Add user generation feature

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

@@ -1,24 +1,121 @@
 /**
  * @file data_generation/llama/generate_user.cc
- * @brief Generates locale-aware user profiles with strict two-line formatting,
- * retry handling, and output sanitization for downstream parsing.
+ * @brief Builds persona/name-grounded user prompts, performs retry-based
+ * inference, and validates structured JSON output for user records.
  */
 
-
 #include <format>
+#include <optional>
+#include <stdexcept>
 #include <string>
+#include <string_view>
 
 #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 = std::format("This is a test user profile from {}.", locale)};
+// GBNF grammar for structured user JSON output.
+static 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";
+
+static constexpr int kUserInitialMaxTokens = 1200;
+
+UserResult LlamaGenerator::GenerateUser(const EnrichedCity& city,
+                                        const UserPersona& persona,
+                                        const Name& name) {
+  std::string style_affinities;
+  for (const std::string& style : persona.style_affinities) {
+    if (!style_affinities.empty()) {
+      style_affinities += ", ";
+    }
+    style_affinities += style;
+  }
+
+  const std::string system_prompt = prompt_directory_->Load("USER_GENERATION");
+
+  std::string user_prompt = std::format(
+      "## NAME:\n{} {}\n\n## GENDER:\n{}\n\n## CITY:\n{}\n\n## COUNTRY:\n{}\n\n"
+      "## PERSONA:\n{}\n\n## PERSONA DESCRIPTION:\n{}\n\n## STYLE "
+      "AFFINITIES:\n{}",
+      name.first_name, name.last_name, name.gender, city.location.city,
+      city.location.country, persona.name, persona.description,
+      style_affinities);
+
+  const std::string retry_context =
+      std::format("Name: {} {}\nCity: {}, {}\nPersona: {}", name.first_name,
+                 name.last_name, city.location.city, city.location.country,
+                 persona.name);
+
+  constexpr int max_attempts = 3;
+  std::string raw;
+  std::string last_error;
+  int max_tokens = kUserInitialMaxTokens;
+
+  for (int attempt = 0; attempt < max_attempts; ++attempt) {
+    raw = this->Infer(system_prompt, user_prompt, max_tokens,
+                      kUserJsonGrammar);
+    if (logger_) {
+      logger_->Log(
+          {.level = LogLevel::Debug,
+           .phase = PipelinePhase::UserGeneration,
+           .message = std::format("LlamaGenerator: raw output (attempt {}): {}",
+                      attempt + 1, raw)});
+    }
+
+    UserResult user;
+    const std::optional<std::string> validation_error =
+        ValidateUserJson(raw, user);
+
+    if (!validation_error.has_value()) {
+      if (logger_) {
+        logger_->Log(
+            {.level = LogLevel::Info,
+             .phase = PipelinePhase::UserGeneration,
+             .message = std::format("LlamaGenerator: successfully generated user data on attempt {}",
+                        attempt + 1)});
+      }
+
+      user.first_name = name.first_name;
+      user.last_name = name.last_name;
+      user.gender = name.gender;
+      return user;
+    }
+
+    last_error = *validation_error;
+    if (logger_) {
+      logger_->Log(
+          {.level = LogLevel::Warn,
+           .phase = PipelinePhase::UserGeneration,
+           .message =
+               std::format("LlamaGenerator: malformed user JSON (attempt {}): {}",
+               attempt + 1, *validation_error)});
+    }
+
+    user_prompt = std::format(
+        "Your previous response was invalid. Error: {}\nReturn the thought "
+        "process before the JSON if needed, then return ONLY valid JSON with "
+        "exactly these keys, in this exact order: {{\"username\": \"<handle "
+        "derived from the given name>\", \"bio\": \"<first-person bio "
+        "grounded in the persona>\", \"activity_weight\": <number between 0 "
+        "and 1>}}.\nDo not include markdown, comments, extra keys, or "
+        "literal placeholder values.\n\n{}",
+        *validation_error, retry_context);
+  }
+
+  if (logger_) {
+    logger_->Log(
+        {.level = LogLevel::Error,
+         .phase = PipelinePhase::UserGeneration,
+       .message = std::format(
+         "LlamaGenerator: malformed user response after {} attempts: {}",
+         max_attempts, last_error.empty() ? raw : last_error)});
+  }
+  throw std::runtime_error("LlamaGenerator: malformed user response");
 }

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

@@ -91,6 +91,22 @@ bool HasSchemaPlaceholder(const std::array<std::string*, 4>& values) {
 
   return false;
 }
+
+bool HasSchemaPlaceholder(const std::array<std::string*, 2>& 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
 
 /**
@@ -207,3 +223,58 @@ std::optional<std::string> ValidateBreweryJson(const std::string& raw,
 
   return std::nullopt;
 }
+
+std::optional<std::string> ValidateUserJson(const std::string& raw,
+                                            UserResult& user_out) {
+  boost::system::error_code error_code;
+  const std::string_view raw_view(raw);
+  const size_t opening_brace = raw_view.find('{');
+  if (opening_brace == std::string_view::npos) {
+    return "JSON parse error: missing opening brace '{'";
+  }
+
+  const std::string_view json_payload = raw_view.substr(opening_brace);
+  boost::json::value json_value = boost::json::parse(json_payload, error_code);
+  if (error_code) {
+    return "JSON parse error: " + error_code.message();
+  }
+
+  if (!json_value.is_object()) {
+    return "JSON root must be an object";
+  }
+
+  const auto& obj = json_value.get_object();
+  if (obj.size() != 3) {
+    return "JSON object must contain exactly three keys";
+  }
+
+  std::string validation_error;
+  if (!ReadRequiredTrimmedStringField(obj, "username", user_out.username,
+                                      &validation_error)) {
+    return validation_error;
+  }
+
+  if (!ReadRequiredTrimmedStringField(obj, "bio", user_out.bio,
+                                      &validation_error)) {
+    return validation_error;
+  }
+
+  const boost::json::value* activity_weight_field =
+      obj.if_contains("activity_weight");
+  if (activity_weight_field == nullptr || !activity_weight_field->is_number()) {
+    return "Missing or invalid numeric field: activity_weight";
+  }
+
+  const double activity_weight = activity_weight_field->to_number<double>();
+  if (activity_weight < 0.0 || activity_weight > 1.0) {
+    return "activity_weight must be between 0 and 1";
+  }
+  user_out.activity_weight = static_cast<float>(activity_weight);
+
+  const std::array schema_placeholders = {&user_out.username, &user_out.bio};
+  if (HasSchemaPlaceholder(schema_placeholders)) {
+    return "JSON appears to be a schema placeholder, not content";
+  }
+
+  return std::nullopt;
+}