Pipeline: Add LLM and mocked user generation to the pipeline (#230)

tooling/pipeline/includes/data_generation/data_generator.h

@@ -28,12 +28,16 @@ class DataGenerator {
                                         const std::string& region_context) = 0;
 
   /**
-   * @brief Generates a user profile for a locale.
+   * @brief Generates a user profile grounded in a sampled name and persona.
    *
-   * @param locale Locale hint used by generator.
+   * @param city Enriched city the user is associated with.
+   * @param persona Persona archetype grounding the generated bio.
+   * @param name Sampled first/last name (and gender)
    * @return User generation result.
    */
-  virtual UserResult GenerateUser(const std::string& locale) = 0;
+  virtual UserResult GenerateUser(const EnrichedCity& city,
+                                  const UserPersona& persona,
+                                  const Name& name) = 0;
 };
 
 #endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_DATA_GENERATOR_H_

tooling/pipeline/includes/data_generation/json_grammars.h

@@ -0,0 +1,52 @@
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_JSON_GRAMMARS_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_JSON_GRAMMARS_H_
+
+/**
+ * @file data_generation/json_grammars.h
+ * @brief GBNF grammars constraining structured JSON output from
+ * LlamaGenerator inference calls.
+ */
+
+#include <string_view>
+
+// GBNF grammar for structured user JSON output.
+// thought-block permits the model to emit free-form reasoning before the
+// JSON object (the prompts explicitly invite this); only the "{...}" tail is
+// constrained to the expected shape.
+inline constexpr std::string_view kUserJsonGrammar = R"json_user(
+root ::= thought-block (
+    "{" ws
+    "\"username\"" ws ":" ws string ws "," ws
+    "\"bio\"" ws ":" ws string ws "," ws
+    "\"activity_weight\"" ws ":" ws number ws
+  "}" ws
+)
+thought-block ::= [^{]*
+ws            ::= [ \t\n\r]*
+string        ::= "\"" char+ "\""
+char          ::= [^"\\\x7F\x00-\x1F] | [\\] escape
+escape        ::= ["\\/bfnrt] | "u" hex hex hex hex
+hex           ::= [0-9a-fA-F]
+number        ::= "-"? ("0" | [1-9] [0-9]*) ("." [0-9]+)?
+)json_user";
+
+// GBNF grammar for structured brewery JSON output (see thought-block note
+// above).
+inline 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 ::= [^{]*
+ws            ::= [ \t\n\r]*
+string        ::= "\"" char+ "\""
+char          ::= [^"\\\x7F\x00-\x1F] | [\\] escape
+escape        ::= ["\\/bfnrt] | "u" hex hex hex hex
+hex           ::= [0-9a-fA-F]
+)json_brewery";
+
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_JSON_GRAMMARS_H_

tooling/pipeline/includes/data_generation/llama_generator.h

@@ -1,24 +1,23 @@
 #ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_LLAMA_GENERATOR_H_
 #define BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_LLAMA_GENERATOR_H_
 
-#include <filesystem>
-
 /**
  * @file data_generation/llama_generator.h
  * @brief llama.cpp-backed implementation of DataGenerator.
  */
 
 #include <cstdint>
+#include <filesystem>
 #include <memory>
 #include <random>
 #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/models.h"
 #include "services/logging/logger.h"
+#include "services/prompting/prompt_directory.h"
 
 struct llama_model;
 struct llama_context;
@@ -44,14 +43,9 @@ class LlamaGenerator final : public DataGenerator {
 
   ~LlamaGenerator() override;
 
-  // disable copy constructor
   LlamaGenerator(const LlamaGenerator&) = delete;
-
-  // disable copy assignment operator
   LlamaGenerator& operator=(const LlamaGenerator&) = delete;
-  // disable move constructor
   LlamaGenerator(LlamaGenerator&&) = delete;
-  // disable move assignment operator
   LlamaGenerator& operator=(LlamaGenerator&&) = delete;
 
   /**
@@ -65,12 +59,15 @@ class LlamaGenerator final : public DataGenerator {
                                 const std::string& region_context) override;
 
   /**
-   * @brief Generates a user profile for the provided locale.
+   * @brief Generates a user profile grounded in a sampled name and persona.
    *
-   * @param locale Locale hint.
+   * @param city Enriched city the user is associated with.
+   * @param persona Persona archetype grounding the generated bio.
+   * @param name Sampled first/last name -- not LLM-invented.
    * @return Generated user profile.
    */
-  UserResult GenerateUser(const std::string& locale) override;
+  UserResult GenerateUser(const EnrichedCity& city, const UserPersona& persona,
+                          const Name& name) override;
 
  private:
   static constexpr int32_t kDefaultMaxTokens = 10000;

tooling/pipeline/includes/data_generation/llama_generator_helpers.h

@@ -47,4 +47,18 @@ void AppendTokenPiece(const llama_vocab* vocab, llama_token token,
 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_

tooling/pipeline/includes/data_generation/mock_generator.h

@@ -28,12 +28,16 @@ class MockGenerator final : public DataGenerator {
                                 const std::string& region_context) override;
 
   /**
-   * @brief Generates deterministic user data for a locale.
+   * @brief Generates deterministic user data grounded in a sampled name and
+   * persona.
    *
-   * @param locale Locale hint.
+   * @param city Enriched city the user is associated with.
+   * @param persona Persona archetype.
+   * @param name Sampled first/last name, copied directly into the result.
    * @return Generated user result.
    */
-  UserResult GenerateUser(const std::string& locale) override;
+  UserResult GenerateUser(const EnrichedCity& city, const UserPersona& persona,
+                          const Name& name) override;
 
  private:
   /**
@@ -44,12 +48,25 @@ class MockGenerator final : public DataGenerator {
    */
   static size_t DeterministicHash(const Location& location);
 
+  /**
+   * @brief Combines city, persona, and name into a stable hash value.
+   *
+   * @param location City and country names.
+   * @param persona Persona archetype.
+   * @param name Sampled first/last name.
+   * @return Deterministic hash value.
+   */
+  static size_t DeterministicHash(const Location& location,
+                                  const UserPersona& persona, const Name& name);
+
   // 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 size_t kActivityWeightHashStride = 17;
+  static constexpr size_t kActivityWeightHashRange = 1000;
 
   static constexpr std::array<std::string_view, 18> kBreweryAdjectives = {
       "Craft",      "Heritage", "Local",  "Artisan",  "Pioneer",    "Golden",
@@ -124,7 +141,8 @@ class MockGenerator final : public DataGenerator {
       "Visits breweries for the stories, stays for the flagship pours.",
       "Craft beer fan mapping tasting notes and favorite brew routes.",
       "Always ready to trade recommendations for underrated local breweries.",
-      "Keeping a running list of must-try collab releases and tap takeovers."};
+      "Keeping a running list of must-try collab releases and tap "
+      "takeovers."};
 };
 
 #endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_MOCK_GENERATOR_H_