Update generate pipeline to add OpenAI api as an additional backend (for comparison testing), add brewery coordinates (#244)

* add brewery coordinates

* Add openai mode

* Add coordinates to schema

* Fix C++ review findings in pipeline: k-prefixed enum values, include ordering, populated validation error messages, conventional const notation, and endl replaced with newline

tooling/pipeline/includes/data_generation/llama_generator_helpers.h

@@ -3,30 +3,17 @@
 
 /**
  * @file data_generation/llama_generator_helpers.h
- * @brief Shared helper APIs used by LlamaGenerator translation units.
+ * @brief Llama.cpp-specific helper APIs used by LlamaGenerator translation
+ * units. Generator-agnostic helpers (prompt-context prep, JSON validation)
+ * live in data_generation/generation_json_validation.h instead.
  */
 
-#include <cstddef>
 #include <cstdint>
-#include <optional>
 #include <string>
-#include <string_view>
-
-#include "data_model/generated_models.h"
 
 struct llama_vocab;
 using llama_token = int32_t;
 
-/**
- * @brief Normalizes and truncates regional context.
- *
- * @param region_context Input regional context text.
- * @param max_chars Maximum output length.
- * @return Processed region context.
- */
-std::string PrepareRegionContext(std::string_view region_context,
-                                 size_t max_chars = 2000);
-
 /**
  * @brief Decodes a sampled token and appends it to output text.
  *
@@ -37,28 +24,4 @@ std::string PrepareRegionContext(std::string_view region_context,
 void AppendTokenPiece(const llama_vocab* vocab, llama_token token,
                       std::string& output);
 
-/**
- * @brief Validates and parses brewery JSON output.
- *
- * @param raw Raw model output.
- * @param brewery_out Parsed brewery payload.
- * @return Validation error message if invalid, or std::nullopt on success.
- */
-std::optional<std::string> ValidateBreweryJson(const std::string& raw,
-                                               BreweryResult& brewery_out);
-
-/**
- * @brief Validates and parses user JSON output.
- *
- * Only populates `username`, `bio`, and `activity_weight` -- `first_name`
- * and `last_name` are not LLM-authored and are set separately from the
- * sampled Name.
- *
- * @param raw Raw model output.
- * @param user_out Parsed user payload.
- * @return Validation error message if invalid, or std::nullopt on success.
- */
-std::optional<std::string> ValidateUserJson(const std::string& raw,
-                                            UserResult& user_out);
-
 #endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_LLAMA_GENERATOR_HELPERS_H_