1 Commits

Author SHA1 Message Date
6a66619c70 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
2026-05-22 22:00:38 -04:00
39 changed files with 329 additions and 245 deletions

View File

@@ -26,6 +26,7 @@ skinparam note {
title The Biergarten Data Pipeline - Class Diagram
class BiergartenDataGenerator {
- logger_ : std::shared_ptr<ILogger>
- context_service_ : std::unique_ptr<IEnrichmentService>
- generator_ : std::unique_ptr<DataGenerator>
- exporter_ : std::unique_ptr<IExportService>
@@ -36,6 +37,46 @@ class BiergartenDataGenerator {
- LogResults() : void
}
class LogLevel <<enumeration>> {
Debug
Info
Warn
Error
}
class PipelinePhase <<enumeration>> {
Startup
UserGeneration
BreweryAndBeerGeneration
CheckinGeneration
RatingGeneration
FollowGeneration
Teardown
}
struct LogEntry {
+ timestamp : std::chrono::system_clock::time_point
+ level : LogLevel
+ phase : PipelinePhase
+ message : std::string
+ worker : std::optional<std::string>
}
interface ILogger <<interface>> {
+ Log(entry : const LogEntry&) : void
}
class LogProducer {
- channel_ : BoundedChannel<LogEntry>&
+ Log(entry : const LogEntry&) : void
}
class LogDispatcher {
- channel_ : BoundedChannel<LogEntry>&
+ Run() : void
- ToSpdlogLevel(level) : spdlog::level::level_enum
}
interface IEnrichmentService <<interface>> {
+ GetLocationContext(loc : const Location&) : std::string
}
@@ -123,10 +164,17 @@ class SystemDateTimeProvider {
}
' Structural Relationships / Dependency Injection
BiergartenDataGenerator *-- ILogger : owns
BiergartenDataGenerator *-- IEnrichmentService : owns
BiergartenDataGenerator *-- DataGenerator : owns
BiergartenDataGenerator *-- IExportService : owns
LogEntry *-- LogLevel
LogEntry *-- PipelinePhase
ILogger <|.. LogProducer : implements
LogProducer ..> LogEntry : emits
LogDispatcher ..> LogEntry : consumes
IEnrichmentService <|.. WikipediaService : implements
WikipediaService *-- WebClient : owns

View File

@@ -275,32 +275,29 @@ package "Infrastructure: Logging" {
+ level : LogLevel
+ phase : PipelinePhase
+ message : std::string
+ city : std::optional<std::string>
+ entity_id : std::optional<std::string>
+ worker : std::optional<std::string>
}
interface Logger <<interface>> {
+ Log(level, phase, message,\n city, entity_id, worker) : void
interface ILogger <<interface>> {
+ Log(entry : const LogEntry&) : void
}
class PipelineLogger {
- log_ch_ : BoundedChannel<LogEntry>&
+ Log(level, phase, message,\n city, entity_id, worker) : void
class LogProducer {
- channel_ : BoundedChannel<LogEntry>&
+ Log(entry : const LogEntry&) : void
}
class LogWorker {
- log_ch_ : BoundedChannel<LogEntry>&
class LogDispatcher {
- channel_ : BoundedChannel<LogEntry>&
+ Run() : void
- FormatTimestamp(tp) : std::string
- ToSpdlogLevel(level) : spdlog::level::level_enum
- ToString(phase) : std::string
}
LogEntry *-- LogLevel
LogEntry *-- PipelinePhase
PipelineLogger ..> LogEntry : emits
LogWorker ..> LogEntry : consumes
ILogger <|.. LogProducer
LogProducer ..> LogEntry : emits
LogDispatcher ..> LogEntry : consumes
}
package "Infrastructure: Pipeline Channel" {

View File

@@ -249,6 +249,11 @@ target_compile_definitions(${PROJECT_NAME} PRIVATE
$<$<CONFIG:Debug>:DEBUG>
)
target_compile_options(biergarten-pipeline PRIVATE
-fmacro-prefix-map=${CMAKE_SOURCE_DIR}/tooling/pipeline/src/=
)
# 7. Runtime Assets
configure_file(
${CMAKE_SOURCE_DIR}/locations.json
@@ -260,3 +265,4 @@ add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD
${CMAKE_SOURCE_DIR}/prompts
${CMAKE_BINARY_DIR}/prompts
)

View File

@@ -1,8 +1,8 @@
#ifndef BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_PIPELINE_ORCHESTRATOR_H_
#define BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_PIPELINE_ORCHESTRATOR_H_
#ifndef BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
#define BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
/**
* @file biergarten_pipeline_orchestrator.h
* @file biergarten_data_generator.h
* @brief Orchestration for end-to-end brewery data generation pipeline.
*
* Intent: Coordinates location loading, enrichment, and generation phases
@@ -28,14 +28,14 @@
*/
class BiergartenPipelineOrchestrator {
public:
/**
* @brief Constructs the orchestrator with injected pipeline dependencies.
*
* @param context_service Provides regional context for locations.
* @param generator Implementation (Llama or Mock) for brewery/user generation.
* @param exporter Database backend for persisting generated records.
* @param application_options CLI configuration and paths.
*/
/**
* @brief Constructs the orchestrator with injected pipeline dependencies.
*
* @param context_service Provides regional context for locations.
* @param generator Implementation (Llama or Mock) for brewery/user generation.
* @param exporter Database backend for persisting generated records.
* @param application_options CLI configuration and paths.
*/
BiergartenPipelineOrchestrator(
std::shared_ptr<ILogger> logger,
std::unique_ptr<IEnrichmentService> context_service,
@@ -51,6 +51,12 @@ class BiergartenPipelineOrchestrator {
* 2. Resolve context for each city using the injected context service
* 3. Generate brewery data for sampled cities
*
* @note STRUCTURAL CONCURRENCY REQUIREMENT:
* When transitioned to a multithreaded design, this method MUST structurally
* enforce that all deployed worker threads are joined before returning (e.g.
* by using std::jthread or a structured concurrency primitive). This ensures
* workers do not attempt to log to a closed channel during application teardown.
*
* @return true if successful, false if not
*/
bool Run();
@@ -65,11 +71,11 @@ class BiergartenPipelineOrchestrator {
/// @brief Generator dependency selected in the composition root.
std::unique_ptr<DataGenerator> generator_;
/// @brief Storage backend for generated brewery records.
std::unique_ptr<IExportService> exporter_;
/// @brief Storage backend for generated brewery records.
std::unique_ptr<IExportService> exporter_;
/// @brief CLI configuration: paths, model settings, generation parameters.
ApplicationOptions application_options_;
/// @brief CLI configuration: paths, model settings, generation parameters.
ApplicationOptions application_options_;
/**
* @brief Load locations from JSON and sample cities.
@@ -93,5 +99,4 @@ class BiergartenPipelineOrchestrator {
/// @brief Stores generated brewery data.
std::vector<GeneratedBrewery> generated_breweries_;
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_PIPELINE_ORCHESTRATOR_H_
#endif // BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_

View File

@@ -8,7 +8,7 @@
#include <queue>
/**
* @file concurrency/bounded_channel.h
* @file bounded_channel.h
* @brief Thread-safe, bounded multi-producer/multi-consumer synchronous channel.
*
* Intent: Enables asynchronous inter-thread communication with backpressure.

View File

@@ -38,8 +38,7 @@ class LlamaGenerator final : public DataGenerator {
* @param prompt_directory Directory service for loading named prompt files.
*/
LlamaGenerator(const ApplicationOptions& options,
const std::string& model_path,
std::shared_ptr<ILogger> logger,
const std::string& model_path, std::shared_ptr<ILogger> logger,
std::unique_ptr<IPromptFormatter> prompt_formatter,
std::unique_ptr<IPromptDirectory> prompt_directory);

View File

@@ -1,11 +1,6 @@
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_GEMMA4_JINJA_PROMPT_FORMATTER_H_
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_GEMMA4_JINJA_PROMPT_FORMATTER_H_
/**
* @file data_generation/prompt_formatting/gemma4_jinja_prompt_formatter.h
* @brief Prompt formatter for Google Gemma 4 model using Jinja2 template syntax.
*/
#include <string>
#include <string_view>

View File

@@ -1,11 +1,6 @@
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_PROMPT_FORMATTER_H_
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_PROMPT_FORMATTER_H_
/**
* @file data_generation/prompt_formatting/prompt_formatter.h
* @brief Abstract interface for formatting system and user prompts.
*/
#include <string>
#include <string_view>

View File

@@ -2,7 +2,7 @@
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_EXPORT_SERVICE_H_
/**
* @file services/database/export_service.h
* @file services/export_service.h
* @brief Abstraction for persisting generated brewery data.
*/

View File

@@ -2,7 +2,7 @@
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_CONNECTION_HELPERS_H_
/**
* @file services/database/sqlite_connection_helpers.h
* @file services/sqlite_connection_helpers.h
* @brief Declarations for connection-level SQLite helper functions.
*/

View File

@@ -2,7 +2,7 @@
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_EXPORT_SERVICE_H_
/**
* @file services/database/sqlite_export_service.h
* @file services/sqlite_export_service.h
* @brief SQLite-backed export service for generated brewery data.
*/

View File

@@ -2,7 +2,7 @@
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_STATEMENT_HELPERS_H_
/**
* @file services/database/sqlite_statement_helpers.h
* @file services/sqlite_statement_helpers.h
* @brief Declarations for statement-level SQLite helper functions and
* constants.
*/

View File

@@ -2,7 +2,7 @@
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATETIME_DATE_TIME_PROVIDER_H_
/**
* @file services/datetime/date_time_provider.h
* @file services/date_time_provider.h
* @brief Abstraction for UTC timestamp generation.
*/

View File

@@ -4,7 +4,7 @@
#include <chrono>
/**
* @file services/datetime/timer.h
* @file services/timer.h
* @brief Simple timer utility for measuring elapsed time.
*/
class Timer {

View File

@@ -2,7 +2,7 @@
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_ENRICHMENT_SERVICE_H_
/**
* @file services/enrichment/enrichment_service.h
* @file services/enrichment_service.h
* @brief Abstraction for resolving contextual enrichment for a location.
*/

View File

@@ -1,29 +1,15 @@
//
// Created by aaronpo on 13/05/2026.
//
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_MOCK_ENRICHMENT_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_MOCK_ENRICHMENT_H_
/**
* @file services/enrichment/mock_enrichment.h
* @brief Mock implementation of enrichment service for testing.
*/
#include <string>
#include "enrichment_service.h"
/**
* @brief Mock implementation of enrichment service for testing and prototyping.
*
* Returns empty context without performing actual web queries or enrichment.
* Useful for unit tests and development scenarios.
*/
class MockEnrichmentService final : public IEnrichmentService {
public:
/**
* @brief Returns empty location context.
*
* @param loc Unused location parameter.
* @return Empty string (no enrichment performed).
*/
std::string GetLocationContext(const Location& /*loc*/) override {
return {};
}

View File

@@ -2,7 +2,7 @@
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_WIKIPEDIA_SERVICE_H_
/**
* @file services/enrichment/wikipedia_service.h
* @file services/wikipedia_service.h
* @brief Wikipedia summary retrieval service with in-memory caching.
*/

View File

@@ -1,6 +1,3 @@
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_ENTRY_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_ENTRY_H_
/**
* @file services/logging/log_entry.h
* @brief Structured log record shared by the pipeline logging infra.
@@ -9,10 +6,14 @@
* logging producer and dispatcher through BoundedChannel<LogEntry>.
*/
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_ENTRY_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_ENTRY_H_
#include <chrono>
#include <thread>
#include <source_location>
#include <string>
#include <thread>
#include <vector>
/**
* @enum LogLevel
@@ -42,17 +43,35 @@ enum class PipelinePhase {
Teardown, ///< Finalization and cleanup.
};
/**
* @struct LogDTO
* @brief User-provided subset of log fields. Used to capture call-site info transparently.
*/
struct LogDTO {
LogLevel level;
PipelinePhase phase;
std::string message;
};
/**
* @struct LogEntry
* @brief Single structured log event.
*
* All fields are value types, which keeps transfer across the bounded channel
* simple and avoids shared ownership.
*
* NOTE: timestamp, thread_id, and origin must be populated by ILogger::Log()
* before the entry is dispatched.
*/
struct LogEntry {
/// @brief Timestamp when the entry was created.
std::chrono::system_clock::time_point timestamp =
std::chrono::system_clock::now();
std::chrono::system_clock::time_point timestamp{};
/// @brief Source location where the log call was made.
std::source_location origin{};
/// @brief Thread responsible for emitting the log.
std::thread::id thread_id{};
/// @brief Severity level of this entry.
@@ -66,4 +85,4 @@ struct LogEntry {
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_ENTRY_H_
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_ENTRY_H_

View File

@@ -6,8 +6,8 @@
* a bounded channel for later processing by the dispatcher.
*/
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_PRODUCER_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_PRODUCER_H_
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_CHANNEL_LOGGER_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_CHANNEL_LOGGER_H_
#include <string_view>
@@ -41,12 +41,13 @@ class LogProducer final : public ILogger {
/**
* @brief Queue a log message for asynchronous processing.
*
* Blocks while the channel applies backpressure.
* Blocks while the channel applies backpressure. This blocking behavior
* under heavy load is an accepted trade-off for simplicity.
*/
void Log(LogEntry const& entry) override;
void DoLog(LogEntry log_entry) override;
private:
BoundedChannel<LogEntry>& channel_;
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_PRODUCER_H_
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_CHANNEL_LOGGER_H_

View File

@@ -1,6 +1,3 @@
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_
/**
* @file services/logging/logger.h
* @brief Abstract logging interface used by pipeline components.
@@ -9,10 +6,12 @@
* transport, buffering, and formatting implementation.
*/
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_
#include <optional>
#include <source_location>
#include <string>
#include <string_view>
#include <utility>
#include "services/logging/log_entry.h"
@@ -35,10 +34,31 @@ class ILogger {
/**
* @brief Submit a log message to the logging subsystem.
*
* @param entry Structured log record containing message and metadata.
*
* @param payload User-provided log data (level, phase, message).
* @param origin Auto-captured source location of the call site.
*/
virtual void Log(const LogEntry& entry) = 0;
void Log(LogDTO payload,
std::source_location origin = std::source_location::current(),
std::chrono::system_clock::time_point timestamp = std::chrono::system_clock::now(),
std::thread::id thread_id = std::this_thread::get_id()) {
LogEntry entry;
entry.timestamp = timestamp;
entry.thread_id = thread_id;
entry.level = payload.level;
entry.phase = payload.phase;
entry.message = std::move(payload.message);
entry.origin = origin;
DoLog(std::move(entry));
}
protected:
/**
* @brief Underlying implementation to transport the log entry.
*
* Implementations must be thread-safe as DoLog can be called concurrently
* from multiple worker threads.
*/
virtual void DoLog(LogEntry log_entry) = 0;
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_

View File

@@ -2,7 +2,7 @@
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_PROMPTING_PROMPT_DIRECTORY_H_
/**
* @file services/prompting/prompt_directory.h
* @file services/prompt_directory.h
* @brief Interface and filesystem-backed implementation for named prompt
* loading.
*

View File

@@ -1,18 +1,19 @@
/**
* @file web_client/http_web_client.h
* @brief cpp-httplib implementation of the WebClient interface.
*/
* @file web_client/http_web_client.h
* @brief cpp-httplib implementation of the WebClient interface.
*/
#ifndef BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_HTTP_WEB_CLIENT_H_
#define BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_HTTP_WEB_CLIENT_H_
#include "web_client/web_client.h"
#include "services/logging/logger.h"
#include <memory>
#include <string>
#include <utility>
#include "services/logging/logger.h"
#include "web_client/web_client.h"
/**
* @brief WebClient implementation backed by cpp-httplib.
*
@@ -25,18 +26,9 @@
* bound to a single origin at construction time.
*/
class HttpWebClient final : public WebClient {
public:
/**
* @brief Construct an HTTP web client with a logger.
*
* @param logger Logger instance for diagnostics.
*/
public:
explicit HttpWebClient(std::shared_ptr<ILogger> logger)
: logger_(std::move(logger)) {}
/**
* @brief Destructor.
*/
~HttpWebClient() override = default;
/**
@@ -60,4 +52,5 @@ class HttpWebClient final : public WebClient {
std::shared_ptr<ILogger> logger_;
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_HTTP_WEB_CLIENT_H_
#endif

View File

@@ -1,4 +1,5 @@
#include <chrono>
#include <format>
#include <iostream>
#include <optional>
#include <sstream>
@@ -70,14 +71,12 @@ std::optional<ApplicationOptions> ParseArguments(
return usage_stream.str();
})();
if (logger) {
logger->Log({.level = LogLevel::Info,
logger->Log(LogDTO{.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = title});
logger->Log({.level = LogLevel::Info,
logger->Log(LogDTO{.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = usage});
} else {
std::cout << title << std::endl << usage << std::endl;
}
return std::nullopt;
}
@@ -91,11 +90,9 @@ std::optional<ApplicationOptions> ParseArguments(
std::stringstream help_stream;
help_stream << "\n" << desc;
if (logger) {
logger->Log({.level = LogLevel::Info,
logger->Log(LogDTO{.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = help_stream.str()});
} else {
std::cout << help_stream.str() << std::endl;
}
return std::nullopt;
}
@@ -116,7 +113,7 @@ std::optional<ApplicationOptions> ParseArguments(
const std::string msg =
"Invalid arguments: --mocked and --model are mutually exclusive";
if (logger) {
logger->Log({.level = LogLevel::Error,
logger->Log(LogDTO{.level = LogLevel::Error,
.phase = PipelinePhase::Startup,
.message = msg});
} else {
@@ -129,7 +126,7 @@ std::optional<ApplicationOptions> ParseArguments(
const std::string msg =
"Invalid arguments: either --mocked or --model must be specified";
if (logger) {
logger->Log({.level = LogLevel::Error,
logger->Log(LogDTO{.level = LogLevel::Error,
.phase = PipelinePhase::Startup,
.message = msg});
} else {
@@ -173,7 +170,7 @@ std::optional<ApplicationOptions> ParseArguments(
const std::string msg =
"Sampling parameters are ignored when using --mocked";
if (logger) {
logger->Log({.level = LogLevel::Warn,
logger->Log(LogDTO{.level = LogLevel::Warn,
.phase = PipelinePhase::Startup,
.message = msg});
} else {
@@ -199,22 +196,18 @@ std::optional<ApplicationOptions> ParseArguments(
std::string("Failed to parse command-line arguments: ") +
exception.what();
if (logger) {
logger->Log({.level = LogLevel::Error,
logger->Log(LogDTO{.level = LogLevel::Error,
.phase = PipelinePhase::Startup,
.message = msg});
} else {
std::cerr << msg << std::endl;
}
return std::nullopt;
} catch (...) {
const std::string msg =
"Failed to parse command-line arguments: unknown error";
if (logger) {
logger->Log({.level = LogLevel::Error,
logger->Log(LogDTO{.level = LogLevel::Error,
.phase = PipelinePhase::Startup,
.message = msg});
} else {
std::cerr << msg << std::endl;
}
return std::nullopt;
}

View File

@@ -4,6 +4,7 @@
*/
#include <chrono>
#include <format>
#include "biergarten_pipeline_orchestrator.h"
#include "services/logging/logger.h"
@@ -36,34 +37,32 @@ void BiergartenPipelineOrchestrator::GenerateBreweries(
{.level = LogLevel::Warn,
.phase = PipelinePhase::BreweryAndBeerGeneration,
.message =
std::string("[Pipeline] Generated brewery for '") +
location.city + "' (" + location.country +
") but SQLite export failed: " + export_exception.what()});
std::format("[Pipeline] Generated brewery for '{}' ({}) but SQLite export failed: {}",
location.city, location.country, export_exception.what())});
}
} catch (const std::exception& e) {
++skipped_count;
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::BreweryAndBeerGeneration,
.message = std::string("[Pipeline] Skipping city '") +
location.city + " (" + location.country +
"): brewery generation failed: " + e.what()});
.message = std::format("[Pipeline] Skipping city '{}' ({}): brewery generation failed: {}",
location.city, location.country, e.what())});
}
}
if (skipped_count > 0) {
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::BreweryAndBeerGeneration,
.message = std::string("[Pipeline] Skipped ") +
std::to_string(skipped_count) +
" city/cities due to generation errors"});
.message = std::format(
"[Pipeline] Skipped {} city/cities due to generation errors",
skipped_count)});
}
if (export_failed_count > 0) {
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Teardown,
.message = std::string("[Pipeline] Failed to export ") +
std::to_string(export_failed_count) +
" generated brewery/breweries to SQLite"});
.message = std::format(
"[Pipeline] Failed to export {} generated brewery/breweries to SQLite",
export_failed_count)});
}
}

View File

@@ -34,4 +34,4 @@ void BiergartenPipelineOrchestrator::LogResults() const {
logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Teardown,
.message = oss.str()});
}
}

View File

@@ -4,6 +4,7 @@
*/
#include <chrono>
#include <format>
#include <utility>
#include "biergarten_pipeline_orchestrator.h"
@@ -33,18 +34,18 @@ bool BiergartenPipelineOrchestrator::Run() {
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message = std::string("[Pipeline] Skipping city '") + city.city +
" (" + city.country +
"): context lookup failed: " + exception.what()});
.message = std::format(
"[Pipeline] Skipping city '{}' ({}): context lookup failed: {}",
city.city, city.country, exception.what())});
}
}
if (skipped_count > 0) {
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message = std::string("[Pipeline] Skipped ") +
std::to_string(skipped_count) +
" city/cities due to context lookup errors"});
.message = std::format(
"[Pipeline] Skipped {} city/cities due to context lookup errors",
skipped_count)});
}
this->GenerateBreweries(enriched);
@@ -56,7 +57,7 @@ bool BiergartenPipelineOrchestrator::Run() {
{.level = LogLevel::Error,
.phase = PipelinePhase::Teardown,
.message =
std::string("Pipeline execution failed with error: ") + e.what()});
std::format("Pipeline execution failed with error: {}", e.what())});
return false;
}
}

View File

@@ -103,8 +103,8 @@ BreweryResult LlamaGenerator::GenerateBrewery(
logger_->Log(
{.level = LogLevel::Debug,
.phase = PipelinePhase::BreweryAndBeerGeneration,
.message = std::string("LlamaGenerator: raw output (attempt ") +
std::to_string(attempt + 1) + "): " + raw});
.message = std::format("LlamaGenerator: raw output (attempt {}): {}",
attempt + 1, raw)});
}
// Validate output: parse JSON and check required fields
@@ -120,9 +120,8 @@ BreweryResult LlamaGenerator::GenerateBrewery(
logger_->Log(
{.level = LogLevel::Info,
.phase = PipelinePhase::BreweryAndBeerGeneration,
.message = std::string("LlamaGenerator: successfully generated "
"brewery data on attempt ") +
std::to_string(attempt + 1)});
.message = std::format("LlamaGenerator: successfully generated brewery data on attempt {}",
attempt + 1)});
}
return brewery;
@@ -136,8 +135,8 @@ BreweryResult LlamaGenerator::GenerateBrewery(
{.level = LogLevel::Warn,
.phase = PipelinePhase::BreweryAndBeerGeneration,
.message =
std::string("LlamaGenerator: malformed brewery JSON (attempt ") +
std::to_string(attempt + 1) + "): " + *validation_error});
std::format("LlamaGenerator: malformed brewery JSON (attempt {}): {}",
attempt + 1, *validation_error)});
}
// Update prompt with error details to guide LLM toward correct output.
@@ -159,10 +158,9 @@ BreweryResult LlamaGenerator::GenerateBrewery(
logger_->Log(
{.level = LogLevel::Error,
.phase = PipelinePhase::BreweryAndBeerGeneration,
.message =
std::string("LlamaGenerator: malformed brewery response after ") +
std::to_string(max_attempts) +
" attempts: " + (last_error.empty() ? raw : last_error)});
.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");
}

View File

@@ -5,6 +5,7 @@
*/
#include <format>
#include <string>
#include "data_generation/llama_generator.h"
@@ -19,5 +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)};
}

View File

@@ -53,46 +53,45 @@ LlamaGenerator::LlamaGenerator(
"LlamaGenerator: prompt directory dependency must not be null");
}
const auto [temperature, top_p, top_k, n_ctx, seed, n_gpu_layers] =
options.generator.sampling.value_or(SamplingOptions{});
const auto sampling = options.generator.sampling.value_or(SamplingOptions{});
if (temperature < 0.0F) {
if (sampling.temperature < 0.0F) {
throw std::runtime_error(
"LlamaGenerator: sampling temperature must be >= 0");
}
if (top_p <= 0.0F || top_p > 1.0F) {
if (sampling.top_p <= 0.0F || sampling.top_p > 1.0F) {
throw std::runtime_error(
"LlamaGenerator: sampling top-p must be in (0, 1]");
}
if (top_k == 0U) {
if (sampling.top_k == 0U) {
throw std::runtime_error("LlamaGenerator: sampling top-k must be > 0");
}
if (seed < -1) {
if (sampling.seed < -1) {
throw std::runtime_error(
"LlamaGenerator: seed must be >= 0, or -1 for random");
}
if (n_ctx == 0 || n_ctx > kMaxContextSize) {
if (sampling.n_ctx == 0 || sampling.n_ctx > kMaxContextSize) {
throw std::runtime_error(
"LlamaGenerator: context size must be in range [1, 32768]");
}
sampling_temperature_ = temperature;
sampling_top_p_ = top_p;
sampling_top_k_ = top_k;
sampling_temperature_ = sampling.temperature;
sampling_top_p_ = sampling.top_p;
sampling_top_k_ = sampling.top_k;
if (seed == -1) {
if (sampling.seed == -1) {
std::random_device random_device;
rng_.seed(random_device());
} else {
rng_.seed(static_cast<uint32_t>(seed));
rng_.seed(static_cast<uint32_t>(sampling.seed));
}
n_ctx_ = n_ctx;
n_gpu_layers_ = n_gpu_layers;
n_ctx_ = sampling.n_ctx;
n_gpu_layers_ = sampling.n_gpu_layers;
this->Load(model_path);
}

View File

@@ -6,6 +6,7 @@
#include "json_handling/json_loader.h"
#include <format>
#include "services/logging/logger.h"
#include <iostream>
@@ -20,8 +21,8 @@ static std::string ReadRequiredString(const boost::json::object& object,
const char* key) {
const boost::json::value* value = object.if_contains(key);
if (value == nullptr || !value->is_string()) {
throw std::runtime_error(std::string("Missing or invalid string field: ") +
key);
throw std::runtime_error(
std::format("Missing or invalid string field: {}", key));
}
const std::string_view text = value->as_string();
return std::string(text);
@@ -31,8 +32,8 @@ static double ReadRequiredNumber(const boost::json::object& object,
const char* key) {
const boost::json::value* value = object.if_contains(key);
if (value == nullptr || !value->is_number()) {
throw std::runtime_error(std::string("Missing or invalid numeric field: ") +
key);
throw std::runtime_error(
std::format("Missing or invalid numeric field: {}", key));
}
return value->to_number<double>();
}
@@ -42,7 +43,7 @@ static std::vector<std::string> ReadRequiredStringArray(
const boost::json::value* value = object.if_contains(key);
if (value == nullptr || !value->is_array()) {
throw std::runtime_error(
std::string("Missing or invalid string array field: ") + key);
std::format("Missing or invalid string array field: {}", key));
}
const auto& array = value->as_array();
@@ -51,7 +52,7 @@ static std::vector<std::string> ReadRequiredStringArray(
for (const auto& item : array) {
if (!item.is_string()) {
throw std::runtime_error(
std::string("Missing or invalid string array field: ") + key);
std::format("Missing or invalid string array field: {}", key));
}
items.emplace_back(item.as_string());
}

View File

@@ -66,8 +66,8 @@ int main(const int argc, char** argv) {
const LlamaBackendState llama_backend_state;
#endif
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "STARTING PIPELINE"});
const std::optional<ApplicationOptions> parsed_options =
@@ -89,8 +89,8 @@ int main(const int argc, char** argv) {
prompt_directory = std::make_unique<PromptDirectory>(
options.pipeline.prompt_dir, log_producer);
} catch (const std::exception& dir_error) {
log_producer->Log({.level = LogLevel::Error,
.phase = PipelinePhase::Startup,
log_producer->Log({.level = LogLevel::Error,
.phase = PipelinePhase::Startup,
.message = std::format("Invalid --prompt-dir: {}",
dir_error.what())});
@@ -108,7 +108,7 @@ int main(const int argc, char** argv) {
{
log_producer->Log(
{.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.phase = PipelinePhase::Startup,
.message = "Prompt formatter: none (mock mode)"});
}
return std::unique_ptr<IPromptFormatter>(nullptr);
@@ -116,7 +116,7 @@ int main(const int argc, char** argv) {
{
log_producer->Log(
{.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.phase = PipelinePhase::Startup,
.message = "Prompt formatter: Gemma4JinjaPromptFormatter"});
}
return std::unique_ptr<IPromptFormatter>(
@@ -125,15 +125,15 @@ int main(const int argc, char** argv) {
di::bind<WebClient>().to([options, log_producer] {
if (options.generator.use_mocked) {
{
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "Web client: none (mock mode)"});
}
return std::unique_ptr<WebClient>(nullptr);
}
{
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "Web client: HttpWebClient"});
}
return std::unique_ptr<WebClient>(
@@ -144,15 +144,15 @@ int main(const int argc, char** argv) {
const auto& inj) -> std::unique_ptr<IEnrichmentService> {
if (options.generator.use_mocked) {
{
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "Enrichment: mock"});
}
return std::make_unique<MockEnrichmentService>();
}
{
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "Enrichment: Wikipedia"});
}
return std::make_unique<WikipediaEnrichmentService>(
@@ -164,8 +164,8 @@ int main(const int argc, char** argv) {
&log_producer](const auto& inj) -> std::unique_ptr<DataGenerator> {
if (options.generator.use_mocked) {
{
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "Generator: mock"});
}
return std::make_unique<MockGenerator>();
@@ -173,7 +173,7 @@ int main(const int argc, char** argv) {
{
log_producer->Log(
{.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.phase = PipelinePhase::Startup,
.message = std::format(
"Generator: LlamaGenerator | model={} | temp={:.2f} "
"top_p={:.2f} top_k={} n_ctx={} seed={}",
@@ -190,23 +190,23 @@ int main(const int argc, char** argv) {
injector.create<std::unique_ptr<BiergartenPipelineOrchestrator>>();
if (!orchestrator->Run()) {
log_producer->Log({.level = LogLevel::Error,
.phase = PipelinePhase::Teardown,
log_producer->Log({.level = LogLevel::Error,
.phase = PipelinePhase::Teardown,
.message = "Pipeline execution failed"});
return shutdown(EXIT_FAILURE);
}
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Teardown,
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Teardown,
.message = std::format("Pipeline complete in {} ms",
timer.Elapsed())});
return shutdown(EXIT_SUCCESS);
} catch (const std::exception& exception) {
const LogEntry log_entry{.level = LogLevel::Error,
.phase = PipelinePhase::Teardown,
.message = exception.what()};
const LogDTO log_entry{.level = LogLevel::Error,
.phase = PipelinePhase::Teardown,
.message = exception.what()};
if (log_producer) {
log_producer->Log(log_entry);
} else {

View File

@@ -22,8 +22,7 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
if (logger_) {
logger_->Log({.level = LogLevel::Debug,
.phase = PipelinePhase::UserGeneration,
.message = std::string("Wikipedia: Cache hit for ") +
cache_key + "!"});
.message = std::format("Wikipedia: Cache hit for {}!", cache_key)});
}
return cache_it->second;
}
@@ -49,8 +48,8 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message = std::string("WikipediaService: JSON parse error for '") +
std::string(query) + "': " + ec.message()});
.message = std::format("WikipediaService: JSON parse error for '{}': {}",
std::string(query), ec.message())});
}
return {};
}
@@ -63,8 +62,8 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message =
std::string("WikipediaService: Expected root object for '") +
std::string(query) + "'"});
std::format("WikipediaService: Expected root object for '{}'",
std::string(query))});
}
return {};
}
@@ -81,8 +80,8 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message =
std::string("WikipediaService: Missing query.pages for '") +
std::string(query) + "'"});
std::format("WikipediaService: Missing query.pages for '{}'",
std::string(query))});
}
return {};
}
@@ -94,8 +93,8 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message = std::string("WikipediaService: No pages returned for '") +
std::string(query) + "'"});
.message = std::format("WikipediaService: No pages returned for '{}'",
std::string(query))});
}
this->extract_cache_.emplace(cache_key, "");
return {};
@@ -111,8 +110,8 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message =
std::string("WikipediaService: Unexpected page format for '") +
std::string(query) + "'"});
std::format("WikipediaService: Unexpected page format for '{}'",
std::string(query))});
}
return {};
}
@@ -124,8 +123,8 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
if (logger_) {
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message = std::string("WikipediaService: Page '") +
std::string(query) + "' does not exist"});
.message = std::format("WikipediaService: Page '{}' does not exist",
std::string(query))});
}
this->extract_cache_.emplace(cache_key, "");
return {};
@@ -139,8 +138,8 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message =
std::string("WikipediaService: No extract string found for '") +
std::string(query) + "'"});
std::format("WikipediaService: No extract string found for '{}'",
std::string(query))});
}
this->extract_cache_.emplace(cache_key, "");
return {};
@@ -151,9 +150,8 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
if (logger_) {
logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::UserGeneration,
.message = std::string("WikipediaService: Fetched ") +
std::to_string(extract.size()) + " chars for '" +
std::string(query) + "'"});
.message = std::format("WikipediaService: Fetched {} chars for '{}'",
extract.size(), std::string(query))});
}
this->extract_cache_.insert_or_assign(cache_key, extract);

View File

@@ -52,8 +52,8 @@ std::string WikipediaEnrichmentService::GetLocationContext(
if (logger_) {
logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::UserGeneration,
.message = std::string("Done fetching for ") +
location_query + ". Sleeping for 10 seconds."});
.message = std::format("Done fetching for {}. Sleeping for 10 seconds.",
location_query)});
}
std::this_thread::sleep_for(10s);
@@ -62,8 +62,8 @@ std::string WikipediaEnrichmentService::GetLocationContext(
logger_->Log(
{.level = LogLevel::Debug,
.phase = PipelinePhase::UserGeneration,
.message = std::string("WikipediaService lookup failed for '") +
location_query + "': " + e.what()});
.message = std::format("WikipediaService lookup failed for '{}': {}",
location_query, e.what())});
}
}
return result;

View File

@@ -13,6 +13,29 @@
#include "concurrency/bounded_channel.h"
#include "services/logging/log_entry.h"
namespace {
[[nodiscard]] constexpr std::string_view PipelinePhaseToString(
PipelinePhase phase) {
switch (phase) {
case PipelinePhase::Startup:
return "Startup";
case PipelinePhase::UserGeneration:
return "User Generation";
case PipelinePhase::BreweryAndBeerGeneration:
return "Brewery & Beer Gen";
case PipelinePhase::CheckinGeneration:
return "Checkin Gen";
case PipelinePhase::RatingGeneration:
return "Rating Gen";
case PipelinePhase::FollowGeneration:
return "Follow Gen";
case PipelinePhase::Teardown:
return "Teardown";
}
return "Unknown";
}
} // namespace
LogDispatcher::LogDispatcher(BoundedChannel<LogEntry>& channel)
: channel_(channel) {}
@@ -28,7 +51,11 @@ void LogDispatcher::Run() {
const auto& log = entry.value();
logger->log(ToSpdlogLevel(log.level), log.message);
logger->log(ToSpdlogLevel(log.level),
"{:<20} │ thread: {:016x} │ [{}:{}] │ {}",
PipelinePhaseToString(log.phase),
std::hash<std::thread::id>{}(log.thread_id),
log.origin.file_name(), log.origin.line(), log.message);
}
}

View File

@@ -16,4 +16,4 @@
LogProducer::LogProducer(BoundedChannel<LogEntry>& channel)
: channel_(channel) {}
void LogProducer::Log(const LogEntry& entry) { channel_.Send(entry); }
void LogProducer::DoLog(LogEntry entry) { channel_.Send(std::move(entry)); }

View File

@@ -8,6 +8,7 @@
#include <chrono>
#include <filesystem>
#include <format>
#include <fstream>
#include <stdexcept>
#include <string>
@@ -44,8 +45,8 @@ PromptDirectory::PromptDirectory(const std::filesystem::path& prompt_dir,
std::filesystem::directory_iterator probe(prompt_dir_, ec);
if (ec) {
throw std::runtime_error(
"PromptDirectory: prompt directory is not readable: " +
prompt_dir_.string() + " (" + ec.message() + ")");
std::format("PromptDirectory: prompt directory is not readable: {} ({})",
prompt_dir_.string(), ec.message()));
}
if (logger_) {
@@ -69,13 +70,13 @@ std::string PromptDirectory::Load(std::string_view key) {
// Scenario 3: resolve <prompt_dir>/<key>.md and require it to exist.
const std::filesystem::path file_path =
prompt_dir_ / std::filesystem::path(key_str + ".md");
prompt_dir_ / std::filesystem::path(std::format("{}.md", key_str));
std::ifstream file(file_path);
if (!file.is_open()) {
throw std::runtime_error(
"PromptDirectory: prompt file not found for key '" + key_str +
"': " + file_path.string());
std::format("PromptDirectory: prompt file not found for key '{}': {}",
key_str, file_path.string()));
}
std::string content((std::istreambuf_iterator<char>(file)),
@@ -83,16 +84,15 @@ std::string PromptDirectory::Load(std::string_view key) {
file.close();
if (content.empty()) {
throw std::runtime_error("PromptDirectory: prompt file for key '" +
key_str + "' is empty: " + file_path.string());
throw std::runtime_error(std::format("PromptDirectory: prompt file for key '{}' is empty: {}",
key_str, file_path.string()));
}
if (logger_) {
logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = std::string("[PromptDirectory] Loaded prompt '") +
key_str + "' from '" + file_path.string() + "' (" +
std::to_string(content.size()) + " chars)"});
.message = std::format("[PromptDirectory] Loaded prompt '{}' from '{}' ({} chars)",
key_str, file_path.string(), content.size())});
}
cache_.emplace(key_str, content);

View File

@@ -1,5 +1,6 @@
#include "services/database/sqlite_connection_helpers.h"
#include <format>
#include <stdexcept>
namespace sqlite_export_service_internal {
@@ -20,7 +21,7 @@ void SqliteStatementDeleter::operator()(
void ThrowSqliteError(sqlite3* db_handle, std::string_view action) {
const std::string message =
db_handle != nullptr ? sqlite3_errmsg(db_handle) : "unknown SQLite error";
throw std::runtime_error(std::string(action) + ": " + message);
throw std::runtime_error(std::format("{}: {}", action, message));
}
SqliteDatabaseHandle OpenDatabase(const std::filesystem::path& path) {
@@ -50,7 +51,7 @@ void ExecSql(const SqliteDatabaseHandle& db_handle, std::string_view sql,
? error_message
: sqlite3_errmsg(db_handle.get());
sqlite3_free(error_message);
throw std::runtime_error(std::string(action) + ": " + message);
throw std::runtime_error(std::format("{}: {}", action, message));
}
}

View File

@@ -4,6 +4,7 @@
*/
#include <filesystem>
#include <format>
#include <memory>
#include <stdexcept>
#include <string>
@@ -18,8 +19,8 @@ std::filesystem::path SqliteExportService::BuildDatabasePath() const {
for (int suffix = 1; std::filesystem::exists(candidate); ++suffix) {
candidate = output_path_ /
std::filesystem::path("biergarten_seed_" + run_timestamp_utc_ +
"-" + std::to_string(suffix) + ".sqlite");
std::filesystem::path(std::format("biergarten_seed_{}-{}.sqlite",
run_timestamp_utc_, suffix));
}
return candidate;

View File

@@ -8,6 +8,7 @@
#include <httplib.h>
#include <chrono>
#include <format>
#include <regex>
#include <stdexcept>
#include <string>
@@ -47,8 +48,9 @@ std::string HttpWebClient::Get(const std::string& url) {
const httplib::Result result = client.Get(path);
if (!result) {
throw std::runtime_error("[HttpWebClient] Request failed for URL: " + url +
"" + httplib::to_string(result.error()));
throw std::runtime_error(std::format(
"[HttpWebClient] Request failed for URL: {} — {}", url,
httplib::to_string(result.error())));
}
if (result->status < kSuccessMin || result->status >= kSuccessMax) {
@@ -56,12 +58,11 @@ std::string HttpWebClient::Get(const std::string& url) {
logger_->Log(
{.level = LogLevel::Error,
.phase = PipelinePhase::UserGeneration,
.message =
std::string("[HttpWebClient] Request failed for URL: ") + url});
.message =
std::format("[HttpWebClient] Request failed for URL: {}", url)});
}
throw std::runtime_error("[HttpWebClient] HTTP " +
std::to_string(result->status) +
" for URL: " + url);
throw std::runtime_error(std::format("[HttpWebClient] HTTP {} for URL: {}",
result->status, url));
}
return result->body;