format codebase

pipeline/includes/data_generation/data_downloader.h

@@ -9,22 +9,23 @@
 
 /// @brief Downloads and caches source geography JSON payloads.
 class DataDownloader {
-public:
-  /// @brief Initializes global curl state used by this downloader.
-  explicit DataDownloader(std::shared_ptr<WebClient> web_client);
+  public:
+   /// @brief Initializes global curl state used by this downloader.
+   explicit DataDownloader(std::shared_ptr<WebClient> web_client);
 
-  /// @brief Cleans up global curl state.
-  ~DataDownloader();
+   /// @brief Cleans up global curl state.
+   ~DataDownloader();
 
-  /// @brief Returns a local JSON path, downloading it when cache is missing.
-  std::string DownloadCountriesDatabase(
-      const std::string &cache_path,
-      const std::string &commit = "c5eb7772" // Stable commit: 2026-03-28 export
-  );
+   /// @brief Returns a local JSON path, downloading it when cache is missing.
+   std::string DownloadCountriesDatabase(
+       const std::string& cache_path,
+       const std::string& commit =
+           "c5eb7772"  // Stable commit: 2026-03-28 export
+   );
 
-private:
-  static bool FileExists(const std::string &file_path);
-  std::shared_ptr<WebClient> web_client_;
+  private:
+   static bool FileExists(const std::string& file_path);
+   std::shared_ptr<WebClient> web_client_;
 };
 
 #endif  // BIERGARTEN_PIPELINE_DATA_GENERATION_DATA_DOWNLOADER_H_

pipeline/includes/data_generation/data_generator.h

@@ -4,26 +4,26 @@
 #include <string>
 
 struct BreweryResult {
-  std::string name;
-  std::string description;
+   std::string name;
+   std::string description;
 };
 
 struct UserResult {
-  std::string username;
-  std::string bio;
+   std::string username;
+   std::string bio;
 };
 
 class DataGenerator {
-public:
-  virtual ~DataGenerator() = default;
+  public:
+   virtual ~DataGenerator() = default;
 
-  virtual void Load(const std::string &model_path) = 0;
+   virtual void Load(const std::string& model_path) = 0;
 
-  virtual BreweryResult GenerateBrewery(const std::string &city_name,
-                                        const std::string &country_name,
-                                        const std::string &region_context) = 0;
+   virtual BreweryResult GenerateBrewery(const std::string& city_name,
+                                         const std::string& country_name,
+                                         const std::string& region_context) = 0;
 
-  virtual UserResult GenerateUser(const std::string &locale) = 0;
+   virtual UserResult GenerateUser(const std::string& locale) = 0;
 };
 
 #endif  // BIERGARTEN_PIPELINE_DATA_GENERATION_DATA_GENERATOR_H_

pipeline/includes/data_generation/llama_generator.h

@@ -10,32 +10,32 @@ struct llama_model;
 struct llama_context;
 
 class LlamaGenerator final : public DataGenerator {
-public:
-  LlamaGenerator() = default;
-  ~LlamaGenerator() override;
+  public:
+   LlamaGenerator() = default;
+   ~LlamaGenerator() override;
 
-  void SetSamplingOptions(float temperature, float top_p, int seed = -1);
+   void SetSamplingOptions(float temperature, float top_p, int seed = -1);
 
-  void Load(const std::string &model_path) override;
-  BreweryResult GenerateBrewery(const std::string &city_name,
-                                const std::string &country_name,
-                                const std::string &region_context) override;
-  UserResult GenerateUser(const std::string &locale) override;
+   void Load(const std::string& model_path) override;
+   BreweryResult GenerateBrewery(const std::string& city_name,
+                                 const std::string& country_name,
+                                 const std::string& region_context) override;
+   UserResult GenerateUser(const std::string& locale) override;
 
-private:
-  std::string Infer(const std::string &prompt, int max_tokens = 10000);
-  // Overload that allows passing a system message separately so chat-capable
-  // models receive a proper system role instead of having the system text
-  // concatenated into the user prompt (helps avoid revealing internal
-  // reasoning or instructions in model output).
-  std::string Infer(const std::string &system_prompt, const std::string &prompt,
-                    int max_tokens = 10000);
+  private:
+   std::string Infer(const std::string& prompt, int max_tokens = 10000);
+   // Overload that allows passing a system message separately so chat-capable
+   // models receive a proper system role instead of having the system text
+   // concatenated into the user prompt (helps avoid revealing internal
+   // reasoning or instructions in model output).
+   std::string Infer(const std::string& system_prompt,
+                     const std::string& prompt, int max_tokens = 10000);
 
-  llama_model *model_ = nullptr;
-  llama_context *context_ = nullptr;
-  float sampling_temperature_ = 0.8f;
-  float sampling_top_p_ = 0.92f;
-  uint32_t sampling_seed_ = 0xFFFFFFFFu;
+   llama_model* model_ = nullptr;
+   llama_context* context_ = nullptr;
+   float sampling_temperature_ = 0.8f;
+   float sampling_top_p_ = 0.92f;
+   uint32_t sampling_seed_ = 0xFFFFFFFFu;
 };
 
 #endif  // BIERGARTEN_PIPELINE_DATA_GENERATION_LLAMA_GENERATOR_H_

pipeline/includes/data_generation/llama_generator_helpers.h

@@ -12,18 +12,17 @@ typedef int llama_token;
 std::string PrepareRegionContextPublic(std::string_view region_context,
                                        std::size_t max_chars = 700);
 
-std::pair<std::string, std::string>
-ParseTwoLineResponsePublic(const std::string& raw,
-                           const std::string& error_message);
+std::pair<std::string, std::string> ParseTwoLineResponsePublic(
+    const std::string& raw, const std::string& error_message);
 
-std::string ToChatPromptPublic(const llama_model *model,
+std::string ToChatPromptPublic(const llama_model* model,
                                const std::string& user_prompt);
 
-std::string ToChatPromptPublic(const llama_model *model,
+std::string ToChatPromptPublic(const llama_model* model,
                                const std::string& system_prompt,
                                const std::string& user_prompt);
 
-void AppendTokenPiecePublic(const llama_vocab *vocab, llama_token token,
+void AppendTokenPiecePublic(const llama_vocab* vocab, llama_token token,
                             std::string& output);
 
 std::string ValidateBreweryJsonPublic(const std::string& raw,

pipeline/includes/data_generation/mock_generator.h

@@ -1,27 +1,28 @@
 #ifndef BIERGARTEN_PIPELINE_DATA_GENERATION_MOCK_GENERATOR_H_
 #define BIERGARTEN_PIPELINE_DATA_GENERATION_MOCK_GENERATOR_H_
 
-#include "data_generation/data_generator.h"
 #include <string>
 #include <vector>
 
+#include "data_generation/data_generator.h"
+
 class MockGenerator final : public DataGenerator {
-public:
-  void Load(const std::string &model_path) override;
-  BreweryResult GenerateBrewery(const std::string &city_name,
-                                const std::string &country_name,
-                                const std::string &region_context) override;
-  UserResult GenerateUser(const std::string &locale) override;
+  public:
+   void Load(const std::string& model_path) override;
+   BreweryResult GenerateBrewery(const std::string& city_name,
+                                 const std::string& country_name,
+                                 const std::string& region_context) override;
+   UserResult GenerateUser(const std::string& locale) override;
 
-private:
-  static std::size_t DeterministicHash(const std::string &a,
-                                       const std::string &b);
+  private:
+   static std::size_t DeterministicHash(const std::string& a,
+                                        const std::string& b);
 
-  static const std::vector<std::string> kBreweryAdjectives;
-  static const std::vector<std::string> kBreweryNouns;
-  static const std::vector<std::string> kBreweryDescriptions;
-  static const std::vector<std::string> kUsernames;
-  static const std::vector<std::string> kBios;
+   static const std::vector<std::string> kBreweryAdjectives;
+   static const std::vector<std::string> kBreweryNouns;
+   static const std::vector<std::string> kBreweryDescriptions;
+   static const std::vector<std::string> kUsernames;
+   static const std::vector<std::string> kBios;
 };
 
 #endif  // BIERGARTEN_PIPELINE_DATA_GENERATION_MOCK_GENERATOR_H_