sh-mcp/packages/internal-data/src/tools.ts

226 lines
6.4 KiB
TypeScript
Raw Normal View History

Phase 0b slice: monorepo scaffold + @sh-mcp/shared core + integration packages (#2) * Phase 0b slice: monorepo scaffold + shared core + integration packages The 0a-INDEPENDENT code slice (one-shot via af-0b-package-slice workflow: Haiku scaffold + Sonnet packages, Sonnet fix-to-green). Nothing deploys; no CDK/servers. - Monorepo scaffold: npm workspaces, strict TS (NodeNext), vitest (80% gate), eslint 9 flat config, prettier; ci.yaml/deploy.yaml callers (Node 24, enable-qemu). - @sh-mcp/shared: transport-agnostic core — Scope/AuthContext/ToolDef, ToolRegistry, redact()+maskValue() (PII), OpenAPI 3.1 generator. AUTH STUBBED behind an AuthProvider interface (TODO auth-layer-0a); JWT/aud/client_id/JWKS/deny-list deferred per design.md §2. - 9 integration packages (qbo, google-maps, internal-data, payments, knowledge-base, gmail, calendar, tasks, reminders): tools against shared, external deps mocked behind injected client interfaces; finance handlers call redact(). Verified green: tsc -b clean, vitest 245/245, eslint 0 errors. Auth mechanism intentionally deferred until the 0a spike resolves it (G16/§0.4). * Complete Cognito auth provider + Phase 1 build brief Finish the WIP CognitoAuthProvider (client_id allow-list as audience boundary, finance TTL ceiling, deny-list, scope-prefix stripping) with its test suite, and check in docs/build-plan-phase-1.md so the Phase 1 work has its governing brief in-tree (design.md §2.5). * ci: disable cdk synth for Phase 0b (no CDK app yet) The reusable ci-typescript-cdk workflow defaults run-cdk-synth: true, but the Phase 0b package scaffold has no cdk.json or stacks, so cdk synth fails with '--app is required'. Disable it here; Phase 1 re-enables it with the server CDK stubs.
2026-06-26 12:42:17 -04:00
/**
* Tool definitions for the internal-data package.
*
* Three read-only ops-tier tools backed by the injected InternalDataClient:
* - lookup_work_order
* - lookup_purchase_order
* - lookup_site
*
* All three require the `ops:read` scope (§3 of design.md).
*
* Finance-tier note: these tools are ops-tier, so `redact()` is not called on
* their responses. If a future refactor moves payment or financial amounts here,
* call redact() on those fields per the design requirement that finance handlers
* MUST redact sensitive output.
*
* The client is passed in at server startup (not imported from a module-level
* singleton) so that tests can inject a mock without AWS credentials.
*/
import { defineTool, requireScope } from '@sh-mcp/shared';
import type { AuthContext } from '@sh-mcp/shared';
import type { InternalDataClient } from './client.js';
// ---------------------------------------------------------------------------
// Input / output types
// ---------------------------------------------------------------------------
export interface LookupWorkOrderInput {
workOrderId: string;
}
export interface LookupWorkOrderOutput {
found: boolean;
workOrder?: {
workOrderId: string;
title: string;
status: string;
siteId?: string;
assignedTo?: string;
createdAt: string;
updatedAt: string;
description?: string;
};
}
export interface LookupPurchaseOrderInput {
purchaseOrderId: string;
}
export interface LookupPurchaseOrderOutput {
found: boolean;
purchaseOrder?: {
purchaseOrderId: string;
vendor: string;
status: string;
totalAmount?: number;
currency?: string;
issuedAt: string;
updatedAt: string;
lineItems?: Array<{ description: string; quantity: number; unitPrice: number }>;
};
}
export interface LookupSiteInput {
siteId: string;
}
export interface LookupSiteOutput {
found: boolean;
site?: {
siteId: string;
name: string;
address?: string;
region?: string;
status: string;
assignedTechnicians?: string[];
};
}
// ---------------------------------------------------------------------------
// Tool factories — call makeTools(client) once at server startup
// ---------------------------------------------------------------------------
export function makeTools(client: InternalDataClient) {
const lookupWorkOrder = defineTool<LookupWorkOrderInput, LookupWorkOrderOutput>({
name: 'lookup_work_order',
description:
'Retrieve a Sea Haven work order by its ID. Returns current status, assigned site, ' +
'assigned technician, and description. Returns found=false when the ID does not exist.',
tier: 'ops',
requiredScope: 'ops:read',
inputSchema: {
type: 'object',
required: ['workOrderId'],
additionalProperties: false,
properties: {
workOrderId: {
type: 'string',
description: 'The unique work-order identifier (e.g. WO-20240101-001).',
minLength: 1,
maxLength: 128,
},
},
},
handler: async (
input: LookupWorkOrderInput,
ctx: AuthContext,
): Promise<LookupWorkOrderOutput> => {
requireScope(ctx, 'ops:read');
const record = await client.getWorkOrder(input.workOrderId);
if (record === null) {
return { found: false };
}
return {
found: true,
workOrder: {
workOrderId: record.workOrderId,
title: record.title,
status: record.status,
siteId: record.siteId,
assignedTo: record.assignedTo,
createdAt: record.createdAt,
updatedAt: record.updatedAt,
description: record.description,
},
};
},
});
const lookupPurchaseOrder = defineTool<LookupPurchaseOrderInput, LookupPurchaseOrderOutput>({
name: 'lookup_purchase_order',
description:
'Retrieve a Sea Haven purchase order by its ID. Returns vendor name, status, total amount, ' +
'and line items. Returns found=false when the ID does not exist.',
tier: 'ops',
requiredScope: 'ops:read',
inputSchema: {
type: 'object',
required: ['purchaseOrderId'],
additionalProperties: false,
properties: {
purchaseOrderId: {
type: 'string',
description: 'The unique purchase-order identifier (e.g. PO-2024-00123).',
minLength: 1,
maxLength: 128,
},
},
},
handler: async (
input: LookupPurchaseOrderInput,
ctx: AuthContext,
): Promise<LookupPurchaseOrderOutput> => {
requireScope(ctx, 'ops:read');
const record = await client.getPurchaseOrder(input.purchaseOrderId);
if (record === null) {
return { found: false };
}
return {
found: true,
purchaseOrder: {
purchaseOrderId: record.purchaseOrderId,
vendor: record.vendor,
status: record.status,
totalAmount: record.totalAmount,
currency: record.currency,
issuedAt: record.issuedAt,
updatedAt: record.updatedAt,
lineItems: record.lineItems,
},
};
},
});
const lookupSite = defineTool<LookupSiteInput, LookupSiteOutput>({
name: 'lookup_site',
description:
'Retrieve a Sea Haven site assignment record by its ID. Returns site name, address, ' +
'region, status, and assigned technicians. Returns found=false when the ID does not exist.',
tier: 'ops',
requiredScope: 'ops:read',
inputSchema: {
type: 'object',
required: ['siteId'],
additionalProperties: false,
properties: {
siteId: {
type: 'string',
description: 'The unique site identifier (e.g. SITE-NYC-001).',
minLength: 1,
maxLength: 128,
},
},
},
Phase 1: runnable MCP + OpenAPI servers (ops + finance) (#3) * Add shared transport: dispatch, MCP + OpenAPI adapters, local auth Add the single authoritative tool-execution path (executeTool) plus the two universal interfaces over it (design.md §2.5, §7.3): - dispatch.ts: scope enforcement, ajv input validation, rate limiting, finance egress redaction (redactDeep), and structured audit emission on one path. - audit.ts / rate-limit.ts: injected AuditLogger + RateLimiter abstractions. - mcp.ts: low-level MCP Server with scope-filtered tools/list (tool-hiding) and tools/call routed through executeTool. - http.ts: Express host mounting /mcp, /openapi.json, POST /tools/:name, /healthz. - openapi.ts: buildOpenApiDocument wraps the existing path generator into a full OpenAPI 3.1 document. - local-auth.ts: LocalAuthProvider (dev bearer tokens) that refuses to construct outside SH_MCP_ENV=local and enforces audience binding (design.md §3, §6). * Add in-memory dev clients; make package tool exports lazy Add an in-memory Client implementation per integration package (seeded fake data, no network) selected when SH_MCP_ENV=local (build-plan §4). Gmail/calendar/ tasks dev clients partition by ctx.sub; payments/qbo seed sensitive-looking fields so the redaction egress path has real targets to mask. Make the eager default-tool exports in tasks/reminders/qbo LAZY (getDefaultTools) so importing a package barrel no longer constructs an AWS client at module load (build-plan §7 'no I/O at import time') — the previous eager construction broke server startup. Fix payments tsconfig rootDir (src, was '.') so its declarations resolve under dist/index.d.ts like the other 8 packages. * Add runnable sh-mcp-ops and sh-mcp-finance servers Two thin composition-root servers over the shared transport (design.md §3): - ops: internal-data, knowledge-base, google-maps, gmail, calendar, tasks, reminders. finance: qbo, payments (audited + redacted on egress). - config from env only (no hardcoded ids/issuer/tables); SH_MCP_ENV selects LocalAuthProvider + dev clients (local) vs CognitoAuthProvider + real stubs (aws). Finance applies the 15-min finance-token TTL ceiling (design.md §2.5). - index.ts is the only place .listen() is called; a Lambda handler placeholder is exported but not depended on. - synth-only CDK stubs (no real IAM/Cognito/WAF) so 'cdk synth' has a valid app (build-plan §6); READMEs document local run, dev tokens, curl, MCP Inspector. * Add security-weighted test suite + coverage gate; wire tooling Add tests for the highest-risk surface (build-plan §5, design.md §7.3): tool-hiding, server-side scope enforcement (incl. forced hidden calls), audience binding, input-schema validation, finance redaction on egress, audit emission with hashed args, prompt-injection regression (tool output is data), rate limiting, MCP conformance (in-memory transport round-trip), OpenAPI 3.1 validity, and local-auth safety. Add HTTP integration tests (supertest) for both servers and per-package dev-client tests. 405 tests pass. Wire the coverage gate into vitest.config.ts: 80% overall, with per-file thresholds on the auth + dispatch crown jewels; exclude deferred real client stubs, entrypoints, cdk apps, and aws-only config from the gate (documented). Extend eslint flat config + add .prettierignore to cover servers/. Commit the updated package-lock.json. * Suppress pre-existing dev-tooling + out-of-scope scanner findings Add written-justification suppressions for the 4 confirmed crit/high pre-push scanner findings, none of which are in this PR's Phase 1 production code: - npmaudit vitest / @vitest/coverage-v8 / vite: dev/test-only deps that never run in the deployed server/Lambda runtime (pins carried from Phase 0b; Dependabot will bump). - gitleaks docs/agentforce-plan.md secret: that file is not on this branch and not in this changeset; flagged for the maintainer to scrub on its own branch. The deep agentic /sh-security-review (required for this auth/authz-touching PR) was NOT run by the agent and is flagged outstanding in the PR body. * Address CodeQL findings: bound ajv error work + edge rate limiting GHAS code-scanning alerts on this PR: - dispatch.ts (js/resource-exhaustion): ajv ran with allErrors:true on untrusted input, letting a crafted payload force unbounded error enumeration. Switch to allErrors:false (default) so validation short-circuits on the first failure; the 400 still names that path. - http.ts (js/missing-rate-limiting): the authenticated routes (/mcp, /tools/:name) had no edge throttle — auth/JWT verification ran on every request before the per-sub dispatch limiter could apply. Add an IP-keyed express-rate-limit in front of authenticate (120/60s default, configurable), returning the standard 429 shape. Defense-in-depth over the per-sub + per-tool limiter in executeTool; API GW/WAF remains the production edge. Tests: +2 cases proving the edge limiter throttles before auth (429, not 401) on /tools and /mcp. 407 pass; tsc/eslint/prettier clean. * Fix polynomial ReDoS in Bearer-token extraction (CodeQL js/polynomial-redos) extractBearerToken matched /^Bearer\s+(.+)$/ — \s and . both match a space, so the two quantifiers overlap and a crafted header can drive polynomial backtracking. Require the capture to start with a non-whitespace char (/^Bearer\s+(\S.*)$/), removing the ambiguity → linear match. Behavior is unchanged for real tokens; +2 regression tests. * Harden auth + finance redaction (sh-security-review confirmed mediums) Two confirmed medium findings from the agentic security review: - Fail-open SH_MCP_ENV: config defaulted to 'local' when the var was unset, so a deploy that forgot SH_MCP_ENV=aws would silently run LocalAuthProvider and accept static dev bearer tokens (dev-finance-admin -> finance:admin). Now fail-closed: SH_MCP_ENV must be explicitly 'local' or 'aws' or the server refuses to start. Plus an independent guard in LocalAuthProvider that refuses to construct in an AWS runtime (AWS_LAMBDA_FUNCTION_NAME / AWS_EXECUTION_ENV present), regardless of the env flag. - Finance egress redaction gap: redactDeep only wholesale-masked a sensitive key when its value was a scalar; an object/array under a sensitive key was recursed into, letting a bare nested value (e.g. {account:{number:...}}) escape the keyword-gated pattern matcher. Now the entire subtree under a sensitive key is masked. No current finance tool emitted such shapes (all flat strings), so this closes a latent hole in the universal safety net. +4 tests (subtree redaction, AWS-runtime guard). 411 pass; coverage gate green. Review also produced lows (memo free-text digits, unsalted argsHash, unauth /openapi.json by-design, session-cap no-reset by-design) tracked separately; 0 confirmed critical/high — review verdict PASS.
2026-06-26 13:33:21 -04:00
handler: async (input: LookupSiteInput, ctx: AuthContext): Promise<LookupSiteOutput> => {
Phase 0b slice: monorepo scaffold + @sh-mcp/shared core + integration packages (#2) * Phase 0b slice: monorepo scaffold + shared core + integration packages The 0a-INDEPENDENT code slice (one-shot via af-0b-package-slice workflow: Haiku scaffold + Sonnet packages, Sonnet fix-to-green). Nothing deploys; no CDK/servers. - Monorepo scaffold: npm workspaces, strict TS (NodeNext), vitest (80% gate), eslint 9 flat config, prettier; ci.yaml/deploy.yaml callers (Node 24, enable-qemu). - @sh-mcp/shared: transport-agnostic core — Scope/AuthContext/ToolDef, ToolRegistry, redact()+maskValue() (PII), OpenAPI 3.1 generator. AUTH STUBBED behind an AuthProvider interface (TODO auth-layer-0a); JWT/aud/client_id/JWKS/deny-list deferred per design.md §2. - 9 integration packages (qbo, google-maps, internal-data, payments, knowledge-base, gmail, calendar, tasks, reminders): tools against shared, external deps mocked behind injected client interfaces; finance handlers call redact(). Verified green: tsc -b clean, vitest 245/245, eslint 0 errors. Auth mechanism intentionally deferred until the 0a spike resolves it (G16/§0.4). * Complete Cognito auth provider + Phase 1 build brief Finish the WIP CognitoAuthProvider (client_id allow-list as audience boundary, finance TTL ceiling, deny-list, scope-prefix stripping) with its test suite, and check in docs/build-plan-phase-1.md so the Phase 1 work has its governing brief in-tree (design.md §2.5). * ci: disable cdk synth for Phase 0b (no CDK app yet) The reusable ci-typescript-cdk workflow defaults run-cdk-synth: true, but the Phase 0b package scaffold has no cdk.json or stacks, so cdk synth fails with '--app is required'. Disable it here; Phase 1 re-enables it with the server CDK stubs.
2026-06-26 12:42:17 -04:00
requireScope(ctx, 'ops:read');
const record = await client.getSite(input.siteId);
if (record === null) {
return { found: false };
}
return {
found: true,
site: {
siteId: record.siteId,
name: record.name,
address: record.address,
region: record.region,
status: record.status,
assignedTechnicians: record.assignedTechnicians,
},
};
},
});
return [lookupWorkOrder, lookupPurchaseOrder, lookupSite] as const;
}