Add continuum-schema-instance: build JSON instances from a JSON Schema

The Rust equivalent of json-schema-faker, scoped to what's actually
useful in Rust: resolves $ref (relative to whichever file references
it)/allOf, fills const/enum/default, and builds a value only for
properties listed in required - everything else is left out. For code
that has to construct a raw serde_json::Value against a schema it
doesn't own, instead of a typed struct.

Verified against continuum-schemas' real bambulab schemas manually, and
against local fixtures in tests (round-tripped through the jsonschema
crate to confirm the output actually validates).

README.md

@@ -6,5 +6,6 @@ Shared, dependency-light building blocks used across the Continuum cloud and edg
 
 - **`packages/ts-core`** - TypeScript package consumed by `continuum-backend` (and other Bun/Node services). Provides a structured logger, a Supabase JWT verification helper, and ElysiaJS-compatible HTTP error transformers.
 - **`packages/rust-core`** - Rust crate consumed by `continuum-proxy` and `continuum-ai-worker`. Provides a shared `thiserror`-based error type, `tracing` initialization, and G-code checksum/header parsing helpers.
+- **`packages/rust-schema-instance`** - Rust crate consumed by `continuum-proxy` and `continuum-ai-worker`. Builds a `serde_json::Value` instance from a JSON Schema file (resolves `$ref`/`allOf`, fills `const`/`enum`/`default`, only builds `required` properties) - for code that has to construct a raw JSON message against some other system's schema instead of a typed struct.
 
 Each package is versioned and published independently; see their own READMEs (inline doc comments) for usage.

packages/rust-schema-instance/Cargo.toml

@@ -0,0 +1,12 @@
+[package]
+name = "continuum-schema-instance"
+version = "0.1.0"
+edition = "2021"
+description = "Builds a JSON instance from a JSON Schema - fills const/enum/default, only builds required properties, everything else is left out"
+
+[dependencies]
+serde_json = "1"
+thiserror = "1.0"
+
+[dev-dependencies]
+jsonschema = "0.53.0"

packages/rust-schema-instance/src/lib.rs

@@ -0,0 +1,268 @@
+//! Builds a `serde_json::Value` instance from a JSON Schema file - the
+//! Rust equivalent of what `json-schema-faker` is used for in JS/TS,
+//! adapted to what's actually useful in Rust: this crate doesn't invent
+//! random data for you (a typed struct already forces you to supply every
+//! field it requires at compile time - there's nothing left for a faker
+//! to do there). It's for code that has to build a raw `serde_json::Value`
+//! against a schema it doesn't own - some other system's wire format -
+//! instead of a typed struct: fill in the one or two fields you actually
+//! have a value for, and let this fill in everything else the schema
+//! already determines on its own.
+//!
+//! What it does, walking a schema node:
+//! - `$ref` - loads the referenced file, resolved relative to the
+//!   directory of whichever file is doing the referencing (so a chain of
+//!   refs across several files each resolves against its own location,
+//!   not the original caller's). Only whole-file refs are supported - a
+//!   `#/json/pointer` fragment is an error, not silently ignored.
+//! - `allOf` - merges every branch's `properties`/`required` into one
+//!   combined object schema before building it. Branches are resolved
+//!   (following their own `$ref`s) before merging, but a merged
+//!   property's *own* schema is then built relative to the outermost
+//!   file's directory, not the branch it came from - harmless for every
+//!   schema in this project today (no property schema anywhere uses
+//!   `$ref`), but worth knowing if you add one that does.
+//! - `oneOf`/`anyOf` - deterministically picks the *first* listed
+//!   variant. If you need a specific one, point at that variant's own
+//!   schema file directly instead of the dispatcher.
+//! - `const` / `enum` / `default` - used as-is (enum takes its first
+//!   value).
+//! - `object` - builds a value **only** for properties listed in
+//!   `required`; anything not required is left out of the result
+//!   entirely. This is the "skip the rest" behavior - equivalent to
+//!   `json-schema-faker`'s `alwaysFakeOptionals: false` (its default).
+//! - `array` - builds `minItems` copies of `items` (zero if unset).
+//! - anything else - a simple placeholder for the declared `type`
+//!   (respecting `minLength`/`minimum` where trivial), so the result is
+//!   always schema-shaped even before you fill in the fields you actually
+//!   care about.
+//!
+//! Typical use: build the skeleton, then set the one or two fields you
+//! actually have a value for with plain `serde_json::Value` indexing -
+//! there's no separate "overrides" API here, because `value["field"] =
+//! json!(...)` already does that job in one line:
+//!
+//! ```no_run
+//! # use std::path::Path;
+//! # use serde_json::json;
+//! let mut message = continuum_schema_instance::build_instance_from_file(
+//!     Path::new("schemas/some_event.schema.json"),
+//! ).unwrap();
+//! message["some_field"] = json!("some value");
+//! ```
+
+use std::path::{Path, PathBuf};
+
+use serde_json::Value;
+
+/// Guards against a `$ref` cycle (or just a schema nested deeper than any
+/// real one here goes) turning into infinite recursion.
+const MAX_DEPTH: usize = 64;
+
+#[derive(Debug, thiserror::Error)]
+pub enum BuildError {
+    #[error("failed to read schema file {0}: {1}")]
+    Io(PathBuf, #[source] std::io::Error),
+    #[error("failed to parse schema file {0}: {1}")]
+    Json(PathBuf, #[source] serde_json::Error),
+    #[error("invalid schema: {0}")]
+    InvalidSchema(String),
+    #[error("schema nested too deep (possible $ref cycle)")]
+    TooDeep,
+    #[error("schema is `false` - always fails validation, nothing to build")]
+    AlwaysInvalid,
+}
+
+/// Loads `path` as a JSON Schema and builds an instance of it. `$ref`s
+/// inside it resolve relative to `path`'s own directory.
+pub fn build_instance_from_file(path: &Path) -> Result<Value, BuildError> {
+    let schema = load_schema_file(path)?;
+    let base_dir = path.parent().unwrap_or_else(|| Path::new("."));
+    build(&schema, base_dir, 0)
+}
+
+/// Same as [`build_instance_from_file`], but for a schema you've already
+/// parsed - `base_dir` is where any `$ref` inside it resolves from.
+pub fn build_instance(schema: &Value, base_dir: &Path) -> Result<Value, BuildError> {
+    build(schema, base_dir, 0)
+}
+
+fn build(schema: &Value, base_dir: &Path, depth: usize) -> Result<Value, BuildError> {
+    if depth > MAX_DEPTH {
+        return Err(BuildError::TooDeep);
+    }
+    let depth = depth + 1;
+
+    if let Some(allowed) = schema.as_bool() {
+        return if allowed { Ok(Value::Null) } else { Err(BuildError::AlwaysInvalid) };
+    }
+    let obj = schema
+        .as_object()
+        .ok_or_else(|| BuildError::InvalidSchema("a schema must be a JSON object or boolean".into()))?;
+
+    if let Some(r) = obj.get("$ref").and_then(Value::as_str) {
+        let (resolved, new_base) = load_ref(r, base_dir)?;
+        return build(&resolved, &new_base, depth);
+    }
+
+    if let Some(branches) = obj.get("allOf").and_then(Value::as_array) {
+        let merged = merge_all_of(branches, base_dir, depth)?;
+        return build(&merged, base_dir, depth);
+    }
+
+    if let Some(variants) =
+        obj.get("oneOf").and_then(Value::as_array).or_else(|| obj.get("anyOf").and_then(Value::as_array))
+    {
+        let first =
+            variants.first().ok_or_else(|| BuildError::InvalidSchema("oneOf/anyOf with no variants".into()))?;
+        return build(first, base_dir, depth);
+    }
+
+    if let Some(c) = obj.get("const") {
+        return Ok(c.clone());
+    }
+
+    if let Some(values) = obj.get("enum").and_then(Value::as_array) {
+        return values.first().cloned().ok_or_else(|| BuildError::InvalidSchema("enum with no values".into()));
+    }
+
+    if let Some(d) = obj.get("default") {
+        return Ok(d.clone());
+    }
+
+    let ty = obj.get("type").and_then(Value::as_str);
+
+    if ty == Some("object") || obj.contains_key("properties") {
+        return build_object(obj, base_dir, depth);
+    }
+
+    if ty == Some("array") {
+        return build_array(obj, base_dir, depth);
+    }
+
+    Ok(placeholder_for_type(ty, obj))
+}
+
+/// Builds a value only for properties listed in `required` - everything
+/// else in `properties` is left out entirely.
+fn build_object(
+    obj: &serde_json::Map<String, Value>,
+    base_dir: &Path,
+    depth: usize,
+) -> Result<Value, BuildError> {
+    let properties = obj.get("properties").and_then(Value::as_object);
+    let required = obj.get("required").and_then(Value::as_array);
+
+    let mut result = serde_json::Map::new();
+    if let Some(required) = required {
+        for name in required {
+            let Some(name) = name.as_str() else { continue };
+            let prop_schema = properties.and_then(|p| p.get(name)).ok_or_else(|| {
+                BuildError::InvalidSchema(format!("'{name}' is required but has no schema in properties"))
+            })?;
+            result.insert(name.to_string(), build(prop_schema, base_dir, depth)?);
+        }
+    }
+    Ok(Value::Object(result))
+}
+
+fn build_array(obj: &serde_json::Map<String, Value>, base_dir: &Path, depth: usize) -> Result<Value, BuildError> {
+    let Some(items_schema) = obj.get("items") else {
+        return Ok(Value::Array(Vec::new()));
+    };
+    let min_items = obj.get("minItems").and_then(Value::as_u64).unwrap_or(0);
+
+    let mut items = Vec::new();
+    for _ in 0..min_items {
+        items.push(build(items_schema, base_dir, depth)?);
+    }
+    Ok(Value::Array(items))
+}
+
+/// A schema with no `const`/`enum`/`default` still needs *something*
+/// there if it's required - the simplest value satisfying its declared
+/// type (and, where trivial, `minLength`/`minimum`).
+fn placeholder_for_type(ty: Option<&str>, obj: &serde_json::Map<String, Value>) -> Value {
+    match ty {
+        Some("string") => {
+            let min_length = obj.get("minLength").and_then(Value::as_u64).unwrap_or(0) as usize;
+            Value::String("x".repeat(min_length))
+        }
+        Some("integer") => Value::from(obj.get("minimum").and_then(Value::as_i64).unwrap_or(0)),
+        Some("number") => Value::from(obj.get("minimum").and_then(Value::as_f64).unwrap_or(0.0)),
+        Some("boolean") => Value::Bool(false),
+        _ => Value::Null,
+    }
+}
+
+/// Resolves each `allOf` branch (following its own `$ref`/nested `allOf`)
+/// down to a plain object schema, then unions their `properties` (later
+/// branches win on a key clash) and `required` (deduplicated) into one
+/// combined object schema.
+fn merge_all_of(branches: &[Value], base_dir: &Path, depth: usize) -> Result<Value, BuildError> {
+    if depth > MAX_DEPTH {
+        return Err(BuildError::TooDeep);
+    }
+
+    let mut properties = serde_json::Map::new();
+    let mut required: Vec<Value> = Vec::new();
+
+    for branch in branches {
+        let resolved = resolve_schema_object(branch, base_dir, depth + 1)?;
+        if let Some(props) = resolved.get("properties").and_then(Value::as_object) {
+            for (k, v) in props {
+                properties.insert(k.clone(), v.clone());
+            }
+        }
+        if let Some(req) = resolved.get("required").and_then(Value::as_array) {
+            for r in req {
+                if !required.contains(r) {
+                    required.push(r.clone());
+                }
+            }
+        }
+    }
+
+    Ok(serde_json::json!({ "type": "object", "properties": properties, "required": required }))
+}
+
+/// Follows `$ref`/`allOf` (without building anything yet) until it lands
+/// on a plain object schema - the schema-level equivalent of `build`,
+/// used only while merging `allOf` branches.
+fn resolve_schema_object(schema: &Value, base_dir: &Path, depth: usize) -> Result<Value, BuildError> {
+    if depth > MAX_DEPTH {
+        return Err(BuildError::TooDeep);
+    }
+    let obj = schema
+        .as_object()
+        .ok_or_else(|| BuildError::InvalidSchema("an allOf branch must be a JSON object schema".into()))?;
+
+    if let Some(r) = obj.get("$ref").and_then(Value::as_str) {
+        let (resolved, new_base) = load_ref(r, base_dir)?;
+        return resolve_schema_object(&resolved, &new_base, depth + 1);
+    }
+    if let Some(branches) = obj.get("allOf").and_then(Value::as_array) {
+        return merge_all_of(branches, base_dir, depth + 1);
+    }
+    Ok(schema.clone())
+}
+
+fn load_ref(r: &str, base_dir: &Path) -> Result<(Value, PathBuf), BuildError> {
+    if let Some(fragment) = r.split('#').nth(1) {
+        if !fragment.is_empty() {
+            return Err(BuildError::InvalidSchema(format!(
+                "'{r}' - in-document JSON Pointer refs aren't supported, only whole-file refs"
+            )));
+        }
+    }
+    let file_part = r.split('#').next().unwrap_or(r);
+    let target = base_dir.join(file_part);
+    let schema = load_schema_file(&target)?;
+    let new_base = target.parent().map(Path::to_path_buf).unwrap_or_else(|| PathBuf::from("."));
+    Ok((schema, new_base))
+}
+
+fn load_schema_file(path: &Path) -> Result<Value, BuildError> {
+    let text = std::fs::read_to_string(path).map_err(|err| BuildError::Io(path.to_path_buf(), err))?;
+    serde_json::from_str(&text).map_err(|err| BuildError::Json(path.to_path_buf(), err))
+}

packages/rust-schema-instance/tests/build_test.rs

@@ -0,0 +1,64 @@
+use std::path::PathBuf;
+
+use continuum_schema_instance::build_instance_from_file;
+use serde_json::json;
+
+fn fixture(relative: &str) -> PathBuf {
+    PathBuf::from(env!("CARGO_MANIFEST_DIR")).join("tests/fixtures").join(relative)
+}
+
+/// Validates `instance` against the real schema file - closes the loop:
+/// this confirms the builder's output is actually accepted by a real JSON
+/// Schema validator (the `jsonschema` crate), not just "looks right".
+fn assert_valid(schema_path: &PathBuf, instance: &serde_json::Value) {
+    let schema_text = std::fs::read_to_string(schema_path).unwrap();
+    let mut schema: serde_json::Value = serde_json::from_str(&schema_text).unwrap();
+    // These fixtures have no `$id` (real schemas in continuum-schemas do,
+    // as an absolute https:// URL) - the `jsonschema` crate resolves a
+    // relative `$ref` against the schema's own `$id`, so give it one
+    // pointing at this file's real location for the relative `$ref`s
+    // inside to resolve from during this check.
+    let absolute_path = schema_path.canonicalize().unwrap();
+    schema["$id"] = json!(format!("file://{}", absolute_path.display()));
+
+    let validator = jsonschema::validator_for(&schema).expect("schema itself should compile");
+    let errors: Vec<_> = validator.iter_errors(instance).collect();
+    assert!(errors.is_empty(), "instance {instance} did not validate: {errors:?}");
+}
+
+#[test]
+fn required_fields_are_filled_and_optional_fields_are_left_out() {
+    let path = fixture("events/item_created.schema.json");
+    let mut instance = build_instance_from_file(&path).unwrap();
+
+    // "type" has no const at the envelope level, but item_created's own
+    // allOf branch overrides it to one - that const wins.
+    assert_eq!(instance["type"], json!("item_created"));
+    // "event_id"/"item_id" are required with no const - each gets a
+    // placeholder, ready to be overridden.
+    assert!(instance.get("event_id").is_some());
+    assert!(instance.get("item_id").is_some());
+    // "note" is optional and correctly left out entirely.
+    assert_eq!(instance.as_object().unwrap().len(), 3);
+
+    assert_valid(&path, &instance);
+
+    // The one field the caller actually has a value for - plain
+    // serde_json::Value indexing, no special "overrides" API needed.
+    instance["item_id"] = json!("item-42");
+    assert_valid(&path, &instance);
+}
+
+#[test]
+fn allof_merge_lets_a_later_branch_override_an_earlier_ones_property() {
+    let path = fixture("events/item_deleted.schema.json");
+    let instance = build_instance_from_file(&path).unwrap();
+
+    // "type" is defined twice across the allOf: a plain string in the
+    // shared envelope, then overridden to `const: "item_deleted"` in this
+    // event's own branch - the later branch has to win.
+    assert_eq!(instance["type"], json!("item_deleted"));
+    assert_eq!(instance.as_object().unwrap().len(), 2); // event_id, type
+
+    assert_valid(&path, &instance);
+}

packages/rust-schema-instance/tests/fixtures/common/envelope.schema.json

@@ -0,0 +1,11 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "title": "EventEnvelope",
+  "type": "object",
+  "properties": {
+    "event_id": { "type": "string" },
+    "type": { "type": "string" },
+    "note": { "type": "string" }
+  },
+  "required": ["event_id", "type"]
+}

packages/rust-schema-instance/tests/fixtures/events/item_created.schema.json

@@ -0,0 +1,15 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "title": "ItemCreatedEvent",
+  "allOf": [
+    { "$ref": "../common/envelope.schema.json" },
+    {
+      "type": "object",
+      "properties": {
+        "type": { "const": "item_created" },
+        "item_id": { "type": "string" }
+      },
+      "required": ["item_id"]
+    }
+  ]
+}

packages/rust-schema-instance/tests/fixtures/events/item_deleted.schema.json

@@ -0,0 +1,13 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "title": "ItemDeletedEvent",
+  "allOf": [
+    { "$ref": "../common/envelope.schema.json" },
+    {
+      "type": "object",
+      "properties": {
+        "type": { "const": "item_deleted" }
+      }
+    }
+  ]
+}