add future plans

pipeline/diagrams/future-possible-architecture.puml

@@ -0,0 +1,501 @@
+@startuml
+skinparam style strictuml
+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 class {
+  BackgroundColor #FAFCF9
+  HeaderBackgroundColor #EAF0E8
+  BorderColor #547461
+  ArrowColor #628A5B
+  FontColor #28342A
+}
+
+skinparam note {
+  BackgroundColor #EAF0E8
+  BorderColor #547461
+  FontColor #28342A
+}
+
+skinparam package {
+  BackgroundColor #F2F6F0
+  BorderColor #547461
+  FontColor #28342A
+}
+
+title The Biergarten Data Pipeline — Architecture v4 (Unified Orchestrator)
+
+' ─────────────────────────────────────────────
+' DOMAIN: VALUE OBJECTS
+' ─────────────────────────────────────────────
+package "Domain: Value Objects & Contracts" {
+
+  class Location {
+    + city : std::string
+    + state_province : std::string
+    + iso3166_2 : std::string
+    + country : std::string
+    + iso3166_1 : std::string
+    + local_languages : std::vector<std::string>
+    + latitude : double
+    + longitude : double
+  }
+
+  class LocationContext {
+    + text : std::string
+    + completeness : Completeness
+    + char_count : size_t
+    --
+    <<enum>> Completeness
+    Full
+    Partial
+    Absent
+  }
+
+  class EnrichedCity {
+    + location : Location
+    + context : LocationContext
+  }
+
+  class BreweryResult {
+    + name_en : std::string
+    + description_en : std::string
+    + name_local : std::string
+    + description_local : std::string
+  }
+
+  class BeerResult {
+    + name_en : std::string
+    + description_en : std::string
+    + name_local : std::string
+    + description_local : std::string
+    + style : std::string
+    + abv : float
+    + ibu : int
+  }
+
+  class UserResult {
+    + username : std::string
+    + 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
+    + note : std::string
+  }
+
+  class RatingResult {
+    + score : float
+    + note : std::string
+  }
+
+  class GeneratedBrewery {
+    + brewery_id : sqlite3_int64
+    + location : Location
+    + brewery : BreweryResult
+    + context_completeness : LocationContext::Completeness
+    + generated_at : std::string
+  }
+
+  class GeneratedBeer {
+    + beer_id : sqlite3_int64
+    + brewery_id : sqlite3_int64
+    + location : Location
+    + beer : BeerResult
+    + generated_at : std::string
+  }
+
+  class GeneratedUser {
+    + user_id : sqlite3_int64
+    + location : Location
+    + user : UserResult
+    + generated_at : std::string
+  }
+
+  class GeneratedCheckin {
+    + checkin_id : sqlite3_int64
+    + user_id : sqlite3_int64
+    + brewery_id : sqlite3_int64
+    + checkin : CheckinResult
+    + generated_at : std::string
+  }
+
+  class GeneratedRating {
+    + user_id : sqlite3_int64
+    + beer_id : sqlite3_int64
+    + checkin_id : sqlite3_int64
+    + rating : RatingResult
+    + generated_at : std::string
+  }
+
+}
+
+' ─────────────────────────────────────────────
+' DOMAIN POLICY
+' ─────────────────────────────────────────────
+package "Domain Policy" {
+
+  interface IContextStrategy <<interface>> {
+    + QueriesFor(loc : const Location&) : std::vector<std::string>
+    + MaxContextChars() : size_t
+  }
+
+  class BreweryContextStrategy {
+    + QueriesFor(loc : const Location&) : std::vector<std::string>
+    + MaxContextChars() : size_t
+  }
+
+  class BeerContextStrategy {
+    + QueriesFor(loc : const Location&) : std::vector<std::string>
+    + MaxContextChars() : size_t
+  }
+
+  interface ISamplingStrategy <<interface>> {
+    + Sample(locations : const std::vector<Location>&) : std::vector<Location>
+  }
+
+  class UniformSamplingStrategy {
+    - sample_size_ : size_t
+    + Sample(locations : const std::vector<Location>&) : std::vector<Location>
+  }
+
+  interface ICheckinDistributionStrategy <<interface>> {
+    + AssignActivityWeights(users : std::vector<GeneratedUser>&) : void
+    + CheckinsForUser(user : const GeneratedUser&, brewery_count : size_t) : size_t
+    + TimestampFor(user : const GeneratedUser&, index : size_t) : std::string
+  }
+  note right of ICheckinDistributionStrategy
+    Injected into the orchestrator.
+    Owns all statistical policy:
+    J-curve weight assignment,
+    bursty weekend timestamps,
+    per-user checkin volume.
+    No mediator required to hold this —
+    the orchestrator calls it directly
+    before the checkin phase opens.
+  end note
+
+  class JCurveCheckinStrategy {
+    - rng_ : std::mt19937
+    + AssignActivityWeights(users : std::vector<GeneratedUser>&) : void
+    + CheckinsForUser(user : const GeneratedUser&, brewery_count : size_t) : size_t
+    + TimestampFor(user : const GeneratedUser&, index : size_t) : std::string
+  }
+
+}
+
+' ─────────────────────────────────────────────
+' INFRASTRUCTURE: ENRICHMENT
+' ─────────────────────────────────────────────
+package "Infrastructure: Enrichment" {
+
+  interface IEnrichmentService <<interface>> {
+    + GetLocationContext(loc : const Location&, strategy : const IContextStrategy&) : LocationContext
+  }
+
+  class WikipediaService {
+    - client_ : std::unique_ptr<WebClient>
+    - extract_cache_ : std::unordered_map<std::string, std::string>
+    + GetLocationContext(loc : const Location&, strategy : const IContextStrategy&) : LocationContext
+    - FetchExtract(query : std::string_view) : std::string
+  }
+
+  interface WebClient <<interface>> {
+    + Get(url : const std::string&) : std::string
+    + UrlEncode(value : const std::string&) : std::string
+  }
+
+  class CURLWebClient {
+    + Get(url : const std::string&) : std::string
+    + UrlEncode(value : const std::string&) : std::string
+  }
+
+}
+
+' ─────────────────────────────────────────────
+' INFRASTRUCTURE: GENERATION
+' ─────────────────────────────────────────────
+package "Infrastructure: Generation" {
+
+  interface DataGenerator <<interface>> {
+    + GenerateBrewery(location : const Location&, context : const LocationContext&) : BreweryResult
+    + GenerateBeer(brewery_id : sqlite3_int64, location : const Location&, context : const LocationContext&) : BeerResult
+    + GenerateUser(location : const Location&) : UserResult
+    + GenerateCheckin(user : const GeneratedUser&, brewery : const GeneratedBrewery&, timestamp : const std::string&) : CheckinResult
+    + GenerateRating(user : const GeneratedUser&, beer : const GeneratedBeer&, checkin_id : sqlite3_int64) : RatingResult
+  }
+
+  class MockGenerator {
+    + GenerateBrewery(...) : BreweryResult
+    + GenerateBeer(...) : BeerResult
+    + GenerateUser(...) : UserResult
+    + GenerateCheckin(...) : CheckinResult
+    + GenerateRating(...) : RatingResult
+    - DeterministicHash(location : const Location&) : size_t
+  }
+
+  class LlamaGenerator {
+    - model_ : ModelHandle
+    - context_ : ContextHandle
+    - prompt_formatter_ : std::unique_ptr<IPromptFormatter>
+    - config_ : LlamaConfig
+    - rng_ : std::mt19937
+    + GenerateBrewery(...) : BreweryResult
+    + GenerateBeer(...) : BeerResult
+    + GenerateUser(...) : UserResult
+    + GenerateCheckin(...) : CheckinResult
+    + GenerateRating(...) : RatingResult
+    - Load(config : const LlamaConfig&) : void
+    - Infer(system_prompt, user_prompt, max_tokens, grammar) : std::string
+    - ValidateModelArchitecture() : void
+  }
+
+  class RestGenerator {
+    - config_ : RestConfig
+    + GenerateBrewery(...) : BreweryResult
+    + GenerateBeer(...) : BeerResult
+    + GenerateUser(...) : UserResult
+    + GenerateCheckin(...) : CheckinResult
+    + GenerateRating(...) : RatingResult
+  }
+  note right of RestGenerator
+    Future REST-backed implementation.
+    Slots in at the DI root with zero
+    changes to orchestration logic.
+  end note
+
+  interface IPromptFormatter <<interface>> {
+    + Format(system_prompt : std::string_view, user_prompt : std::string_view) : std::string
+    + ExpectedArchitecture() : std::string_view
+  }
+
+  class Gemma4JinjaPromptFormatter {
+    + Format(...) : std::string
+    + ExpectedArchitecture() : std::string_view
+  }
+
+  class LlamaConfig {
+    + model_path : std::string
+    + temperature : float
+    + top_p : float
+    + top_k : uint32_t
+    + n_ctx : uint32_t
+    + seed : int
+  }
+
+  class RestConfig {
+    + endpoint : std::string
+    + api_key : std::string
+    + timeout : std::chrono::milliseconds
+  }
+
+}
+
+' ─────────────────────────────────────────────
+' INFRASTRUCTURE: PIPELINE CHANNEL
+' ─────────────────────────────────────────────
+package "Infrastructure: Pipeline Channel" {
+
+  class "BoundedChannel<T>" as BoundedChannel {
+    - queue_ : std::queue<T>
+    - mutex_ : std::mutex
+    - not_full_ : std::condition_variable
+    - not_empty_ : std::condition_variable
+    - capacity_ : size_t
+    - closed_ : bool
+    + Send(item : T) : void
+    + Receive() : std::optional<T>
+    + Close() : void
+  }
+  note right of BoundedChannel
+    Used within each phase to
+    decouple production from export.
+    Phase boundaries are explicit
+    sequential barriers in the
+    orchestrator's Run() method —
+    not channel-mediated.
+  end note
+
+}
+
+' ─────────────────────────────────────────────
+' INFRASTRUCTURE: EXPORT
+' ─────────────────────────────────────────────
+package "Infrastructure: Export" {
+
+  interface IExportService <<interface>> {
+    + Initialize() : void
+    + ProcessBrewery(brewery : const GeneratedBrewery&) : sqlite3_int64
+    + ProcessBeer(beer : const GeneratedBeer&) : sqlite3_int64
+    + ProcessUser(user : const GeneratedUser&) : sqlite3_int64
+    + ProcessCheckin(checkin : const GeneratedCheckin&) : sqlite3_int64
+    + ProcessRating(rating : const GeneratedRating&) : void
+    + Finalize() : void
+  }
+  note right of IExportService
+    Process* methods return
+    sqlite3_int64 row IDs.
+    Orchestrator uses these to
+    populate FK fields on all
+    downstream fixture types.
+  end note
+
+  class SqliteExportService {
+    - date_time_provider_ : std::unique_ptr<IDateTimeProvider>
+    - db_handle_ : SqliteDatabaseHandle
+    - insert_location_stmt_ : SqliteStatementHandle
+    - insert_brewery_stmt_ : SqliteStatementHandle
+    - insert_beer_stmt_ : SqliteStatementHandle
+    - insert_user_stmt_ : SqliteStatementHandle
+    - insert_checkin_stmt_ : SqliteStatementHandle
+    - insert_rating_stmt_ : SqliteStatementHandle
+    - transaction_open_ : bool
+    - location_cache_ : std::unordered_map<std::string, sqlite3_int64>
+    + Initialize() : void
+    + ProcessBrewery(brewery : const GeneratedBrewery&) : sqlite3_int64
+    + ProcessBeer(beer : const GeneratedBeer&) : sqlite3_int64
+    + ProcessUser(user : const GeneratedUser&) : sqlite3_int64
+    + ProcessCheckin(checkin : const GeneratedCheckin&) : sqlite3_int64
+    + ProcessRating(rating : const GeneratedRating&) : void
+    + Finalize() : void
+    - InitializeSchema() : void
+    - PrepareStatements() : void
+    - RollbackAndCloseNoThrow() : void
+    - FinalizeStatements() : void
+  }
+  note right of SqliteExportService
+    brewery_cache_ removed — row IDs
+    are now carried on GeneratedBrewery
+    and GeneratedBeer value objects
+    and threaded through by the
+    orchestrator directly.
+  end note
+
+  interface IDateTimeProvider <<interface>> {
+    + GetUtcTimestamp() : std::string
+  }
+
+  class SystemDateTimeProvider {
+    + GetUtcTimestamp() : std::string
+  }
+
+}
+
+' ─────────────────────────────────────────────
+' ORCHESTRATION
+' ─────────────────────────────────────────────
+package "Orchestration" {
+
+  class BiergartenPipelineOrchestrator {
+    - enrichment_service_ : std::unique_ptr<IEnrichmentService>
+    - generator_ : std::unique_ptr<DataGenerator>
+    - exporter_ : std::unique_ptr<IExportService>
+    - brewery_context_strategy_ : std::unique_ptr<IContextStrategy>
+    - beer_context_strategy_ : std::unique_ptr<IContextStrategy>
+    - sampling_strategy_ : std::unique_ptr<ISamplingStrategy>
+    - checkin_strategy_ : std::unique_ptr<ICheckinDistributionStrategy>
+    --
+    - user_pool_ : std::vector<GeneratedUser>
+    - brewery_pool_ : std::vector<GeneratedBrewery>
+    - beer_pool_ : std::vector<GeneratedBeer>
+    - checkin_pool_ : std::vector<GeneratedCheckin>
+    --
+    + Run() : bool
+    - RunUserPhase(locations : const std::vector<Location>&) : void
+    - RunBreweryPhase(locations : const std::vector<Location>&) : void
+    - RunBeerPhase() : void
+    - RunCheckinPhase() : void
+    - RunRatingPhase() : void
+  }
+  note right of BiergartenPipelineOrchestrator
+    Single component owns all
+    sequencing. Run() reads as a
+    linear narrative:
+      1. RunUserPhase
+      2. RunBreweryPhase
+      3. RunBeerPhase
+      4. checkin_strategy_->AssignActivityWeights
+      5. RunCheckinPhase
+      6. RunRatingPhase
+    The checkin gate is an explicit
+    sequential barrier between steps
+    3 and 5 — not a hidden internal
+    trigger in a separate object.
+    Pools are members: each phase
+    appends to them and the next
+    phase reads from them directly.
+    No mediator. No shared_ptr.
+    Ownership is unambiguous.
+  end note
+
+  class JsonLoader {
+    + {static} LoadLocations(filepath : const std::filesystem::path&) : std::vector<Location>
+  }
+
+}
+
+' ─────────────────────────────────────────────
+' RELATIONSHIPS
+' ─────────────────────────────────────────────
+
+' Orchestration
+BiergartenPipelineOrchestrator *-- IEnrichmentService : owns
+BiergartenPipelineOrchestrator *-- DataGenerator : owns
+BiergartenPipelineOrchestrator *-- IExportService : owns
+BiergartenPipelineOrchestrator *-- ICheckinDistributionStrategy : owns
+BiergartenPipelineOrchestrator *-- ISamplingStrategy : owns
+BiergartenPipelineOrchestrator ..> JsonLoader : uses
+
+' Policy implementations
+IContextStrategy <|.. BreweryContextStrategy : implements
+IContextStrategy <|.. BeerContextStrategy : implements
+ISamplingStrategy <|.. UniformSamplingStrategy : implements
+ICheckinDistributionStrategy <|.. JCurveCheckinStrategy : implements
+
+' Enrichment
+IEnrichmentService <|.. WikipediaService : implements
+WikipediaService *-- WebClient : owns
+WikipediaService ..> IContextStrategy : uses (parameter)
+WebClient <|.. CURLWebClient : implements
+
+' Generation
+DataGenerator <|.. MockGenerator : implements
+DataGenerator <|.. LlamaGenerator : implements
+DataGenerator <|.. RestGenerator : implements
+LlamaGenerator *-- IPromptFormatter : owns
+LlamaGenerator ..> LlamaConfig : constructed with
+RestGenerator ..> RestConfig : constructed with
+IPromptFormatter <|.. Gemma4JinjaPromptFormatter : implements
+
+' Export
+IExportService <|.. SqliteExportService : implements
+SqliteExportService *-- IDateTimeProvider : owns
+IDateTimeProvider <|.. SystemDateTimeProvider : implements
+
+' Data flow
+EnrichedCity *-- Location : contains
+EnrichedCity *-- LocationContext : contains
+GeneratedBrewery *-- Location : contains
+GeneratedBrewery *-- BreweryResult : contains
+GeneratedBeer *-- Location : contains
+GeneratedBeer *-- BeerResult : contains
+GeneratedUser *-- Location : contains
+GeneratedUser *-- UserResult : contains
+GeneratedCheckin *-- CheckinResult : contains
+GeneratedRating *-- RatingResult : contains
+
+@enduml