From 3d16026eb04a93022336052a6d43923df0d3b05e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 9 Jul 2026 01:09:21 +0800 Subject: [PATCH] feat(core): scope-aware registries and session dispatch carriers dsh-tools and dsh-system-prompt gain a per-scope registration layer over dsh-scope: a registration through a scoped context files into that scope, shadows a same-named global contribution for that scope (per-agent persona and tool variants), and unwinds with the scope. tools.restrict() masks the global surface per scope (snapshot-at-registration, loud unknown-name validation, intersection composition; scoped grants bypass). One visibility function feeds schemas/get/execute, so prompt, presentation, and dispatch can never disagree; out-of-view executes as UNKNOWN_TOOL. Prompt tool providers now receive the AssembleContext and return {schemas, knownNames}: toolOrder validates against the pre-restriction name universe (a typo fails every assembly loudly) while ordering operates on the post-restriction schemas (a restricted-away tool is a normal absence). dsh-session captures each session's dispatch carrier at enter() from the entering context's scope tag, and the new sessions.flush(session) owns the awaited session/flush dispatch. tools/pre|post-execute and system-prompt/assemble dispatch with scope carriers keyed by their subject; session/created|event|flush by the owning session's scope. --- .../core/agent-loop/tests/tool-order.spec.ts | 2 +- packages/core/session/package.json | 2 + packages/core/session/src/index.ts | 78 +++++- packages/core/session/tests/scoped.spec.ts | 112 ++++++++ packages/core/session/tsconfig.json | 3 + packages/core/system-prompt/package.json | 2 + packages/core/system-prompt/src/index.ts | 246 +++++++++++++----- .../core/system-prompt/tests/scoped.spec.ts | 138 ++++++++++ .../system-prompt/tests/system-prompt.spec.ts | 16 +- .../system-prompt/tests/tool-order.spec.ts | 26 +- packages/core/system-prompt/tsconfig.json | 3 + packages/core/tools/package.json | 2 + packages/core/tools/src/index.ts | 237 +++++++++++++++-- packages/core/tools/tests/scoped.spec.ts | 172 ++++++++++++ packages/core/tools/tsconfig.json | 3 + pnpm-lock.yaml | 15 ++ 16 files changed, 940 insertions(+), 117 deletions(-) create mode 100644 packages/core/session/tests/scoped.spec.ts create mode 100644 packages/core/system-prompt/tests/scoped.spec.ts create mode 100644 packages/core/tools/tests/scoped.spec.ts diff --git a/packages/core/agent-loop/tests/tool-order.spec.ts b/packages/core/agent-loop/tests/tool-order.spec.ts index 35329ce679..d9b0a87e1d 100644 --- a/packages/core/agent-loop/tests/tool-order.spec.ts +++ b/packages/core/agent-loop/tests/tool-order.spec.ts @@ -107,7 +107,7 @@ describe('loop-level canonical tool order', () => { agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(0) - expect(errors.map(e => e.message)).toEqual(['toolOrder lists unregistered tool "ghost"; registered tools: alpha']) + expect(errors.map(e => e.message)).toEqual(['toolOrder lists unregistered tool "ghost"; known tools: alpha']) expect(foldRequestHeader(agent.session.events)).toBeUndefined() const end = agent.session.events.find(e => e.type === 'turn/end') expect(end?.type === 'turn/end' && end.data.reason).toMatchObject({ kind: 'error', step: 1 }) diff --git a/packages/core/session/package.json b/packages/core/session/package.json index 8c6645e37e..454a0d7cc3 100644 --- a/packages/core/session/package.json +++ b/packages/core/session/package.json @@ -24,11 +24,13 @@ "peerDependencies": { "@deepseek-ai/dsh-brand": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-scope": "^0.0.1", "cordis": "^4.0.0-rc.6" }, "devDependencies": { "@deepseek-ai/dsh-brand": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-scope": "workspace:^", "cordis": "^4.0.0-rc.6" } } diff --git a/packages/core/session/src/index.ts b/packages/core/session/src/index.ts index cd9e1828b2..0bbd957a79 100644 --- a/packages/core/session/src/index.ts +++ b/packages/core/session/src/index.ts @@ -9,6 +9,8 @@ import { Context, Service } from 'cordis' import { isAbsolute } from 'node:path' import { deepFreeze } from '@deepseek-ai/dsh-llm' +import { scopeOf, scopeTarget } from '@deepseek-ai/dsh-scope' +import type { Scoped } from '@deepseek-ai/dsh-scope' import type { ContentBlock, Message, MessageSource } from '@deepseek-ai/dsh-llm' import { SESSION_FORMAT_VERSION, SessionId } from './types.ts' import type { CreateSessionOptions, EpochHeader, SessionEvent, SessionEventMap, SessionEventType, SessionHeader, SurfaceIntent, SurfaceEventType } from './types.ts' @@ -33,28 +35,48 @@ declare module 'cordis' { interface Events { /** * A session was created in the store. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): the carrier is the + * session's owner scope, captured when the session was ENTERED (an agent's + * session is entered through `agent.ctx`, so its events dispatch in that + * agent's scope; a bare `sessions.create()` from a plain plugin dispatches + * subject-less). A listener registered through `agent.ctx` hears only that + * agent's sessions; a plain plugin listener hears every session. * @param session - the session just entered and announced. * @mode emit */ - 'session/created'(session: Session): void + 'session/created'(this: Scoped, session: Session): void /** * An event was appended to a session log (sync, fire-and-forget). This is * the per-append feed a UI or invariant plugin tails. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): the carrier is the + * session's owner scope, captured when the session was ENTERED (an agent's + * session is entered through `agent.ctx`, so its events dispatch in that + * agent's scope; a bare `sessions.create()` from a plain plugin dispatches + * subject-less). A listener registered through `agent.ctx` hears only that + * agent's sessions; a plain plugin listener hears every session. * @param session - the session whose log grew. * @param event - the appended event, exactly as recorded. * @mode emit */ - 'session/event'(session: Session, event: SessionEvent): void + 'session/event'(this: Scoped, session: Session, event: SessionEvent): void /** * Awaited durability checkpoint. The agent loop awaits - * `ctx.parallel('session/flush', session)` at every turn end; persistence + * `ctx.sessions.flush(session)` at every turn end; persistence * plugins (JSONL, SQLite) drain their write-behind buffers here and on * fiber dispose. Awaited (parallel), not a waterfall: every listener runs - * and the loop waits for all of them, but none can veto. + * and the caller waits for all of them, but none can veto. Dispatch it + * through {@link SessionStore.flush} — the store owns the carrier — never + * via a raw `ctx.parallel`. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): the carrier is the + * session's owner scope, captured when the session was ENTERED (an agent's + * session is entered through `agent.ctx`, so its events dispatch in that + * agent's scope; a bare `sessions.create()` from a plain plugin dispatches + * subject-less). A listener registered through `agent.ctx` hears only that + * agent's sessions; a plain plugin listener hears every session. * @param session - the session whose buffered events must reach durable storage. * @mode parallel */ - 'session/flush'(session: Session): Promise | void + 'session/flush'(this: Scoped, session: Session): Promise | void } } @@ -404,6 +426,14 @@ export class SessionForkError extends Error { */ export class SessionStore extends Service { private store = new Map() + /** + * Each live session's dispatch carrier, captured at {@link enter} from the + * ENTERING context's scope tag (an agent session is entered through + * `agent.ctx` ⇒ its events dispatch in that agent's scope; a bare session ⇒ + * subject-less carrier). WeakMap so a detached session drops its carrier + * with the entry. + */ + private carriers = new WeakMap>() private counter = 0 constructor(ctx: Context) { @@ -498,7 +528,15 @@ export class SessionStore extends Service { */ enter(session: Session): () => void { if (this.store.has(session.id)) throw new Error(`session "${session.id}" already exists`) - session.onAppend = (event) => { this.ctx.emit('session/event', session, event) } + // The carrier is decided HERE, once, from the ENTERING context's scope tag + // (`this.ctx` is the caller's context — the tracker mechanism): every + // session/created|event|flush dispatch for this session uses it, so the + // session's whole event feed is scope-filtered consistently. The base is + // the session itself (scoped listeners' `this` is the session). + const carrier = scopeTarget(session, scopeOf(this.ctx)) + this.carriers.set(session, carrier) + const emitCtx = this.ctx + session.onAppend = (event) => { emitCtx.emit(carrier, 'session/event', session, event) } this.store.set(session.id, session) return () => { session.onAppend = undefined @@ -506,12 +544,32 @@ export class SessionStore extends Service { } } - /** Emit `session/created` for an {@link enter}ed session. Separate from - * {@link enter} so the caller can yield the detach disposer first (rollback - * safety — see {@link enter}). + /** Emit `session/created` for an {@link enter}ed session (with the carrier + * {@link enter} captured). Separate from {@link enter} so the caller can + * yield the detach disposer first (rollback safety — see {@link enter}). * @param session - the entered session to announce to listeners. */ announce(session: Session): void { - this.ctx.emit('session/created', session) + this.ctx.emit(this.carrierFor(session), 'session/created', session) + } + + /** + * Dispatch the awaited `session/flush` durability checkpoint for `session`, + * with the carrier captured at {@link enter}. THE flush entry point: the + * store owns the carrier, so callers (the loop's turn-end checkpoint, idle + * injection, teardown drains) must come through here rather than dispatch a + * raw `ctx.parallel('session/flush', …)` — one owner, one spelling, and the + * scoped-dispatch invariant can pin it. + * @param session - the session whose buffered events must reach durable storage. + * @returns resolves when every flush listener has settled; rejects if one rejects. + */ + async flush(session: Session): Promise { + await this.ctx.parallel(this.carrierFor(session), 'session/flush', session) + } + + /** The carrier {@link enter} captured, or a subject-less one for a session + * never entered (defensive: dispatch stays filtered either way). */ + private carrierFor(session: Session): Scoped { + return this.carriers.get(session) ?? scopeTarget(session, undefined) } /** diff --git a/packages/core/session/tests/scoped.spec.ts b/packages/core/session/tests/scoped.spec.ts new file mode 100644 index 0000000000..743b72def3 --- /dev/null +++ b/packages/core/session/tests/scoped.spec.ts @@ -0,0 +1,112 @@ +import { describe, expect, it } from 'vitest' +import { Context } from 'cordis' +import { createScope, scopeOf } from '@deepseek-ai/dsh-scope' +import type { Scope, ScopeKey } from '@deepseek-ai/dsh-scope' +import SessionStore from '@deepseek-ai/dsh-session' +import type { Session } from '@deepseek-ai/dsh-session' + +async function mount(): Promise { + const ctx = new Context() + await ctx.plugin(SessionStore) + return ctx +} + +async function mintScope(ctx: Context, name: string): Promise { + let scope!: Scope + // The scoped context resolves services through the MINTING plugin's + // dependency chain — the minter must inject what scope holders will reach. + await ctx.plugin(Object.assign((inner: Context) => { scope = createScope(inner, { name }) }, + { inject: ['sessions'] })) + return scope +} + +/** The key a test scope was minted with. */ +function keyOf(scope: Scope): ScopeKey { + + return scopeOf(scope.ctx)! +} + +describe('session dispatch carriers', () => { + it('a session entered through a scoped context dispatches its events in that scope', async () => { + const ctx = await mount() + const scope = await mintScope(ctx, 'owner') + const otherScope = await mintScope(ctx, 'other') + + const heard: string[] = [] + ctx.on('session/event', (_session, event) => void heard.push(`global:${event.type}`)) + scope.ctx.on('session/event', (_session, event) => void heard.push(`owner:${event.type}`)) + otherScope.ctx.on('session/event', (_session, event) => void heard.push(`other:${event.type}`)) + scope.ctx.on('session/created', session => void heard.push(`owner-created:${session.id}`)) + otherScope.ctx.on('session/created', session => void heard.push(`other-created:${session.id}`)) + + const session = scope.ctx.sessions.create() + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + + expect(heard).toEqual([ + `owner-created:${session.id}`, + 'global:turn/start', + 'owner:turn/start', + ]) + }) + + it('a bare session dispatches subject-less: scoped listeners never hear it', async () => { + const ctx = await mount() + const scope = await mintScope(ctx, 'owner') + const heard: string[] = [] + ctx.on('session/event', (_s, event) => void heard.push(`global:${event.type}`)) + scope.ctx.on('session/event', (_s, event) => void heard.push(`owner:${event.type}`)) + + const bare = ctx.sessions.create() + bare.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + expect(heard).toEqual(['global:turn/start']) + }) +}) + +describe('sessions.flush()', () => { + it('dispatches session/flush with the owning carrier and awaits all listeners', async () => { + const ctx = await mount() + const scope = await mintScope(ctx, 'owner') + const flushed: string[] = [] + ctx.on('session/flush', async (session: Session) => { + await Promise.resolve() + flushed.push(`global:${session.id}`) + }) + scope.ctx.on('session/flush', (session: Session) => void flushed.push(`owner:${session.id}`)) + + const owned = scope.ctx.sessions.create() + const bare = ctx.sessions.create() + await ctx.sessions.flush(owned) + await ctx.sessions.flush(bare) + + // Parallel dispatch: listener completion order is unspecified (the global + // listener awaits a microtask) — assert set membership per flush instead. + expect(flushed.slice(0, 2).sort()).toEqual([`global:${owned.id}`, `owner:${owned.id}`]) + expect(flushed.slice(2)).toEqual([`global:${bare.id}`]) + }) + + it('propagates a rejecting flush listener (the caller owns the failure policy)', async () => { + const ctx = await mount() + ctx.on('session/flush', () => Promise.reject(new Error('disk full'))) + const session = ctx.sessions.create() + await expect(ctx.sessions.flush(session)).rejects.toThrow('disk full') + }) + + it('flushes a never-entered session with a subject-less carrier (defensive path)', async () => { + const ctx = await mount() + const scope = await mintScope(ctx, 'owner') + const flushed: string[] = [] + ctx.on('session/flush', (session: Session) => void flushed.push(`global:${session.id}`)) + scope.ctx.on('session/flush', (session: Session) => void flushed.push(`owner:${session.id}`)) + + const detached = ctx.sessions.prepare() + await ctx.sessions.flush(detached) + expect(flushed).toEqual([`global:${detached.id}`]) + }) + + it('keyOf sanity: distinct scopes carry distinct keys', async () => { + const ctx = await mount() + const a = await mintScope(ctx, 'a') + const b = await mintScope(ctx, 'b') + expect(keyOf(a)).not.toBe(keyOf(b)) + }) +}) diff --git a/packages/core/session/tsconfig.json b/packages/core/session/tsconfig.json index 7ca1556695..b19b98c5ad 100644 --- a/packages/core/session/tsconfig.json +++ b/packages/core/session/tsconfig.json @@ -19,6 +19,9 @@ }, { "path": "../../llm/llm" + }, + { + "path": "../../core/scope" } ] } diff --git a/packages/core/system-prompt/package.json b/packages/core/system-prompt/package.json index d97a7b8538..120e10ef11 100644 --- a/packages/core/system-prompt/package.json +++ b/packages/core/system-prompt/package.json @@ -23,6 +23,7 @@ "license": "BSD-3-Clause", "peerDependencies": { "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-scope": "^0.0.1", "cordis": "^4.0.0-rc.6" }, "dependencies": { @@ -30,6 +31,7 @@ }, "devDependencies": { "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-scope": "workspace:^", "cordis": "^4.0.0-rc.6" } } diff --git a/packages/core/system-prompt/src/index.ts b/packages/core/system-prompt/src/index.ts index 81ca8087bb..8fa2daf3b0 100644 --- a/packages/core/system-prompt/src/index.ts +++ b/packages/core/system-prompt/src/index.ts @@ -14,6 +14,8 @@ import { Context, Service } from 'cordis' import z from 'schemastery' +import { scopeOf, scopeTarget } from '@deepseek-ai/dsh-scope' +import type { ScopeKey, Scoped } from '@deepseek-ai/dsh-scope' import type { ToolSchema } from '@deepseek-ai/dsh-llm' declare module 'cordis' { @@ -30,15 +32,23 @@ declare module 'cordis' { * @param assembly - the assembly built from the registered sections, tool * providers, and variable providers; listeners may mutate it or return a * replacement. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): the carrier is keyed + * by `context.scope` — a listener registered through `agent.ctx` fires only + * for that agent's assemblies; a plain plugin listener fires for every + * assembly (scope-less ones included, dispatched subject-less). * @param context - the per-assembly {@link AssembleContext} the caller * passed to {@link SystemPrompt.assemble} (e.g. which agent the prompt * is for), so a listener can filter or extend per agent. * @mode waterfall */ - 'system-prompt/assemble'(this: SystemPrompt, assembly: PromptAssembly, context: AssembleContext, next: () => Promise): Promise + 'system-prompt/assemble'(this: Scoped, assembly: PromptAssembly, context: AssembleContext, next: () => Promise): Promise /** * A section, tool provider, or variable provider was registered or - * unregistered (the assembly inputs changed). + * unregistered (the assembly inputs changed — possibly for one scope + * only). An UNFILTERED registry-subject notification, deliberately not + * scope-filtered dispatch: a global change concerns every agent's next + * assembly, so a scoped listener subscribing here sees every change, not + * just its own scope's. * @mode emit */ 'system-prompt/change'(): void @@ -47,13 +57,24 @@ declare module 'cordis' { /** * Per-assembly input: what one {@link SystemPrompt.assemble} call is FOR. - * Declared empty here so this package stays agnostic of who assembles; - * merge-extensible — `@deepseek-ai/dsh-agent` declares the `agent` field, so - * section text and variable providers can be functions of the calling agent. - * Every field is optional by nature: a bare `assemble()` (tests, diagnostics) - * carries an empty context, and providers must tolerate absent fields. + * Merge-extensible and agnostic of who assembles — `@deepseek-ai/dsh-agent` + * declares the `agent` field, so section text and variable providers can be + * functions of the calling agent. Every field is optional by nature: a bare + * `assemble()` (tests, diagnostics) carries an empty, scope-less context, and + * providers must tolerate absent fields. */ -export interface AssembleContext {} +export interface AssembleContext { + /** + * The scope layer this assembly resolves (`@deepseek-ai/dsh-scope`): scoped + * sections/variables/tool-providers registered through this key's context + * join the assembly (shadowing same-named global contributions), and the + * `system-prompt/assemble` waterfall dispatches in this scope. The agent + * loop sets it to the agent (alongside the `agent` DX field — never set + * `agent` without `scope`; the dev invariants flag the mismatch). Absent = + * a scope-less assembly: global layer only, subject-less dispatch. + */ + scope?: ScopeKey +} /** One contributed section of the system prompt (registry input). */ export interface PromptSection { @@ -83,6 +104,23 @@ export interface AssembledSection { text: string } +/** + * What one tool-schema provider contributes to an assembly + * ({@link SystemPrompt.tools}). `schemas` is the provider's POST-restriction + * visible set for the assembly's scope — exactly what the model may be shown. + * `knownNames` is its PRE-restriction name universe: the set configured names + * (`toolOrder`) are validated against, so a config typo fails loud while a + * restricted-away tool stays a normal, non-erroneous absence. Omitted, + * `knownNames` defaults to the names of `schemas` (right for providers with no + * restriction concept). + */ +export interface ToolProviderResult { + /** The schemas this provider contributes to THIS assembly. */ + schemas: ToolSchema[] + /** The pre-restriction name universe for config validation (defaults to `schemas`' names). */ + knownNames?: readonly string[] +} + /** * The assembled prompt. * @@ -146,23 +184,26 @@ function validateToolOrder(toolOrder: string[] | undefined): string[] | undefine * list, plain lexicographic name order; with one, listed names take their * listed position and every unlisted tool lands at the * {@link TOOL_ORDER_REST} rest entry in lexicographic name order. A listed - * name with no collected tool throws — misconfiguration fails loud, and this - * is the earliest moment the registered tool set exists to check against - * (tool plugins register after the service constructs, so load time is too - * early): the assembly rejects, failing the caller's turn before any model - * request. Never drops a tool, and both sorts are stable, so tools sharing a - * name keep their collection order. + * name outside `knownNames` — the providers' PRE-restriction name universe — + * throws: misconfiguration fails loud, and each assembly is the earliest + * moment the registered tool set exists to check against (tool plugins + * register after the service constructs, so load time is too early); the + * assembly rejects, failing the caller's turn before any model request. A + * listed name that is KNOWN but not collected (a tool restricted away for + * this assembly's scope) is a normal absence: its position simply + * contributes nothing — `toolOrder` stays compatible with per-agent + * `restrict()` masks. Never drops a collected tool, and both sorts are + * stable, so tools sharing a name keep their collection order. */ -function orderTools(tools: ToolSchema[], toolOrder: string[] | undefined): ToolSchema[] { +function orderTools(tools: ToolSchema[], toolOrder: string[] | undefined, knownNames: ReadonlySet): ToolSchema[] { const reserved = tools.find(tool => tool.name === TOOL_ORDER_REST) if (reserved !== undefined) { throw new Error(`tool provider returned reserved tool name "${TOOL_ORDER_REST}" (reserved for toolOrder's rest entry)`) } if (toolOrder === undefined) return tools.sort(compareToolNames) - const registered = new Set(tools.map(tool => tool.name)) - const unknown = toolOrder.filter(name => name !== TOOL_ORDER_REST && !registered.has(name)) + const unknown = toolOrder.filter(name => name !== TOOL_ORDER_REST && !knownNames.has(name)) if (unknown.length > 0) { - throw new Error(`toolOrder lists unregistered tool${unknown.length > 1 ? 's' : ''} ${unknown.map(name => `"${name}"`).join(', ')}; registered tools: ${[...registered].sort().join(', ') || '(none)'}`) + throw new Error(`toolOrder lists unregistered tool${unknown.length > 1 ? 's' : ''} ${unknown.map(name => `"${name}"`).join(', ')}; known tools: ${[...knownNames].sort().join(', ') || '(none)'}`) } const listed = new Set(toolOrder) const rest = tools.filter(tool => !listed.has(tool.name)).sort(compareToolNames) @@ -181,7 +222,10 @@ export interface Config { * The deployment's persona — the ONE deployment-authored fragment of the * system prompt, rendered as the order-0 `deployment:persona` section * (after the harness identity, before all tool guidance). Every agent in - * the context shares it, subagents included. Template, not free-form text: + * the context shares it by default; a per-agent persona is a SCOPED section + * of the same name registered through that agent's `agent.ctx` (it shadows + * this one for that agent — the subagent seam's `persona` request field does + * exactly that). Template, not free-form text: * every complete `{{…}}` group is interpreted strictly against the * registered prompt variables (the shipped agent loop registers `{{model}}` * and `{{cwd}}`), and there is no escape syntax for literal `{{…}}` prose @@ -301,8 +345,12 @@ export class SystemPrompt extends Service { }) private sections: PromptSection[] = [] - private toolProviders: (() => ToolSchema[])[] = [] + private toolProviders: ((context: AssembleContext) => ToolProviderResult)[] = [] private variableProviders = new Map string | undefined>() + /** Per-scope layers (`@deepseek-ai/dsh-scope`); entries drop when a layer empties, so a disposed scope leaves no residue. */ + private scopedSections = new Map() + private scopedToolProviders = new Map ToolProviderResult)[]>() + private scopedVariableProviders = new Map string | undefined>>() private readonly toolOrder: string[] | undefined constructor(ctx: Context, public config: Config) { @@ -330,27 +378,44 @@ export class SystemPrompt extends Service { /** * Contribute a text section to the system prompt. Order is determined by - * `section.order` (ascending). Throws if a section with the same name is - * already registered (a duplicate would silently double prompt text — e.g. - * a double-loaded tool plugin). The section is removed when the calling - * fiber is disposed. Emits `system-prompt/change` on register/unregister. + * `section.order` (ascending). The layer is decided by the CALLING context + * (`@deepseek-ai/dsh-scope`): a plain plugin context contributes globally; a + * scoped context (`agent.ctx`) contributes to that scope alone — and a + * scoped section SHADOWS a same-named global section for that scope's + * assemblies (most-specific-wins; this is how a per-agent persona overrides + * `deployment:persona`). Throws if the SAME layer already has the name (a + * duplicate would silently double prompt text — e.g. a double-loaded tool + * plugin; the global-duplicate message names `agent.ctx` as the per-agent + * alternative). Removed when the calling fiber is disposed. Emits + * `system-prompt/change` on register/unregister. * @param section - the section to contribute (name, order, text or provider). * @returns the disposer that removes the section. */ section(section: PromptSection): () => void { + const scope = scopeOf(this.ctx) const dispose = this.ctx.effect(function* (this: SystemPrompt) { - if (this.sections.some(existing => existing.name === section.name)) { - throw new Error(`prompt section "${section.name}" is already registered`) + const layer = scope === undefined + ? this.sections + : this.scopedSections.get(scope) ?? (() => { + const created: PromptSection[] = [] + this.scopedSections.set(scope, created) + return created + })() + if (layer.some(existing => existing.name === section.name)) { + throw new Error(scope === undefined + ? `prompt section "${section.name}" is already registered (for a per-agent override, register through that agent's \`agent.ctx\` instead)` + : `prompt section "${section.name}" is already registered in this scope`) } - this.sections.push(section) + layer.push(section) // Yield the rollback BEFORE emitting `system-prompt/change`: a generator // effect collects each yielded disposer before the next step runs, so a // throwing change listener removes the section instead of leaking it into // every future assembly. yield () => { - const index = this.sections.indexOf(section) + const index = layer.indexOf(section) /* v8 ignore next 3 -- defensive: section was registered, so indexOf is guaranteed >= 0 */ - if (index >= 0) this.sections.splice(index, 1) + if (index >= 0) layer.splice(index, 1) + if (scope !== undefined && layer.length === 0) this.scopedSections.delete(scope) this.ctx.emit('system-prompt/change') } this.ctx.emit('system-prompt/change') @@ -361,23 +426,36 @@ export class SystemPrompt extends Service { } /** - * Contribute a tool-schema provider that is evaluated at each assembly - * call (so it can reflect the live registry state). The provider is - * removed when the calling fiber is disposed. A provider must not return a - * schema named {@link TOOL_ORDER_REST}; that name is reserved for + * Contribute a tool-schema provider, evaluated at each assembly call with + * that assembly's {@link AssembleContext} (so it reflects the live registry + * state AND the assembly's scope — see {@link ToolProviderResult} for the + * `schemas`/`knownNames` split). The layer is decided by the calling + * context: a scoped provider (registered through `agent.ctx`) is consulted + * only for that scope's assemblies. Removed when the calling fiber is + * disposed. A provider must not return a schema named + * {@link TOOL_ORDER_REST}; that name is reserved for * {@link Config.toolOrder}'s rest entry and rejects the assembly. Emits * `system-prompt/change`. * @param provider - evaluated at every {@link assemble} for fresh schemas. * @returns the disposer that removes the provider. */ - tools(provider: () => ToolSchema[]): () => void { + tools(provider: (context: AssembleContext) => ToolProviderResult): () => void { + const scope = scopeOf(this.ctx) const dispose = this.ctx.effect(function* (this: SystemPrompt) { - this.toolProviders.push(provider) + const layer = scope === undefined + ? this.toolProviders + : this.scopedToolProviders.get(scope) ?? (() => { + const created: ((context: AssembleContext) => ToolProviderResult)[] = [] + this.scopedToolProviders.set(scope, created) + return created + })() + layer.push(provider) // Yield the rollback BEFORE emitting `system-prompt/change` (see section()). yield () => { - const index = this.toolProviders.indexOf(provider) + const index = layer.indexOf(provider) /* v8 ignore next 3 -- defensive: provider was registered, so indexOf is guaranteed >= 0 */ - if (index >= 0) this.toolProviders.splice(index, 1) + if (index >= 0) layer.splice(index, 1) + if (scope !== undefined && layer.length === 0) this.scopedToolProviders.delete(scope) this.ctx.emit('system-prompt/change') } this.ctx.emit('system-prompt/change') @@ -392,26 +470,40 @@ export class SystemPrompt extends Service { * `{{name}}`. The provider is evaluated at each assembly with that * assembly's {@link AssembleContext}; returning `undefined` means "no value * for this assembly" (a section referencing it then fails to render — a - * deployment must not claim facts it does not have). Throws on a name that - * does not match `[a-z][a-z0-9_]*` (it could never be referenced) or is - * already registered. Removed when the calling fiber is disposed; emits - * `system-prompt/change` on register/unregister. + * deployment must not claim facts it does not have). The layer is decided + * by the calling context: a scoped variable (registered through + * `agent.ctx`) resolves only for that scope's assemblies and SHADOWS a + * same-named global variable there. Throws on a name that does not match + * `[a-z][a-z0-9_]*` (it could never be referenced) or one already + * registered in the SAME layer. Removed when the calling fiber is disposed; + * emits `system-prompt/change` on register/unregister. * @param name - the reference name (matches `[a-z][a-z0-9_]*`). * @param provider - evaluated at every {@link assemble} for the value. * @returns the disposer that removes the variable. */ variable(name: string, provider: (context: AssembleContext) => string | undefined): () => void { + const scope = scopeOf(this.ctx) const dispose = this.ctx.effect(function* (this: SystemPrompt) { if (!VARIABLE_NAME.test(name)) { throw new Error(`invalid prompt variable name "${name}" (must match ${String(VARIABLE_NAME)})`) } - if (this.variableProviders.has(name)) { - throw new Error(`prompt variable "${name}" is already registered`) + const layer = scope === undefined + ? this.variableProviders + : this.scopedVariableProviders.get(scope) ?? (() => { + const created = new Map string | undefined>() + this.scopedVariableProviders.set(scope, created) + return created + })() + if (layer.has(name)) { + throw new Error(scope === undefined + ? `prompt variable "${name}" is already registered (for a per-agent value, register through that agent's \`agent.ctx\` instead)` + : `prompt variable "${name}" is already registered in this scope`) } - this.variableProviders.set(name, provider) + layer.set(name, provider) // Yield the rollback BEFORE emitting `system-prompt/change` (see section()). yield () => { - this.variableProviders.delete(name) + layer.delete(name) + if (scope !== undefined && layer.size === 0) this.scopedVariableProviders.delete(scope) this.ctx.emit('system-prompt/change') } this.ctx.emit('system-prompt/change') @@ -422,13 +514,17 @@ export class SystemPrompt extends Service { } /** - * Assemble the current prompt for one caller: section texts are resolved - * against `context` and sorted by order, tools collected from all providers - * and put in the canonical model-facing order ({@link Config.toolOrder}, or - * lexicographic name order when unconfigured — provider registration order - * is a plugin-load artifact and never reaches the assembly; a configured - * order naming a tool no provider contributed rejects the assembly), and every - * registered variable resolved against `context` into `assembly.variables`. + * Assemble the current prompt for one caller: the global layer merged with + * {@link AssembleContext.scope}'s layer (scoped sections/variables SHADOW + * same-named global ones — most-specific-wins) — section texts resolved + * against `context` and sorted by order across the union, tools collected + * from the global providers plus the scope's and put in the canonical + * model-facing order ({@link Config.toolOrder}, or lexicographic name order + * when unconfigured — provider registration order is a plugin-load artifact + * and never reaches the assembly; a configured order naming a tool outside + * the providers' `knownNames` universe rejects the assembly, while a known + * name restricted away for this scope is a normal absence), and every + * visible variable resolved against `context` into `assembly.variables`. * Tool schemas are deep-cloned because adapters and request waterfalls may * mutate schema objects. Runs through the `system-prompt/assemble` * waterfall, giving listeners the opportunity to mutate or replace the @@ -445,25 +541,59 @@ export class SystemPrompt extends Service { // rejection: a Promise-returning method must not throw synchronously // (`assemble().catch(...)` would miss it). async assemble(context: AssembleContext = {}): Promise { + const scope = context.scope + // Variables: global layer first, then the scope's layer OVERWRITES + // same-named entries (shadowing — a per-agent value wins for that agent). const variables: Record = {} for (const [name, provider] of this.variableProviders) { variables[name] = provider(context) } + const scopedVariables = scope === undefined ? undefined : this.scopedVariableProviders.get(scope) + for (const [name, provider] of scopedVariables ?? []) { + variables[name] = provider(context) + } + // Sections: merge by name, scoped REPLACING same-named global entries + // (most-specific-wins — the per-agent persona mechanism), then sort by + // order across the union. Registration order within a layer is preserved + // for equal orders (stable sort). + const sectionByName = new Map() + for (const section of this.sections) sectionByName.set(section.name, section) + for (const section of (scope === undefined ? [] : this.scopedSections.get(scope)) ?? []) { + sectionByName.set(section.name, section) + } + // Tools: consult the global providers plus the scope's, each with this + // assembly's context. `schemas` are what the model may see (already + // post-restriction, per provider); `knownNames` (defaulting to the + // schemas' names) form the pre-restriction universe `toolOrder` is + // validated against, so a restricted-away tool is a normal absence while + // a config typo still fails every assembly loudly. + const providers = [ + ...this.toolProviders, + ...(scope === undefined ? [] : this.scopedToolProviders.get(scope)) ?? [], + ] + const collected: ToolSchema[] = [] + const knownNames = new Set() + for (const provider of providers) { + const result = provider(context) + for (const tool of result.schemas) { + collected.push({ ...tool, parameters: structuredClone(tool.parameters) }) + } + for (const name of result.knownNames ?? result.schemas.map(tool => tool.name)) { + knownNames.add(name) + } + } const assembly: PromptAssembly = { - sections: this.sections + sections: [...sectionByName.values()] .map(section => ({ name: section.name, order: section.order, text: typeof section.text === 'function' ? section.text(context) : section.text, })) .sort((a, b) => a.order - b.order), - tools: orderTools( - this.toolProviders.flatMap(provider => - provider().map(tool => ({ ...tool, parameters: structuredClone(tool.parameters) }))), - this.toolOrder), + tools: orderTools(collected, this.toolOrder, knownNames), variables, } - return this.ctx.waterfall(this, 'system-prompt/assemble', assembly, context, () => Promise.resolve(assembly)) + return this.ctx.waterfall(scopeTarget(this, scope), 'system-prompt/assemble', assembly, context, () => Promise.resolve(assembly)) } } diff --git a/packages/core/system-prompt/tests/scoped.spec.ts b/packages/core/system-prompt/tests/scoped.spec.ts new file mode 100644 index 0000000000..9c448bc2ac --- /dev/null +++ b/packages/core/system-prompt/tests/scoped.spec.ts @@ -0,0 +1,138 @@ +import { describe, expect, it } from 'vitest' +import { Context } from 'cordis' +import { createScope, scopeOf } from '@deepseek-ai/dsh-scope' +import type { Scope, ScopeKey } from '@deepseek-ai/dsh-scope' +import SystemPrompt, { TOOL_ORDER_REST, renderPrompt } from '@deepseek-ai/dsh-system-prompt' +import type { Config, PromptAssembly } from '@deepseek-ai/dsh-system-prompt' + +async function mount(config: Config = {}): Promise { + const ctx = new Context() + await ctx.plugin(SystemPrompt, config) + return ctx +} + +async function mintScope(ctx: Context, name: string): Promise { + let scope!: Scope + // The scoped context resolves services through the MINTING plugin's + // dependency chain — the minter must inject what scope holders will reach. + await ctx.plugin(Object.assign((inner: Context) => { scope = createScope(inner, { name }) }, + { inject: ['systemPrompt'] })) + return scope +} + +const schema = (name: string) => ({ name, description: `tool ${name}`, parameters: {} }) + +/** The key a test scope was minted with (scopeOf over the scope's own ctx). */ +function scopeKeyOf(scope: Scope): ScopeKey { + // scopeOf never answers undefined for a context the scope itself minted. + + return scopeOf(scope.ctx)! +} + +describe('scoped sections', () => { + it('a scoped persona shadows deployment:persona for that scope only (either order)', async () => { + const ctx = await mount({ persona: 'You are the deployment.' }) + const scope = await mintScope(ctx, 'child') + scope.ctx.systemPrompt.section({ name: 'deployment:persona', order: 0, text: 'You run tests.' }) + + const scoped = renderPrompt(await ctx.systemPrompt.assemble({ scope: scopeKeyOf(scope) })) + const global = renderPrompt(await ctx.systemPrompt.assemble()) + expect(scoped).toContain('You run tests.') + expect(scoped).not.toContain('You are the deployment.') + expect(global).toContain('You are the deployment.') + expect(global).not.toContain('You run tests.') + }) + + it('scoped-only sections join that scope alone; disposal removes them', async () => { + const ctx = await mount() + const scope = await mintScope(ctx, 'child') + scope.ctx.systemPrompt.section({ name: 'child:extra', order: 50, text: 'Extra guidance.' }) + + expect(renderPrompt(await ctx.systemPrompt.assemble({ scope: scopeKeyOf(scope) }))).toContain('Extra guidance.') + expect(renderPrompt(await ctx.systemPrompt.assemble())).not.toContain('Extra guidance.') + await scope.dispose() + expect(renderPrompt(await ctx.systemPrompt.assemble({ scope: scopeKeyOf(scope) }))).not.toContain('Extra guidance.') + }) + + it('duplicate names throw per layer, naming agent.ctx for the global case', async () => { + const ctx = await mount() + const scope = await mintScope(ctx, 'child') + ctx.systemPrompt.section({ name: 'x', order: 1, text: 'a' }) + expect(() => ctx.systemPrompt.section({ name: 'x', order: 1, text: 'b' })).toThrow(/agent\.ctx/) + scope.ctx.systemPrompt.section({ name: 'y', order: 1, text: 'a' }) + expect(() => scope.ctx.systemPrompt.section({ name: 'y', order: 1, text: 'b' })).toThrow(/already registered in this scope/) + }) +}) + +describe('scoped variables', () => { + it('a scoped variable shadows its global name-twin for that scope', async () => { + const ctx = await mount({ persona: 'Mode: {{mode}}.' }) + const scope = await mintScope(ctx, 'child') + ctx.systemPrompt.variable('mode', () => 'normal') + scope.ctx.systemPrompt.variable('mode', () => 'strict') + + expect(renderPrompt(await ctx.systemPrompt.assemble({ scope: scopeKeyOf(scope) }))).toContain('Mode: strict.') + expect(renderPrompt(await ctx.systemPrompt.assemble())).toContain('Mode: normal.') + }) + + it('same-layer duplicates throw; scoped layer cleans up on dispose', async () => { + const ctx = await mount() + const scope = await mintScope(ctx, 'child') + scope.ctx.systemPrompt.variable('v', () => '1') + expect(() => scope.ctx.systemPrompt.variable('v', () => '2')).toThrow(/already registered in this scope/) + await scope.dispose() + // Re-minting a scope with the SAME key starts clean. + const again = await mintScope(ctx, 'child2') + again.ctx.systemPrompt.variable('v', () => '3') + }) +}) + +describe('scoped tool providers and toolOrder × restriction', () => { + it('scoped providers are consulted only for their scope', async () => { + const ctx = await mount() + const scope = await mintScope(ctx, 'child') + ctx.systemPrompt.tools(() => ({ schemas: [schema('global_tool')] })) + scope.ctx.systemPrompt.tools(() => ({ schemas: [schema('scoped_tool')] })) + + const scoped = await ctx.systemPrompt.assemble({ scope: scopeKeyOf(scope) }) + const global = await ctx.systemPrompt.assemble() + expect(scoped.tools.map(t => t.name)).toEqual(['global_tool', 'scoped_tool']) + expect(global.tools.map(t => t.name)).toEqual(['global_tool']) + }) + + it('a toolOrder entry restricted away for a scope is a normal absence, while a typo still throws', async () => { + const ctx = await mount({ toolOrder: ['bash', TOOL_ORDER_REST] }) + // A provider mimicking the registry's restriction split: bash exists + // (knownNames) but is masked for this assembly (schemas). + ctx.systemPrompt.tools(() => ({ + schemas: [schema('read')], + knownNames: ['read', 'bash'], + })) + const assembly = await ctx.systemPrompt.assemble() + expect(assembly.tools.map(t => t.name)).toEqual(['read']) + + const bad = await mount({ toolOrder: ['basj', TOOL_ORDER_REST] }) + bad.systemPrompt.tools(() => ({ schemas: [schema('read')], knownNames: ['read', 'bash'] })) + await expect(bad.systemPrompt.assemble()).rejects.toThrow('toolOrder lists unregistered tool "basj"; known tools: bash, read') + }) +}) + +describe('scoped assemble dispatch', () => { + it('an agent.ctx assemble listener shapes only its own scope\'s assemblies', async () => { + const ctx = await mount() + const scope = await mintScope(ctx, 'child') + const shaped: (ScopeKey | undefined)[] = [] + scope.ctx.on('system-prompt/assemble', async (_assembly: PromptAssembly, context, next: () => Promise) => { + shaped.push(context.scope) + const result = await next() + result.sections.push({ name: 'listener:extra', order: 999, text: 'listener text' }) + return result + }) + + const scoped = await ctx.systemPrompt.assemble({ scope: scopeKeyOf(scope) }) + const global = await ctx.systemPrompt.assemble() + expect(scoped.sections.some(s => s.name === 'listener:extra')).toBe(true) + expect(global.sections.some(s => s.name === 'listener:extra')).toBe(false) + expect(shaped).toHaveLength(1) + }) +}) diff --git a/packages/core/system-prompt/tests/system-prompt.spec.ts b/packages/core/system-prompt/tests/system-prompt.spec.ts index c0bd8be6d2..560a640643 100644 --- a/packages/core/system-prompt/tests/system-prompt.spec.ts +++ b/packages/core/system-prompt/tests/system-prompt.spec.ts @@ -52,7 +52,7 @@ describe('SystemPrompt', () => { ctx.systemPrompt.section({ name: 'cwd', order: 20, text: () => 'cwd: /tmp' }) ctx.systemPrompt.section({ name: 'rules', order: 10, text: 'Be precise.' }) - ctx.systemPrompt.tools(() => [{ name: 'echo', description: 'echo back', parameters: {} }]) + ctx.systemPrompt.tools(() => ({ schemas: [{ name: 'echo', description: 'echo back', parameters: {} }] })) const assembly = await ctx.systemPrompt.assemble() expect(assembly.sections.map(s => s.name)).toEqual(['harness:identity', 'deployment:persona', 'rules', 'cwd']) @@ -84,7 +84,7 @@ describe('SystemPrompt', () => { const fiber = await ctx.plugin(Object.assign((inner: Context) => { inner.systemPrompt.section({ name: 'scoped', order: 0, text: 'scoped section' }) - inner.systemPrompt.tools(() => [{ name: 'scoped-tool', description: '', parameters: {} }]) + inner.systemPrompt.tools(() => ({ schemas: [{ name: 'scoped-tool', description: '', parameters: {} }] })) inner.systemPrompt.variable('scoped_var', () => 'v') }, { inject: ['systemPrompt'] })) @@ -141,11 +141,11 @@ describe('SystemPrompt', () => { if (!threw) { threw = true; throw new Error('boom change listener') } }) - expect(() => ctx.systemPrompt.tools(() => [{ name: 't', description: '', parameters: {} }])).toThrow('boom change listener') + expect(() => ctx.systemPrompt.tools(() => ({ schemas: [{ name: 't', description: '', parameters: {} }] }))).toThrow('boom change listener') expect((await ctx.systemPrompt.assemble()).tools).toHaveLength(0) // nothing leaked off() - ctx.systemPrompt.tools(() => [{ name: 't', description: '', parameters: {} }]) + ctx.systemPrompt.tools(() => ({ schemas: [{ name: 't', description: '', parameters: {} }] })) expect((await ctx.systemPrompt.assemble()).tools.map(t => t.name)).toEqual(['t']) }) @@ -209,7 +209,7 @@ describe('SystemPrompt', () => { const ctx = new Context() await ctx.plugin(SystemPrompt) ctx.systemPrompt.section({ name: 'base', order: 0, text: 'base' }) - ctx.systemPrompt.tools(() => [{ name: 't', description: 'tool', parameters: { type: 'object', properties: {} } }]) + ctx.systemPrompt.tools(() => ({ schemas: [{ name: 't', description: 'tool', parameters: { type: 'object', properties: {} } }] })) const first = await ctx.systemPrompt.assemble() first.sections[0]!.name = 'mutated' @@ -243,7 +243,7 @@ describe('SystemPrompt', () => { let changeCount = 0 ctx.on('system-prompt/change', () => void changeCount++) - const dispose = ctx.systemPrompt.tools(() => []) + const dispose = ctx.systemPrompt.tools(() => ({ schemas: [] })) // registration emits change expect(changeCount).toBe(1) @@ -257,7 +257,7 @@ describe('SystemPrompt', () => { await ctx.plugin(SystemPrompt) const fiber = await ctx.plugin(Object.assign((inner: Context) => { - inner.systemPrompt.tools(() => [{ name: 'fiber-tool', description: '', parameters: {} }]) + inner.systemPrompt.tools(() => ({ schemas: [{ name: 'fiber-tool', description: '', parameters: {} }] })) }, { inject: ['systemPrompt'] })) expect((await ctx.systemPrompt.assemble()).tools).toHaveLength(1) @@ -280,7 +280,7 @@ describe('SystemPrompt', () => { const ctx = new Context() await ctx.plugin(SystemPrompt) - const dispose = ctx.systemPrompt.tools(() => [{ name: 'direct-tool', description: '', parameters: {} }]) + const dispose = ctx.systemPrompt.tools(() => ({ schemas: [{ name: 'direct-tool', description: '', parameters: {} }] })) expect((await ctx.systemPrompt.assemble()).tools).toHaveLength(1) dispose() diff --git a/packages/core/system-prompt/tests/tool-order.spec.ts b/packages/core/system-prompt/tests/tool-order.spec.ts index 02cc99b2d7..16eff6e354 100644 --- a/packages/core/system-prompt/tests/tool-order.spec.ts +++ b/packages/core/system-prompt/tests/tool-order.spec.ts @@ -26,39 +26,39 @@ describe('SystemPrompt tool order', () => { it('assembles tools in lexicographic name order when no toolOrder is configured', async () => { const ctx = await mount() - ctx.systemPrompt.tools(() => [tool('charlie'), tool('alpha')]) - ctx.systemPrompt.tools(() => [tool('bravo')]) + ctx.systemPrompt.tools(() => ({ schemas: [tool('charlie'), tool('alpha')] })) + ctx.systemPrompt.tools(() => ({ schemas: [tool('bravo')] })) expect(names(await ctx.systemPrompt.assemble())).toEqual(['alpha', 'bravo', 'charlie']) }) it('assembles the same order regardless of provider registration order', async () => { const forward = await mount() - forward.systemPrompt.tools(() => [tool('alpha')]) - forward.systemPrompt.tools(() => [tool('zulu')]) + forward.systemPrompt.tools(() => ({ schemas: [tool('alpha')] })) + forward.systemPrompt.tools(() => ({ schemas: [tool('zulu')] })) const backward = await mount() - backward.systemPrompt.tools(() => [tool('zulu')]) - backward.systemPrompt.tools(() => [tool('alpha')]) + backward.systemPrompt.tools(() => ({ schemas: [tool('zulu')] })) + backward.systemPrompt.tools(() => ({ schemas: [tool('alpha')] })) expect(names(await forward.systemPrompt.assemble())).toEqual(['alpha', 'zulu']) expect(names(await backward.systemPrompt.assemble())).toEqual(['alpha', 'zulu']) }) it('applies a configured toolOrder: listed positions, rest at the rest entry lexicographically', async () => { const ctx = await mount({ toolOrder: ['todo_write', TOOL_ORDER_REST, 'bash'] }) - ctx.systemPrompt.tools(() => [tool('bash'), tool('echo_b'), tool('todo_write'), tool('echo_a')]) + ctx.systemPrompt.tools(() => ({ schemas: [tool('bash'), tool('echo_b'), tool('todo_write'), tool('echo_a')] })) expect(names(await ctx.systemPrompt.assemble())).toEqual(['todo_write', 'echo_a', 'echo_b', 'bash']) }) it('rejects the assembly when toolOrder names a tool that is not registered (misconfiguration blocks work)', async () => { const ctx = await mount({ toolOrder: ['todo_write', 'ghost', TOOL_ORDER_REST, 'wraith'] }) - ctx.systemPrompt.tools(() => [tool('bash'), tool('todo_write')]) + ctx.systemPrompt.tools(() => ({ schemas: [tool('bash'), tool('todo_write')] })) await expect(ctx.systemPrompt.assemble()).rejects.toThrow( - 'toolOrder lists unregistered tools "ghost", "wraith"; registered tools: bash, todo_write') + 'toolOrder lists unregistered tools "ghost", "wraith"; known tools: bash, todo_write') }) it('names the single unregistered tool when no tools are registered at all', async () => { const ctx = await mount({ toolOrder: ['ghost', TOOL_ORDER_REST] }) await expect(ctx.systemPrompt.assemble()).rejects.toThrow( - 'toolOrder lists unregistered tool "ghost"; registered tools: (none)') + 'toolOrder lists unregistered tool "ghost"; known tools: (none)') }) it.each([ @@ -66,21 +66,21 @@ describe('SystemPrompt tool order', () => { ['with only the rest entry configured', [TOOL_ORDER_REST]], ])('rejects a provider tool named like the reserved rest entry %s', async (_case, toolOrder) => { const ctx = await mount(toolOrder === undefined ? {} : { toolOrder }) - ctx.systemPrompt.tools(() => [tool(TOOL_ORDER_REST)]) + ctx.systemPrompt.tools(() => ({ schemas: [tool(TOOL_ORDER_REST)] })) await expect(ctx.systemPrompt.assemble()).rejects.toThrow( `tool provider returned reserved tool name "${TOOL_ORDER_REST}"`) }) it('keeps collection order between tools that share a name (stable sort)', async () => { const ctx = await mount() - ctx.systemPrompt.tools(() => [tool('dup', 'first'), tool('anchor'), tool('dup', 'second')]) + ctx.systemPrompt.tools(() => ({ schemas: [tool('dup', 'first'), tool('anchor'), tool('dup', 'second')] })) const assembly = await ctx.systemPrompt.assemble() expect(assembly.tools.map(t => t.description)).toEqual(['anchor', 'first', 'second']) }) it('canonicalizes BEFORE the assemble waterfall: listeners see the ordered list and own their own edits', async () => { const ctx = await mount() - ctx.systemPrompt.tools(() => [tool('zulu'), tool('alpha')]) + ctx.systemPrompt.tools(() => ({ schemas: [tool('zulu'), tool('alpha')] })) let seen: string[] | undefined ctx.on('system-prompt/assemble', function (assembly, _context, next) { seen = assembly.tools.map(t => t.name) diff --git a/packages/core/system-prompt/tsconfig.json b/packages/core/system-prompt/tsconfig.json index e9de391ba1..91e7bf1ba4 100644 --- a/packages/core/system-prompt/tsconfig.json +++ b/packages/core/system-prompt/tsconfig.json @@ -19,6 +19,9 @@ }, { "path": "../../llm/llm" + }, + { + "path": "../../core/scope" } ] } diff --git a/packages/core/tools/package.json b/packages/core/tools/package.json index a6d3bbe0ca..377b522490 100644 --- a/packages/core/tools/package.json +++ b/packages/core/tools/package.json @@ -24,12 +24,14 @@ "peerDependencies": { "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-scope": "^0.0.1", "@deepseek-ai/dsh-system-prompt": "^0.0.1", "cordis": "^4.0.0-rc.6" }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-scope": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", "cordis": "^4.0.0-rc.6" } diff --git a/packages/core/tools/src/index.ts b/packages/core/tools/src/index.ts index 39dafd6f1a..cfbeffbd57 100644 --- a/packages/core/tools/src/index.ts +++ b/packages/core/tools/src/index.ts @@ -9,6 +9,8 @@ */ import { Context, Service } from 'cordis' +import { scopeOf, scopeTarget } from '@deepseek-ai/dsh-scope' +import type { ScopeKey, Scoped } from '@deepseek-ai/dsh-scope' import type { CallId, ContentBlock, ToolSchema } from '@deepseek-ai/dsh-llm' import { HarnessError } from '@deepseek-ai/dsh-llm' import type { Agent, HookContext } from '@deepseek-ai/dsh-agent' @@ -70,10 +72,14 @@ declare module 'cordis' { * tool body never runs. Input rewrite is deliberately NOT offered here (see * {@link PreToolDecision}); `ask` degrades to deny until the permission * system lands (`FIXME(permissions)`). + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): the carrier is keyed by + * `exec.agent` — a listener registered through `agent.ctx` fires only for + * that agent's calls; a plain plugin listener fires for every call + * (including agent-less ones, which dispatch subject-less). * @param exec - the pending call (name, parsed arguments, caller agent). * @mode waterfall */ - 'tools/pre-execute'(this: ToolRegistry, exec: ToolExecution, next: () => Promise): Promise + 'tools/pre-execute'(this: Scoped, exec: ToolExecution, next: () => Promise): Promise /** * Waterfall AFTER a tool runs — where hook plugins inspect the result and * accept it (optionally REPLACING the model-facing content, and/or attaching @@ -85,13 +91,22 @@ declare module 'cordis' { * `execute`'s outer try/catch (and the tool body keeps its own inner * try/catch, so a thrown tool still reaches `post-execute` as an `isError` * result). + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): the carrier is keyed by + * `exec.agent` — a listener registered through `agent.ctx` fires only for + * that agent's calls; a plain plugin listener fires for every call + * (including agent-less ones, which dispatch subject-less). * @param exec - the call that just ran (name, parsed arguments, caller agent). * @param result - the dispatch outcome a listener may accept, replace, or block. * @mode waterfall */ - 'tools/post-execute'(this: ToolRegistry, exec: ToolExecution, result: ToolExecutionResult, next: () => Promise): Promise + 'tools/post-execute'(this: Scoped, exec: ToolExecution, result: ToolExecutionResult, next: () => Promise): Promise /** - * A tool was registered or unregistered (the available tool set changed). + * A tool was registered or unregistered, or a scoped restriction changed + * (the available tool set changed — possibly for one scope only). An + * UNFILTERED registry-subject notification, deliberately not scope-filtered + * dispatch: a global change concerns every agent's next assembly, so a + * scoped listener subscribing here sees every change, not just its own + * scope's. * @mode emit */ 'tools/change'(): void @@ -269,44 +284,88 @@ function errorInfo(error: unknown): ToolErrorInfo | undefined { return error instanceof HarnessError ? { name: error.name, code: error.code } : undefined } +/** + * A per-scope restriction over the GLOBAL tool surface, registered via + * {@link ToolRegistry.restrict}. `allow` keeps only the listed global tools; + * `deny` removes the listed ones; both present = allow first, then deny. + * Restrictions never touch scoped registrations — a tool registered through + * the same scope is an explicit grant that bypasses them (which is what keeps + * e.g. a structured-output capture tool alive under an allow-list). Multiple + * restrictions on one scope compose by intersection: every one must admit. + */ +export interface ToolRestriction { + /** Global tool names that stay visible; everything else is removed. */ + allow?: string[] + /** Global tool names removed from visibility. */ + deny?: string[] +} + /** * Tool registry (`ctx.tools`): tool plugins register definitions; the agent * loop executes calls through the `tools/pre-execute` → dispatch → * `tools/post-execute` pipeline. The registry contributes its schemas into the * system-prompt assembly. + * + * Two registration layers (`@deepseek-ai/dsh-scope`): a registration through a + * plain plugin context is GLOBAL (visible to every agent); one through a + * scoped context (`agent.ctx`) is filed in that scope's layer — visible to + * that agent alone, disposed with the scope, and SHADOWING a global tool of + * the same name for that agent (most-specific-wins; within one layer a + * duplicate name still throws). {@link restrict} masks the global layer per + * scope. One visibility function ({@link visible}) feeds prompt assembly, + * {@link get}, and {@link execute}, so what the model is shown, what a + * presenter renders, and what dispatches can never disagree. */ export class ToolRegistry extends Service { static inject = ['systemPrompt'] - private store = new Map() + private global = new Map() + private scoped = new Map>() + /** Snapshot-at-registration restriction filters, per scope (see {@link restrict}). */ + private restrictions = new Map() constructor(ctx: Context) { super(ctx, 'tools') - ctx.systemPrompt.tools(() => this.schemas()) + ctx.systemPrompt.tools(context => ({ + schemas: this.schemas(context.scope), + knownNames: this.knownNames(context.scope), + })) } /** - * Register a tool. Throws if a tool with the same name is already - * registered. The tool's schema (minus the `execute` function) is - * automatically contributed to the system-prompt assembly. Disposed - * with the calling fiber. Emits `tools/change` on register/unregister. + * Register a tool. The layer is decided by the CALLING context: a plain + * plugin context registers globally; a scoped context (`agent.ctx`) + * registers into that scope's layer — visible to that agent alone, disposed + * with the scope, and shadowing a same-named global tool for that agent. + * Throws if the SAME layer already has the name (cross-layer name twins are + * the shadowing feature, not an error; the global-duplicate message names + * `agent.ctx` as the per-agent alternative). The visible schema set flows + * into prompt assembly automatically. Disposed with the calling fiber. + * Emits `tools/change` on register/unregister. * @param definition - the tool's schema plus its execute (and optional * presentation) functions. * @returns the disposer that unregisters the tool. */ register(definition: ToolDefinition): () => void { + const scope = scopeOf(this.ctx) const dispose = this.ctx.effect(function* (this: ToolRegistry) { - if (this.store.has(definition.name)) { - throw new Error(`tool "${definition.name}" is already registered`) + const layer = scope === undefined ? this.global : this.layerFor(scope) + if (layer.has(definition.name)) { + throw new Error(scope === undefined + ? `tool "${definition.name}" is already registered (for a per-agent variant, register through that agent's \`agent.ctx\` instead)` + : `tool "${definition.name}" is already registered in this scope`) } - this.store.set(definition.name, definition) + layer.set(definition.name, definition) // Yield the rollback BEFORE emitting `tools/change`: a generator effect // collects each yielded disposer before the next step runs, so a throwing // `tools/change` listener removes the tool instead of leaking it (a leak // would wedge the duplicate-name check until restart). The duplicate // throw above fires before any mutation — it leaks nothing. yield () => { - this.store.delete(definition.name) + layer.delete(definition.name) + // An emptied scope layer is dropped so a disposed scope leaves no + // residue keyed by its (dead) key. + if (scope !== undefined && layer.size === 0) this.scoped.delete(scope) this.ctx.emit('tools/change') } this.ctx.emit('tools/change') @@ -317,33 +376,150 @@ export class ToolRegistry extends Service { } /** - * Look up a registered tool. - * @param name - the tool name as registered. - * @returns the definition, or undefined when no tool has that name. + * Restrict the GLOBAL tool surface for the calling scope. Must be called + * through a scoped context (`agent.ctx`) — restricting "everyone" is not a + * thing (throw), and an empty filter (neither `allow` nor `deny`) is a no-op + * that can only be a bug (throw — the materialized-empty-config trap). + * Validates every listed name against the scope's CURRENT pre-restriction + * name universe ({@link knownNames}) and throws on an unknown one (fail loud + * beats a typo silently filtering nothing) — register restrictions after the + * global tools they mask exist (the agent-creation `setup` window satisfies + * this). The filter is SNAPSHOT at registration: later caller mutation of + * the arrays changes nothing. Multiple restrictions compose by intersection. + * Scoped registrations bypass restrictions (explicit grants win). Disposed + * with the calling fiber (revocable independently); emits `tools/change`. + * @param filter - global-surface mask: `allow` (keep only) and/or `deny` (remove). + * @returns the disposer that lifts this restriction. */ - get(name: string): ToolDefinition | undefined { - return this.store.get(name) + restrict(filter: ToolRestriction): () => void { + const scope = scopeOf(this.ctx) + if (scope === undefined) { + throw new Error('tools.restrict() requires a scoped context (agent.ctx): a context-global restriction would mask every agent — deny the tool for the intended agent instead') + } + if (filter.allow === undefined && filter.deny === undefined) { + throw new Error('tools.restrict({}) is a no-op: pass `allow` and/or `deny` (an empty filter is almost always a materialized-empty-config bug)') + } + // Snapshot BEFORE validation so what was checked is what is enforced. + const snapshot: ToolRestriction = { + ...filter.allow !== undefined ? { allow: [...filter.allow] } : {}, + ...filter.deny !== undefined ? { deny: [...filter.deny] } : {}, + } + const known = new Set(this.knownNames(scope)) + const unknown = [...snapshot.allow ?? [], ...snapshot.deny ?? []].filter(name => !known.has(name)) + if (unknown.length > 0) { + throw new Error(`tools.restrict() names unknown tool${unknown.length > 1 ? 's' : ''} ${unknown.map(n => `"${n}"`).join(', ')}; known tools for this scope: ${[...known].sort().join(', ') || '(none)'}`) + } + const dispose = this.ctx.effect(function* (this: ToolRegistry) { + const list = this.restrictions.get(scope) ?? [] + this.restrictions.set(scope, list) + list.push(snapshot) + yield () => { + const index = list.indexOf(snapshot) + /* v8 ignore next 3 -- defensive: the snapshot was pushed, so indexOf is guaranteed >= 0 */ + if (index >= 0) list.splice(index, 1) + if (list.length === 0) this.restrictions.delete(scope) + this.ctx.emit('tools/change') + } + this.ctx.emit('tools/change') + }.bind(this), 'tools.restrict()') + // ctx.effect's disposer returns Promise; our disposer API is + // synchronous fire-and-forget — discard the (always-resolved) promise. + return () => void dispose() + } + + /** The (created-on-demand) scoped layer for `scope`. */ + private layerFor(scope: ScopeKey): Map { + let layer = this.scoped.get(scope) + if (!layer) { + layer = new Map() + this.scoped.set(scope, layer) + } + return layer + } + + /** Whether every restriction registered for `scope` admits the global tool `name` (intersection semantics). */ + private admits(scope: ScopeKey | undefined, name: string): boolean { + if (scope === undefined) return true + const filters = this.restrictions.get(scope) + if (!filters) return true + return filters.every(filter => + (filter.allow === undefined || filter.allow.includes(name)) + && (filter.deny === undefined || !filter.deny.includes(name))) } /** - * Return all registered tool schemas — exactly the model-facing fields - * (`name`, `description`, `parameters`), as sent to the model via the + * THE visibility function — one resolution feeding prompt assembly, + * {@link get}, and {@link execute}: the global layer masked by the scope's + * restrictions, unioned with the scope's own layer, scoped shadowing global + * on a name conflict. No scope = the unrestricted global view. + * @param scope - the viewing scope (the agent), or undefined for the global view. + * @returns the visible definitions (scoped shadows applied), in per-layer + * registration order, global layer first. + */ + visible(scope?: ScopeKey): ToolDefinition[] { + const layer = scope === undefined ? undefined : this.scoped.get(scope) + const result = new Map() + for (const [name, definition] of this.global) { + if (this.admits(scope, name)) result.set(name, definition) + } + // Scoped layer second: same-name entries REPLACE (shadow) the global ones, + // and grants bypass restrictions by construction (never filtered above). + for (const [name, definition] of layer ?? []) result.set(name, definition) + return [...result.values()] + } + + /** + * Look up a tool as one scope sees it ({@link visible} semantics: scoped + * shadows global; a restricted-away global reads as absent). Presenters pass + * the calling agent so the rendered card matches the definition that + * actually executed. + * @param name - the tool name as registered. + * @param scope - the viewing scope (the agent); omitted = the global view. + * @returns the definition the scope resolves, or undefined when none is visible. + */ + get(name: string, scope?: ScopeKey): ToolDefinition | undefined { + const shadowed = scope === undefined ? undefined : this.scoped.get(scope)?.get(name) + if (shadowed) return shadowed + if (!this.admits(scope, name)) return undefined + return this.global.get(name) + } + + /** + * The model-facing schemas of everything `scope` can see — exactly the + * fields (`name`, `description`, `parameters`) sent to the model via the * system-prompt assembly. Constructed EXPLICITLY rather than by stripping * known non-schema members: a `ToolDefinition` also carries `execute` and the * optional `presentCall`/`presentResult` UI callbacks, and those (especially * the functions) must never leak into a model request. An allowlist can't * drift when a new non-schema member is added to the definition; a denylist * (rest-destructure) would silently leak it. - * @returns one deep-cloned schema per registered tool, in registration order. + * @param scope - the viewing scope (the agent); omitted = the global view. + * @returns one deep-cloned schema per visible tool. */ - schemas(): ToolSchema[] { - return [...this.store.values()].map(({ name, description, parameters }): ToolSchema => ({ + schemas(scope?: ScopeKey): ToolSchema[] { + return this.visible(scope).map(({ name, description, parameters }): ToolSchema => ({ name, description, parameters: structuredClone(parameters), })) } + /** + * The PRE-restriction name universe for `scope`: every global name plus the + * scope's own layer, ignoring restrictions. This is the set configuration + * (`toolOrder`, `restrict()` filters) validates against, so a typo fails + * loud while a restricted-away tool remains a normal, non-erroneous absence. + * @param scope - the viewing scope (the agent); omitted = global names only. + * @returns the known names, deduplicated. + */ + knownNames(scope?: ScopeKey): string[] { + const names = new Set(this.global.keys()) + if (scope !== undefined) { + for (const name of this.scoped.get(scope)?.keys() ?? []) names.add(name) + } + return [...names] + } + /** * Execute one tool call through the `tools/pre-execute` → dispatch → * `tools/post-execute` pipeline. The two waterfalls are the gate (allow/deny) @@ -362,9 +538,12 @@ export class ToolRegistry extends Service { async execute(exec: ToolExecution): Promise { try { // --- Gate: tools/pre-execute. A deny (or an ask, which degrades to deny - // until the permission system lands) skips dispatch entirely. --- + // until the permission system lands) skips dispatch entirely. The + // carrier keys the dispatch by exec.agent, so an `agent.ctx` listener + // gates only its own agent's calls (agent-less calls are subject-less). + const carrier = scopeTarget(this, exec.agent) const decision = await this.ctx.waterfall( - this, 'tools/pre-execute', exec, + carrier, 'tools/pre-execute', exec, () => Promise.resolve({ kind: 'allow' }), ) if (decision.kind !== 'allow') { @@ -387,7 +566,11 @@ export class ToolRegistry extends Service { // inspect it; an unknown tool routes through the same catch. --- let result: ToolExecutionResult try { - const tool = this.store.get(exec.name) + // Resolve through the CALLER's visible view ({@link get}): a scoped + // tool shadows its global name-twin for that agent, and a + // restricted-away global tool is exactly as absent as a nonexistent + // one — same UNKNOWN_TOOL result, no capability leak in the error. + const tool = this.get(exec.name, exec.agent) if (!tool) throw new ToolNotFoundError(exec.name) // Normalize the two `execute` return shapes: a bare ContentBlock[] (no // meta) or a { content, meta } object (a tool attaching a private @@ -435,7 +618,7 @@ export class ToolRegistry extends Service { ...result.meta !== undefined ? { meta: result.meta } : {}, } const decision = await this.ctx.waterfall( - this, 'tools/post-execute', exec, result, + scopeTarget(this, exec.agent), 'tools/post-execute', exec, result, () => Promise.resolve({ kind: 'accept' }), ) const additionalContext = decision.additionalContext diff --git a/packages/core/tools/tests/scoped.spec.ts b/packages/core/tools/tests/scoped.spec.ts new file mode 100644 index 0000000000..027b5798de --- /dev/null +++ b/packages/core/tools/tests/scoped.spec.ts @@ -0,0 +1,172 @@ +import { describe, expect, it } from 'vitest' +import { Context } from 'cordis' +import { createScope } from '@deepseek-ai/dsh-scope' +import type { Scope } from '@deepseek-ai/dsh-scope' +import SystemPrompt from '@deepseek-ai/dsh-system-prompt' +import ToolRegistry from '@deepseek-ai/dsh-tools' +import type { PreToolDecision, ToolDefinition, ToolExecution } from '@deepseek-ai/dsh-tools' +import type { Agent, AgentId } from '@deepseek-ai/dsh-agent' +import { CallId } from '@deepseek-ai/dsh-llm' +import type { ContentBlock } from '@deepseek-ai/dsh-llm' + +/** Mount the registry (with its systemPrompt dependency) on a fresh context. */ +async function mount(): Promise { + const ctx = new Context() + await ctx.plugin(SystemPrompt, {}) + await ctx.plugin(ToolRegistry) + return ctx +} + +/** Mint a scope whose key doubles as a minimal Agent-like object. */ +async function mintAgentScope(ctx: Context, name: string): Promise<{ scope: Scope; key: Agent }> { + const key = { id: name as AgentId } as Agent + let scope!: Scope + // The scoped context resolves services through the MINTING plugin's + // dependency chain — the minter must inject what scope holders will reach + // (in production the agent loop's inject list plays this role). + await ctx.plugin(Object.assign((inner: Context) => { scope = createScope(inner, key) }, + { inject: ['tools', 'systemPrompt'] })) + return { scope, key } +} + +function tool(name: string, reply = `ran:${name}`): ToolDefinition { + return { + name, + description: `tool ${name}`, + parameters: { type: 'object', properties: {} }, + execute: (): Promise => Promise.resolve([{ type: 'text', text: reply }]), + } +} + +async function run(ctx: Context, name: string, agent?: Agent): Promise { + const result = await ctx.tools.execute({ + callId: CallId('c1'), + name, + arguments: {}, + ...agent ? { agent } : {}, + }) + const first = result.content[0] + return first?.type === 'text' ? first.text : JSON.stringify(result.content) +} + +describe('scoped tool registration', () => { + it('files a scoped tool in its layer: visible/executable for that scope only', async () => { + const ctx = await mount() + const { scope, key } = await mintAgentScope(ctx, 'a') + const other = { id: 'other' as AgentId } as Agent + ctx.tools.register(tool('shared')) + scope.ctx.tools.register(tool('mine')) + + expect(ctx.tools.schemas(key).map(t => t.name).sort()).toEqual(['mine', 'shared']) + expect(ctx.tools.schemas().map(t => t.name)).toEqual(['shared']) + expect(ctx.tools.schemas(other).map(t => t.name)).toEqual(['shared']) + + expect(await run(ctx, 'mine', key)).toBe('ran:mine') + // Out-of-view execution is indistinguishable from a nonexistent tool. + expect(await run(ctx, 'mine', other)).toBe('Error: unknown tool "mine"') + expect(await run(ctx, 'mine')).toBe('Error: unknown tool "mine"') + }) + + it('scoped shadows global on a name conflict, in either registration order', async () => { + const ctx = await mount() + const { scope, key } = await mintAgentScope(ctx, 'a') + // scoped-then-global + scope.ctx.tools.register(tool('bash', 'restricted-bash')) + ctx.tools.register(tool('bash', 'global-bash')) + expect(await run(ctx, 'bash', key)).toBe('restricted-bash') + expect(await run(ctx, 'bash')).toBe('global-bash') + expect(ctx.tools.get('bash', key)?.description).toBe(ctx.tools.get('bash', key)?.description) + // Exactly one 'bash' in the scope's schema view (the shadow, not a double). + expect(ctx.tools.schemas(key).filter(t => t.name === 'bash')).toHaveLength(1) + }) + + it('rejects a duplicate name within one layer, naming agent.ctx for the global case', async () => { + const ctx = await mount() + const { scope } = await mintAgentScope(ctx, 'a') + ctx.tools.register(tool('x')) + expect(() => ctx.tools.register(tool('x'))).toThrow(/agent\.ctx/) + scope.ctx.tools.register(tool('y')) + expect(() => scope.ctx.tools.register(tool('y'))).toThrow(/already registered in this scope/) + }) + + it('disposing the scope unwinds its registrations and leaves no residue', async () => { + const ctx = await mount() + const { scope, key } = await mintAgentScope(ctx, 'a') + scope.ctx.tools.register(tool('mine')) + expect(ctx.tools.get('mine', key)).toBeDefined() + await scope.dispose() + expect(ctx.tools.get('mine', key)).toBeUndefined() + expect(ctx.tools.knownNames(key)).toEqual([]) + }) +}) + +describe('restrict()', () => { + it('masks global tools for the scope; grants bypass; assembly and execute agree', async () => { + const ctx = await mount() + const { scope, key } = await mintAgentScope(ctx, 'a') + ctx.tools.register(tool('read')) + ctx.tools.register(tool('bash')) + scope.ctx.tools.register(tool('capture')) + scope.ctx.tools.restrict({ allow: ['read'] }) + + // The scoped grant survives the allow-list; the unlisted global is gone. + expect(ctx.tools.schemas(key).map(t => t.name).sort()).toEqual(['capture', 'read']) + expect(await run(ctx, 'bash', key)).toBe('Error: unknown tool "bash"') + expect(await run(ctx, 'read', key)).toBe('ran:read') + expect(await run(ctx, 'capture', key)).toBe('ran:capture') + // Other scopes and the global view are untouched. + expect(ctx.tools.schemas().map(t => t.name).sort()).toEqual(['bash', 'read']) + }) + + it('composes multiple restrictions by intersection and lifts each independently', async () => { + const ctx = await mount() + const { scope, key } = await mintAgentScope(ctx, 'a') + for (const name of ['a', 'b', 'c']) ctx.tools.register(tool(name)) + const liftAllow = scope.ctx.tools.restrict({ allow: ['a', 'b'] }) + scope.ctx.tools.restrict({ deny: ['b'] }) + expect(ctx.tools.schemas(key).map(t => t.name)).toEqual(['a']) + liftAllow() + // The deny remains after the allow-list is lifted. + expect(ctx.tools.schemas(key).map(t => t.name).sort()).toEqual(['a', 'c']) + }) + + it('snapshots the filter at registration (caller mutation changes nothing)', async () => { + const ctx = await mount() + const { scope, key } = await mintAgentScope(ctx, 'a') + ctx.tools.register(tool('a')) + ctx.tools.register(tool('b')) + const filter = { deny: ['a'] } + scope.ctx.tools.restrict(filter) + filter.deny.push('b') + expect(ctx.tools.schemas(key).map(t => t.name)).toEqual(['b']) + }) + + it('fails loud on an unscoped call, an empty filter, and unknown names', async () => { + const ctx = await mount() + const { scope } = await mintAgentScope(ctx, 'a') + ctx.tools.register(tool('real')) + expect(() => ctx.tools.restrict({ deny: ['real'] })).toThrow(/requires a scoped context/) + expect(() => scope.ctx.tools.restrict({})).toThrow(/no-op/) + expect(() => scope.ctx.tools.restrict({ allow: ['reall'] })).toThrow(/unknown tool "reall"; known tools for this scope: real/) + }) +}) + +describe('scoped execution dispatch', () => { + it('an agent.ctx pre-execute listener gates only its own agent (and never subject-less calls)', async () => { + const ctx = await mount() + const { scope, key } = await mintAgentScope(ctx, 'a') + const other = { id: 'other' as AgentId } as Agent + ctx.tools.register(tool('t')) + + const seen: (string | undefined)[] = [] + scope.ctx.on('tools/pre-execute', (exec: ToolExecution, _next: () => Promise) => { + seen.push(exec.agent?.id) + return Promise.resolve({ kind: 'deny', reason: 'scoped veto' }) + }) + + expect(await run(ctx, 't', key)).toBe('Error: scoped veto') + expect(await run(ctx, 't', other)).toBe('ran:t') + expect(await run(ctx, 't')).toBe('ran:t') + expect(seen).toEqual(['a']) + }) +}) diff --git a/packages/core/tools/tsconfig.json b/packages/core/tools/tsconfig.json index dedc111d87..be21db9ada 100644 --- a/packages/core/tools/tsconfig.json +++ b/packages/core/tools/tsconfig.json @@ -22,6 +22,9 @@ }, { "path": "../../core/agent" + }, + { + "path": "../../core/scope" } ] } diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 8251dc62e9..9238bbea1e 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -183,6 +183,9 @@ importers: '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm + '@deepseek-ai/dsh-scope': + specifier: workspace:^ + version: link:../scope '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../session @@ -245,6 +248,9 @@ importers: '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm + '@deepseek-ai/dsh-scope': + specifier: workspace:^ + version: link:../scope '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../session @@ -278,6 +284,9 @@ importers: '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm + '@deepseek-ai/dsh-scope': + specifier: workspace:^ + version: link:../scope cordis: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) @@ -291,6 +300,9 @@ importers: '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm + '@deepseek-ai/dsh-scope': + specifier: workspace:^ + version: link:../scope cordis: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) @@ -303,6 +315,9 @@ importers: '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm + '@deepseek-ai/dsh-scope': + specifier: workspace:^ + version: link:../scope '@deepseek-ai/dsh-system-prompt': specifier: workspace:^ version: link:../system-prompt