extract mermaid docs

docs/diagrams/pipeline/current/activity.mmd

@@ -0,0 +1,74 @@
+flowchart TD
+    Start([start]) --> ParseArgs["main.cc: ParseArguments(argc, argv)"]
+    ParseArgs --> ArgsValid{Arguments valid?}
+    ArgsValid -- no --> LogErr[Log error / usage info] --> Stop1([stop])
+    ArgsValid -- yes --> Init["main.cc: Init OpenSSL global state and LlamaBackendState"]
+    Init --> DI["main.cc: di::make_injector(...)<br/>binds ILogger, IEnrichmentService, DataGenerator, IExportService, IPromptFormatter, WebClient based on --mocked vs. model-backed mode"]
+    DI --> LogThread["main.cc: create BoundedChannel log_channel, spawn log dispatcher thread (LogDispatcher::Run)"]
+    LogThread --> CreateOrch["main.cc: injector.create BiergartenPipelineOrchestrator"]
+    CreateOrch --> Run["BiergartenPipelineOrchestrator::Run()"]
+
+    Run --> SqliteInit["SqliteExportService.Initialize()<br/>builds biergarten_seed_&lt;UTC datetime&gt;.sqlite (numeric suffix if it exists), opens DB connection, executes schema DDL, begins transaction"]
+    SqliteInit --> QueryLoc[Orchestrator: QueryLocations]
+    QueryLoc --> LoadLoc["JsonLoader.LoadLocations(locations.json)"]
+    LoadLoc --> SampleLoc["std::ranges::sample(all_locations, --location-count) — defaults to 10"]
+
+    SampleLoc --> EnrichLoop{For each sampled Location}
+    EnrichLoop --> GetContext["IEnrichmentService.GetLocationContext(loc)<br/>WikipediaEnrichmentService fetches a generic 'brewing' extract and a 'beer in {country}' extract (not city/region-specific); MockEnrichmentService (--mocked) returns an empty string"]
+    GetContext --> LookupFailed{Lookup failed?}
+    LookupFailed -- yes --> SkipCity1[Log warning, skip city] --> EnrichLoop
+    LookupFailed -- no --> StoreEnriched["Store EnrichedCity{Location, region_context}"] --> EnrichLoop
+    EnrichLoop -- done --> GenUsers[Orchestrator: GenerateUsers enriched_cities]
+
+    GenUsers --> LoadUserData["JsonLoader: LoadPersonas / LoadForenamesByCountry / LoadSurnamesByCountry<br/>each memoized after first parse; MockCuratedDataService (--mocked) returns a fixed in-memory dataset instead, skipping these JSON files"]
+
+    LoadUserData --> UserLoop{For each EnrichedCity}
+    UserLoop --> SampleName["SampleName(forenames_by_country, surnames_by_country, location.iso3166_1)"]
+    SampleName --> NamesAvail{Names available for country?}
+    NamesAvail -- no --> SkipCity2[Log warning, skip city] --> UserLoop
+    NamesAvail -- yes --> SamplePersona["Sample UserPersona (uniform random)"]
+    SamplePersona --> UserGenMode{Generator mode}
+
+    UserGenMode -- MockGenerator --> UserMockGen[DeterministicHash and Format]
+    UserGenMode -- LlamaGenerator --> UserLlamaLoad["prompt_directory_.Load(USER_GENERATION) → USER_GENERATION.md in --prompt-dir"]
+    UserLlamaLoad --> UserLlamaRetry["Infer(...) with kUserJsonGrammar → ValidateUserJson<br/>retry up to 3 attempts, appending validation error to the retry prompt on failure"]
+    UserGenMode -- OpenAIGenerator --> UserOAILoad["prompt_directory_.Load(USER_GENERATION) — same prompt file as LlamaGenerator, content is backend-agnostic"]
+    UserOAILoad --> UserOAIRetry["CallChatCompletionsApi(...) with kUserJsonSchema → ValidateUserJson<br/>retry up to 2 attempts — Structured Outputs (json_schema, strict) already guarantees schema shape, so retries only cover transient failures / placeholder text"]
+
+    UserMockGen --> UserGenDone{Generation successful?}
+    UserLlamaRetry --> UserGenDone
+    UserOAIRetry --> UserGenDone
+
+    UserGenDone -- yes --> UserPostProc["GetRandomCoordsWithinRange (5km jitter), BuildEmail, GenerateDateOfBirth<br/>email and date_of_birth are generated programmatically, never LLM-authored; generation + coordinate jitter run inside one try/catch per record"]
+    UserGenDone -- no --> UserGenFail["Log warning: generation failed, skipping"] --> UserLoop
+
+    UserPostProc --> UserExport["SqliteExportService.ProcessRecord(UserRecord)<br/>reuse cached location_id or insert Location and cache its id; insert User (FK location_id)"]
+    UserExport --> UserExportFail{Exception during insert?}
+    UserExportFail -- yes --> UserExportWarn["Log warning: SQLite export failed"] --> UserLoop
+    UserExportFail -- no --> UserLoop
+    UserLoop -- done --> GenBrew[Orchestrator: GenerateBreweries enriched_cities]
+
+    GenBrew --> BrewLoop{For each EnrichedCity}
+    BrewLoop --> BrewGenMode{Generator mode}
+
+    BrewGenMode -- MockGenerator --> BrewMockGen[DeterministicHash and Format]
+    BrewGenMode -- LlamaGenerator --> BrewLlamaLoad["PrepareRegionContext, prompt_directory_.Load(BREWERY_GENERATION) → BREWERY_GENERATION.md"]
+    BrewLlamaLoad --> BrewLlamaRetry["Infer(...) with kBreweryJsonGrammar → ValidateBreweryJson<br/>retry up to 3 attempts; max_tokens is fixed across retries, not raised on truncation"]
+    BrewGenMode -- OpenAIGenerator --> BrewOAILoad["PrepareRegionContext, prompt_directory_.Load(BREWERY_GENERATION) — same prompt file as LlamaGenerator"]
+    BrewOAILoad --> BrewOAIRetry["CallChatCompletionsApi(...) with kBreweryJsonSchema → ValidateBreweryJson<br/>retry up to 2 attempts — Structured Outputs already guarantees schema shape"]
+
+    BrewMockGen --> BrewGenDone{Generation successful?}
+    BrewLlamaRetry --> BrewGenDone
+    BrewOAIRetry --> BrewGenDone
+
+    BrewGenDone -- yes --> BrewPostProc["GetRandomCoordsWithinRange (5km jitter)<br/>generation + jitter run inside one try/catch per record"]
+    BrewGenDone -- no --> BrewGenFail["Log warning: generation failed, skipping"] --> BrewLoop
+
+    BrewPostProc --> BrewExport["SqliteExportService.ProcessRecord(GeneratedBrewery)<br/>reuse cached location_id or insert Location and cache its id; insert Brewery (FK location_id)"]
+    BrewExport --> BrewExportFail{Exception during insert?}
+    BrewExportFail -- yes --> BrewExportWarn["Log warning: SQLite export failed (data loss prevented per-record; pipeline continues)"] --> BrewLoop
+    BrewExportFail -- no --> BrewLoop
+    BrewLoop -- done --> Finalize["SqliteExportService.Finalize()<br/>commits transaction, closes database connection"]
+
+    Finalize --> CloseLog["main.cc: close log_channel, join log dispatcher thread"]
+    CloseLog --> Stop2(["return 0 / stop"])

docs/diagrams/pipeline/current/class.mmd

@@ -0,0 +1,260 @@
+classDiagram
+    class BiergartenPipelineOrchestrator {
+        -shared_ptr~ILogger~ logger_
+        -unique_ptr~IEnrichmentService~ context_service_
+        -unique_ptr~DataGenerator~ generator_
+        -unique_ptr~IExportService~ exporter_
+        -unique_ptr~ICuratedDataService~ curated_data_service_
+        -ApplicationOptions application_options_
+        -vector~BreweryRecord~ generated_breweries_
+        -vector~UserRecord~ generated_users_
+        +Run() bool
+        -QueryLocations() vector~City~
+        -GenerateBreweries(cities) void
+        -GenerateUsers(cities) void
+        -LogResults() void
+    }
+    note for BiergartenPipelineOrchestrator "GenerateBreweries/GenerateUsers jitter each address via GetRandomCoordsWithinRange(), uniformly within 5km of the city centre"
+
+    class LogLevel {
+        <<enumeration>>
+        Debug
+        Info
+        Warn
+        Error
+    }
+
+    class PipelinePhase {
+        <<enumeration>>
+        Startup
+        Enrichment
+        UserGeneration
+        BreweryAndBeerGeneration
+        CheckinGeneration
+        RatingGeneration
+        FollowGeneration
+        Teardown
+    }
+
+    class LogDTO {
+        <<struct>>
+        +LogLevel level
+        +PipelinePhase phase
+        +string message
+    }
+
+    class LogEntry {
+        <<struct>>
+        +time_point timestamp
+        +source_location origin
+        +thread::id thread_id
+        +LogLevel level
+        +PipelinePhase phase
+        +string message
+    }
+
+    class ILogger {
+        <<interface>>
+        +Log(payload) void
+        -DoLog(entry)* void
+    }
+
+    class LogProducer {
+        -BoundedChannel~LogEntry~ channel_
+        -DoLog(entry) void
+    }
+
+    class LogDispatcher {
+        -BoundedChannel~LogEntry~ channel_
+        +Run() void
+        -ToSpdlogLevel(level) level_enum
+    }
+
+    class IEnrichmentService {
+        <<interface>>
+        +GetLocationContext(loc) string
+    }
+
+    class MockEnrichmentService {
+        +GetLocationContext(loc) string
+    }
+
+    class WikipediaEnrichmentService {
+        -unique_ptr~WebClient~ client_
+        -unordered_map~string, string~ extract_cache_
+        +GetLocationContext(loc) string
+        -FetchExtract(query) string
+    }
+
+    class WebClient {
+        <<interface>>
+        +Get(url) string
+        +UrlEncode(value) string
+    }
+
+    class HttpWebClient {
+        +Get(url) string
+        +UrlEncode(value) string
+    }
+
+    class DataGenerator {
+        <<interface>>
+        +GenerateBrewery(city) BreweryResult
+        +GenerateUser(city, persona, name) UserResult
+    }
+
+    class MockGenerator {
+        +GenerateBrewery(city) BreweryResult
+        +GenerateUser(city, persona, name) UserResult
+        -DeterministicHash(location) size_t
+        -DeterministicHash(location, persona, name) size_t
+    }
+
+    class LlamaGenerator {
+        -ModelHandle model_
+        -ContextHandle context_
+        -unique_ptr~IPromptFormatter~ prompt_formatter_
+        -unique_ptr~IPromptDirectory~ prompt_directory_
+        -mt19937 rng_
+        +GenerateBrewery(...) BreweryResult
+        +GenerateUser(...) UserResult
+        -Load(model_path) void
+        -Infer(...) string
+        -InferFormatted(...) string
+    }
+
+    class OpenAIGenerator {
+        -string api_key_
+        -string model_
+        -shared_ptr~ILogger~ logger_
+        -unique_ptr~IPromptDirectory~ prompt_directory_
+        -unique_ptr~WebClient~ web_client_
+        +GenerateBrewery(city) BreweryResult
+        +GenerateUser(city, persona, name) UserResult
+        -CallChatCompletionsApi(...) string
+    }
+    note for OpenAIGenerator "Chat Completions with Structured Outputs (json_schema, strict) guarantees schema-valid JSON, replacing llama.cpp's GBNF grammar — no IPromptFormatter needed"
+
+    class IPromptFormatter {
+        <<interface>>
+        +Format(system_prompt, user_prompt) string
+    }
+
+    class Gemma4JinjaPromptFormatter {
+        +Format(system_prompt, user_prompt) string
+    }
+
+    class IPromptDirectory {
+        <<interface>>
+        +Load(key) string
+    }
+
+    class PromptDirectory {
+        -path prompt_dir_
+        -unordered_map~string, string~ cache_
+        +Load(key) string
+    }
+
+    class ICuratedDataService {
+        <<interface>>
+        +LoadLocations(filepath) vector~Location~
+        +LoadPersonas(filepath) vector~UserPersona~
+        +LoadForenamesByCountry(filepath) unordered_map~string, forename_list~
+        +LoadSurnamesByCountry(filepath) unordered_map~string, surname_list~
+    }
+
+    class JsonLoader {
+        -cache cache_
+        +LoadLocations(filepath) vector~Location~
+        +LoadPersonas(filepath) vector~UserPersona~
+        +LoadForenamesByCountry(filepath) unordered_map~string, forename_list~
+        +LoadSurnamesByCountry(filepath) unordered_map~string, surname_list~
+    }
+    note for JsonLoader "Each Load* method memoizes its result in cache_ after its first call"
+
+    class MockCuratedDataService {
+        -vector~Location~ locations_
+        -vector~UserPersona~ personas_
+        -unordered_map~string, forename_list~ forenames_by_country_
+        -unordered_map~string, surname_list~ surnames_by_country_
+        +LoadLocations(filepath) vector~Location~
+        +LoadPersonas(filepath) vector~UserPersona~
+        +LoadForenamesByCountry(filepath) unordered_map~string, forename_list~
+        +LoadSurnamesByCountry(filepath) unordered_map~string, surname_list~
+    }
+    note for MockCuratedDataService "Fixed 4-location/3-persona dataset (US, DE, FR, BE) for --mocked runs; filepath arguments are ignored"
+
+    class IExportService {
+        <<interface>>
+        +Initialize() void
+        +ProcessRecord(brewery) uint64_t
+        +ProcessRecord(user) uint64_t
+        +Finalize() void
+    }
+
+    class SqliteExportService {
+        -unique_ptr~IDateTimeProvider~ date_time_provider_
+        -string run_timestamp_utc_
+        -path database_path_
+        -SqliteDatabaseHandle db_handle_
+        -SqliteStatementHandle insert_location_stmt_
+        -SqliteStatementHandle insert_brewery_stmt_
+        -SqliteStatementHandle insert_user_stmt_
+        -bool transaction_open_
+        -unordered_map~string, sqlite3_int64~ location_cache_
+        +Initialize() void
+        +ProcessRecord(brewery) uint64_t
+        +ProcessRecord(user) uint64_t
+        +Finalize() void
+        -InitializeSchema() void
+        -ResolveLocationId(location) sqlite3_int64
+    }
+
+    class IDateTimeProvider {
+        <<interface>>
+        +GetUtcTimestamp() string
+    }
+
+    class SystemDateTimeProvider {
+        +GetUtcTimestamp() string
+    }
+
+    BiergartenPipelineOrchestrator *-- ILogger : owns
+    BiergartenPipelineOrchestrator *-- IEnrichmentService : owns
+    BiergartenPipelineOrchestrator *-- DataGenerator : owns
+    BiergartenPipelineOrchestrator *-- IExportService : owns
+    BiergartenPipelineOrchestrator *-- ICuratedDataService : owns
+
+    LogEntry *-- LogLevel
+    LogEntry *-- PipelinePhase
+    LogDTO *-- LogLevel
+    LogDTO *-- PipelinePhase
+    ILogger <|.. LogProducer : implements
+    LogProducer ..> LogEntry : emits
+    LogDispatcher ..> LogEntry : consumes
+
+    IEnrichmentService <|.. WikipediaEnrichmentService : implements
+    IEnrichmentService <|.. MockEnrichmentService : implements
+    WikipediaEnrichmentService *-- WebClient : owns
+
+    WebClient <|.. HttpWebClient : implements
+
+    DataGenerator <|.. MockGenerator : implements
+    DataGenerator <|.. LlamaGenerator : implements
+    DataGenerator <|.. OpenAIGenerator : implements
+
+    LlamaGenerator *-- IPromptFormatter : uses
+    LlamaGenerator *-- IPromptDirectory : uses
+
+    OpenAIGenerator *-- IPromptDirectory : uses
+    OpenAIGenerator *-- WebClient : uses
+
+    IPromptFormatter <|.. Gemma4JinjaPromptFormatter : implements
+    IPromptDirectory <|.. PromptDirectory : implements
+
+    ICuratedDataService <|.. JsonLoader : implements
+    ICuratedDataService <|.. MockCuratedDataService : implements
+
+    IExportService <|.. SqliteExportService : implements
+    SqliteExportService *-- IDateTimeProvider : owns
+    IDateTimeProvider <|.. SystemDateTimeProvider : implements

docs/diagrams/pipeline/planned/activity.mmd

@@ -0,0 +1,194 @@
+flowchart TD
+    Start([start]) --> ParseArgs["Main: ParseArguments(argc, argv)"]
+    ParseArgs --> InvalidArgs{Invalid args?}
+    InvalidArgs -- yes --> LogErr["spdlog::error"] --> Stop1([stop])
+    InvalidArgs -- no --> InitOpenSSL["Main: Init OpenSSL global state and LlamaBackendState"]
+    InitOpenSSL --> BuildDI["Main: Build DI injector"]
+    BuildDI --> InitSqlite["Main: Initialize SqliteExportService<br/>opens SQLite connection; transactions now managed per-phase via batching"]
+    InitSqlite --> LogSetup["Main: create BoundedChannel log_ch, spawn Log Worker thread<br/>drains log_ch for the pipeline lifetime; all workers emit LogEntry via PipelineLogger, never spdlog directly"]
+    LogSetup --> OrchRun["BiergartenPipelineOrchestrator::Run()"]
+
+    OrchRun --> PL1["JsonLoader.LoadBeerStyles → EnrichmentService.PreWarmBeerStyleCache"]
+    OrchRun --> PL2["JsonLoader.LoadLocations → EnrichmentService.PreWarmLocationCache"]
+    OrchRun --> PL3["JsonLoader.LoadForenamesByCountry"]
+    OrchRun --> PL4["JsonLoader.LoadSurnamesByCountry"]
+    OrchRun --> PL5["JsonLoader.LoadPersonas"]
+    PL1 & PL2 & PL3 & PL4 & PL5 --> UserPhase["Orchestrator: RunUserPhase(sampled_locations)<br/>each Load* call memoized after first parse; MockCuratedDataService (--mocked) returns a fixed in-memory dataset instead, skipping these JSON files"]
+
+    UserPhase --> UCreate["Create BoundedChannels (loc_ch, exp_ch)"]
+
+    subgraph USERGEN["Phase 0 — User Generation (concurrent)"]
+        direction LR
+        subgraph U_PROD["Orchestrator (producer)"]
+            UP1["Loop: send Location → loc_ch"]
+            UP1 --> UP2["Close loc_ch"]
+        end
+        subgraph U_LLM["LLM Worker"]
+            UL1{"loc_ch has items?"}
+            UL1 -- yes --> UL2["Receive Location"]
+            UL2 --> UL3["GetLocationContextFromCache(location) — guaranteed cache hit from startup"]
+            UL3 --> UL4["IPersonaSelectionStrategy.SelectPersona(personas_palette_) — guaranteed cache hit; returns Persona{style_affinities, abv_range, ibu_preference, checkin_weight}"]
+            UL4 --> UL5["SampleName(forenames_by_country, surnames_by_country, iso3166_1, rng)<br/>deterministic, no LLM; free function; skips the city if either map has no entry for iso3166_1"]
+            UL5 --> UL6["GenerateUser(enriched_city, persona, sampled_name) via DataGenerator<br/>LLM receives EnrichedCity context + persona description + sampled name"]
+            UL6 --> UL7["PipelineLogger.Log(Info, UserGeneration, city, user_id, llm)"]
+            UL7 --> UL8["Send GeneratedUser → exp_ch"]
+            UL8 --> UL1
+            UL1 -- no --> UL9["Close exp_ch"]
+        end
+        subgraph U_SQL["SQLite Worker"]
+            US1["BEGIN TRANSACTION"] --> US2{"exp_ch has items?"}
+            US2 -- yes --> US3["Receive GeneratedUser"]
+            US3 --> US4["ProcessUser(user)"]
+            US4 --> US5["PipelineLogger.Log(Info, UserGeneration, city, user_id, sqlite)"]
+            US5 --> US6["Append → user_pool_"]
+            US6 --> US7{"Batch size reached?"}
+            US7 -- yes --> US8["COMMIT and BEGIN"] --> US2
+            US7 -- no --> US2
+            US2 -- no --> US9["COMMIT (Final)"]
+        end
+    end
+
+    UCreate --> UP1
+    UP2 -.->|loc_ch| UL1
+    UL9 -.->|exp_ch| US2
+    UL9 & US9 --> UserJoin["Orchestrator: Join LLM Worker, SQLite Worker"]
+
+    UserJoin --> BreweryPhase["Orchestrator: RunBreweryPhase(sampled_locations)"]
+    BreweryPhase --> BCreate["Create BoundedChannels (loc_ch, exp_ch)"]
+
+    subgraph BREWGEN["Phase 1a — Brewery Generation (concurrent)"]
+        direction LR
+        subgraph B_PROD["Orchestrator (producer)"]
+            BP1["Loop: sample User from user_pool_, pair with Location"]
+            BP1 --> BP2["Send BreweryTask(Location, User) → loc_ch"]
+            BP2 --> BP3["Close loc_ch"]
+        end
+        subgraph B_LLM["LLM Worker"]
+            BL1{"loc_ch has items?"}
+            BL1 -- yes --> BL2["Receive BreweryTask(Location, User)"]
+            BL2 --> BL3["GetLocationContextFromCache(task.location) — guaranteed cache hit"]
+            BL3 --> BL4["GenerateBrewery(enriched_city, context, task.user) via DataGenerator<br/>KV cache stays warm; brewery linked to sampled owner_user_id"]
+            BL4 --> BL5["PipelineLogger.Log(Info, BreweryGeneration, city, brewery_id, llm)"]
+            BL5 --> BL6["Send GeneratedBrewery → exp_ch"]
+            BL6 --> BL1
+            BL1 -- no --> BL7["Close exp_ch"]
+        end
+        subgraph B_SQL["SQLite Worker"]
+            BS1["BEGIN TRANSACTION"] --> BS2{"exp_ch has items?"}
+            BS2 -- yes --> BS3["Receive GeneratedBrewery"]
+            BS3 --> BS4["ProcessBrewery(brewery)"]
+            BS4 --> BS5["PipelineLogger.Log(Info, BreweryGeneration, city, brewery_id, sqlite)"]
+            BS5 --> BS6["Append → brewery_pool_"]
+            BS6 --> BS7{"Batch size reached?"}
+            BS7 -- yes --> BS8["COMMIT and BEGIN"] --> BS2
+            BS7 -- no --> BS2
+            BS2 -- no --> BS9["COMMIT (Final)"]
+        end
+    end
+
+    BCreate --> BP1
+    BP3 -.->|loc_ch| BL1
+    BL7 -.->|exp_ch| BS2
+    BL7 & BS9 --> BrewJoin["Orchestrator: Join LLM Worker, SQLite Worker<br/>brewery_pool_ is now fully populated"]
+
+    BrewJoin --> BeerPhase["Orchestrator: RunBeerPhase()"]
+    BeerPhase --> BeCreate["Create BoundedChannels (brew_ch, exp_ch)"]
+
+    subgraph BEERGEN["Phase 1b — Beer Generation (concurrent)"]
+        direction LR
+        subgraph BE_PROD["Orchestrator (producer)"]
+            BeP1["Loop: send Breweries → brew_ch"]
+            BeP1 --> BeP2["Close brew_ch"]
+        end
+        subgraph BE_LLM["LLM Worker"]
+            BeL1{"brew_ch has items?"}
+            BeL1 -- yes --> BeL2["Receive GeneratedBrewery"]
+            BeL2 --> BeL3["IBeerSelectionStrategy.SelectStyles(brewery, beer_style_palette_)"]
+            BeL3 --> BeL4{"For each selected BeerStyle"}
+            BeL4 -- remaining --> BeL5["GetStyleContextFromCache(style) — guaranteed cache hit; KV cache stays warm across all beer generations in this phase"]
+            BeL5 --> BeL6["GenerateBeer(brewery, style_context) via DataGenerator"]
+            BeL6 --> BeL7["Attach GeneratedBeer to bundle"] --> BeL4
+            BeL4 -- done --> BeL8["PipelineLogger.Log(Info, BeerGeneration, city, brewery_id, llm)"]
+            BeL8 --> BeL9["Send BeersBundle → exp_ch"]
+            BeL9 --> BeL1
+            BeL1 -- no --> BeL10["Close exp_ch"]
+        end
+        subgraph BE_SQL["SQLite Worker"]
+            BeS1["BEGIN TRANSACTION"] --> BeS2{"exp_ch has items?"}
+            BeS2 -- yes --> BeS3["Receive BeersBundle"]
+            BeS3 --> BeS4{"For each beer in bundle"}
+            BeS4 -- remaining --> BeS5["Set beer.brewery_id from bundle"]
+            BeS5 --> BeS6["ProcessBeer(beer)"]
+            BeS6 --> BeS7["Append → beer_pool_"] --> BeS4
+            BeS4 -- done --> BeS8["PipelineLogger.Log(Info, BeerGeneration, city, brewery_id, sqlite)"]
+            BeS8 --> BeS9{"Batch size reached?"}
+            BeS9 -- yes --> BeS10["COMMIT and BEGIN"] --> BeS2
+            BeS9 -- no --> BeS2
+            BeS2 -- no --> BeS11["COMMIT (Final)"]
+        end
+    end
+
+    BeCreate --> BeP1
+    BeP2 -.->|brew_ch| BeL1
+    BeL10 -.->|exp_ch| BeS2
+    BeL10 & BeS11 --> BeerJoin["Orchestrator: Join LLM Worker, SQLite Worker<br/>brewery_pool_ and beer_pool_ are now completely populated — Checkin and Follow phases may run in parallel"]
+
+    BeerJoin --> CheckinPhase["Orchestrator: RunCheckinPhase()"]
+    BeerJoin --> FollowPhase["Orchestrator: RunFollowPhase()"]
+
+    subgraph CHECKIN["Checkin Generation"]
+        CK1["ICheckinDistributionStrategy.AssignActivityWeights(user_pool_)<br/>weights seeded from persona.checkin_weight; J-curve profile emerges from persona distribution"]
+        CK1 --> CK2["BEGIN TRANSACTION"]
+        CK2 --> CK3{"For each GeneratedUser in user_pool_"}
+        CK3 -- remaining --> CK4["CheckinsForUser(user, brewery_pool_.size())"]
+        CK4 --> CK5{"For each checkin index"}
+        CK5 -- remaining --> CK6["TimestampFor(user, index)"]
+        CK6 --> CK7["Select brewery from brewery_pool_"]
+        CK7 --> CK8["GenerateCheckin(user, brewery, timestamp) via DataGenerator"]
+        CK8 --> CK9["ProcessCheckin(checkin)"]
+        CK9 --> CK10["PipelineLogger.Log(Info, CheckinGeneration, nullopt, checkin_id, sqlite)"]
+        CK10 --> CK11["Append → checkin_pool_"]
+        CK11 --> CK12{"Batch size reached?"}
+        CK12 -- yes --> CK13["COMMIT and BEGIN"] --> CK5
+        CK12 -- no --> CK5
+        CK5 -- done --> CK3
+        CK3 -- done --> CK14["COMMIT (Final)"]
+    end
+
+    subgraph FOLLOW["Follow Generation"]
+        FL1["IFollowGenerationStrategy.AssignFollowWeights(user_pool_)<br/>RandomFollowStrategy: uniform weights; ActivityWeightedFollowStrategy: derived from user.activity_weight so high-activity users attract more followers"]
+        FL1 --> FL2["BEGIN TRANSACTION"]
+        FL2 --> FL3["IFollowGenerationStrategy.GenerateFollows(user_pool_)<br/>self-follow constraint (follower_id != followed_id) enforced here and at the DB schema level"]
+        FL3 --> FL4{"For each GeneratedFollow"}
+        FL4 -- remaining --> FL5["ProcessFollow(follow)"]
+        FL5 --> FL6["PipelineLogger.Log(Info, FollowGeneration, nullopt, follower_id, sqlite)"]
+        FL6 --> FL7["Append → follow_pool_"]
+        FL7 --> FL8{"Batch size reached?"}
+        FL8 -- yes --> FL9["COMMIT and BEGIN"] --> FL4
+        FL8 -- no --> FL4
+        FL4 -- done --> FL10["COMMIT (Final)"]
+    end
+
+    CheckinPhase --> CK1
+    FollowPhase --> FL1
+    CK14 & FL10 --> PhaseJoin["Orchestrator: Join CheckinPhase, FollowPhase<br/>checkin_pool_ and follow_pool_ are now fully populated"]
+
+    PhaseJoin --> RatingPhase["Orchestrator: RunRatingPhase()<br/>beer selection biased by user.persona.style_affinities and abv_range; rating skew modulated per persona"]
+    RatingPhase --> RT1["BEGIN TRANSACTION"]
+    RT1 --> RT2{"For each GeneratedCheckin in checkin_pool_"}
+    RT2 -- remaining --> RT3["Match brewery_id, select beer from beer_pool_ (same brewery_id, biased by persona affinities)"]
+    RT3 --> RT4{"Beer exists for brewery?"}
+    RT4 -- yes --> RT5["GenerateRating(user, beer, checkin_id) via DataGenerator"]
+    RT5 --> RT6["ProcessRating(rating)"]
+    RT6 --> RT7["PipelineLogger.Log(Info, RatingGeneration, nullopt, rating_id, sqlite)"]
+    RT7 --> RT8{"Batch size reached?"}
+    RT8 -- yes --> RT9["COMMIT and BEGIN"] --> RT2
+    RT8 -- no --> RT2
+    RT4 -- no --> RT10["Log warning; skip — brewery has no beers"] --> RT2
+    RT2 -- done --> RT11["COMMIT (Final)"]
+
+    RT11 --> Teardown["Orchestrator: Finalize SqliteExportService — safely closes the DB connection"]
+    Teardown --> CloseLogCh["Orchestrator: close log_ch"]
+    CloseLogCh --> MainDone["Main: spdlog::info 'Pipeline complete in X ms'"]
+    MainDone --> JoinLog["Main: Join Log Worker — drain guarantees no LogEntry is dropped at shutdown"]
+    JoinLog --> Stop2([stop])

docs/diagrams/pipeline/planned/class.mmd

@@ -0,0 +1,584 @@
+classDiagram
+    namespace DomainModels {
+        class Location {
+            +string city
+            +string state_province
+            +string iso3166_2
+            +string country
+            +string iso3166_1
+            +vector~string~ local_languages
+            +double latitude
+            +double longitude
+        }
+
+        class LocationContext {
+            +string text
+            +Completeness completeness
+            +size_t char_count
+        }
+
+        class Completeness {
+            <<enumeration>>
+            Full
+            Partial
+            Absent
+        }
+
+        class EnrichedCity {
+            +Location location
+            +LocationContext context
+        }
+
+        class BeerStyle {
+            +string name
+            +string description
+            +float min_abv
+            +float max_abv
+            +int min_ibu
+            +int max_ibu
+        }
+
+        class BreweryResult {
+            +string name_en
+            +string description_en
+            +string name_local
+            +string description_local
+        }
+
+        class BeerResult {
+            +string name_en
+            +string description_en
+            +string name_local
+            +string description_local
+            +string style
+            +float abv
+            +int ibu
+        }
+
+        class UserResult {
+            +string first_name
+            +string last_name
+            +string gender
+            +string username
+            +string bio
+            +float activity_weight
+        }
+
+        class Name {
+            +string first_name
+            +string last_name
+            +string gender
+        }
+
+        class ForenameEntry {
+            +string name
+            +string gender
+        }
+
+        class CheckinResult {
+            +string checked_in_at
+            +string note
+        }
+
+        class RatingResult {
+            +float score
+            +string note
+        }
+
+        class GenerationMetadata {
+            +uint64_t generation_id
+            +string generated_time
+            +bool context_provided
+            +string generated_with
+        }
+
+        class GeneratedBrewery {
+            +uint64_t brewery_id
+            +Location location
+            +BreweryResult brewery
+            +Completeness context_completeness
+            +GenerationMetadata metadata
+        }
+
+        class GeneratedBeer {
+            +uint64_t beer_id
+            +uint64_t brewery_id
+            +Location location
+            +BeerStyle style
+            +BeerResult beer
+            +GenerationMetadata metadata
+        }
+
+        class GeneratedUser {
+            +uint64_t user_id
+            +Location location
+            +UserResult user
+            +string email
+            +string date_of_birth
+            +string password
+            +GenerationMetadata metadata
+        }
+
+        class GeneratedCheckin {
+            +uint64_t checkin_id
+            +uint64_t user_id
+            +uint64_t brewery_id
+            +CheckinResult checkin
+            +GenerationMetadata metadata
+        }
+
+        class GeneratedRating {
+            +uint64_t user_id
+            +uint64_t beer_id
+            +uint64_t checkin_id
+            +RatingResult rating
+            +GenerationMetadata metadata
+        }
+
+        class GeneratedFollow {
+            +uint64_t follower_id
+            +uint64_t followed_id
+            +GenerationMetadata metadata
+        }
+
+        class UserPersona {
+            +string name
+            +string description
+            +vector~string~ style_affinities
+        }
+    }
+    note for ForenameEntry "forename_list/surname_list are unordered_set aliases, keyed by ISO 3166-1 country code via ICuratedDataService. SampleName() is a free function, not a method, sourced from popular-names-by-country-dataset (CC0)."
+    note for GeneratedUser "email, date_of_birth, and password are generated programmatically by the orchestrator (not LLM-authored) so a downstream auth-account seeding consumer can register real accounts from this export."
+    ForenameEntry ..> Name : SampleName() produces
+    LocationContext *-- Completeness
+
+    namespace DomainApplicationConfiguration {
+        class SamplingOptions {
+            +float temperature
+            +float top_p
+            +uint32_t top_k
+            +uint32_t n_ctx
+            +int seed
+        }
+
+        class GeneratorOptions {
+            +path model_path
+            +bool use_mocked
+            +optional~SamplingOptions~ sampling
+        }
+
+        class PipelineOptions {
+            +path output_path
+            +path log_path
+        }
+
+        class ApplicationOptions {
+            +GeneratorOptions generator
+            +PipelineOptions pipeline
+        }
+    }
+    ApplicationOptions *-- GeneratorOptions
+    ApplicationOptions *-- PipelineOptions
+    GeneratorOptions o-- SamplingOptions
+
+    namespace DomainPolicy {
+        class ContextStrategy {
+            <<interface>>
+            +QueriesFor(loc) vector~string~
+            +MaxContextChars() size_t
+        }
+
+        class BreweryContextStrategy {
+            +QueriesFor(loc) vector~string~
+            +MaxContextChars() size_t
+        }
+
+        class BeerContextStrategy {
+            +QueriesFor(loc) vector~string~
+            +MaxContextChars() size_t
+        }
+
+        class SamplingStrategy {
+            <<interface>>
+            +Sample(locations) vector~Location~
+        }
+
+        class UniformSamplingStrategy {
+            -size_t sample_size_
+            +Sample(locations) vector~Location~
+        }
+
+        class BeerSelectionStrategy {
+            <<interface>>
+            +SelectStyles(brewery, palette) vector~BeerStyle~
+        }
+
+        class RandomBeerSelectionStrategy {
+            -mt19937 rng_
+            -size_t min_beers_
+            -size_t max_beers_
+            +SelectStyles(brewery, palette) vector~BeerStyle~
+        }
+
+        class CheckinDistributionStrategy {
+            <<interface>>
+            +AssignActivityWeights(users) void
+            +CheckinsForUser(user, brewery_count) size_t
+            +TimestampFor(user, index) string
+        }
+
+        class JCurveCheckinStrategy {
+            -mt19937 rng_
+            +AssignActivityWeights(users) void
+            +CheckinsForUser(user, brewery_count) size_t
+            +TimestampFor(user, index) string
+        }
+
+        class RandomCheckinStrategy {
+            -mt19937 rng_
+            -size_t min_checkins_
+            -size_t max_checkins_
+            +AssignActivityWeights(users) void
+            +CheckinsForUser(user, brewery_count) size_t
+            +TimestampFor(user, index) string
+        }
+
+        class FollowGenerationStrategy {
+            <<interface>>
+            +GenerateFollows(users) vector~GeneratedFollow~
+        }
+
+        class RandomFollowStrategy {
+            -mt19937 rng_
+            -size_t min_follows_
+            -size_t max_follows_
+            +GenerateFollows(users) vector~GeneratedFollow~
+        }
+
+        class ActivityWeightedFollowStrategy {
+            -mt19937 rng_
+            -size_t min_follows_
+            -size_t max_follows_
+            +GenerateFollows(users) vector~GeneratedFollow~
+        }
+    }
+
+    namespace InfrastructureLogging {
+        class LogLevel {
+            <<enumeration>>
+            Debug
+            Info
+            Warn
+            Error
+        }
+
+        class PipelinePhase {
+            <<enumeration>>
+            Startup
+            UserGeneration
+            BreweryAndBeerGeneration
+            CheckinGeneration
+            RatingGeneration
+            FollowGeneration
+            Teardown
+        }
+
+        class LogEntry {
+            +time_point timestamp
+            +LogLevel level
+            +PipelinePhase phase
+            +string message
+            +optional~string~ worker
+        }
+
+        class ILogger {
+            <<interface>>
+            +Log(entry) void
+        }
+
+        class LogProducer {
+            -BoundedChannel~LogEntry~ channel_
+            +Log(entry) void
+        }
+
+        class LogDispatcher {
+            -BoundedChannel~LogEntry~ channel_
+            +Run() void
+            -ToSpdlogLevel(level) level_enum
+        }
+    }
+    LogEntry *-- LogLevel
+    LogEntry *-- PipelinePhase
+    ILogger <|.. LogProducer
+    LogProducer ..> LogEntry : emits
+    LogDispatcher ..> LogEntry : consumes
+
+    namespace InfrastructurePipelineChannel {
+        class BoundedChannel~T~ {
+            -queue~T~ queue_
+            -mutex mutex_
+            -condition_variable not_full_
+            -condition_variable not_empty_
+            -size_t capacity_
+            -bool closed_
+            +Send(item) void
+            +Receive() optional~T~
+            +Close() void
+        }
+    }
+
+    namespace InfrastructureDataPreloading {
+        class ICuratedDataService {
+            <<interface>>
+            +LoadLocations(filepath) vector~Location~
+            +LoadBeerStyles(filepath) vector~BeerStyle~
+            +LoadPersonas(filepath) vector~UserPersona~
+            +LoadForenamesByCountry(filepath) unordered_map~string, forename_list~
+            +LoadSurnamesByCountry(filepath) unordered_map~string, surname_list~
+        }
+
+        class JsonLoader {
+            +LoadLocations(filepath) vector~Location~
+            +LoadBeerStyles(filepath) vector~BeerStyle~
+            +LoadPersonas(filepath) vector~UserPersona~
+            +LoadForenamesByCountry(filepath) unordered_map~string, forename_list~
+            +LoadSurnamesByCountry(filepath) unordered_map~string, surname_list~
+        }
+
+        class MockCuratedDataService {
+            +LoadLocations(filepath) vector~Location~
+            +LoadBeerStyles(filepath) vector~BeerStyle~
+            +LoadPersonas(filepath) vector~UserPersona~
+            +LoadForenamesByCountry(filepath) unordered_map~string, forename_list~
+            +LoadSurnamesByCountry(filepath) unordered_map~string, surname_list~
+        }
+    }
+    note for JsonLoader "Each Load* call is memoized after its first parse — implemented today, ahead of LoadBeerStyles which is still planned."
+    note for MockCuratedDataService "Fixed in-memory dataset for --mocked mode, implemented today for Locations/Personas/Forenames/Surnames; would need a LoadBeerStyles fixture too once that method is implemented."
+
+    namespace InfrastructureEnrichment {
+        class EnrichmentService {
+            <<interface>>
+            +GetLocationContext(loc, strategy) LocationContext
+        }
+
+        class WikipediaService {
+            -unique_ptr~WebClient~ client_
+            -unordered_map~string, string~ extract_cache_
+            +GetLocationContext(loc, strategy) LocationContext
+            -FetchExtract(query) string
+        }
+
+        class WebClient {
+            <<interface>>
+            +Get(url) string
+            +UrlEncode(value) string
+        }
+
+        class HttpWebClient {
+            +Get(url) string
+            +UrlEncode(value) string
+        }
+    }
+
+    namespace InfrastructurePrompting {
+        class IPromptDirectory {
+            <<interface>>
+            +Load(key) string
+        }
+
+        class PromptDirectory {
+            -path prompt_dir_
+            -unordered_map~string, string~ cache_
+            +PromptDirectory(prompt_dir)
+            +Load(key) string
+        }
+    }
+    IPromptDirectory <|.. PromptDirectory
+
+    namespace InfrastructureDataGeneration {
+        class DataGenerator {
+            <<interface>>
+            +GenerateBrewery(location, context) BreweryResult
+            +GenerateBeer(brewery_id, location, context, style) BeerResult
+            +GenerateUser(city, persona, name) UserResult
+            +GenerateCheckin(user, brewery, timestamp) CheckinResult
+            +GenerateRating(user, beer, checkin_id) RatingResult
+        }
+
+        class MockGenerator {
+            +GenerateBrewery(...) BreweryResult
+            +GenerateBeer(...) BeerResult
+            +GenerateUser(...) UserResult
+            +GenerateCheckin(...) CheckinResult
+            +GenerateRating(...) RatingResult
+            -DeterministicHash(location) size_t
+        }
+
+        class LlamaGenerator {
+            -ModelHandle model_
+            -ContextHandle context_
+            -unique_ptr~PromptFormatter~ prompt_formatter_
+            -unique_ptr~IPromptDirectory~ prompt_directory_
+            -mt19937 rng_
+            +GenerateBrewery(...) BreweryResult
+            +GenerateBeer(...) BeerResult
+            +GenerateUser(...) UserResult
+            +GenerateCheckin(...) CheckinResult
+            +GenerateRating(...) RatingResult
+            -Load(opts) void
+            -Infer(system_prompt, user_prompt, max_tokens, grammar) string
+            -ValidateModelArchitecture() void
+        }
+
+        class PromptFormatter {
+            <<interface>>
+            +Format(system_prompt, user_prompt) string
+            +ExpectedArchitecture() string_view
+        }
+
+        class Gemma4JinjaPromptFormatter {
+            +Format(system_prompt, user_prompt) string
+            +ExpectedArchitecture() string_view
+        }
+    }
+
+    namespace InfrastructureDataExport {
+        class ExportService {
+            <<interface>>
+            +Initialize() void
+            +ProcessBrewery(brewery) uint64_t
+            +ProcessBeer(beer) uint64_t
+            +ProcessUser(user) uint64_t
+            +ProcessCheckin(checkin) uint64_t
+            +ProcessRating(rating) void
+            +ProcessFollow(follow) void
+            +Finalize() void
+        }
+
+        class SqliteExportService {
+            -unique_ptr~DateTimeProvider~ date_time_provider_
+            -SqliteDatabaseHandle db_handle_
+            -SqliteStatementHandle insert_location_stmt_
+            -SqliteStatementHandle insert_brewery_stmt_
+            -SqliteStatementHandle insert_beer_stmt_
+            -SqliteStatementHandle insert_user_stmt_
+            -SqliteStatementHandle insert_checkin_stmt_
+            -SqliteStatementHandle insert_rating_stmt_
+            -SqliteStatementHandle insert_follow_stmt_
+            -bool transaction_open_
+            -unordered_map~string, uint64_t~ location_cache_
+            -unordered_map~string, uint64_t~ brewery_cache_
+            +Initialize() void
+            +ProcessRecord(brewery) uint64_t
+            +ProcessRecord(beer) uint64_t
+            +ProcessRecord(user) uint64_t
+            +ProcessRecord(checkin) uint64_t
+            +ProcessRecord(rating) void
+            +ProcessRecord(follow) void
+            +Finalize() void
+            -InitializeSchema() void
+            -PrepareStatements() void
+            -RollbackAndCloseNoThrow() void
+            -FinalizeStatements() void
+        }
+
+        class DateTimeProvider {
+            <<interface>>
+            +GetUtcTimestamp() string
+        }
+
+        class SystemDateTimeProvider {
+            +GetUtcTimestamp() string
+        }
+    }
+
+    class BiergartenPipelineOrchestrator {
+        -unique_ptr~ICuratedDataService~ curated_data_service_
+        -unique_ptr~EnrichmentService~ enrichment_service_
+        -unique_ptr~DataGenerator~ generator_
+        -unique_ptr~Logger~ logger_
+        -unique_ptr~ExportService~ exporter_
+        -unique_ptr~ContextStrategy~ brewery_context_strategy_
+        -unique_ptr~SamplingStrategy~ sampling_strategy_
+        -unique_ptr~BeerSelectionStrategy~ beer_selection_strategy_
+        -unique_ptr~CheckinDistributionStrategy~ checkin_strategy_
+        -unique_ptr~FollowGenerationStrategy~ follow_strategy_
+        -vector~BeerStyle~ beer_style_palette_
+        -ApplicationOptions options_
+        -vector~GeneratedUser~ user_pool_
+        -vector~GeneratedBrewery~ brewery_pool_
+        -vector~GeneratedBeer~ beer_pool_
+        -vector~GeneratedCheckin~ checkin_pool_
+        -vector~GeneratedFollow~ follow_pool_
+        +Run() bool
+        -RunUserPhase(locations) void
+        -RunBreweryAndBeerPhase(locations) void
+        -RunCheckinPhase() void
+        -RunRatingPhase() void
+        -RunFollowPhase() void
+    }
+
+    BiergartenPipelineOrchestrator *-- ICuratedDataService
+    BiergartenPipelineOrchestrator *-- EnrichmentService
+    BiergartenPipelineOrchestrator *-- DataGenerator
+    BiergartenPipelineOrchestrator *-- ExportService
+    BiergartenPipelineOrchestrator *-- CheckinDistributionStrategy
+    BiergartenPipelineOrchestrator *-- FollowGenerationStrategy
+    BiergartenPipelineOrchestrator *-- SamplingStrategy
+    BiergartenPipelineOrchestrator *-- BeerSelectionStrategy
+    BiergartenPipelineOrchestrator *-- ApplicationOptions
+    BiergartenPipelineOrchestrator *-- Logger
+
+    BiergartenPipelineOrchestrator "1" *-- "0..*" GeneratedUser : user_pool_
+    BiergartenPipelineOrchestrator "1" *-- "0..*" GeneratedBrewery : brewery_pool_
+    BiergartenPipelineOrchestrator "1" *-- "0..*" GeneratedBeer : beer_pool_
+    BiergartenPipelineOrchestrator "1" *-- "0..*" GeneratedCheckin : checkin_pool_
+    BiergartenPipelineOrchestrator "1" *-- "0..*" GeneratedFollow : follow_pool_
+
+    ICuratedDataService <|.. JsonLoader
+    ICuratedDataService <|.. MockCuratedDataService
+    Logger <|.. PipelineLogger
+    ContextStrategy <|.. BreweryContextStrategy
+    ContextStrategy <|.. BeerContextStrategy
+    SamplingStrategy <|.. UniformSamplingStrategy
+    BeerSelectionStrategy <|.. RandomBeerSelectionStrategy
+    CheckinDistributionStrategy <|.. JCurveCheckinStrategy
+    CheckinDistributionStrategy <|.. RandomCheckinStrategy
+    FollowGenerationStrategy <|.. RandomFollowStrategy
+    FollowGenerationStrategy <|.. ActivityWeightedFollowStrategy
+    EnrichmentService <|.. WikipediaService
+    WebClient <|.. HttpWebClient
+    DataGenerator <|.. MockGenerator
+    DataGenerator <|.. LlamaGenerator
+    PromptFormatter <|.. Gemma4JinjaPromptFormatter
+    ExportService <|.. SqliteExportService
+    DateTimeProvider <|.. SystemDateTimeProvider
+
+    WikipediaService *-- WebClient
+    WikipediaService ..> ContextStrategy
+    LlamaGenerator *-- PromptFormatter
+    LlamaGenerator *-- IPromptDirectory
+    LlamaGenerator ..> GeneratorOptions
+    SqliteExportService *-- DateTimeProvider
+
+    PipelineLogger o-- BoundedChannel : logs to
+    LogWorker o-- BoundedChannel : drains from
+
+    EnrichedCity *-- Location
+    EnrichedCity *-- LocationContext
+    GeneratedBrewery *-- Location
+    GeneratedBrewery *-- BreweryResult
+    GeneratedBrewery *-- GenerationMetadata
+    GeneratedBeer *-- Location
+    GeneratedBeer *-- BeerStyle
+    GeneratedBeer *-- BeerResult
+    GeneratedBeer *-- GenerationMetadata
+    GeneratedUser *-- Location
+    GeneratedUser *-- UserResult
+    GeneratedUser *-- GenerationMetadata
+    GeneratedCheckin *-- CheckinResult
+    GeneratedCheckin *-- GenerationMetadata
+    GeneratedRating *-- RatingResult
+    GeneratedRating *-- GenerationMetadata
+    GeneratedFollow *-- GenerationMetadata