From aa0e3f79b92df4125216e95436176585cd1b5232 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Iwo=20Strzebo=C5=84ski?= Date: Sun, 11 Oct 2026 16:58:57 +0000 Subject: [PATCH] Write down the backend <-> ai-worker contract `stream:camera_frames` and `channel:print_alerts` are the only interface between `continuum-backend` and `continuum-ai-worker`, and there was nothing specifying either. They had drifted completely: the backend wrote `farmId`, `printerId`, `r2ObjectKey` and `capturedAt`; the worker read a single field called `printer_id` and ignored the rest. Every task was delivered, acknowledged, and attributed to a printer called "unknown" - and nothing errored, because a stream entry is a flat string map and asking it for a field that is not there is not a failure. Same shape as the /ws/edge/v1 drift, found the same way. `schemas/continuum/v1/ai/` is now canonical, with a TypeBox mirror in ts-types and a Rust mirror in the worker. Two things the schemas have to say that JSON Schema does not naturally express, both of which caused real bugs: - A Valkey stream entry is a flat field/value map of *strings*. No nesting, no numbers, no null. So FrameTask has no numeric or nested properties, and a field with no value is omitted from the XADD rather than written as `""` - an empty string is a value, and the producer was writing one for `print_job_id`, which a consumer would carry into a lookup or a uuid column. - PrintAlert, by contrast, *is* a JSON document, because PUBLISH carries one opaque string. It is also fire-and-forget with no persistence, so it can only ever be a live-console feed and never the record of a detection. The README's layout section was stale (it still listed four DTOs that were removed in 2026-09) and did not mention `edge/` or `ai/` at all. It now names both, says why the inter-service protocols live here, and notes that their Rust mirrors sit in the single repo that consumes each rather than in `packages/rust-types`. Co-Authored-By: Claude Opus 5 --- README.md | 32 +++++-- packages/ts-types/src/schemas/ai.ts | 96 +++++++++++++++++++ packages/ts-types/src/schemas/index.ts | 5 + .../continuum/v1/ai/frame_task.schema.json | 43 +++++++++ .../continuum/v1/ai/print_alert.schema.json | 47 +++++++++ 5 files changed, 217 insertions(+), 6 deletions(-) create mode 100644 packages/ts-types/src/schemas/ai.ts create mode 100644 schemas/continuum/v1/ai/frame_task.schema.json create mode 100644 schemas/continuum/v1/ai/print_alert.schema.json diff --git a/README.md b/README.md index fab6148..925d86f 100644 --- a/README.md +++ b/README.md @@ -13,19 +13,39 @@ JSON Schema, compiled into two consumer packages: ## Layout ``` -schemas/continuum/v1/ Continuum's own domain model (PrintJob, Template, ...) +schemas/continuum/v1/ Continuum's own model + ai/ continuum-backend <-> continuum-ai-worker: the + stream:camera_frames work queue and the + channel:print_alerts notification channel + edge/ continuum-backend <-> continuum-proxy: the + /ws/edge/v1 gateway uplink protocol + material/ printer/ domain objects + vendor.schema.json schemas/bambulab/ Bambu Lab MQTT wire schemas (v1/v2, report + request) packages/ts-types/ TypeBox schemas (hand-written, mirrors schemas/) packages/rust-types/ serde structs (hand-written, mirrors schemas/) ``` +The two inter-service protocols - `edge/` and `ai/` - are here for a +specific reason: each has two independent implementations, one per repo, and +when there was nothing written down between them they drifted completely +while every test passed. `/ws/edge/v1` had an `auth` handshake the gateway +never sent; `stream:camera_frames` had a producer writing `printerId` and a +consumer reading `printer_id`, so every frame was attributed to a printer +called "unknown". Neither failure was visible from either side alone, which +is what a canonical schema plus a contract test on each end is for. + `schemas/continuum/v1/*.schema.json` is the canonical shape for each domain object; `packages/ts-types/src/schemas/` and -`packages/rust-types/src/lib.rs` both mirror it by hand. There are only -four small, stable DTOs here (`PrintJob`, `MaterialProfile`, -`PrintParameters`, `Template`), so keeping two hand-synced copies in sync -is less overhead than running a codegen pipeline (`protoc`/`ts-proto`/ -`prost-build`) nothing actually consumed - see git history for the +`packages/rust-types/src/lib.rs` both mirror it by hand. A mirror is added +per schema only once something actually consumes it, so not every file here +has one, and the two inter-service protocols keep their Rust mirror in the +single repo that consumes it rather than in `packages/rust-types`: +`edge/` in `continuum-proxy/src/uplink/protocol.rs`, `ai/` in +`continuum-ai-worker/src/task.rs`. The set is small and changes slowly, +which is why keeping hand-synced copies in sync is less overhead than a +codegen pipeline (`protoc`/`ts-proto`/`prost-build`) nothing actually +consumed - see git history for the protobuf version this replaced, and why it was dropped: every service in this system talks JSON (JSON Schema for the wire, TypeBox/serde for runtime validation), so protobuf's actual value - a single schema compiled diff --git a/packages/ts-types/src/schemas/ai.ts b/packages/ts-types/src/schemas/ai.ts new file mode 100644 index 0000000..780df1d --- /dev/null +++ b/packages/ts-types/src/schemas/ai.ts @@ -0,0 +1,96 @@ +import { Type, type Static } from "@sinclair/typebox"; + +/** + * The `stream:camera_frames` work queue and the `channel:print_alerts` + * notification channel, mirroring `schemas/continuum/v1/ai/*.schema.json` + * by hand - the JSON Schema files are canonical, and the Rust mirror lives + * in `continuum-ai-worker/src/task.rs`. + * + * These two are the only interface between `continuum-backend` and + * `continuum-ai-worker`. They are written down here because the previous + * arrangement - a producer and a consumer each naming their own fields, + * with nothing in between - produced exactly the drift it sounds like: the + * backend wrote `printerId` and the worker read `printer_id`, so every + * frame the worker ever handled was attributed to a printer called + * "unknown", and nothing failed. + */ + +/** + * One entry on `stream:camera_frames`. + * + * ## Every value is a string + * + * A Valkey stream entry is a flat field/value map of strings. There is no + * nesting and no numeric type, which is why `FrameTaskSchema` has no + * numbers and no nested objects - a producer that needs one has to encode + * it, and then both sides have to agree on the encoding, which is the thing + * this file exists to avoid. + * + * ## An absent field is absent + * + * `print_job_id` is omitted from the XADD when the frame belongs to no + * tracked job - not written as `""`. An empty string is a value: a consumer + * that passes it along ends up looking up job id `""`, and one that writes + * it to Postgres violates a uuid column. So the producer omits the field and + * the consumer treats absent and empty alike. + */ +export const FrameTaskSchema = Type.Object({ + /** `farms.id`. */ + farm_id: Type.String({ format: "uuid" }), + /** + * `printers.id` - the backend's UUID, already resolved from the gateway's + * own printer id, which means nothing outside its farm. + */ + printer_id: Type.String({ format: "uuid" }), + /** `print_jobs.id`, or omitted. Never `""`. */ + print_job_id: Type.Optional(Type.String({ format: "uuid" })), + /** Where the frame is in R2. The bytes are never in the stream. */ + r2_object_key: Type.String({ minLength: 1 }), + /** + * The gateway's clock, at capture - not enqueue time. A gateway that + * buffered frames through an uplink outage produces tasks whose + * `captured_at` is minutes old. + */ + captured_at: Type.String({ format: "date-time" }), +}); +export type FrameTask = Static; + +/** + * One message on `channel:print_alerts`, as JSON. + * + * Unlike a stream entry this one is a document, because PUBLISH carries a + * single opaque string. It is also fire-and-forget: an alert published with + * no subscriber is gone, so this channel is a live-console feed and not the + * record of a detection. + */ +export const PrintAlertSchema = Type.Object({ + printer_id: Type.String({ format: "uuid" }), + print_job_id: Type.Optional(Type.String({ format: "uuid" })), + /** + * Free string, not an enum: the label set belongs to the model file and + * changes without this schema changing. + */ + label: Type.String(), + /** + * The model's own score. Thresholding is the consumer's policy - an + * operator may well want to see near-misses. + */ + confidence: Type.Number({ minimum: 0, maximum: 1 }), + /** From the frame, so a console shows when the printer looked like this. */ + captured_at: Type.String({ format: "date-time" }), + /** So a console can show the picture, not just the label. */ + r2_object_key: Type.String(), +}); +export type PrintAlert = Static; + +/** The stream the tasks go on, and the group the worker reads as. */ +export const CAMERA_FRAMES_STREAM = "stream:camera_frames"; +export const AI_WORKER_CONSUMER_GROUP = "ai-worker"; +/** + * Where entries go that cannot be processed and must not be retried - a + * malformed task, or one that has been redelivered too many times. Separate + * from the main stream so a poison message cannot block the queue and + * cannot be lost silently either. + */ +export const CAMERA_FRAMES_DEAD_LETTER_STREAM = "stream:camera_frames:dead"; +export const PRINT_ALERTS_CHANNEL = "channel:print_alerts"; diff --git a/packages/ts-types/src/schemas/index.ts b/packages/ts-types/src/schemas/index.ts index 762ff6e..481c3ff 100644 --- a/packages/ts-types/src/schemas/index.ts +++ b/packages/ts-types/src/schemas/index.ts @@ -9,3 +9,8 @@ // a TypeBox mirror here, consumed by continuum-backend's edge WebSocket // route. Mirrors schemas/continuum/v1/edge/. export * from "./edge"; + +// The continuum-backend -> continuum-ai-worker interface: the +// stream:camera_frames work queue and the channel:print_alerts notification +// channel. Mirrors schemas/continuum/v1/ai/. +export * from "./ai"; diff --git a/schemas/continuum/v1/ai/frame_task.schema.json b/schemas/continuum/v1/ai/frame_task.schema.json new file mode 100644 index 0000000..783f103 --- /dev/null +++ b/schemas/continuum/v1/ai/frame_task.schema.json @@ -0,0 +1,43 @@ +{ + "$schema": "https://json-schema.org/draft/2020-12/schema", + "$id": "https://git.octoturge.com/Continuum/continuum-schemas/raw/branch/main/schemas/continuum/v1/ai/frame_task.schema.json", + "title": "FrameTask", + "description": "One camera still, handed from continuum-backend to continuum-ai-worker for print-failure scoring. Produced by XADD onto the stream named below; consumed by XREADGROUP.\n\nThis is a Valkey stream entry, not a JSON document: the wire form is a flat field/value map and EVERY value is a string. That is why there are no numeric or boolean properties here and why a field with no value is omitted from the XADD rather than written as an empty string - an empty string is a value, and a consumer that treats it as one ends up looking up the object key \"\".\n\nField names are snake_case, matching every other schema in this repository. The backend's HTTP routes are camelCase; this wire is not an HTTP route, and the consumer on the other end is serde-derived Rust.", + "x-stream": "stream:camera_frames", + "x-consumer-group": "ai-worker", + "type": "object", + "properties": { + "farm_id": { + "type": "string", + "format": "uuid", + "description": "`farms.id`. Carried so a consumer can attribute load and alerts per farm without a database round trip." + }, + "printer_id": { + "type": "string", + "format": "uuid", + "description": "`printers.id` - the backend's own UUID, already resolved from the gateway's printer id. NOT the gateway's `printers.toml` id, which means nothing outside its own farm." + }, + "print_job_id": { + "type": "string", + "format": "uuid", + "description": "`print_jobs.id`, when the frame belongs to a tracked job. Omitted entirely when it does not - a printer may be streaming while idle, or running something queued outside Continuum. Consumers must treat an absent key and an empty value alike, and must not fabricate a job id." + }, + "r2_object_key": { + "type": "string", + "minLength": 1, + "description": "Where the frame actually is, in the R2 bucket. The frame bytes are deliberately NOT in the stream: a stream entry is held in memory by the server and replayed to every consumer group, and a JPEG per printer per second would make the stream the largest thing in the deployment." + }, + "captured_at": { + "type": "string", + "format": "date-time", + "description": "When the camera took the frame, from the gateway's clock - not when the backend enqueued it. These can differ by a lot: a gateway buffers frames while its uplink is down, so a task may arrive minutes after the moment it describes." + } + }, + "required": [ + "farm_id", + "printer_id", + "r2_object_key", + "captured_at" + ], + "additionalProperties": false +} diff --git a/schemas/continuum/v1/ai/print_alert.schema.json b/schemas/continuum/v1/ai/print_alert.schema.json new file mode 100644 index 0000000..3486355 --- /dev/null +++ b/schemas/continuum/v1/ai/print_alert.schema.json @@ -0,0 +1,47 @@ +{ + "$schema": "https://json-schema.org/draft/2020-12/schema", + "$id": "https://git.octoturge.com/Continuum/continuum-schemas/raw/branch/main/schemas/continuum/v1/ai/print_alert.schema.json", + "title": "PrintAlert", + "description": "A print-failure detection, published by continuum-ai-worker for live operator consoles.\n\nUnlike FrameTask this one IS a JSON document: it travels as the payload of a Valkey PUBLISH, which carries a single opaque string, so the structure has to be inside it.\n\nPUBLISH is fire-and-forget with no persistence and no delivery guarantee: an alert published while nothing is subscribed is gone. That is acceptable for the live-console path it feeds and is NOT acceptable as the record of a detection, which belongs in Postgres. As of 2026-10-11 nothing subscribes to this channel and nothing persists it - see the README section on the AI path.", + "x-channel": "channel:print_alerts", + "type": "object", + "properties": { + "printer_id": { + "type": "string", + "format": "uuid", + "description": "`printers.id`, taken from the frame task that produced the detection." + }, + "print_job_id": { + "type": "string", + "format": "uuid", + "description": "Omitted when the frame was not attributed to a tracked job." + }, + "label": { + "type": "string", + "description": "What the model thinks it saw, e.g. \"spaghetti\", \"layer_shift\", \"detachment\". A free string rather than an enum on purpose: the label set is a property of the model file, which changes without this schema changing." + }, + "confidence": { + "type": "number", + "minimum": 0, + "maximum": 1, + "description": "The model's own score. Whether it is high enough to act on is the consumer's policy decision, not the worker's - the worker publishes what it found and does not threshold on behalf of an operator who may want to see near-misses." + }, + "captured_at": { + "type": "string", + "format": "date-time", + "description": "From the frame, not from the detection. An operator needs to know when the printer looked like this, not when a GPU got round to looking." + }, + "r2_object_key": { + "type": "string", + "description": "The frame the detection came from, so a console can show the operator the picture rather than only a label." + } + }, + "required": [ + "printer_id", + "label", + "confidence", + "captured_at", + "r2_object_key" + ], + "additionalProperties": false +}