updates

2026-05-31 17:53:59 +00:00 · 2026-04-20 23:56:27 -04:00
parent 6657015ee3
commit bbe8970bf6
2 changed files with 285 additions and 218 deletions
--- a/pipeline/diagrams/future-activity-diagram.puml
+++ b/pipeline/diagrams/future-activity-diagram.puml
@@ -1,18 +1,26 @@
-@startuml future_possible_activity
+@startuml biergarten_activity
 skinparam defaultFontName "DM Sans"
 skinparam defaultFontSize 13
 skinparam titleFontName "Volkhov"
 skinparam titleFontSize 20
-skinparam backgroundColor #FAFCF9
-skinparam defaultFontColor #28342A
-skinparam titleFontColor #28342A
-skinparam ArrowColor #628A5B
-skinparam ActivityBackgroundColor #EAF0E8
-skinparam ActivityBorderColor #547461
-skinparam ActivityDiamondBackgroundColor #DCE8D8
-skinparam ActivityDiamondBorderColor #547461
-skinparam NoteBackgroundColor #EAF0E8
-skinparam NoteBorderColor #547461
+skinparam backgroundColor #FCFCF7
+skinparam defaultFontColor #14180C
+skinparam titleFontColor #14180C
+skinparam ArrowColor #656F33
+skinparam activityStartColor #EBECE3
+skinparam activityEndColor #4A5837
+skinparam activityStopColor #4A5837
+skinparam ActivityBackgroundColor #EBECE3
+skinparam ActivityBorderColor #4A5837
+skinparam ActivityDiamondBackgroundColor #CBD2B5
+skinparam ActivityDiamondBorderColor #4A5837
+skinparam NoteBackgroundColor #DBEEDD
+skinparam NoteFontColor #14180C
+skinparam NoteBorderColor #4A5837
+skinparam SwimlaneBorderColor #4A5837
+skinparam SwimlaneBorderThickness 1
+skinparam monochrome reverse
+

 title The Biergarten Data Pipeline — Activity Diagram

@@ -27,6 +35,25 @@ endif
 :Init CurlGlobalState & LlamaBackendState;
 :Build DI injector;

+
+:Initialize SqliteExportService;
+note right
+  Opens SQLite connection.
+  Begins a single transaction
+  covering all five fixture types.
+end note
+
+:Create BoundedChannel<LogEntry> log_ch;
+:Spawn Log Worker thread;
+note right
+  Log worker drains log_ch for the
+  entire pipeline lifetime.
+  All workers emit LogEntry structs
+  via PipelineLogger — never spdlog directly.
+end note
+
+:BiergartenPipelineOrchestrator::Run();
+|BiergartenPipelineOrchestrator::Run()|
 :JsonLoader::LoadLocations("locations.json");
 :JsonLoader::LoadBeerStyles("beer-styles.json");
 :JsonLoader::LoadPersonas("personas.json");
@@ -42,17 +69,10 @@ end note
 :EnrichmentService::PreWarmPersonaCache(personas);
 note right
  Persona descriptions do not need location context.
-  All persona Wikipedia/description lookups are
-  resolved and cached globally at startup.
+  All persona lookups are resolved and cached
+  globally at startup.
 end note

-:Initialize SqliteExportService;
-note right
-  Opens SQLite connection.
-  Begins a single transaction
-  covering all five fixture types.
-end note
-:BiergartenPipelineOrchestrator::Run();

 ' ═══════════════════════════════════════════
 ' PHASE 0 — USER GENERATION
@@ -73,24 +93,27 @@ fork again
    :IPersonaSelectionStrategy::SelectPersona(\n  personas_palette_);
    note right
      Guaranteed cache hit from startup.
-      Returns a Persona struct with style_affinities,
-      abv_range, ibu_preference, checkin_weight.
+      Returns a Persona struct carrying
+      style_affinities, abv_range,
+      ibu_preference, checkin_weight.
    end note

    :NamesByCountry::SampleName(\n  location.iso3166_1);
    note right
      Deterministic lookup — no LLM involved.
-      Name is selected from a pre-keyed table
+      Name selected from pre-keyed table
      and passed into the generation prompt.
    end note

    :GenerateUser(location, persona, sampled_name)\nvia DataGenerator;
    note right
-      LLM receives: Location fields + persona description
-      + sampled name. Generates bio and preference
-      signals grounded in both.
+      LLM receives: Location fields + persona
+      description + sampled name. Generates
+      bio and preference signals grounded
+      in locale and persona.
    end note

+    :PipelineLogger::Log(Info, UserGeneration,\n  city, user_id, "llm");
    :Send GeneratedUser → llm_ch;
  endwhile (no)
  :Close llm_ch;
@@ -99,6 +122,7 @@ fork again
  while (llm_ch has items?) is (yes)
    :Receive GeneratedUser;
    :ProcessUser(user) → sqlite3_int64;
+    :PipelineLogger::Log(Info, UserGeneration,\n  city, user_id, "sqlite");
    :Append → user_pool_;
  endwhile (no)
 end fork
@@ -108,7 +132,6 @@ end fork

 ' ═══════════════════════════════════════════
 ' PHASE 1 — BREWERY & BEER GENERATION
-' Combined into a single dependent unit of work.
 ' ═══════════════════════════════════════════
 :RunBreweryAndBeerPhase(sampled_locations);
 :Create BoundedChannels\n(loc_ch, llm_ch, exp_ch);
@@ -122,6 +145,7 @@ fork again
  while (loc_ch has items?) is (yes)
    :Receive Location;
    :GetLocationContext(location,\nBreweryContextStrategy);
+    :PipelineLogger::Log(Info,\n  BreweryAndBeerGeneration,\n  city, nullopt, "enrichment");
    :Send EnrichedCity → llm_ch;
  endwhile (no)
  |Orchestrator|
@@ -145,12 +169,8 @@ fork again
      :Attach GeneratedBeer to Brewery bundle;
    endwhile (done)

+    :PipelineLogger::Log(Info,\n  BreweryAndBeerGeneration,\n  city, brewery_id, "llm");
    :Send BreweryWithBeers Bundle → exp_ch;
-    note right
-      The next generation of a brewery is
-      entirely dependent on the current
-      brewery and its beers completing.
-    end note
  endwhile (no)
  :Close exp_ch;
 fork again
@@ -165,6 +185,8 @@ fork again
      :ProcessBeer(beer) → sqlite3_int64;
      :Append → beer_pool_;
    endwhile (done)
+
+    :PipelineLogger::Log(Info,\n  BreweryAndBeerGeneration,\n  city, brewery_id, "sqlite");
  endwhile (no)
 end fork

@@ -177,16 +199,13 @@ end note

 ' ═══════════════════════════════════════════
 ' PHASE 2 — CHECKIN GENERATION
-' Sequential now that Breweries/Beers are done.
 ' ═══════════════════════════════════════════
 :RunCheckinPhase();
 :ICheckinDistributionStrategy::\nAssignActivityWeights(user_pool_);
 note right
-  Weights are seeded from each user's
-  persona.checkin_weight — high-activity
-  personas (craft enthusiasts) check in more,
-  casual personas less. J-curve profile
-  emerges from the persona distribution.
+  Weights seeded from each user's
+  persona.checkin_weight. J-curve profile
+  emerges from persona distribution.
 end note

 while (For each GeneratedUser in user_pool_?) is (remaining)
@@ -196,6 +215,7 @@ while (For each GeneratedUser in user_pool_?) is (remaining)
    :Select brewery from brewery_pool_;
    :GenerateCheckin(user, brewery, timestamp)\nvia DataGenerator;
    :ProcessCheckin(checkin) → sqlite3_int64;
+    :PipelineLogger::Log(Info, CheckinGeneration,\n  nullopt, checkin_id, "sqlite");
    :Append → checkin_pool_;
  endwhile (done)
 endwhile (done)
@@ -205,11 +225,9 @@ endwhile (done)
 ' ═══════════════════════════════════════════
 :RunRatingPhase();
 note right
-  Beer selection during rating is biased by
-  user.persona.style_affinities and abv_range —
-  users are more likely to rate beers matching
-  their persona profile. Rating skew (positive
-  with long tail) is also modulated per persona.
+  Beer selection biased by
+  user.persona.style_affinities and abv_range.
+  Rating skew modulated per persona.
 end note

 while (For each GeneratedCheckin in checkin_pool_?) is (remaining)
@@ -217,7 +235,9 @@ while (For each GeneratedCheckin in checkin_pool_?) is (remaining)
  if (Beer exists for brewery?) then (yes)
    :GenerateRating(user, beer, checkin_id)\nvia DataGenerator;
    :ProcessRating(rating);
+    :PipelineLogger::Log(Info, RatingGeneration,\n  nullopt, rating_id, "sqlite");
  else (no)
+    :PipelineLogger::Log(Warn, RatingGeneration,\n  nullopt, brewery_id, "sqlite");
    :Skip — brewery has no beers;
  endif
 endwhile (done)
@@ -230,6 +250,12 @@ endwhile (done)
 note right
  COMMIT covers all five fixture types.
 end note
+:Close log_ch;
+:Join Log Worker;
+note right
+  Drain guarantees no LogEntry is
+  dropped at shutdown.
+end note
 :spdlog::info "Pipeline complete in X ms";
 stop

--- a/pipeline/diagrams/future-class-diagram.puml
+++ b/pipeline/diagrams/future-class-diagram.puml
@@ -1,40 +1,52 @@
@startuml future_possible_architecture
-skinparam style strictuml
+
+' ==========================================
+' CONFIGURATION & STYLING
+' ==========================================
+left to right direction
+skinparam linetype ortho
+
+' --- Typography ---
 skinparam defaultFontName "DM Sans"
 skinparam defaultFontSize 14
 skinparam titleFontName "Volkhov"
 skinparam titleFontSize 20
-skinparam backgroundColor #FAFCF9
-skinparam defaultFontColor #28342A
-skinparam titleFontColor #28342A
-skinparam ArrowColor #628A5B
-skinparam linetype ortho
-skinparam class {
-  BackgroundColor #FAFCF9
-  HeaderBackgroundColor #EAF0E8
-  BorderColor #547461
-  ArrowColor #628A5B
-  FontColor #28342A
-}

-skinparam note {
-  BackgroundColor #EAF0E8
-  BorderColor #547461
-  FontColor #28342A
+' --- Global Colors ---
+skinparam backgroundColor #FCFCF7
+skinparam defaultFontColor #14180C
+skinparam titleFontColor #14180C
+skinparam ArrowColor #656F33
+
+skinparam class {
+  BackgroundColor #EBECE3
+  HeaderBackgroundColor #CBD2B5
+  BorderColor #4A5837
+  ArrowColor #656F33
+  FontColor #14180C
 }

 skinparam package {
-  BackgroundColor #F2F6F0
-  BorderColor #547461
-  FontColor #28342A
+  BackgroundColor #DBEEDD
+  BorderColor #4A5837
+  FontColor #14180C
 }

+skinparam note {
+  BackgroundColor #DBEEDD
+  BorderColor #4A5837
+  FontColor #14180C
+}
+
+skinparam monochrome reverse
+
 title The Biergarten Data Pipeline — Planned Architecture

-left to right direction
-
-
+' ==========================================
+' DOMAIN MODELS
+' ==========================================
 package "Domain Models" {
+
  class Location {
    + city : std::string
    + state_province : std::string
@@ -70,15 +82,6 @@ package "Domain Models" {
    + min_ibu : int
    + max_ibu : int
  }
-  note right of BeerStyle
-    Loaded once at startup from
-    beer-styles.json via JsonLoader.
-    Passed as std::span<const BeerStyle>
-    to IBeerSelectionStrategy.
-    Generator receives the selected
-    style as a parameter — it never
-    reads the palette directly.
-  end note

  class BreweryResult {
    + name_en : std::string
@@ -102,13 +105,6 @@ package "Domain Models" {
    + bio : std::string
    + activity_weight : float
  }
-  note right of UserResult
-    activity_weight assigned by
-    ICheckinDistributionStrategy
-    after the full user pool is
-    committed. Drives J-curve
-    checkin volume per user.
-  end note

  class CheckinResult {
    + checked_in_at : std::string
@@ -143,11 +139,6 @@ package "Domain Models" {
    + user : UserResult
    + generated_at : std::string
  }
-  note right of GeneratedUser
-    user_id populated after SQLite
-    insert. Live FK carried in pool
-    for checkin and rating references.
-  end note

  class GeneratedCheckin {
    + checkin_id : sqlite3_int64
@@ -172,38 +163,93 @@ package "Domain Models" {
    + n_ctx : uint32_t = 8192
    + seed : int = -1
  }
-  note right of SamplingOptions
-    Ignored when GeneratorOptions::
-    use_mocked = true.
-  end note

  class GeneratorOptions {
-    + model_path : std::string
+    + model_path : std::filesystem::path
    + use_mocked : bool = false
    + sampling : SamplingOptions
  }

  class PipelineOptions {
+    + output_path : std::filesystem::path
+    + log_path : std::filesystem::path
  }
-  note right of PipelineOptions
-    Reserved for future config:
-    n_locations, concurrency,
-    output_path, etc.
-  end note

  class ApplicationOptions {
    + generator : GeneratorOptions
    + pipeline : PipelineOptions
  }

+  ' --- Domain Model Relationships ---
  ApplicationOptions *-- GeneratorOptions
  ApplicationOptions *-- PipelineOptions
  GeneratorOptions   *-- SamplingOptions
+  LocationContext    *-- Completeness
 }

+
+' ==========================================
+' LOGGING
+' ==========================================
+package "Logging" {
+
+  enum LogLevel {
+    Debug
+    Info
+    Warn
+    Error
+  }
+
+  enum PipelinePhase {
+    Startup
+    UserGeneration
+    BreweryAndBeerGeneration
+    CheckinGeneration
+    RatingGeneration
+    Teardown
+  }
+
+  class LogEntry {
+    + timestamp : std::chrono::system_clock::time_point
+    + 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
+  }
+
+  class PipelineLogger {
+    - log_ch_ : BoundedChannel<LogEntry>&
+    + Log(level, phase, message,\n  city, entity_id, worker) : void
+  }
+
+  class LogWorker {
+    - log_ch_ : BoundedChannel<LogEntry>&
+    + Run() : void
+    - FormatTimestamp(tp) : std::string
+    - ToSpdlogLevel(level) : spdlog::level::level_enum
+    - ToString(phase) : std::string
+  }
+
+  ' --- Logging Relationships ---
+  LogEntry       *--  LogLevel
+  LogEntry       *--  PipelinePhase
+  PipelineLogger ..>  LogEntry       : emits
+  LogWorker      ..>  LogEntry       : consumes
+}
+
+
+' ==========================================
+' DOMAIN POLICY
+' ==========================================
 package "Domain Policy" {

-  interface IContextStrategy <<interface>> {
+  interface ContextStrategy <<interface>> {
    + QueriesFor(loc : const Location&) : std::vector<std::string>
    + MaxContextChars() : size_t
  }
@@ -218,7 +264,7 @@ package "Domain Policy" {
    + MaxContextChars() : size_t
  }

-  interface ISamplingStrategy <<interface>> {
+  interface SamplingStrategy <<interface>> {
    + Sample(locations : const std::vector<Location>&) : std::vector<Location>
  }

@@ -227,16 +273,9 @@ package "Domain Policy" {
    + Sample(locations : const std::vector<Location>&) : std::vector<Location>
  }

-  interface IBeerSelectionStrategy <<interface>> {
+  interface BeerSelectionStrategy <<interface>> {
    + SelectStyles(brewery : const GeneratedBrewery&,\n  palette : std::span<const BeerStyle>) : std::vector<BeerStyle>
  }
-  note right of IBeerSelectionStrategy
-    Decides how many beers a brewery
-    gets and which styles are selected.
-    Count distribution and style
-    deduplication logic live here,
-    not in the orchestrator or generator.
-  end note

  class RandomBeerSelectionStrategy {
    - rng_ : std::mt19937
@@ -244,24 +283,12 @@ package "Domain Policy" {
    - max_beers_ : size_t
    + SelectStyles(brewery : const GeneratedBrewery&,\n  palette : std::span<const BeerStyle>) : std::vector<BeerStyle>
  }
-  note right of RandomBeerSelectionStrategy
-    Draws a random count in [min, max].
-    Samples without replacement from
-    palette to avoid duplicate styles
-    per brewery.
-  end note

-  interface ICheckinDistributionStrategy <<interface>> {
+  interface CheckinDistributionStrategy <<interface>> {
    + AssignActivityWeights(users : std::vector<GeneratedUser>&) : void
    + CheckinsForUser(user : const GeneratedUser&,\n  brewery_count : size_t) : size_t
    + TimestampFor(user : const GeneratedUser&,\n  index : size_t) : std::string
  }
-  note right of ICheckinDistributionStrategy
-    Owns all statistical policy:
-    J-curve weight assignment,
-    bursty weekend timestamps,
-    per-user checkin volume.
-  end note

  class JCurveCheckinStrategy {
    - rng_ : std::mt19937
@@ -273,17 +300,28 @@ package "Domain Policy" {
 }


-
+' ==========================================
+' ORCHESTRATION
+' ==========================================
 package "Orchestration" {

+  interface DataPreloader <<interface>> {
+    + LoadLocations(filepath : const std::filesystem::path&) : std::vector<Location>
+    + LoadBeerStyles(filepath : const std::filesystem::path&) : std::vector<BeerStyle>
+    + LoadPersonas(filepath : const std::filesystem::path&) : std::vector<Persona>
+    + LoadNamesByCountry(filepath : const std::filesystem::path&) : NamesByCountry
+  }
+
  class BiergartenPipelineOrchestrator {
-    - enrichment_service_ : std::unique_ptr<IEnrichmentService>
+    - preloader_ : std::unique_ptr<DataPreloader>
+    - enrichment_service_ : std::unique_ptr<EnrichmentService>
    - generator_ : std::unique_ptr<DataGenerator>
-    - exporter_ : std::unique_ptr<IExportService>
-    - brewery_context_strategy_ : std::unique_ptr<IContextStrategy>
-    - sampling_strategy_ : std::unique_ptr<ISamplingStrategy>
-    - beer_selection_strategy_ : std::unique_ptr<IBeerSelectionStrategy>
-    - checkin_strategy_ : std::unique_ptr<ICheckinDistributionStrategy>
+    - logger_ : std::unique_ptr<Logger>
+    - exporter_ : std::unique_ptr<ExportService>
+    - brewery_context_strategy_ : std::unique_ptr<ContextStrategy>
+    - sampling_strategy_ : std::unique_ptr<SamplingStrategy>
+    - beer_selection_strategy_ : std::unique_ptr<BeerSelectionStrategy>
+    - checkin_strategy_ : std::unique_ptr<CheckinDistributionStrategy>
    - beer_style_palette_ : std::vector<BeerStyle>
    - options_ : ApplicationOptions
    --
@@ -298,33 +336,39 @@ package "Orchestration" {
    - RunCheckinPhase() : void
    - RunRatingPhase() : void
  }
+}
+
+
+' ==========================================
+' INFRASTRUCTURE: PRELOADING
+' ==========================================
+package "Infrastructure: Preloading" {

  class JsonLoader {
-    + {static} LoadLocations(filepath : const std::filesystem::path&) : std::vector<Location>
-    + {static} LoadBeerStyles(filepath : const std::filesystem::path&) : std::vector<BeerStyle>
-    + {static} LoadPersonas(filepath : const std::filesystem::path&) : std::vector<Persona>
-    + {static} LoadNamesByCountry(filepath : const std::filesystem::path&) : NamesByCountry
-  }
+    + LoadLocations(filepath : const std::filesystem::path&) : std::vector<Location>
+    + LoadBeerStyles(filepath : const std::filesystem::path&) : std::vector<BeerStyle>
+    + LoadPersonas(filepath : const std::filesystem::path&) : std::vector<Persona>
+    + LoadNamesByCountry(filepath : const std::filesystem::path&) : NamesByCountry
  }

+}
+
+
+' ==========================================
+' INFRASTRUCTURE: ENRICHMENT
+' ==========================================
 package "Infrastructure: Enrichment" {

-  interface IEnrichmentService <<interface>> {
-    + GetLocationContext(loc : const Location&,\n  strategy : const IContextStrategy&) : LocationContext
+  interface EnrichmentService <<interface>> {
+    + GetLocationContext(loc : const Location&,\n  strategy : const ContextStrategy&) : LocationContext
  }

  class WikipediaService {
    - client_ : std::unique_ptr<WebClient>
    - extract_cache_ : std::unordered_map<std::string, std::string>
-    + GetLocationContext(loc : const Location&,\n  strategy : const IContextStrategy&) : LocationContext
+    + GetLocationContext(loc : const Location&,\n  strategy : const ContextStrategy&) : LocationContext
    - FetchExtract(query : std::string_view) : std::string
  }
-  note right of WikipediaService
-    extract_cache_ keyed by query string.
-    Beer pass gets near-100% cache hits
-    since locations were already fetched
-    during the brewery pass.
-  end note

  interface WebClient <<interface>> {
    + Get(url : const std::string&) : std::string
@@ -338,6 +382,10 @@ package "Infrastructure: Enrichment" {

 }

+
+' ==========================================
+' INFRASTRUCTURE: GENERATION
+' ==========================================
 package "Infrastructure: Generation" {

  interface DataGenerator <<interface>> {
@@ -347,12 +395,6 @@ package "Infrastructure: Generation" {
    + GenerateCheckin(user : const GeneratedUser&,\n  brewery : const GeneratedBrewery&,\n  timestamp : const std::string&) : CheckinResult
    + GenerateRating(user : const GeneratedUser&,\n  beer : const GeneratedBeer&,\n  checkin_id : sqlite3_int64) : RatingResult
  }
-  note right of DataGenerator
-    GenerateBeer receives BeerStyle
-    as a parameter. Style selection
-    and count decisions live in
-    IBeerSelectionStrategy, not here.
-  end note

  class MockGenerator {
    + GenerateBrewery(...) : BreweryResult
@@ -366,7 +408,7 @@ package "Infrastructure: Generation" {
  class LlamaGenerator {
    - model_ : ModelHandle
    - context_ : ContextHandle
-    - prompt_formatter_ : std::unique_ptr<IPromptFormatter>
+    - prompt_formatter_ : std::unique_ptr<PromptFormatter>
    - rng_ : std::mt19937
    + GenerateBrewery(...) : BreweryResult
    + GenerateBeer(...) : BeerResult
@@ -377,15 +419,8 @@ package "Infrastructure: Generation" {
    - Infer(system_prompt, user_prompt,\n  max_tokens, grammar) : std::string
    - ValidateModelArchitecture() : void
  }
-  note right of LlamaGenerator
-    Constructed from GeneratorOptions.
-    SamplingOptions fields are applied
-    during Load(). LlamaConfig removed —
-    GeneratorOptions is the sole
-    configuration surface.
-  end note

-  interface IPromptFormatter <<interface>> {
+  interface PromptFormatter <<interface>> {
    + Format(system_prompt : std::string_view,\n  user_prompt : std::string_view) : std::string
    + ExpectedArchitecture() : std::string_view
  }
@@ -397,6 +432,10 @@ package "Infrastructure: Generation" {

 }

+
+' ==========================================
+' INFRASTRUCTURE: PIPELINE CHANNEL
+' ==========================================
 package "Infrastructure: Pipeline Channel" {

  class "BoundedChannel<T>" as BoundedChannel {
@@ -410,19 +449,16 @@ package "Infrastructure: Pipeline Channel" {
    + Receive() : std::optional<T>
    + Close() : void
  }
-  note right of BoundedChannel
-    Back-pressure via capacity_ bound.
-    Stalls fast producers (enrichment ×N)
-    when the LLM worker cannot keep up.
-    Close() is the termination signal —
-    workers drain remaining items then exit.
-  end note

 }

+
+' ==========================================
+' INFRASTRUCTURE: EXPORT
+' ==========================================
 package "Infrastructure: Export" {

-  interface IExportService <<interface>> {
+  interface ExportService <<interface>> {
    + Initialize() : void
    + ProcessBrewery(brewery : const GeneratedBrewery&) : sqlite3_int64
    + ProcessBeer(beer : const GeneratedBeer&) : sqlite3_int64
@@ -433,7 +469,7 @@ package "Infrastructure: Export" {
  }

  class SqliteExportService {
-    - date_time_provider_ : std::unique_ptr<IDateTimeProvider>
+    - date_time_provider_ : std::unique_ptr<DateTimeProvider>
    - db_handle_ : SqliteDatabaseHandle
    - insert_location_stmt_ : SqliteStatementHandle
    - insert_brewery_stmt_ : SqliteStatementHandle
@@ -456,15 +492,8 @@ package "Infrastructure: Export" {
    - RollbackAndCloseNoThrow() : void
    - FinalizeStatements() : void
  }
-  note right of SqliteExportService
-    Single writer — no lock contention.
-    location_cache_ deduplicates city rows.
-    brewery_cache_ resolves beer FK without
-    re-querying. Single long-running
-    transaction committed in Finalize().
-  end note

-  interface IDateTimeProvider <<interface>> {
+  interface DateTimeProvider <<interface>> {
    + GetUtcTimestamp() : std::string
  }

@@ -475,43 +504,55 @@ package "Infrastructure: Export" {
 }


+' ==========================================
+' GLOBAL RELATIONSHIPS
+' ==========================================

-' Orchestration
-BiergartenPipelineOrchestrator *-- IEnrichmentService
+' --- Orchestration Aggregations (Services & Strategies) ---
+BiergartenPipelineOrchestrator *--  DataPreloader
+BiergartenPipelineOrchestrator *--  EnrichmentService
 BiergartenPipelineOrchestrator *--  DataGenerator
-BiergartenPipelineOrchestrator *-- IExportService
-BiergartenPipelineOrchestrator *-- ICheckinDistributionStrategy
-BiergartenPipelineOrchestrator *-- ISamplingStrategy
-BiergartenPipelineOrchestrator *-- IBeerSelectionStrategy
+BiergartenPipelineOrchestrator *--  ExportService
+BiergartenPipelineOrchestrator *--  CheckinDistributionStrategy
+BiergartenPipelineOrchestrator *--  SamplingStrategy
+BiergartenPipelineOrchestrator *--  BeerSelectionStrategy
 BiergartenPipelineOrchestrator *--  ApplicationOptions
-BiergartenPipelineOrchestrator ..> JsonLoader
+BiergartenPipelineOrchestrator *--  Logger

-' Policy implementations
-IContextStrategy <|.. BreweryContextStrategy
-IContextStrategy <|.. BeerContextStrategy
-ISamplingStrategy <|.. UniformSamplingStrategy
-IBeerSelectionStrategy <|.. RandomBeerSelectionStrategy
-ICheckinDistributionStrategy <|.. JCurveCheckinStrategy
+' --- Orchestration Aggregations (Data Pools) ---
+BiergartenPipelineOrchestrator *-- "0..*" GeneratedUser    : user_pool_
+BiergartenPipelineOrchestrator *-- "0..*" GeneratedBrewery : brewery_pool_
+BiergartenPipelineOrchestrator *-- "0..*" GeneratedBeer    : beer_pool_
+BiergartenPipelineOrchestrator *-- "0..*" GeneratedCheckin : checkin_pool_

-' Enrichment
-IEnrichmentService <|.. WikipediaService
-WikipediaService *-- WebClient
-WikipediaService ..> IContextStrategy
+' --- Interfaces & Implementations ---
+DataPreloader                  <|.. JsonLoader
+Logger                         <|.. PipelineLogger
+ContextStrategy                <|.. BreweryContextStrategy
+ContextStrategy                <|.. BeerContextStrategy
+SamplingStrategy               <|.. UniformSamplingStrategy
+BeerSelectionStrategy          <|.. RandomBeerSelectionStrategy
+CheckinDistributionStrategy    <|.. JCurveCheckinStrategy
+EnrichmentService              <|.. WikipediaService
 WebClient                      <|.. CURLWebClient
-
-' Generation
 DataGenerator                  <|.. MockGenerator
 DataGenerator                  <|.. LlamaGenerator
-LlamaGenerator *-- IPromptFormatter
+PromptFormatter                <|.. Gemma4JinjaPromptFormatter
+ExportService                  <|.. SqliteExportService
+DateTimeProvider               <|.. SystemDateTimeProvider
+
+' --- Service Compositions & Dependencies ---
+WikipediaService               *--  WebClient
+WikipediaService               ..>  ContextStrategy
+LlamaGenerator                 *--  PromptFormatter
 LlamaGenerator                 ..>  GeneratorOptions
-IPromptFormatter <|.. Gemma4JinjaPromptFormatter
+SqliteExportService            *--  DateTimeProvider

-' Export
-IExportService <|.. SqliteExportService
-SqliteExportService *-- IDateTimeProvider
-IDateTimeProvider <|.. SystemDateTimeProvider
+' --- Cross-Component Aggregations (Held References) ---
+PipelineLogger                 o--  BoundedChannel : logs to
+LogWorker                      o--  BoundedChannel : drains from

-' Domain containment
+' --- Domain Containment ---
 EnrichedCity                   *--  Location
 EnrichedCity                   *--  LocationContext
 GeneratedBrewery               *--  Location