformed brewery response");
 }

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

@@ -4,15 +4,21 @@
  * retry handling, and output sanitization for downstream parsing.
  */
 
-#include <spdlog/spdlog.h>
 
-#include <stdexcept>
+#include <format>
 #include <string>
 
 #include "data_generation/llama_generator.h"
 #include "data_generation/llama_generator_helpers.h"
 
+// TODO: Implement locale-aware user profile generation.
+// Current implementation returns a hardcoded test value and ignores the
+// locale parameter. Future implementation should:
+// 1. Load a USER_GENERATION.md prompt template with locale context
+// 2. Perform LLM inference with locale-specific username/bio generation
+// 3. Parse and validate JSON output with retry handling (similar to brewery)
+// 4. Return locale-aware username and biography
 UserResult LlamaGenerator::GenerateUser(const std::string& locale) {
   return {.username = "test_user",
-          .bio = "This is a test user profile from " + locale + "."};
+          .bio = std::format("This is a test user profile from {}.", locale)};
 }

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

@@ -16,11 +16,11 @@
 
 #include "data_generation/llama_generator_helpers.h"
 #include "llama.h"
-
+namespace {
 /**
  * String trimming: removes leading and trailing whitespace
  */
-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());
 
@@ -58,6 +58,41 @@ static std::string CondenseWhitespace(std::string_view text) {
   return out;
 }
 
+// Guard against truncating in the first half of the string.
+// This preserves the critical opening content and avoids cutting critical
+// context words early in the region description.
+constexpr size_t kTruncationGuardDivisor = 2;
+
+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
  * boundaries
@@ -71,7 +106,8 @@ std::string PrepareRegionContext(std::string_view region_context,
 
   normalized.resize(max_chars);
   const size_t last_space = normalized.find_last_of(' ');
-  if (last_space != std::string::npos && last_space > max_chars / 2) {
+  if (last_space != std::string::npos &&
+      last_space > max_chars / kTruncationGuardDivisor) {
     normalized.resize(last_space);
   }
 
@@ -115,47 +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;
@@ -203,7 +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>
@@ -19,6 +19,9 @@
 #include "llama.h"
 
 static constexpr size_t kPromptTokenSlack = 8;
+// Minimum tokens to keep when using top-p sampling. Ensures at least one
+// candidate token remains available even with very restrictive top-p values.
+static constexpr size_t kTopPMinKeep = 1;
 
 namespace {
 
@@ -62,7 +65,7 @@ SamplerHandle MakeSamplerChain(const llama_vocab* vocab,
               "LlamaGenerator: failed to initialize temperature sampler");
   add_sampler(llama_sampler_init_top_k(static_cast<int32_t>(config.top_k)),
               "LlamaGenerator: failed to initialize top-k sampler");
-  add_sampler(llama_sampler_init_top_p(config.top_p, 1),
+  add_sampler(llama_sampler_init_top_p(config.top_p, kTopPMinKeep),
               "LlamaGenerator: failed to initialize top-p sampler");
   add_sampler(llama_sampler_init_dist(config.seed),
               "LlamaGenerator: failed to initialize distribution sampler");
@@ -104,7 +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)
@@ -168,10 +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

@@ -11,7 +11,7 @@
 #include <stdexcept>
 #include <string>
 
-#include "data_model/application_options.h"
+#include "data_model/models.h"
 #include "llama.h"
 
 static constexpr uint32_t kMaxContextSize = 32768U;
@@ -32,9 +32,13 @@ void LlamaGenerator::ContextDeleter::operator()(
 
 LlamaGenerator::LlamaGenerator(
     const ApplicationOptions& options, const std::string& model_path,
-    std::unique_ptr<IPromptFormatter> prompt_formatter)
+    std::shared_ptr<ILogger> logger,
+    std::unique_ptr<IPromptFormatter> prompt_formatter,
+    std::unique_ptr<IPromptDirectory> prompt_directory)
     : rng_(std::random_device{}()),
-      prompt_formatter_(std::move(prompt_formatter)) {
+      logger_(std::move(logger)),
+      prompt_formatter_(std::move(prompt_formatter)),
+      prompt_directory_(std::move(prompt_directory)) {
   if (model_path.empty()) {
     throw std::runtime_error("LlamaGenerator: model path must not be empty");
   }
@@ -44,41 +48,50 @@ LlamaGenerator::LlamaGenerator(
         "LlamaGenerator: prompt formatter dependency must not be null");
   }
 
-  if (options.temperature < 0.0F) {
+  if (!prompt_directory_) {
+    throw std::runtime_error(
+        "LlamaGenerator: prompt directory dependency must not be null");
+  }
+
+  const auto sampling = options.generator.sampling.value_or(SamplingOptions{});
+
+  if (sampling.temperature < 0.0F) {
     throw std::runtime_error(
         "LlamaGenerator: sampling temperature must be >= 0");
   }
 
-  if (options.top_p <= 0.0F || options.top_p > 1.0F) {
+  if (sampling.top_p <= 0.0F || sampling.top_p > 1.0F) {
     throw std::runtime_error(
         "LlamaGenerator: sampling top-p must be in (0, 1]");
   }
 
-  if (options.top_k == 0U) {
+  if (sampling.top_k == 0U) {
     throw std::runtime_error("LlamaGenerator: sampling top-k must be > 0");
   }
 
-  if (options.seed < -1) {
+  if (sampling.seed < -1) {
     throw std::runtime_error(
         "LlamaGenerator: seed must be >= 0, or -1 for random");
   }
 
-  if (options.n_ctx == 0 || options.n_ctx > kMaxContextSize) {
+  if (sampling.n_ctx == 0 || sampling.n_ctx > kMaxContextSize) {
     throw std::runtime_error(
         "LlamaGenerator: context size must be in range [1, 32768]");
   }
 
-  sampling_temperature_ = options.temperature;
-  sampling_top_p_ = options.top_p;
-  sampling_top_k_ = options.top_k;
+  sampling_temperature_ = sampling.temperature;
+  sampling_top_p_ = sampling.top_p;
+  sampling_top_k_ = sampling.top_k;
 
-  if (options.seed == -1) {
+  if (sampling.seed == -1) {
     std::random_device random_device;
     rng_.seed(random_device());
   } else {
-    rng_.seed(static_cast<uint32_t>(options.seed));
+    rng_.seed(static_cast<uint32_t>(sampling.seed));
   }
-  n_ctx_ = options.n_ctx;
+
+  n_ctx_ = sampling.n_ctx;
+  n_gpu_layers_ = sampling.n_gpu_layers;
 
   this->Load(model_path);
 }

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

@@ -4,23 +4,34 @@
  * context, and resets prior resources during model initialization.
  */
 
-#include <spdlog/spdlog.h>
-
 #include <algorithm>
+#include <chrono>
 #include <stdexcept>
 #include <string>
 #include <utility>
 
 #include "data_generation/llama_generator.h"
+#include "ggml-backend.h"
 #include "llama.h"
 
+// Maximum batch size for decode operations. Capping the batch prevents
+// excessive memory allocation while maintaining inference performance.
+static constexpr uint32_t kMaxBatchSize = 5000U;
+
 void LlamaGenerator::Load(const std::string& model_path) {
   context_.reset();
   model_.reset();
 
-  const llama_model_params model_params = llama_model_default_params();
-  LlamaGenerator::ModelHandle loaded_model(
+  // Specifically load dynamic ggml backends (like CUDA) that are provided
+  // externally before attempting to load a model.
+  ggml_backend_load_all();
+
+  llama_model_params model_params = llama_model_default_params();
+  model_params.n_gpu_layers = n_gpu_layers_;
+
+  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);
@@ -28,10 +39,11 @@ void LlamaGenerator::Load(const std::string& model_path) {
 
   llama_context_params context_params = llama_context_default_params();
   context_params.n_ctx = n_ctx_;
-  context_params.n_batch = std::min(n_ctx_, static_cast<uint32_t>(5000));
+  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");
   }
@@ -39,5 +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/data_generation/llama/load_brewery_prompt.cc

@@ -1,55 +0,0 @@
-/**
- * @file data_generation/llama/load_brewery_prompt.cc
- * @brief Resolves brewery system prompt content from cache or a configured
- * filesystem path and provides a robust inline fallback prompt when absent.
- */
-
-#include <spdlog/spdlog.h>
-
-#include <filesystem>
-#include <fstream>
-#include <stdexcept>
-
-#include "data_generation/llama_generator.h"
-
-/**
- * @brief Loads brewery system prompt from disk or cache.
- *
- * @param prompt_file_path Preferred prompt file location.
- * @return Prompt text loaded from disk.
- */
-std::string LlamaGenerator::LoadBrewerySystemPrompt(
-    const std::filesystem::path& prompt_file_path) {
-  // Return cached version if already loaded
-  if (!brewery_system_prompt_.empty()) {
-    return brewery_system_prompt_;
-  }
-
-  std::ifstream prompt_file(prompt_file_path);
-  if (!prompt_file.is_open()) {
-    spdlog::error(
-        "LlamaGenerator: Failed to open brewery system prompt file '{}'",
-        prompt_file_path.string());
-    throw std::runtime_error(
-        "LlamaGenerator: missing brewery system prompt file: " +
-        prompt_file_path.string());
-  }
-
-  const std::string prompt((std::istreambuf_iterator(prompt_file)),
-                           std::istreambuf_iterator<char>());
-  prompt_file.close();
-
-  if (prompt.empty()) {
-    spdlog::error("LlamaGenerator: Brewery system prompt file '{}' is empty",
-                  prompt_file_path.string());
-    throw std::runtime_error(
-        "LlamaGenerator: empty brewery system prompt file: " +
-        prompt_file_path.string());
-  }
-
-  spdlog::info(
-      "LlamaGenerator: Loaded brewery system prompt from '{}' ({} chars)",
-      prompt_file_path.string(), prompt.length());
-  brewery_system_prompt_ = prompt;
-  return brewery_system_prompt_;
-}

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

@@ -17,9 +17,9 @@ BreweryResult MockGenerator::GenerateBrewery(
   const std::string_view adjective =
       kBreweryAdjectives.at(hash % kBreweryAdjectives.size());
   const std::string_view noun =
-      kBreweryNouns.at(hash / 7 % kBreweryNouns.size());
-  const std::string_view base_description =
-      kBreweryDescriptions.at((hash / 13) % kBreweryDescriptions.size());
+      kBreweryNouns.at(hash / kNounHashStride % kBreweryNouns.size());
+  const std::string_view base_description = kBreweryDescriptions.at(
+      (hash / kDescriptionHashStride) % kBreweryDescriptions.size());
 
   const std::string name =
       std::format("{} {} {}", location.city, adjective, noun);

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

@@ -15,7 +15,7 @@ UserResult MockGenerator::GenerateUser(const std::string& locale) {
 
   UserResult result;
   const std::string_view username = kUsernames[hash % kUsernames.size()];
-  const std::string_view bio = kBios[hash / 11 % kBios.size()];
+  const std::string_view bio = kBios[hash / kBioHashStride % kBios.size()];
   result.username = username;
   result.bio = bio;
   return result;

tooling/pipeline/src/json_handling/json_loader.cc

@@ -6,7 +6,9 @@
 
 #include "json_handling/json_loader.h"
 
-#include <spdlog/spdlog.h>
+#include <format>
+#include "services/logging/logger.h"
+#include <iostream>
 
 #include <boost/json.hpp>
 #include <fstream>
@@ -19,8 +21,8 @@ static std::string ReadRequiredString(const boost::json::object& object,
                                       const char* key) {
   const boost::json::value* value = object.if_contains(key);
   if (value == nullptr || !value->is_string()) {
-    throw std::runtime_error(std::string("Missing or invalid string field: ") +
-                             key);
+    throw std::runtime_error(
+        std::format("Missing or invalid string field: {}", key));
   }
   const std::string_view text = value->as_string();
   return std::string(text);
@@ -30,8 +32,8 @@ static double ReadRequiredNumber(const boost::json::object& object,
                                  const char* key) {
   const boost::json::value* value = object.if_contains(key);
   if (value == nullptr || !value->is_number()) {
-    throw std::runtime_error(std::string("Missing or invalid numeric field: ") +
-                             key);
+    throw std::runtime_error(
+        std::format("Missing or invalid numeric field: {}", key));
   }
   return value->to_number<double>();
 }
@@ -41,7 +43,7 @@ static std::vector<std::string> ReadRequiredStringArray(
   const boost::json::value* value = object.if_contains(key);
   if (value == nullptr || !value->is_array()) {
     throw std::runtime_error(
-        std::string("Missing or invalid string array field: ") + key);
+      std::format("Missing or invalid string array field: {}", key));
   }
 
   const auto& array = value->as_array();
@@ -50,7 +52,7 @@ static std::vector<std::string> ReadRequiredStringArray(
   for (const auto& item : array) {
     if (!item.is_string()) {
       throw std::runtime_error(
-          std::string("Missing or invalid string array field: ") + key);
+          std::format("Missing or invalid string array field: {}", key));
     }
     items.emplace_back(item.as_string());
   }
@@ -58,7 +60,7 @@ 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 +106,5 @@ std::vector<Location> JsonLoader::LoadLocations(
     });
   }
 
-  spdlog::info("[JsonLoader] Loaded {} locations from {}", locations.size(),
-               filepath.string());
   return locations;
 }

tooling/pipeline/src/main.cc

@@ -4,195 +4,215 @@
  * 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 <sstream>
 #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/application_options.h"
+#include "data_model/models.h"
 #include "llama_backend_state.h"
-#include "services/enrichment_service.h"
-#include "services/export_service.h"
-#include "services/sqlite_export_service.h"
-#include "services/wikipedia_service.h"
-#include "web_client/curl_web_client.h"
+#include "services/database/export_service.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 prog_opts = boost::program_options;
 namespace di = boost::di;
 
-/**
- * @brief Parse command-line arguments into ApplicationOptions.
- *
- * @param argc Command-line argument count.
- * @param argv Command-line arguments.
- * @return Parsed ApplicationOptions if parsing succeeded, std::nullopt
- * otherwise.
- */
-std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv) {
-  prog_opts::options_description desc("Pipeline Options");
-
-  auto opt = desc.add_options();
-
-  opt("help,h", "Produce help message");
-
-  opt("mocked", prog_opts::bool_switch(),
-      "Use mocked generator for brewery/user data");
-
-  opt("model,m", prog_opts::value<std::string>()->default_value(""),
-      "Path to LLM model (gguf)");
-
-  opt("temperature", prog_opts::value<float>()->default_value(1.0F),
-      "Sampling temperature (higher = more random)");
-
-  opt("top-p", prog_opts::value<float>()->default_value(0.95F),
-      "Nucleus sampling top-p in (0,1] (higher = more random)");
-
-  opt("top-k", prog_opts::value<uint32_t>()->default_value(64),
-      "Top-k sampling parameter (higher = more candidate tokens)");
-
-  opt("n-ctx", prog_opts::value<uint32_t>()->default_value(8192),
-      "Context window size in tokens (1-32768)");
-
-  opt("seed", prog_opts::value<int>()->default_value(-1),
-      "Sampler seed: -1 for random, otherwise non-negative integer");
-
-  // Handle the "no arguments" or "help" case
-  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());
-    return std::nullopt;
-  }
-
-  try {
-    prog_opts::variables_map variables_map;
-    prog_opts::store(prog_opts::parse_command_line(argc, argv, desc),
-                     variables_map);
-    prog_opts::notify(variables_map);
-
-    if (variables_map.contains("help")) {
-      std::stringstream help_stream;
-      help_stream << "\n" << desc;
-      spdlog::info(help_stream.str());
-      return std::nullopt;
-    }
-
-    const auto use_mocked = variables_map["mocked"].as<bool>();
-    const auto model_path = variables_map["model"].as<std::string>();
-
-    if (use_mocked && !model_path.empty()) {
-      spdlog::error(
-          "Invalid arguments: --mocked and --model are mutually exclusive");
-      return std::nullopt;
-    }
-
-    if (!use_mocked && model_path.empty()) {
-      spdlog::error(
-          "Invalid arguments: Either --mocked or --model must be specified");
-      return std::nullopt;
-    }
-
-    const bool has_llm_params = !variables_map["temperature"].defaulted() ||
-                                !variables_map["top-p"].defaulted() ||
-                                !variables_map["top-k"].defaulted() ||
-                                !variables_map["seed"].defaulted();
-
-    if (use_mocked && has_llm_params) {
-      spdlog::warn(
-          "Sampling parameters (--temperature, --top-p, --top-k, --seed) are"
-          " ignored when using --mocked");
-    }
-
-    ApplicationOptions options;
-    options.use_mocked = use_mocked;
-    options.model_path = model_path;
-    options.temperature = variables_map["temperature"].as<float>();
-    options.top_p = variables_map["top-p"].as<float>();
-    options.top_k = variables_map["top-k"].as<uint32_t>();
-    options.n_ctx = variables_map["n-ctx"].as<uint32_t>();
-    options.seed = variables_map["seed"].as<int>();
-
-    return options;
-  } catch (const std::exception& exception) {
-    spdlog::error("Failed to parse command-line arguments: {}",
-                  exception.what());
-    return std::nullopt;
-  } catch (...) {
-    spdlog::error("Failed to parse command-line arguments: unknown error");
-    return std::nullopt;
-  }
-}
-
-struct Timer {
-  std::chrono::steady_clock::time_point start_time =
-      std::chrono::steady_clock::now();
-  [[nodiscard]] int64_t Elapsed() const {
-    return std::chrono::duration_cast<std::chrono::milliseconds>(
-               std::chrono::steady_clock::now() - start_time)
-        .count();
-  }
-};
+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;
-    const CurlGlobalState curl_state;
-    const LlamaBackendState llama_backend_state;
-    spdlog::set_pattern("[%Y-%m-%d %H:%M:%S.%e] [%^%l%$] %v");
 
-    const auto parsed_options = ParseArguments(argc, argv);
+#ifndef BIERGARTEN_MOCK_ONLY
+    const LlamaBackendState llama_backend_state;
+#endif
+
+    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;
+    const std::string model_path = options.generator.model_path.string();
+    const auto sampling =
+        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, log_producer);
+      } catch (const std::exception& dir_error) {
+        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<CURLWebClient>(),
+        di::bind<ILogger>().to(log_producer),
         di::bind<ApplicationOptions>().to(options),
-        di::bind<IEnrichmentService>().to<WikipediaService>(),
+        di::bind<std::string>().to(model_path),
         di::bind<IExportService>().to<SqliteExportService>(),
-        di::bind<IPromptFormatter>().to<Gemma4JinjaPromptFormatter>(),
-        di::bind<std::string>().to(options.model_path),
+        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) {
+                {
+                  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](const auto& inj) -> std::unique_ptr<DataGenerator> {
-              if (options.use_mocked) {
-                spdlog::info(
-                    "[Generator] Using MockGenerator (no model path provided)");
+            [&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={})",
-                  options.model_path, options.temperature, options.top_p,
-                  options.top_k, options.n_ctx, options.seed);
-              return inj.template create<std::unique_ptr<LlamaGenerator>>();
+              {
+                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, 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 LogDTO 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 +1,160 @@
+/**
+ * @file wikipedia/fetch_extract.cc
+ */
+
+#include <boost/json.hpp>
+#include <chrono>
+#include <format>
+#include <string>
+#include <string_view>
+#include <thread>
+
+#include "services/enrichment/wikipedia_service.h"
+
+using namespace boost;
+
+std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
+  const std::string cache_key(query);
+
+  // 1. Cache Lookup
+  if (const auto cache_it = this->extract_cache_.find(cache_key);
+      cache_it != this->extract_cache_.end()) {
+    if (logger_) {
+      logger_->Log({.level = LogLevel::Debug,
+                    .phase = PipelinePhase::UserGeneration,
+                    .message = std::format("Wikipedia: Cache hit for {}!", cache_key)});
+    }
+    return cache_it->second;
+  }
+
+  const std::string encoded = this->client_->EncodeURL(cache_key);
+  const std::string url = std::format(
+      "https://en.wikipedia.org/w/"
+      "api.php?action=query&titles={}&prop=extracts&explaintext=1&format=json",
+      encoded);
+
+  const std::string body = this->client_->Get(url);
+  {
+    using namespace std::literals::chrono_literals;
+    std::this_thread::sleep_for(1s);
+  }
+
+  // 2. Parse JSON
+  system::error_code ec;
+  json::value doc = json::parse(body, ec);
+
+  if (ec) {
+    if (logger_) {
+      logger_->Log(
+          {.level = LogLevel::Warn,
+           .phase = PipelinePhase::UserGeneration,
+           .message = std::format("WikipediaService: JSON parse error for '{}': {}",
+                      std::string(query), ec.message())});
+    }
+    return {};
+  }
+
+  // 3. Safe Extraction
+  const json::object* obj = doc.if_object();
+  if (obj == nullptr) {
+    if (logger_) {
+      logger_->Log(
+          {.level = LogLevel::Warn,
+           .phase = PipelinePhase::UserGeneration,
+           .message =
+               std::format("WikipediaService: Expected root object for '{}'",
+               std::string(query))});
+    }
+    return {};
+  }
+
+  const json::value* query_ptr = obj->if_contains("query");
+  const json::value* pages_ptr =
+      ((query_ptr != nullptr) && query_ptr->is_object())
+          ? query_ptr->get_object().if_contains("pages")
+          : nullptr;
+
+  if ((pages_ptr == nullptr) || !pages_ptr->is_object()) {
+    if (logger_) {
+      logger_->Log(
+          {.level = LogLevel::Warn,
+           .phase = PipelinePhase::UserGeneration,
+           .message =
+               std::format("WikipediaService: Missing query.pages for '{}'",
+               std::string(query))});
+    }
+    return {};
+  }
+
+  const json::object& pages = pages_ptr->get_object();
+
+  if (pages.empty()) {
+    if (logger_) {
+      logger_->Log(
+          {.level = LogLevel::Warn,
+           .phase = PipelinePhase::UserGeneration,
+           .message = std::format("WikipediaService: No pages returned for '{}'",
+                      std::string(query))});
+    }
+    this->extract_cache_.emplace(cache_key, "");
+    return {};
+  }
+
+  // Wikipedia returns the page under a dynamic ID key; we just want the first
+  // one
+  const json::value& page_val = pages.begin()->value();
+
+  if (!page_val.is_object()) {
+    if (logger_) {
+      logger_->Log(
+          {.level = LogLevel::Warn,
+           .phase = PipelinePhase::UserGeneration,
+           .message =
+               std::format("WikipediaService: Unexpected page format for '{}'",
+               std::string(query))});
+    }
+    return {};
+  }
+
+  const json::object& page = page_val.get_object();
+
+  // Handle 404/Missing status
+  if (page.contains("missing")) {
+    if (logger_) {
+      logger_->Log({.level = LogLevel::Warn,
+                    .phase = PipelinePhase::UserGeneration,
+                    .message = std::format("WikipediaService: Page '{}' does not exist",
+                               std::string(query))});
+    }
+    this->extract_cache_.emplace(cache_key, "");
+    return {};
+  }
+
+  const json::value* extract_ptr = page.if_contains("extract");
+
+  if ((extract_ptr == nullptr) || !extract_ptr->is_string()) {
+    if (logger_) {
+      logger_->Log(
+          {.level = LogLevel::Warn,
+           .phase = PipelinePhase::UserGeneration,
+           .message =
+               std::format("WikipediaService: No extract string found for '{}'",
+               std::string(query))});
+    }
+    this->extract_cache_.emplace(cache_key, "");
+    return {};
+  }
+
+  // 4. Success
+  std::string extract(extract_ptr->as_string());
+  if (logger_) {
+    logger_->Log({.level = LogLevel::Info,
+                  .phase = PipelinePhase::UserGeneration,
+                  .message = std::format("WikipediaService: Fetched {} chars for '{}'",
+                             extract.size(), std::string(query))});
+  }
+
+  this->extract_cache_.insert_or_assign(cache_key, extract);
+
+  return extract;
+}

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

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

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

@@ -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 +1,74 @@
+/**
+ * @brief LogDispatcher implementation for asynchronous pipeline logging.
+ *
+ * LogDispatcher drains LogEntry items from a BoundedChannel and forwards them
+ * to spdlog for final output.
+ */
+#include "services/logging/log_dispatcher.h"
+
+#include <spdlog/spdlog.h>
+
+#include <string>
+
+#include "concurrency/bounded_channel.h"
+#include "services/logging/log_entry.h"
+
+namespace {
+[[nodiscard]] constexpr std::string_view PipelinePhaseToString(
+    PipelinePhase phase) {
+  switch (phase) {
+    case PipelinePhase::Startup:
+      return "Startup";
+    case PipelinePhase::UserGeneration:
+      return "User Generation";
+    case PipelinePhase::BreweryAndBeerGeneration:
+      return "Brewery & Beer Gen";
+    case PipelinePhase::CheckinGeneration:
+      return "Checkin Gen";
+    case PipelinePhase::RatingGeneration:
+      return "Rating Gen";
+    case PipelinePhase::FollowGeneration:
+      return "Follow Gen";
+    case PipelinePhase::Teardown:
+      return "Teardown";
+  }
+  return "Unknown";
+}
+}  // namespace
+
+LogDispatcher::LogDispatcher(BoundedChannel<LogEntry>& channel)
+    : channel_(channel) {}
+
+void LogDispatcher::Run() {
+  auto logger = spdlog::default_logger();
+
+  while (true) {
+    auto entry = channel_.Receive();
+    if (!entry.has_value()) {
+      // Channel is closed and drained.
+      break;
+    }
+
+    const auto& log = entry.value();
+
+    logger->log(ToSpdlogLevel(log.level),
+                "{:<20} │ thread: {:016x} │ [{}:{}] │ {}",
+                PipelinePhaseToString(log.phase),
+                std::hash<std::thread::id>{}(log.thread_id),
+                log.origin.file_name(), log.origin.line(), log.message);
+  }
+}
+
+spdlog::level::level_enum LogDispatcher::ToSpdlogLevel(LogLevel level) {
+  switch (level) {
+    case LogLevel::Debug:
+      return spdlog::level::debug;
+    case LogLevel::Info:
+      return spdlog::level::info;
+    case LogLevel::Warn:
+      return spdlog::level::warn;
+    case LogLevel::Error:
+      return spdlog::level::err;
+  }
+  return spdlog::level::info;
+}

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

@@ -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::DoLog(LogEntry entry) { channel_.Send(std::move(entry)); }

tooling/pipeline/src/services/prompt_directory.cc

@@ -0,0 +1,100 @@
+/**
+ * @file services/prompt_directory.cc
+ * @brief PromptDirectory implementation: validates the directory at
+ * construction and loads named prompt files on demand with in-process caching.
+ */
+
+#include "services/prompting/prompt_directory.h"
+
+#include <chrono>
+#include <filesystem>
+#include <format>
+#include <fstream>
+#include <stdexcept>
+#include <string>
+#include <string_view>
+#include <utility>
+
+// ---------------------------------------------------------------------------
+// PromptDirectory
+// ---------------------------------------------------------------------------
+
+PromptDirectory::PromptDirectory(const std::filesystem::path& prompt_dir)
+    : PromptDirectory(prompt_dir, nullptr) {}
+
+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.
+  if (!std::filesystem::exists(prompt_dir_, ec) || ec) {
+    throw std::runtime_error(
+        "PromptDirectory: prompt directory does not exist: " +
+        prompt_dir_.string());
+  }
+
+  // Scenario 4: path must be a directory, not a file.
+  if (!std::filesystem::is_directory(prompt_dir_, ec) || ec) {
+    throw std::runtime_error(
+        "PromptDirectory: prompt directory path is not a directory: " +
+        prompt_dir_.string());
+  }
+
+  // Scenario 4: directory must be readable (probe with directory_iterator).
+  std::filesystem::directory_iterator probe(prompt_dir_, ec);
+  if (ec) {
+    throw std::runtime_error(
+        std::format("PromptDirectory: prompt directory is not readable: {} ({})",
+        prompt_dir_.string(), ec.message()));
+  }
+
+  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) {
+  const std::string key_str(key);
+
+  // Return cached content if already loaded during this run.
+  const auto cache_it = cache_.find(key_str);
+  if (cache_it != cache_.end()) {
+    return cache_it->second;
+  }
+
+  // Scenario 3: resolve <prompt_dir>/<key>.md and require it to exist.
+  const std::filesystem::path file_path =
+      prompt_dir_ / std::filesystem::path(std::format("{}.md", key_str));
+
+  std::ifstream file(file_path);
+  if (!file.is_open()) {
+    throw std::runtime_error(
+        std::format("PromptDirectory: prompt file not found for key '{}': {}",
+        key_str, file_path.string()));
+  }
+
+  std::string content((std::istreambuf_iterator<char>(file)),
+                      std::istreambuf_iterator<char>());
+  file.close();
+
+  if (content.empty()) {
+    throw std::runtime_error(std::format("PromptDirectory: prompt file for key '{}' is empty: {}",
+                             key_str, file_path.string()));
+  }
+
+  if (logger_) {
+    logger_->Log({.level = LogLevel::Info,
+                  .phase = PipelinePhase::Startup,
+                  .message = std::format("[PromptDirectory] Loaded prompt '{}' from '{}' ({} chars)",
+                             key_str, file_path.string(), content.size())});
+  }
+
+  cache_.emplace(key_str, content);
+  return content;
+}

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

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

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

@@ -5,9 +5,8 @@
 
 #include <stdexcept>
 
-#include "services/sqlite_export_service.h"
-#include "services/sqlite_export_service_helpers.h"
-
+#include "services/database/sqlite_export_service.h"
+#include "services/database/sqlite_export_service_helpers.h"
 
 void SqliteExportService::Finalize() {
   if (db_handle_ == nullptr) {

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

@@ -1,5 +1,6 @@
-#include "services/sqlite_connection_helpers.h"
+#include "services/database/sqlite_connection_helpers.h"
 
+#include <format>
 #include <stdexcept>
 
 namespace sqlite_export_service_internal {
@@ -10,7 +11,8 @@ void SqliteDatabaseDeleter::operator()(sqlite3* handle) const noexcept {
   }
 }
 
-void SqliteStatementDeleter::operator()(sqlite3_stmt* statement) const noexcept {
+void SqliteStatementDeleter::operator()(
+    sqlite3_stmt* statement) const noexcept {
   if (statement != nullptr) {
     sqlite3_finalize(statement);
   }
@@ -19,11 +21,10 @@ void SqliteStatementDeleter::operator()(sqlite3_stmt* statement) const noexcept
 void ThrowSqliteError(sqlite3* db_handle, std::string_view action) {
   const std::string message =
       db_handle != nullptr ? sqlite3_errmsg(db_handle) : "unknown SQLite error";
-  throw std::runtime_error(std::string(action) + ": " + message);
+  throw std::runtime_error(std::format("{}: {}", action, message));
 }
 
 SqliteDatabaseHandle OpenDatabase(const std::filesystem::path& path) {
-
   sqlite3* raw_handle = nullptr;
   const int result = sqlite3_open(path.string().c_str(), &raw_handle);
 
@@ -50,11 +51,12 @@ void ExecSql(const SqliteDatabaseHandle& db_handle, std::string_view sql,
                                     ? error_message
                                     : sqlite3_errmsg(db_handle.get());
     sqlite3_free(error_message);
-    throw std::runtime_error(std::string(action) + ": " + message);
+    throw std::runtime_error(std::format("{}: {}", action, message));
   }
 }
 
-void RollbackTransactionNoThrow(const SqliteDatabaseHandle& db_handle) noexcept {
+void RollbackTransactionNoThrow(
+    const SqliteDatabaseHandle& db_handle) noexcept {
   if (!db_handle) {
     return;
   }
@@ -63,4 +65,3 @@ void RollbackTransactionNoThrow(const SqliteDatabaseHandle& db_handle) noexcept
 }
 
 }  // namespace sqlite_export_service_internal
-

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

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

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

@@ -4,13 +4,27 @@
  */
 
 #include <filesystem>
+#include <format>
 #include <memory>
 #include <stdexcept>
 #include <string>
 
-#include "services/sqlite_export_service.h"
-#include "services/sqlite_export_service_helpers.h"
+#include "services/database/sqlite_export_service.h"
+#include "services/database/sqlite_export_service_helpers.h"
 
+std::filesystem::path SqliteExportService::BuildDatabasePath() const {
+  std::filesystem::path base_filename("biergarten_seed_" + run_timestamp_utc_ +
+                                      ".sqlite");
+  std::filesystem::path candidate = output_path_ / base_filename;
+
+  for (int suffix = 1; std::filesystem::exists(candidate); ++suffix) {
+    candidate = output_path_ /
+                std::filesystem::path(std::format("biergarten_seed_{}-{}.sqlite",
+                                      run_timestamp_utc_, suffix));
+  }
+
+  return candidate;
+}
 
 void SqliteExportService::InitializeSchema() const {
   sqlite_export_service_internal::ExecSql(
@@ -46,7 +60,6 @@ void SqliteExportService::RollbackAndCloseNoThrow() noexcept {
   location_cache_.clear();
 }
 
-
 void SqliteExportService::Initialize() {
   if (db_handle_ != nullptr) {
     throw std::runtime_error("SQLite export service is already initialized");

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

@@ -3,11 +3,13 @@
  * @brief SqliteExportService::ProcessRecord() implementation.
  */
 
+#include <iomanip>
+#include <sstream>
 #include <stdexcept>
 #include <string>
 
-#include "services/sqlite_export_service.h"
-#include "services/sqlite_export_service_helpers.h"
+#include "services/database/sqlite_export_service.h"
+#include "services/database/sqlite_export_service_helpers.h"
 
 constexpr int kLocationPrecision = 17;
 

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

@@ -3,12 +3,13 @@
  * @brief SqliteExportService constructor and destructor implementation.
  */
 
-#include "services/sqlite_export_service.h"
+#include "services/database/sqlite_export_service.h"
 
 #include <memory>
 
-SqliteExportService::SqliteExportService()
-    : date_time_provider_(std::make_unique<SystemDateTimeProvider>()) {}
+SqliteExportService::SqliteExportService(const ApplicationOptions& options)
+    : date_time_provider_(std::make_unique<SystemDateTimeProvider>()),
+      output_path_(options.pipeline.output_path) {}
 
 SqliteExportService::~SqliteExportService() {
   if (db_handle_ != nullptr) {

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/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/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/wikipedia_service.h"
-
-#include <utility>
-
-WikipediaService::WikipediaService(std::unique_ptr<WebClient> client)
-    : client_(std::move(client)) {}

tooling/pipeline/src/web_client/curl_global_state.cc

@@ -1,19 +0,0 @@
-/**
- * @file web_client/curl_global_state.cc
- * @brief CurlGlobalState constructor and destructor implementation.
- */
-
-#include <curl/curl.h>
-
-#include <stdexcept>
-
-#include "web_client/curl_web_client.h"
-
-CurlGlobalState::CurlGlobalState() {
-  if (curl_global_init(CURL_GLOBAL_DEFAULT) != CURLE_OK) {
-    throw std::runtime_error(
-        "[CURLWebClient] Failed to initialize libcurl globally");
-  }
-}
-
-CurlGlobalState::~CurlGlobalState() { curl_global_cleanup(); }

tooling/pipeline/src/web_client/curl_web_client_get.cc

@@ -1,86 +0,0 @@
-/**
- * @file web_client/curl_web_client_get.cc
- * @brief CURLWebClient::Get() implementation.
- */
-
-#include <curl/curl.h>
-
-#include <cstdint>
-#include <limits>
-#include <memory>
-#include <stdexcept>
-#include <string>
-
-#include "web_client/curl_web_client.h"
-
-using CurlHandle = std::unique_ptr<CURL, decltype(&curl_easy_cleanup)>;
-
-static constexpr long kConnectionTimeout = 10;
-static constexpr long kRequestTimeout = 30;
-static constexpr int32_t kOkHttpStatus = 200;
-
-static CurlHandle CreateHandle() {
-  CURL* handle = curl_easy_init();
-  if (handle == nullptr) {
-    throw std::runtime_error(
-        "[CURLWebClient] Failed to initialize libcurl handle");
-  }
-  return {handle, &curl_easy_cleanup};
-}
-
-static void SetCommonGetOptions(CURL* curl, const std::string& url) {
-  curl_easy_setopt(curl, CURLOPT_URL, url.c_str());
-  curl_easy_setopt(curl, CURLOPT_USERAGENT, "biergarten-pipeline/0.1.0");
-  curl_easy_setopt(curl, CURLOPT_FOLLOWLOCATION, 1L);
-  curl_easy_setopt(curl, CURLOPT_MAXREDIRS, 5L);
-  curl_easy_setopt(curl, CURLOPT_CONNECTTIMEOUT, kConnectionTimeout);
-  curl_easy_setopt(curl, CURLOPT_TIMEOUT, kRequestTimeout);
-  curl_easy_setopt(curl, CURLOPT_ACCEPT_ENCODING, "gzip");
-}
-
-// curl write callback that appends response data into a std::string
-static size_t WriteCallbackString(void* contents, const size_t size,
-                                  const size_t nmemb, void* userp) {
-  const size_t real_size = size * nmemb;
-  auto* str = static_cast<std::string*>(userp);
-  str->append(static_cast<char*>(contents), real_size);
-  return real_size;
-}
-
-std::string CURLWebClient::Get(const std::string& url) {
-  const CurlHandle curl = CreateHandle();
-
-  std::string response_string;
-
-  SetCommonGetOptions(curl.get(), url);
-
-  curl_easy_setopt(curl.get(), CURLOPT_WRITEFUNCTION, WriteCallbackString);
-  curl_easy_setopt(curl.get(), CURLOPT_WRITEDATA, &response_string);
-
-  CURLcode curl_result = curl_easy_perform(curl.get());
-
-  if (curl_result != CURLE_OK) {
-    const auto error = std::string("[CURLWebClient] GET failed: ") +
-                       curl_easy_strerror(curl_result);
-    throw std::runtime_error(error);
-  }
-
-  long curl_http_code = 0;
-  curl_easy_getinfo(curl.get(), CURLINFO_RESPONSE_CODE, &curl_http_code);
-
-  if (curl_http_code < std::numeric_limits<int32_t>::min() ||
-      curl_http_code > std::numeric_limits<int32_t>::max()) {
-    throw std::runtime_error("[CURLWebClient] Invalid HTTP status code: " +
-                             std::to_string(curl_http_code));
-  }
-
-  const int32_t http_code = static_cast<int32_t>(curl_http_code);
-
-  if (http_code != kOkHttpStatus) {
-    const std::string error = "[CURLWebClient] HTTP error " +
-                              std::to_string(http_code) + " for URL " + url;
-    throw std::runtime_error(error);
-  }
-
-  return response_string;
-}

tooling/pipeline/src/web_client/curl_web_client_url_encode.cc

@@ -1,24 +0,0 @@
-/**
- * @file web_client/curl_web_client_url_encode.cc
- * @brief CURLWebClient::UrlEncode() implementation.
- */
-
-#include <curl/curl.h>
-
-#include <stdexcept>
-#include <string>
-
-#include "web_client/curl_web_client.h"
-
-std::string CURLWebClient::UrlEncode(const std::string& value) {
-  // A NULL handle is fine for UTF-8 encoding according to libcurl docs.
-  char* output = curl_easy_escape(nullptr, value.c_str(), 0);
-
-  if (!output) {
-    throw std::runtime_error("[CURLWebClient] curl_easy_escape failed");
-  }
-
-  std::string result(output);
-  curl_free(output);
-  return result;
-}

tooling/pipeline/src/web_client/http_web_client.cc

@@ -0,0 +1,73 @@
+/**
+ * @file web_client/http_web_client.cc
+ * @brief cpp-httplib implementation of WebClient.
+ */
+
+#include "web_client/http_web_client.h"
+
+#include <httplib.h>
+
+#include <chrono>
+#include <format>
+#include <regex>
+#include <stdexcept>
+#include <string>
+#include <utility>
+
+#include "services/logging/logger.h"
+
+namespace {
+constexpr time_t kConnectionTimeoutSeconds = 5;
+constexpr time_t kReadTimeoutSeconds = 10;
+
+constexpr int kSuccessMin = 200;
+constexpr int kSuccessMax = 300;
+const std::regex kUrlRegex(
+    R"(^(https?://[^/?#]+)(/[^?#]*(?:\?[^#]*)?(?:#.*)?)?)");
+
+std::pair<std::string, std::string> SplitUrl(const std::string& url) {
+  std::smatch match;
+  if (!std::regex_match(url, match, kUrlRegex)) {
+    throw std::invalid_argument("[HttpWebClient] Malformed URL: " + url);
+  }
+
+  return {match[1].str(), match[2].matched ? match[2].str() : "/"};
+}
+}  // namespace
+
+std::string HttpWebClient::Get(const std::string& url) {
+  const auto [origin, path] = SplitUrl(url);
+
+  httplib::Client client(origin);
+  client.set_follow_location(true);
+  client.set_connection_timeout(kConnectionTimeoutSeconds);
+  client.set_read_timeout(kReadTimeoutSeconds);
+  client.set_default_headers({{"Accept", "application/json"},
+                              {"User-Agent", "biergarten-pipeline/1.0"}});
+
+  const httplib::Result result = client.Get(path);
+
+  if (!result) {
+    throw std::runtime_error(std::format(
+        "[HttpWebClient] Request failed for URL: {} — {}", url,
+        httplib::to_string(result.error())));
+  }
+
+  if (result->status < kSuccessMin || result->status >= kSuccessMax) {
+    if (logger_) {
+      logger_->Log(
+          {.level = LogLevel::Error,
+           .phase = PipelinePhase::UserGeneration,
+         .message =
+           std::format("[HttpWebClient] Request failed for URL: {}", url)});
+    }
+    throw std::runtime_error(std::format("[HttpWebClient] HTTP {} for URL: {}",
+                       result->status, url));
+  }
+
+  return result->body;
+}
+
+std::string HttpWebClient::EncodeURL(const std::string& value) {
+  return httplib::encode_uri_component(value);
+}