@united-workforce/cli 0.1.0

package/src/validate-semantic.ts

@@ -0,0 +1,304 @@
+import type { WorkflowPayload } from "@united-workforce/protocol";
+
+type SchemaObj = Record<string, unknown>;
+
+const RESERVED_NAMES = new Set(["$START", "$END", "$SUSPEND"]);
+const PSEUDO_TARGETS = new Set(["$END", "$SUSPEND"]);
+
+/** Extract mustache variable names from a prompt string. */
+function extractMustacheVars(prompt: string): string[] {
+  const vars: string[] = [];
+  const re = /\{\{\{?([^}]+)\}\}\}?/g;
+  let m: RegExpExecArray | null = re.exec(prompt);
+  while (m !== null) {
+    vars.push(m[1]);
+    m = re.exec(prompt);
+  }
+  return vars;
+}
+
+/** Check if a frontmatter schema is a oneOf (multi-exit) type. */
+function isOneOfSchema(fm: unknown): fm is SchemaObj & { oneOf: SchemaObj[] } {
+  if (typeof fm !== "object" || fm === null) return false;
+  const obj = fm as SchemaObj;
+  return Array.isArray(obj.oneOf);
+}
+
+/** Check if a frontmatter schema declares "$status" as an enum (the required form for user roles). */
+function hasStatusEnum(fm: unknown): boolean {
+  if (typeof fm !== "object" || fm === null) return false;
+  const obj = fm as SchemaObj;
+  const props = obj.properties as Record<string, SchemaObj> | undefined;
+  if (!props?.$status) return false;
+  return Array.isArray(props.$status.enum);
+}
+
+/** Extract status values from an enum-based $status field. */
+function getEnumStatuses(fm: SchemaObj): string[] {
+  const props = fm.properties as Record<string, SchemaObj> | undefined;
+  if (!props?.$status) return [];
+  const statusDef = props.$status;
+  if (!Array.isArray(statusDef.enum)) return [];
+  return statusDef.enum as string[];
+}
+
+/** Get property names from a schema object. */
+function getPropertyNames(schema: SchemaObj): Set<string> {
+  const props = schema.properties;
+  if (typeof props !== "object" || props === null) return new Set();
+  return new Set(Object.keys(props as Record<string, unknown>));
+}
+
+/** Extract $status const values from oneOf variants. */
+function getOneOfStatuses(variants: SchemaObj[]): string[] {
+  const statuses: string[] = [];
+  for (const variant of variants) {
+    const props = variant.properties as Record<string, SchemaObj> | undefined;
+    if (props?.$status) {
+      const statusDef = props.$status;
+      if (typeof statusDef.const === "string") {
+        statuses.push(statusDef.const);
+      }
+    }
+  }
+  return statuses;
+}
+
+/** Check reserved names and role/graph reference integrity. */
+function checkRoleReferences(payload: WorkflowPayload, errors: string[]): void {
+  const roleNames = new Set(Object.keys(payload.roles));
+  const graphNodes = new Set(Object.keys(payload.graph));
+
+  for (const name of roleNames) {
+    if (RESERVED_NAMES.has(name)) {
+      errors.push(`reserved name "${name}" must not appear in roles`);
+    }
+  }
+
+  for (const node of graphNodes) {
+    if (!RESERVED_NAMES.has(node) && !roleNames.has(node)) {
+      errors.push(`graph references unknown role "${node}"`);
+    }
+  }
+
+  for (const name of roleNames) {
+    if (RESERVED_NAMES.has(name)) continue;
+    if (!graphNodes.has(name)) {
+      errors.push(`role "${name}" is defined but not referenced in graph`);
+    }
+  }
+}
+
+/** Check $START/$END constraints, edge targets, and reachability. */
+function checkGraphStructure(payload: WorkflowPayload, errors: string[]): void {
+  const roleNames = new Set(Object.keys(payload.roles));
+  const graphNodes = new Set(Object.keys(payload.graph));
+
+  if (!graphNodes.has("$START")) {
+    errors.push("$START must be defined in graph");
+  } else {
+    const startKeys = Object.keys(payload.graph.$START);
+    if (startKeys.length !== 1 || startKeys[0] !== "_") {
+      errors.push('$START must have exactly one edge with status "_"');
+    }
+  }
+
+  if (graphNodes.has("$END")) {
+    errors.push("$END must not have outgoing edges");
+  }
+
+  if (graphNodes.has("$SUSPEND")) {
+    errors.push("$SUSPEND must not have outgoing edges");
+  }
+
+  for (const [node, statusMap] of Object.entries(payload.graph)) {
+    for (const [status, target] of Object.entries(statusMap)) {
+      if (!PSEUDO_TARGETS.has(target.role) && !roleNames.has(target.role)) {
+        errors.push(`edge ${node}→${status}: unknown target role "${target.role}"`);
+      }
+    }
+  }
+
+  checkReachability(roleNames, collectReachableRoles(payload.graph), errors);
+}
+
+/** BFS to collect all roles reachable from $START. */
+function collectReachableRoles(graph: WorkflowPayload["graph"]): Set<string> {
+  const reachable = new Set<string>();
+  const startEdges = graph.$START;
+  if (!startEdges) return reachable;
+
+  const queue: string[] = [];
+  for (const target of Object.values(startEdges)) {
+    if (!PSEUDO_TARGETS.has(target.role) && !reachable.has(target.role)) {
+      reachable.add(target.role);
+      queue.push(target.role);
+    }
+  }
+
+  while (queue.length > 0) {
+    const current = queue.shift() as string;
+    const edges = graph[current];
+    if (!edges) continue;
+    for (const target of Object.values(edges)) {
+      if (!PSEUDO_TARGETS.has(target.role) && !reachable.has(target.role)) {
+        reachable.add(target.role);
+        queue.push(target.role);
+      }
+    }
+  }
+
+  return reachable;
+}
+
+/** Check that all defined roles are reachable from $START. */
+function checkReachability(roleNames: Set<string>, reachable: Set<string>, errors: string[]): void {
+  for (const name of roleNames) {
+    if (RESERVED_NAMES.has(name)) continue;
+    if (!reachable.has(name)) {
+      errors.push(`role "${name}" is not reachable from $START`);
+    }
+  }
+}
+
+/** Check oneOf discriminant validity for a role. */
+function checkOneOfDiscriminant(
+  roleName: string,
+  variants: SchemaObj[],
+  statuses: string[],
+  errors: string[],
+): void {
+  if (statuses.length === variants.length) return;
+
+  let foundMissing = false;
+  for (const variant of variants) {
+    const props = variant.properties as Record<string, SchemaObj> | undefined;
+    if (!props?.$status) {
+      errors.push(`role "${roleName}": oneOf variants must have "$status" as const discriminant`);
+      foundMissing = true;
+      break;
+    }
+    if (typeof props.$status.const !== "string") {
+      errors.push(`role "${roleName}": oneOf variant $status must be a const value`);
+      foundMissing = true;
+      break;
+    }
+  }
+
+  if (!foundMissing) {
+    errors.push(`role "${roleName}": oneOf variant $status must be a const value`);
+  }
+}
+
+/** Check status-edge consistency for a user role. "_" is reserved for $START and rejected here. */
+function checkStatusEdges(
+  roleName: string,
+  graphKeys: Set<string>,
+  statusSet: Set<string>,
+  errors: string[],
+): void {
+  if (graphKeys.has("_")) {
+    errors.push(`role "${roleName}" must use explicit $status keys in graph, not "_"`);
+    return;
+  }
+  if (statusSet.has("_")) {
+    errors.push(`role "${roleName}" $status enum must use explicit values, not "_"`);
+    return;
+  }
+
+  const extraKeys = [...graphKeys].filter((k) => !statusSet.has(k));
+  const missingKeys = [...statusSet].filter((k) => !graphKeys.has(k));
+  if (extraKeys.length > 0) {
+    errors.push(`role "${roleName}" graph has extra status keys: ${extraKeys.join(", ")}`);
+  }
+  if (missingKeys.length > 0) {
+    errors.push(`role "${roleName}" graph is missing status keys: ${missingKeys.join(", ")}`);
+  }
+}
+
+/** Check mustache variables for multi-exit role. */
+function checkMultiExitMustache(
+  roleName: string,
+  graphEntry: Record<string, { role: string; prompt: string }>,
+  variants: SchemaObj[],
+  errors: string[],
+): void {
+  for (const [status, target] of Object.entries(graphEntry)) {
+    const vars = extractMustacheVars(target.prompt);
+    const variant = variants.find((v) => {
+      const props = v.properties as Record<string, SchemaObj> | undefined;
+      return props?.$status?.const === status;
+    });
+    if (!variant) continue;
+    const propNames = getPropertyNames(variant);
+    for (const v of vars) {
+      if (v === "$status") continue;
+      if (!propNames.has(v)) {
+        errors.push(`prompt variable "${v}" not found in role "${roleName}" variant "${status}"`);
+      }
+    }
+  }
+}
+
+/** Check status-edge consistency and mustache for each role. */
+function checkRoleConsistency(payload: WorkflowPayload, errors: string[]): void {
+  for (const [roleName, role] of Object.entries(payload.roles)) {
+    if (RESERVED_NAMES.has(roleName)) continue;
+    const graphEntry = payload.graph[roleName];
+    if (!graphEntry) continue;
+
+    const fm = role.frontmatter as unknown;
+    const graphKeys = new Set(Object.keys(graphEntry));
+
+    if (isOneOfSchema(fm)) {
+      const variants = fm.oneOf as SchemaObj[];
+      const statuses = getOneOfStatuses(variants);
+
+      checkOneOfDiscriminant(roleName, variants, statuses, errors);
+      checkStatusEdges(roleName, graphKeys, new Set(statuses), errors);
+      checkMultiExitMustache(roleName, graphEntry, variants, errors);
+    } else if (hasStatusEnum(fm)) {
+      const statuses = getEnumStatuses(fm as SchemaObj);
+      checkStatusEdges(roleName, graphKeys, new Set(statuses), errors);
+      // For enum-based schemas, mustache vars come from the flat properties
+      checkEnumMustache(roleName, graphEntry, fm as SchemaObj, errors);
+    } else {
+      errors.push(
+        `role "${roleName}" must define "$status" as an enum (or oneOf const) in frontmatter`,
+      );
+    }
+  }
+}
+
+/** Check mustache vars in all edge prompts against flat schema properties. */
+function checkEnumMustache(
+  roleName: string,
+  graphEntry: Record<string, { role: string; prompt: string }>,
+  fm: SchemaObj,
+  errors: string[],
+): void {
+  const propNames = getPropertyNames(fm);
+  for (const [status, target] of Object.entries(graphEntry)) {
+    const vars = extractMustacheVars(target.prompt);
+    for (const v of vars) {
+      if (v === "$status") continue;
+      if (!propNames.has(v)) {
+        errors.push(
+          `prompt variable "${v}" in graph[${roleName}][${status}] not found in role "${roleName}" frontmatter`,
+        );
+      }
+    }
+  }
+}
+
+/**
+ * Validate a parsed WorkflowPayload for semantic correctness.
+ * Returns an array of error messages. Empty array = valid.
+ */
+export function validateWorkflow(payload: WorkflowPayload): string[] {
+  const errors: string[] = [];
+  checkRoleReferences(payload, errors);
+  checkGraphStructure(payload, errors);
+  checkRoleConsistency(payload, errors);
+  return errors;
+}

package/src/validate.ts

@@ -0,0 +1,137 @@
+import { basename, dirname } from "node:path";
+import type { CasRef, WorkflowPayload } from "@united-workforce/protocol";
+
+const CAS_REF_PATTERN = /^[0-9A-HJKMNP-TV-Z]{13}$/;
+
+export function isCasRef(value: string): value is CasRef {
+  return CAS_REF_PATTERN.test(value);
+}
+
+function isRecord(value: unknown): value is Record<string, unknown> {
+  return typeof value === "object" && value !== null && !Array.isArray(value);
+}
+
+function isRoleDefinition(value: unknown): boolean {
+  if (!isRecord(value)) {
+    return false;
+  }
+  const frontmatter = value.frontmatter;
+  const frontmatterOk =
+    isRecord(frontmatter) &&
+    (typeof frontmatter.type === "string" || Array.isArray(frontmatter.oneOf));
+  const capabilities = value.capabilities;
+  const capabilitiesOk =
+    Array.isArray(capabilities) && capabilities.every((c) => typeof c === "string");
+  return (
+    typeof value.description === "string" &&
+    typeof value.goal === "string" &&
+    capabilitiesOk &&
+    typeof value.procedure === "string" &&
+    typeof value.output === "string" &&
+    frontmatterOk
+  );
+}
+
+function isTarget(value: unknown): boolean {
+  if (!isRecord(value)) {
+    return false;
+  }
+  const hasValidLocation =
+    value.location === undefined || value.location === null || typeof value.location === "string";
+  return (
+    typeof value.role === "string" &&
+    typeof value.prompt === "string" &&
+    value.prompt.trim() !== "" &&
+    hasValidLocation
+  );
+}
+
+function isStringRecord(value: unknown, itemCheck: (item: unknown) => boolean): boolean {
+  if (!isRecord(value)) {
+    return false;
+  }
+  return Object.values(value).every(itemCheck);
+}
+
+function isGraph(value: unknown): boolean {
+  if (!isRecord(value)) {
+    return false;
+  }
+  return Object.entries(value).every(([node, statusMap]) => {
+    if (!isRecord(statusMap)) {
+      return false;
+    }
+    return Object.entries(statusMap).every(([status, target]) => {
+      // "_" is only valid as a status key for the $START entry node.
+      if (status === "_" && node !== "$START") {
+        return false;
+      }
+      return isTarget(target);
+    });
+  });
+}
+
+/**
+ * Derive the expected workflow name from a file path (stem without extension).
+ * Returns the stem for `.yaml` / `.yml` files.
+ */
+export function workflowNameFromPath(filePath: string): string {
+  const base = basename(filePath);
+  const stem = base.endsWith(".yaml")
+    ? base.slice(0, -5)
+    : base.endsWith(".yml")
+      ? base.slice(0, -4)
+      : base;
+  if (stem === "index") {
+    return basename(dirname(filePath));
+  }
+  return stem;
+}
+
+/**
+ * Check that the `name` field in a parsed payload matches the expected name
+ * derived from the file path.  Returns an error message string on mismatch,
+ * or null when the names are consistent.
+ */
+export function checkWorkflowFilenameConsistency(
+  filePath: string,
+  payload: WorkflowPayload,
+): string | null {
+  const expected = workflowNameFromPath(filePath);
+  if (payload.name !== expected) {
+    return `workflow name mismatch: file "${basename(filePath)}" implies name "${expected}" but YAML declares name "${payload.name}"`;
+  }
+  return null;
+}
+
+/** Validate YAML-parsed workflow document shape (outputSchema may be inline JSON Schema). */
+// biome-ignore lint/complexity/noExcessiveCognitiveComplexity: validation function with many field checks
+export function parseWorkflowPayload(raw: unknown): WorkflowPayload | null {
+  if (!isRecord(raw)) {
+    return null;
+  }
+  if (typeof raw.name !== "string" || typeof raw.description !== "string") {
+    return null;
+  }
+  if (!isStringRecord(raw.roles, isRoleDefinition) || !isGraph(raw.graph)) {
+    return null;
+  }
+
+  // Normalize location field: undefined → null
+  const normalized = { ...raw } as WorkflowPayload;
+  for (const roleName of Object.keys(normalized.graph)) {
+    const statusMap = normalized.graph[roleName];
+    if (statusMap !== undefined) {
+      for (const status of Object.keys(statusMap)) {
+        const target = statusMap[status];
+        if (target !== undefined) {
+          if (target.location === undefined) {
+            target.location = null;
+          }
+        }
+      }
+    }
+  }
+
+  return normalized;
+}