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
|
|
|
|
/**
|
|
|
|
|
|
* MCP tool definitions for the knowledge-base package.
|
|
|
|
|
|
*
|
|
|
|
|
|
* Exports a factory so callers can inject the KnowledgeBaseClient
|
|
|
|
|
|
* (production: BedrockKnowledgeBaseClient; tests: mock).
|
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
|
|
import { defineTool, requireScope } from '@sh-mcp/shared';
|
|
|
|
|
|
import type { AuthContext, ToolDef } from '@sh-mcp/shared';
|
|
|
|
|
|
import type { KnowledgeBaseClient } from './client.js';
|
|
|
|
|
|
|
|
|
|
|
|
// ---------------------------------------------------------------------------
|
|
|
|
|
|
// Input / output types
|
|
|
|
|
|
// ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
export interface SearchKnowledgeBaseInput {
|
|
|
|
|
|
/** Natural-language question or keyword query. */
|
|
|
|
|
|
query: string;
|
|
|
|
|
|
/**
|
|
|
|
|
|
* Maximum number of passages to return (1–20).
|
|
|
|
|
|
* Defaults to 5 when omitted.
|
|
|
|
|
|
*/
|
|
|
|
|
|
maxResults?: number;
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
export interface SearchKnowledgeBaseResultItem {
|
|
|
|
|
|
/** Source document reference (S3 URI, Notion page title, etc.). */
|
|
|
|
|
|
source: string;
|
|
|
|
|
|
/** Relevance score in [0, 1]. */
|
|
|
|
|
|
score: number;
|
|
|
|
|
|
/** Relevant text passage. */
|
|
|
|
|
|
passage: string;
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
export interface SearchKnowledgeBaseOutput {
|
|
|
|
|
|
/** Ordered list of matching passages, most relevant first. */
|
|
|
|
|
|
results: SearchKnowledgeBaseResultItem[];
|
|
|
|
|
|
/** Total number of results returned. */
|
|
|
|
|
|
count: number;
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
// ---------------------------------------------------------------------------
|
|
|
|
|
|
// Tool factory
|
|
|
|
|
|
// ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
|
* Build the knowledge-base tools array with the supplied client injected.
|
|
|
|
|
|
*
|
|
|
|
|
|
* Production usage:
|
|
|
|
|
|
* import { createBedrockClientFromEnv } from './client.js';
|
|
|
|
|
|
* const tools = createKnowledgeBaseTools(createBedrockClientFromEnv());
|
|
|
|
|
|
*
|
|
|
|
|
|
* Test usage:
|
|
|
|
|
|
* const tools = createKnowledgeBaseTools(mockClient);
|
|
|
|
|
|
*/
|
|
|
|
|
|
export function createKnowledgeBaseTools(
|
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
|
|
|
|
client: KnowledgeBaseClient,
|
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
|
|
|
|
): ToolDef<SearchKnowledgeBaseInput, SearchKnowledgeBaseOutput>[] {
|
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
|
|
|
|
const searchKnowledgeBase = defineTool<SearchKnowledgeBaseInput, SearchKnowledgeBaseOutput>({
|
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
|
|
|
|
name: 'search_knowledge_base',
|
|
|
|
|
|
description:
|
|
|
|
|
|
'Search the Sea Haven internal knowledge base for relevant information. ' +
|
|
|
|
|
|
'The knowledge base is populated from Notion pages, purchase-order records, ' +
|
|
|
|
|
|
'and work-order records. Use this tool to answer questions about company ' +
|
|
|
|
|
|
'procedures, vendor details, site information, or historical work orders.',
|
|
|
|
|
|
tier: 'ops',
|
|
|
|
|
|
requiredScope: 'ops:read',
|
|
|
|
|
|
inputSchema: {
|
|
|
|
|
|
type: 'object',
|
|
|
|
|
|
properties: {
|
|
|
|
|
|
query: {
|
|
|
|
|
|
type: 'string',
|
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
|
|
|
|
description: 'Natural-language question or keyword search query.',
|
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
|
|
|
|
minLength: 1,
|
|
|
|
|
|
maxLength: 1000,
|
|
|
|
|
|
},
|
|
|
|
|
|
maxResults: {
|
|
|
|
|
|
type: 'integer',
|
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
|
|
|
|
description: 'Maximum number of passages to return (1–20). Defaults to 5.',
|
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
|
|
|
|
minimum: 1,
|
|
|
|
|
|
maximum: 20,
|
|
|
|
|
|
default: 5,
|
|
|
|
|
|
},
|
|
|
|
|
|
},
|
|
|
|
|
|
required: ['query'],
|
|
|
|
|
|
additionalProperties: false,
|
|
|
|
|
|
},
|
|
|
|
|
|
|
|
|
|
|
|
async handler(
|
|
|
|
|
|
input: SearchKnowledgeBaseInput,
|
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
|
|
|
|
ctx: AuthContext,
|
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
|
|
|
|
): Promise<SearchKnowledgeBaseOutput> {
|
|
|
|
|
|
// Server-side scope enforcement — never rely solely on UI tool-hiding.
|
|
|
|
|
|
requireScope(ctx, 'ops:read');
|
|
|
|
|
|
|
|
|
|
|
|
// NOTE: This is an ops-tier tool. The output contains knowledge-base
|
|
|
|
|
|
// passages (not finance data), so redact() is not called here.
|
|
|
|
|
|
// Finance-tier tools in other packages MUST call redact() on sensitive fields.
|
|
|
|
|
|
|
|
|
|
|
|
const results = await client.retrieve({
|
|
|
|
|
|
query: input.query,
|
|
|
|
|
|
maxResults: input.maxResults ?? 5,
|
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
|
|
return {
|
|
|
|
|
|
results: results.map((r) => ({
|
|
|
|
|
|
source: r.source,
|
|
|
|
|
|
score: r.score,
|
|
|
|
|
|
passage: r.passage,
|
|
|
|
|
|
})),
|
|
|
|
|
|
count: results.length,
|
|
|
|
|
|
};
|
|
|
|
|
|
},
|
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
|
|
return [searchKnowledgeBase];
|
|
|
|
|
|
}
|