From 1b242e86b5aab4856649698b7cd5f23c3618bb8b Mon Sep 17 00:00:00 2001
From: Aaron Po <apo2@uwo.ca>
Date: Sat, 18 Apr 2026 19:18:21 -0400
Subject: [PATCH] Improve type safety, update logging, remove unused paths

---
 .../data_generation/llama/generate_brewery.cc | 18 ++----------------
 pipeline/src/data_generation/llama/helpers.cc |  2 +-
 pipeline/src/json_handling/json_loader.cc     |  1 +
 .../src/web_client/curl_web_client_get.cc     | 19 ++++++++++++++-----
 4 files changed, 18 insertions(+), 22 deletions(-)

diff --git a/pipeline/src/data_generation/llama/generate_brewery.cc b/pipeline/src/data_generation/llama/generate_brewery.cc
index aab6a01..7e92664 100644
--- a/pipeline/src/data_generation/llama/generate_brewery.cc
+++ b/pipeline/src/data_generation/llama/generate_brewery.cc
@@ -44,8 +44,6 @@ hex ::= [0-9a-fA-F]
 )json_brewery";
 
 static constexpr int kBreweryInitialMaxTokens = 2800;
-static constexpr int kBreweryTruncationRetryTokenBump = 700;
-static constexpr int kBreweryMaxTokensCeiling = 5000;
 
 BreweryResult LlamaGenerator::GenerateBrewery(
     const Location& location, const std::string& region_context) {
@@ -98,8 +96,8 @@ BreweryResult LlamaGenerator::GenerateBrewery(
     // Generate brewery data from LLM
     raw = this->Infer(system_prompt, user_prompt, max_tokens,
                       kBreweryJsonGrammar);
-    spdlog::info("LlamaGenerator: raw output (attempt {}): {}", attempt + 1,
-                 raw);
+    spdlog::debug("LlamaGenerator: raw output (attempt {}): {}", attempt + 1,
+                  raw);
 
     // Validate output: parse JSON and check required fields
 
@@ -123,18 +121,6 @@ BreweryResult LlamaGenerator::GenerateBrewery(
     spdlog::warn("LlamaGenerator: malformed brewery JSON (attempt {}): {}",
                  attempt + 1, *validation_error);
 
-    if (last_error == "JSON parse error: incomplete JSON") {
-      const int previous_max_tokens = max_tokens;
-      max_tokens = std::min(max_tokens + kBreweryTruncationRetryTokenBump,
-                            kBreweryMaxTokensCeiling);
-      spdlog::info(
-          "LlamaGenerator: detected truncated JSON; increasing max_tokens from "
-          "{} to {} and retrying",
-          previous_max_tokens, max_tokens);
-
-      continue;
-    }
-
     // Update prompt with error details to guide LLM toward correct output.
     user_prompt = std::format(
         "Your previous response was invalid. Error: {}\nReturn the thought "
diff --git a/pipeline/src/data_generation/llama/helpers.cc b/pipeline/src/data_generation/llama/helpers.cc
index 6e5e039..66f0c8e 100644
--- a/pipeline/src/data_generation/llama/helpers.cc
+++ b/pipeline/src/data_generation/llama/helpers.cc
@@ -41,7 +41,7 @@ static std::string CondenseWhitespace(std::string_view text) {
 
   bool pending_space = false;
   for (const char chr : text) {
-    if (std::isspace(chr) != 0) {
+    if (std::isspace(static_cast<unsigned char>(chr)) != 0) {
       if (!out.empty()) {
         pending_space = true;
       }
diff --git a/pipeline/src/json_handling/json_loader.cc b/pipeline/src/json_handling/json_loader.cc
index eb592b5..16ed1af 100644
--- a/pipeline/src/json_handling/json_loader.cc
+++ b/pipeline/src/json_handling/json_loader.cc
@@ -9,6 +9,7 @@
 #include <fstream>
 #include <sstream>
 #include <stdexcept>
+#include <string>
 #include <string_view>
 
 #include <boost/json.hpp>
diff --git a/pipeline/src/web_client/curl_web_client_get.cc b/pipeline/src/web_client/curl_web_client_get.cc
index b047cdf..334f0d6 100644
--- a/pipeline/src/web_client/curl_web_client_get.cc
+++ b/pipeline/src/web_client/curl_web_client_get.cc
@@ -6,6 +6,7 @@
 #include "web_client/curl_web_client.h"
 
 #include <cstdint>
+#include <limits>
 #include <memory>
 #include <stdexcept>
 #include <string>
@@ -14,9 +15,9 @@
 
 using CurlHandle = std::unique_ptr<CURL, decltype(&curl_easy_cleanup)>;
 
-static constexpr int64_t kConnectionTimeout = 10;
-static constexpr int64_t kRequestTimeout = 30;
-static constexpr int64_t kOkHttpStatus = 200;
+static constexpr long kConnectionTimeout = 10;
+static constexpr long kRequestTimeout = 30;
+static constexpr int32_t kOkHttpStatus = 200;
 
 static CurlHandle CreateHandle() {
   CURL* handle = curl_easy_init();
@@ -64,8 +65,16 @@ std::string CURLWebClient::Get(const std::string& url) {
     throw std::runtime_error(error);
   }
 
-  int64_t http_code = 0;
-  curl_easy_getinfo(curl.get(), CURLINFO_RESPONSE_CODE, &http_code);
+  long curl_http_code = 0;
+  curl_easy_getinfo(curl.get(), CURLINFO_RESPONSE_CODE, &curl_http_code);
+
+  if (curl_http_code < std::numeric_limits<int32_t>::min() ||
+      curl_http_code > std::numeric_limits<int32_t>::max()) {
+    throw std::runtime_error("[CURLWebClient] Invalid HTTP status code: " +
+                             std::to_string(curl_http_code));
+  }
+
+  const int32_t http_code = static_cast<int32_t>(curl_http_code);
 
   if (http_code != kOkHttpStatus) {
     const std::string error = "[CURLWebClient] HTTP error " +