| .. | ||
| prompts | ||
| .dockerignore | ||
| .env.example | ||
| .gitignore | ||
| appservice.go | ||
| appservice_test.go | ||
| bot.go | ||
| bot_test.go | ||
| concurrency_test.go | ||
| config.go | ||
| context.go | ||
| Dockerfile | ||
| events.go | ||
| go.mod | ||
| go.sum | ||
| logging.go | ||
| main.go | ||
| markdown.go | ||
| markdown_test.go | ||
| matrix.go | ||
| mentions.go | ||
| messages.go | ||
| README.md | ||
| registration.go | ||
| registration_test.go | ||
| store.go | ||
| util.go | ||
| xai.go | ||
ai-bot
A plaintext Matrix bot user (@ai:vojo.chat, display name Vojo AI) that
answers xAI Grok completions in its rooms: @-mentions in group rooms and every
message in a 1:1. It runs as a Synapse application service — Synapse pushes
event transactions to the bot's HTTP endpoint; the bot speaks the Matrix CS-API
back over plain HTTP (no Olm/Megolm — Vojo rooms are unencrypted by default) and
calls the xAI OpenAI-compatible Chat Completions API.
Authentication is the appservice as_token/hs_token (from the registration) —
non-expiring, so there is no token rotation and no stored password.
It is a separate server-side service, deployed next to Synapse. It lives in
this repo (alongside apps/widget-*) but ships nothing to the web client.
Branding: user-facing name is Vojo AI with a generic icon. "Grok" appears only as the factual attribution ("powered by Grok, xAI") and as the real model id — never as the product name or logo (xAI Brand Guidelines).
Design source of truth: docs/plans/grok_bot.md. Privacy/152-ФЗ pre-launch
gating lives there (§6) and is not closed by this code.
Layout
apps/ai-bot/
├── main.go # entrypoint, lifecycle, `check-config` subcommand
├── config.go # env parsing + validation + redacted summary
├── bot.go # event handling, classification, limiter wiring
├── appservice.go # HTTP transaction-push server (hs_token auth, txn idempotency)
├── matrix.go # CS-API client as the appservice user (as_token + ?user_id=)
├── registration.go # generate + read registration.yaml (tokens, mautrix idiom)
├── events.go # Matrix event types + decoders
├── mentions.go # m.mentions + pill/reply fallbacks (F29/F30)
├── context.go # xAI message-window assembly (trigger + bot replies)
├── xai.go # chat/completions client + retry (F6)
├── store.go # SQLite: spend ledger, txn dedup, encrypted-warned set
├── messages.go # bot-authored RU notices
├── markdown.go # markdown → org.matrix.custom.html for the reply's formatted_body
├── util.go # bounded dedup set
├── prompts/system_ru.txt
├── Dockerfile # CGO-free static build → distroless, EXPOSE 8009
└── .env.example
Configuration
All via environment (see .env.example). Required: HOMESERVER_URL, BOT_MXID,
AS_TOKEN, HS_TOKEN, XAI_API_KEY, ALLOWED_SERVERS. AS_ADDR (default
:8009) is the transaction-push listen address — it must match the url port in
the registration. The model is env-configurable (XAI_MODEL, default
grok-4.20-0309-non-reasoning; grok-4.3 is an alternative — **re-verify the id
- price on docs.x.ai before deploy**).
The hard USD ceiling is priced from the API-returned token usage times the
configured XAI_PRICE_*_PER_M fallbacks, so a price change only needs those
constants updated — it can't silently blow the cap.
One-time setup (appservice registration)
Like the mautrix bridges (e.g. telegram), the bot generates its own
registration (random as_token/hs_token) and reads its tokens back from that
same file — the single source of truth shared with Synapse, no hand-copying.
- Generate it (writes
REGISTRATION_PATH, default/data/registration.yaml):docker compose run --rm ai-bot generate-registration - Bind-mount that same file into the Synapse container (e.g. as
/data/ai-registration.yaml) and add it tohomeserver.yaml:app_service_config_files: - /data/ai-registration.yaml - Restart Synapse (it caches AS configs at startup). Synapse auto-creates
@ai:vojo.chatfromsender_localpart— noregister_new_matrix_user.
The bot reads REGISTRATION_PATH for its tokens (no env AS_TOKEN/HS_TOKEN
needed) and sets its own display name (BOT_DISPLAY_NAME, default "Vojo AI") on
startup. The bot writes/reads /data, so that dir must be owned by the image's
runtime uid (distroless nonroot = 65532): sudo chown -R 65532:65532 ~/vojo/ai-bot.
Run
go run . check-config # local config smoke test (no homeserver contact)
go run . # real run (needs env + a reachable homeserver)
Image & secrets model
The image is config-less (a .dockerignore keeps .env, state/ and VCS
out of the build context; the Dockerfile copies only the binary + prompts/).
Build locally and ship like the mautrix bridges (VS Code task Deploy AI bot =
docker build -t ai-bot:custom → docker save | ssh docker load), then run on
the server with config + secrets supplied at runtime.
Config and secrets are separated: non-secret config in ai-bot.env
(env_file); the appservice tokens live in the generated registration.yaml
(read via REGISTRATION_PATH); the only remaining standalone secret is the xAI
key (XAI_API_KEY_FILE).
Compose stanza (add to ~/vojo/docker-compose.yml; the service key ai-bot
must match the registration url host http://ai-bot:8009):
ai-bot:
image: ai-bot:custom
container_name: vojo-ai-bot
restart: unless-stopped
depends_on: [synapse]
env_file: ./ai-bot/ai-bot.env # NON-SECRET config (chmod 600)
environment:
REGISTRATION_PATH: /data/registration.yaml # tokens (generated; shared with Synapse)
STATE_DIR: /data/state # SQLite: spend ledger + txn dedup
XAI_API_KEY_FILE: /data/secrets/xai_api_key # the one standalone secret
volumes:
- ./ai-bot:/data # owned by uid 65532 (see setup)
Also bind-mount the same registration into Synapse and restart it:
synapse:
volumes:
- ./ai-bot/registration.yaml:/data/ai-registration.yaml:ro
HOMESERVER_URL must use the Synapse service name (http://synapse:8008),
not localhost. Synapse and the bot must share a docker network (same compose
project does this) so Synapse can push to http://ai-bot:8009.
Verification status
Compile-level + unit-tested locally:
- ✅
go vetclean,gofmtclean, static CGO-free build. - ✅
go test— appservice transaction handling (hs_token auth → 403 on bad token, txnId idempotency / no re-dispatch, legacy?access_token=, user query 200/404); mention detection (m.mentions, empty-{}F29, no-body-fallback F30, pill, reply-to-bot); DM classification (invited+joined==2, F3: 2 joined + 1 invited is not a 1:1); group-vs-DM context minimisation (groups never leak third-party content); USD pricing; markdown → HTML rendering (escaping, safe-URL allowlist, false-positive guards, oversize/adversarial fallbacks). - ✅
check-configreads env + loads the system prompt.
Deferred to a live homeserver + xAI key + a loaded registration (runtime ✔):
- Synapse pushes transactions → bot replies (
authenticated as @ai:vojo.chatin logs); - invite from
:vojo.chat→ join, foreign-server invite → leave (F11); @-mention / 1:1 message →m.noticereply with reply (and thread, F27) relation, carrying aformatted_body(org.matrix.custom.html) when the answer has markdown;- encrypted room → exactly one notice, not repeated after restart (F5);
- per-user cap → silent drop; global USD ceiling → one notice/room/day;
- a retried transaction (lost 200) is processed at most once (txn dedup).