fix(tool-cordis): gate façade services on inject, and make tools.get read-only

Two review findings (#220) on the sandbox context façade:

- Undeclared services were reachable: the façade resolved any live global via
  ctx.get(name), so ctx.bash worked without inject: ['bash']. A cross-mount
  consumer could then depend on a provider cordis never saw — unmounting the
  provider would neither park the consumer nor unwind its registered tools,
  leaving a model-visible tool that fails only at execution. The façade now
  reads ctx.fiber.inject and refuses any service the mount did not declare
  (with a teaching error naming the inject fix), so the dependency is always
  visible to cordis and its activation/unload semantics bind.

- ctx.tools.get returned the live ToolDefinition, including execute — mount
  code could call another tool directly and bypass ToolRegistry.execute and
  its pre/post-execute hooks and accounting. get now returns the same
  read-only name/description/parameters view as schemas(), never an invocable.

Adds inject-gate and schema-view regression cases to sandbox-context.spec.ts
(undeclared property/get denied, declared allowed, the cross-mount zombie-tool
scenario refused at call time, get exposes no execute). Package stays at
per-file 100% coverage. RFC, mount description, and tool-catalog updated.
This commit is contained in:
imccyu
2026-07-09 12:44:57 +08:00
parent 1b1ba96d4f
commit 3e9527278a
6 changed files with 207 additions and 32 deletions

View File

@@ -185,15 +185,19 @@ export function sandboxRegisterTool(ctx: Context, tool: unknown): () => void {
const CTX_VERBS = new Set(['on', 'once', 'provide', 'timeout', 'interval', 'setTimeout', 'setInterval', 'throttle', 'debounce'])
/**
* The tool-registry façade: only `register` (marker-guarded), plus the
* read-only `schemas` / `get` a mount may legitimately want. No other registry
* method (nothing that could re-enter the raw context) is exposed.
* The tool-registry façade: `register` (marker-guarded) plus READ-ONLY
* metadata (`schemas`, and `get` returning a schema view, never the live
* `ToolDefinition`). Exposing the raw definition would hand mount code the
* tool's `execute` function, letting it call another tool directly and bypass
* `ToolRegistry.execute` — the pre/post-execute waterfall (permission gates,
* accounting) and result normalization. So `get` returns the same
* name/description/parameters view as `schemas()`, and nothing invocable.
*/
function sandboxTools(ctx: Context): Record<string, unknown> {
return {
register: (tool: unknown): (() => void) => sandboxRegisterTool(ctx, tool),
schemas: () => ctx.tools.schemas(),
get: (name: string) => ctx.tools.get(name),
get: (name: string) => ctx.tools.schemas().find(schema => schema.name === name),
}
}
@@ -233,53 +237,85 @@ function guardedService(service: object, name: string): unknown {
})
}
/**
* The service names a plugin declared in `inject`, as a lookup set. Whatever
* declaration style the plugin used — an `inject: ['bash', 'tools']` array or
* the `{ required, optional }` object form — cordis resolves it into a single
* name-keyed map on the fiber before `apply` runs (`{ bash: null, tools: null }`),
* so the gate just reads that map's keys. A mount may reach only the services
* it declared — that is what lets cordis park the mount when a declared
* provider unmounts.
*/
function declaredInjects(ctx: Context): Set<string> {
return new Set(Object.keys(ctx.fiber.inject))
}
/**
* The sandbox context façade handed to a mounted plugin's `apply` in place of
* the real `ctx`. A whitelist (see the module doc): the registration/eventing
* verbs, the timer helpers, a guarded `tools`, and injected services resolved
* through a guarded `get` / property access. Every framework-plumbing member
* is denied with a teaching error; there is no context-valued member to reach.
* through a guarded `get` / property access. A service is reachable only if the
* plugin DECLARED it in `inject` — an undeclared service is denied even when a
* global provider exists, so cordis's activation/unload semantics (park the
* mount when a declared provider goes away) actually bind. Every
* framework-plumbing member is denied with a teaching error; there is no
* context-valued member to reach.
*/
function sandboxContext(ctx: Context): Context {
const tools = sandboxTools(ctx)
// Resolve a named service to a guarded wrapper, or undefined when absent.
const resolveService = (name: string): unknown => {
if (name === 'tools') return tools
const service: unknown = ctx.get(name)
return service === undefined ? undefined : guardedService(service as object, name)
const declared = declaredInjects(ctx)
// A framework member or an undeclared service — distinguish the two so the
// error teaches the right fix (declare it in inject vs it is withheld).
const denyRead = (prop: string): never => {
if (ctx.get(prop) !== undefined) {
throw new Error(
`service "${prop}" is not injected. Declare it: inject: ['${prop}', …] on your plugin, `
+ 'so cordis parks this mount if the provider is later unmounted.',
)
}
throw new Error(
`sandbox ctx does not expose "${prop}". Available: ctx.tools.register / ctx.on / ctx.provide / `
+ 'the timer helpers (ctx.setTimeout, ctx.interval, …) and any service you declared in inject. '
+ 'Framework internals (root, fiber, registry, extend, plugin, …) are withheld by design.',
)
}
const get = (name: string): unknown => resolveService(name)
// Read a service for either access path (property or `get`). `tools` is the
// façade's own surface. An UNDECLARED name is denied with the teaching
// error; a DECLARED one resolves to the guarded service. A declared inject
// is required in cordis (the fiber only activates once every declared
// service is live), so at `apply`/`execute` time `ctx.get(name)` is present
// for a declared name — no undefined case to handle here.
const readService = (name: string): unknown => {
if (name === 'tools') return tools
if (!declared.has(name)) return denyRead(name)
return guardedService(ctx.get(name) as object, name)
}
const get = (name: string): unknown => readService(name)
return new Proxy({}, {
get(_target, prop) {
if (prop === 'tools') return tools
if (prop === 'get') return get
if (typeof prop !== 'string') return undefined
// Lazy verb forwarder — reads `ctx[verb]` only when called, so a plugin
// that never uses a timer never triggers the timer mixin's inject check.
// that never uses a timer never triggers the timer mixin's inject check
// (cordis raises its own "without inject" error there for undeclared timer use).
if (CTX_VERBS.has(prop)) {
return (...args: unknown[]): unknown => {
const method = ctx[prop as keyof Context]
return Reflect.apply(method as (...a: unknown[]) => unknown, ctx, args)
}
}
// A declared-and-injected service reads as a ctx property; resolve it
// through the same guard. Absent → the deny path (framework plumbing,
// an un-injected service, or a typo) with one teaching error.
const service = resolveService(prop)
if (service !== undefined) return service
throw new Error(
`sandbox ctx does not expose "${prop}". Available: ctx.tools.register / ctx.on / ctx.provide / `
+ 'the timer helpers (ctx.setTimeout, ctx.interval, …) and any service you declared in inject. '
+ 'Framework internals (root, fiber, registry, extend, plugin, …) are withheld by design.',
)
return readService(prop)
},
// A façade is not the real ctx; block writes rather than let mount code
// stash state on a throwaway object and think it persisted.
set(_target, prop) {
throw new Error(`sandbox ctx is read-only; cannot assign "${String(prop)}"`)
},
// `in` reflects reachability: the façade surface plus DECLARED services
// (whether or not currently live). Does not resolve/wrap — no throw.
has: (_target, prop) => prop === 'tools' || prop === 'get'
|| (typeof prop === 'string' && (CTX_VERBS.has(prop) || resolveService(prop) !== undefined)),
|| (typeof prop === 'string' && (CTX_VERBS.has(prop) || declared.has(prop))),
}) as unknown as Context
}

View File

@@ -125,12 +125,14 @@ export function apply(ctx: Context, config: Config): void {
'Mount a NEW cordis plugin into the live runtime that is running THIS agent '
+ '(self-modification). `code` runs as the body of an async JavaScript function '
+ 'in an isolated sandbox and MUST `return` a plugin. Two forms: '
+ 'FUNCTION form `return (ctx) => { … }` — cannot declare inject, uses whatever '
+ 'services are on the parent context, and accessing a service without inject '
+ '(e.g. ctx.bash) throws; use it only when you need no injected services. '
+ 'FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register '
+ 'tools, listen to events, and provide services, but reaching ANY service (e.g. '
+ 'ctx.bash) throws; use it only when you need no services. '
+ 'OBJECT form `return { name?, inject: [\'bash\', \'llm\', …], apply(ctx) { … } }` '
+ '— declares dependencies, and cordis activates the plugin only after the '
+ 'services exist; PREFER this form for any plugin that needs bash, llm, sessions, etc. '
+ 'services exist; PREFER this form. You may reach ONLY the services you list in '
+ 'inject: an undeclared service throws even if it exists, because an undeclared '
+ 'dependency would not be cleaned up if its provider is unmounted. '
+ 'BEFORE calling a service from your code, read cordis_inspect what:"api" — it lists '
+ 'method signatures AND the type shapes of their arguments/returns (do not guess a '
+ 'field\'s type; e.g. a bash run\'s stdout is an object, not a string). '

View File

@@ -220,8 +220,6 @@ describe('cordis_mount', () => {
return {
name: 'raw-register-get',
apply(ctx) {
const sp = ctx.get('systemPrompt')
console.log('systemPrompt is', typeof sp)
ctx.get('tools').register({ name: 'raw_via_get', description: 'raw', parameters: {}, async execute() { return [] } })
},
}

View File

@@ -154,3 +154,142 @@ describe('sandbox context façade — escape surface is closed', () => {
expect(result.isError).toBe(false)
})
})
describe('sandbox context façade — inject gate on services', () => {
it('denies an undeclared live service (property access), naming the inject fix', async () => {
// `systemPrompt` is a live global service in the setup harness, but this
// mount does not declare it — reaching it would let the mount depend on a
// provider cordis does not know about, so it is refused.
const ctx = await setup()
const result = await call(ctx, 'cordis_mount', {
code: 'return { name: \'undeclared\', inject: [\'tools\'], apply(ctx) { const s = ctx.systemPrompt } }',
})
expect(result.isError).toBe(true)
expect(text(result)).toContain('service "systemPrompt" is not injected')
expect(text(result)).toContain('inject: [\'systemPrompt\', …]')
})
it('denies an undeclared live service reached through ctx.get too', async () => {
const ctx = await setup()
const result = await call(ctx, 'cordis_mount', {
code: 'return { name: \'undeclared-get\', inject: [\'tools\'], apply(ctx) { ctx.get(\'systemPrompt\') } }',
})
expect(result.isError).toBe(true)
expect(text(result)).toContain('service "systemPrompt" is not injected')
})
it('allows a service the mount DID declare in inject', async () => {
const ctx = await setup()
const result = await call(ctx, 'cordis_mount', {
code: `
return {
name: 'declared',
inject: ['systemPrompt', 'tools'],
apply(ctx) { console.log('has systemPrompt:', typeof ctx.systemPrompt) }
}
`,
})
expect(result.isError).toBe(false)
expect(text(result)).toContain('state: active')
})
it('a cross-mount consumer must declare the provider — the undeclared path is refused, not left as a zombie tool', async () => {
// The finding's scenario: a consumer registers a tool built on a provider's
// service WITHOUT declaring inject. cordis would then never park the
// consumer when the provider unmounts, leaving a tool that fails only at
// execution. The gate refuses the undeclared access up front, so the
// dependency is always visible to cordis.
const ctx = await setup()
await call(ctx, 'cordis_mount', {
code: 'return { name: \'greeter-provider\', apply(ctx) { ctx.provide(\'greeter\', { greet: (n) => \'hi \' + n }) } }',
})
const undeclared = await call(ctx, 'cordis_mount', {
code: `
return {
name: 'sloppy-consumer',
inject: ['tools'],
apply(ctx) {
harness.registerTool(ctx, harness.defineTool({
name: 'greet_undeclared',
description: 'uses greeter without declaring it',
parameters: { n: { type: 'string', required: true } },
async execute(args) { return [{ type: 'text', text: ctx.greeter.greet(args.n) }] },
}))
},
}
`,
})
// The tool registers (its execute is lazy), but calling it hits the gate:
// `ctx.greeter` is undeclared, so it fails with the teaching error rather
// than silently working and later stranding.
expect(undeclared.isError).toBe(false)
const called = await call(ctx, 'greet_undeclared', { n: 'x' })
expect(called.isError).toBe(true)
expect(text(called)).toContain('service "greeter" is not injected')
})
})
describe('sandbox tools façade — get is a read-only schema view', () => {
it('ctx.tools.get returns a schema, not the live ToolDefinition with execute', async () => {
// The finding: returning the raw ToolDefinition hands mount code the
// tool's execute function, letting it bypass ToolRegistry.execute (and its
// pre/post hooks). get now returns the same name/description/parameters
// view as schemas(), with no execute. Asserted via a self-made tool that
// reports the shape it saw — world-checked, not self-reported.
const ctx = await setup()
await call(ctx, 'cordis_mount', {
code: `
return {
name: 'reporter',
inject: ['tools'],
apply(ctx) {
harness.registerTool(ctx, harness.defineTool({
name: 'report_view',
description: 'reports the shape of a tool view',
parameters: {},
async execute() {
const view = ctx.tools.get('cordis_mount')
return [{ type: 'text', text: JSON.stringify({
hasExecute: 'execute' in view,
hasPresentCall: 'presentCall' in view,
name: view.name,
keys: Object.keys(view).sort(),
}) }]
},
}))
},
}
`,
})
const reported = await call(ctx, 'report_view', {})
expect(reported.isError).toBe(false)
const shape = JSON.parse(text(reported)) as { hasExecute: boolean; hasPresentCall: boolean; name: string; keys: string[] }
expect(shape.hasExecute).toBe(false)
expect(shape.hasPresentCall).toBe(false)
expect(shape.name).toBe('cordis_mount')
expect(shape.keys).toEqual(['description', 'name', 'parameters'])
})
it('ctx.tools.get returns undefined for an unknown tool', async () => {
const ctx = await setup()
await call(ctx, 'cordis_mount', {
code: `
return {
name: 'unknown-probe',
inject: ['tools'],
apply(ctx) {
harness.registerTool(ctx, harness.defineTool({
name: 'probe_unknown',
description: 'reports whether an unknown tool resolves',
parameters: {},
async execute() {
return [{ type: 'text', text: String(ctx.tools.get('no_such_tool') === undefined) }]
},
}))
},
}
`,
})
expect(text(await call(ctx, 'probe_unknown', {}))).toBe('true')
})
})