Add multithreaded logging infrastructure for preparation for future designs (#225)

* Update class diagrams

* Implement BoundedChannel and multithreaded logging infra

* Integrate logging channel system

* Update string concatenations to use std::format

* Add pretty print log

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>
@@ -100,8 +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
 
@@ -112,9 +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;
     }
@@ -122,8 +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(
@@ -140,9 +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

@@ -4,9 +4,8 @@
  * retry handling, and output sanitization for downstream parsing.
  */
 
-#include <spdlog/spdlog.h>
 
-#include <stdexcept>
+#include <format>
 #include <string>
 
 #include "data_generation/llama_generator.h"
@@ -21,5 +20,5 @@
 // 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());
 
@@ -61,7 +61,37 @@ static std::string CondenseWhitespace(std::string_view text) {
 // 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.
-static constexpr size_t kTruncationGuardDivisor = 2;
+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
@@ -121,47 +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;
@@ -209,7 +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>
@@ -107,7 +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)
@@ -171,10 +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

@@ -32,9 +32,11 @@ void LlamaGenerator::ContextDeleter::operator()(
 
 LlamaGenerator::LlamaGenerator(
     const ApplicationOptions& options, const std::string& model_path,
+    std::shared_ptr<ILogger> logger,
     std::unique_ptr<IPromptFormatter> prompt_formatter,
     std::unique_ptr<IPromptDirectory> prompt_directory)
     : rng_(std::random_device{}()),
+      logger_(std::move(logger)),
       prompt_formatter_(std::move(prompt_formatter)),
       prompt_directory_(std::move(prompt_directory)) {
   if (model_path.empty()) {

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

@@ -4,9 +4,8 @@
  * context, and resets prior resources during model initialization.
  */
 
-#include <spdlog/spdlog.h>
-
 #include <algorithm>
+#include <chrono>
 #include <stdexcept>
 #include <string>
 #include <utility>
@@ -29,8 +28,10 @@ void LlamaGenerator::Load(const std::string& model_path) {
 
   llama_model_params model_params = llama_model_default_params();
   model_params.n_gpu_layers = n_gpu_layers_;
-  LlamaGenerator::ModelHandle loaded_model(
+
+  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);
@@ -40,8 +41,9 @@ void LlamaGenerator::Load(const std::string& model_path) {
   context_params.n_ctx = n_ctx_;
   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");
   }
@@ -49,5 +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)});
+  }
 }