GameCult/VoidBot
Watch
9
0
Fork
You've already forked VoidBot
 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
VoidBot/notes/voidbot-current-system-map.md

10 KiB
Raw Blame History

VoidBot Current System Map

This note is the source-grounded description of how the live VoidBot stack is shaped right now. It is not a prose replacement for the code, and it is not a second canonical map. Its job is to explain the major organs and their data flow in plain language with concrete path anchors.

Main Organs

  • apps/bot/src/discord-bot.ts
    • Discord gateway shell: client bootstrap, provider wiring, event registration, and top-level orchestration.
  • apps/bot/src/discord-bot-handlers.ts
    • Prompt/command handling, provider dispatch, rate-limit gating, job approval/rejection, reindexing, and slash-command registration helpers.
  • apps/bot/src/discord-bot-support.ts
    • Discord-shape adapters, archive/source conversion helpers, ambient-memory ingestion helpers, source-grounding hint logic, and bot-side message formatting/rendering helpers.
  • apps/worker/src/index.ts
    • owner-job poller, provider execution, handoff packaging, and MCP wiring for the worker-side lane.
  • apps/worker/src/mcp-server.ts
    • thin stdio entrypoint that boots the MCP context and registers the resource/tool surfaces.
  • apps/worker/src/mcp-server-context.ts
    • workspace bootstrap, config loading, archive/vector wiring, retrieval-service creation, and source-context ingester setup for the MCP lane.
  • apps/worker/src/mcp-server-resources.ts
    • MCP resource registration for indexed repos plus history/source semantic-search resource templates.
  • apps/worker/src/mcp-server-tools.ts
    • MCP tool registration for archived history search, indexed source/lore search, context windows, repo listing, and owner notifications.
  • apps/worker/src/mcp-server-shared.ts
    • MCP input schemas, argument types, and shared result-formatting/resource helper functions.
  • apps/worker/src/mcp-server-discord.ts
    • Discord DM-channel creation and message-post helpers for notify_owner.
  • packages/core/src/state-storage.ts
    • Thin state-storage factory that chooses file or Postgres backends and wires the domain stores together.
  • packages/core/src/state-storage-postgres-bootstrap.ts
    • Postgres schema bootstrap plus one-time legacy file-state import.
  • packages/core/src/state-storage-postgres-job-queue.ts
    • Postgres-backed job queue plus job row persistence helpers.
  • packages/core/src/state-storage-postgres-audit-log.ts
    • Postgres-backed audit log plus audit-event upsert helper.
  • packages/core/src/state-storage-postgres-interaction-memory.ts
    • Postgres-backed interaction-memory event storage and profile reconstruction.
  • packages/core/src/state-storage-rate-limit-stores.ts
    • File and Postgres implementations for Void usage rate-limit state.
  • packages/core/src/interaction-memory-analysis.ts
    • Event construction, tone/tag analysis, repetition detection, and persistence gating for remembered interactions.
  • packages/core/src/interaction-memory-profile.ts
    • Profile synthesis, disposition, psychological read, inferred traits, interaction dimensions, and response-guidance construction.
  • packages/core/src/context-builder.ts
    • request context assembly, including interaction-memory/profile attachment plus any precomputed situational social read.
  • packages/core/src/situational-social-read.ts
    • quick Ollama sidecar inferer for ephemeral room-reading scaffolding built from the current prompt, recent room transcript, and longer-horizon interaction memory.
  • packages/providers/src/owner-codex-provider.ts
    • thin orchestration layer for the Discord-safe codex exec lane.
  • packages/providers/src/owner-codex-runtime.ts
    • Codex process execution, stdout/stderr parsing, trace-event normalization, history-tool loop requests, and owner-DM intent parsing.
  • packages/providers/src/owner-codex-render.ts
    • prompt assembly, bundle rendering, and trace/debug transcript rendering for the owner lane.
  • packages/providers/src/owner-codex-shared.ts
    • owner-lane constants, shared types, request-payload shaping, trace formatting helpers, and interaction-memory rendering.
  • packages/providers/src/local-llm-provider.ts
    • thin orchestration shell for the Ollama chat lane plus the bounded host-managed read-only tool loop.
  • packages/providers/src/local-llm-render.ts
    • local-lane prompt assembly, interaction-memory rendering, source-grounding reminders, and artifact rendering.
  • packages/providers/src/local-llm-tools.ts
    • local-lane tool definitions, assistant-message normalization, tool argument parsing, and toolbox execution helpers.
  • packages/providers/src/local-llm-shared.ts
    • local-lane constants, shared request/response/tool types, and low-level text/metadata helpers.
  • packages/rag/src/retrieval-service.ts
    • high-level history/source retrieval API used by bot, worker, and provider tool loops.
  • packages/rag/src/qdrant-vector-store.ts
    • Qdrant vector persistence for history and source collections.
  • packages/rag/src/message-archive.ts
    • archived Discord message store under .voidbot/rag/messages.json, including bot-directed prompts that stay preserved for forensics even when they are excluded from default history retrieval.
  • packages/rag/src/source-document-archive.ts
    • archived source/lore document manifest under .voidbot/rag/source-documents.json plus per-repo shards under .voidbot/rag/source-documents.repos/.

Flow 1: Discord Request To Provider

  1. apps/bot/src/discord-bot.ts receives a slash command or mention-driven request and delegates prompt/command work into apps/bot/src/discord-bot-handlers.ts.
  2. Permission checks run through packages/core/src/permission-engine.ts.
  3. Void usage limits are applied through packages/core/src/void-usage-rate-limiter.ts backed by packages/core/src/state-storage.ts.
  4. apps/bot/src/discord-bot-support.ts adapts Discord message/interaction shapes, ambient-memory events, and source-grounding hints.
  5. packages/core/src/interaction-memory-analysis.ts turns direct prompts or ambient mentions into normalized remembered events; packages/core/src/interaction-memory-profile.ts distills remembered events into a reusable longer-horizon social read.
  6. apps/bot/src/discord-bot-handlers.ts runs a quick think=false local Ollama sidecar pass over the prompt and recent room transcript to infer an ephemeral situational social read, then records that read as an audit event for later aggregation.
  7. packages/core/src/context-builder.ts assembles request context, including recent interaction profile, the situational social read, and any retrieval hints.
  8. Provider selection goes through packages/providers/src/index.ts.
  9. The bot either:
    • answers directly through local_llm, or
    • queues an owner job for the worker / owner_codex path.

Flow 2: Owner Job Execution

  1. apps/worker/src/index.ts polls approved jobs from durable state.
  2. The worker claims a job and dispatches it to the configured provider.
  3. packages/providers/src/owner-codex-provider.ts runs codex exec in the bounded lane, exposes the VoidBot MCP server, records traces, and carries advisory source-grounding hints plus retrieval tools for repo/lore/project questions. Runtime and parsing live in packages/providers/src/owner-codex-runtime.ts; prompt and artifact rendering live in packages/providers/src/owner-codex-render.ts.
  4. If the answer fits the Discord-safe lane, the worker posts it back.
  5. If the task needs deeper work, the worker writes a handoff bundle under .voidbot/artifacts/<job-id>/ and posts the handoff response.

Flow 3: Retrieval And Indexing

  1. packages/rag/src/message-archive.ts and packages/rag/src/source-document-archive.ts keep the raw corpora.
  2. Bot-directed prompts are tagged at ingest, kept in the raw Discord archive, and deliberately skipped when the history ingester builds semantic chunks so repeated summons stop poisoning normal retrieval.
  3. packages/rag/src/retrieval-service.ts translates history/source queries into vector lookups plus metadata filters.
  4. packages/rag/src/qdrant-vector-store.ts executes the live vector lookups against separate history and source collections.
  5. scripts/reconcile-source-repos.ts discovers local Git repos, refreshes push hooks, prunes stale repo shards, and indexes newly discovered repos.
  6. scripts/index-source-repos.ts and scripts/git-post-push-index.mjs drive explicit or detached per-repo source/lore reindex work.
  7. apps/worker/src/mcp-server.ts boots the MCP lane, while mcp-server-resources.ts and mcp-server-tools.ts expose retrieval to Codex and other sessions through search_history, get_message_context, search_sources, get_source_context, and list_indexed_repos.

Flow 4: Ops And Recovery

  • scripts/start-voidbot-stack.ps1
    • stack bootstrap, health checks, fresh build, stale-process cleanup, source-repo reconcile, bot/worker restart, runtime status emission.
  • scripts/install-stack-startup-task.ps1
    • installs the hidden logon task that runs start-voidbot-stack.ps1 automatically after reboot or sign-in.
  • scripts/check-voidbot-operations.ps1
    • watchdog for process liveness, Qdrant, Postgres, Ollama, source-repo reconcile drift, Discord auth, backup freshness, offsite sync freshness, and optional ignored local extension checks.
  • scripts/backup-voidbot-state.ps1
    • local backup of Postgres, Qdrant snapshots, and RAG archives.
  • scripts/restore-voidbot-state.ps1
    • local restore path.
  • scripts/sync-voidbot-backup-offsite.ps1
    • verified offsite backup sync to the Qwen box.
  • scripts/voidbot-operations-dashboard-lib.ps1
    • dashboard rendering for the local ops surface.

When present, an ignored local script at .voidbot/private/check-voidbot-operations.local.ps1 can inject adjacent-service checks into the same ops lane. That keeps private infrastructure gossip out of tracked code while preserving one boring place for smoke alarms to land.

Storage Boundaries

  • Postgres:
    • jobs
    • audit events
    • interaction-memory events
    • provider run records
    • usage rate-limit state
  • Qdrant:
    • Discord history vectors
    • source/lore vectors
  • .voidbot/:
    • archived raw corpora
    • source archive manifest plus per-repo source shards
    • job artifacts and traces
    • logs and status files
    • backups and snapshots

The important scar is that these stores are split on purpose. Do not casually weld them back into one convenient blob and act surprised when it becomes a moon.

Within the Postgres path, the implementation is split on purpose now too:

  • state-storage.ts chooses the backend
  • state-storage-postgres-bootstrap.ts handles schema/bootstrap/import work
  • per-domain modules own queue, audit, interaction-memory, and rate-limit behavior