Merge origin/master into parallel-tool-call
This commit is contained in:
Dudu-0223
@@ -10,10 +10,9 @@ The session log, system-prompt assembly, tool registry, agent vocabulary, and co
|
||||
| `tools/` | Scoped tool registry + pre-policy, guards, around-dispatch, post-policy, and final-result observation | `ctx.tools` |
|
||||
| `agent/` | Agent interface, registry, `agent/*` event vocabulary | `ctx.agents` |
|
||||
| `agent-loop/` | The concrete loop plugin: `ReactLoopAgent` + the loop driver | `ctx.agentLoop` |
|
||||
| `agent-core/` | Bundle plugin: the default executor-less/UI-less spine as code | (loads the spine) |
|
||||
|
||||
`scope/` is the one non-service package here: a dependency-free library (`createScope`/`scopeOf`/`scopeTarget`) the registries and the loop build per-agent scoping on — it sits below `session/` and `system-prompt/` in the module graph precisely so they can consume it without a cycle.
|
||||
|
||||
`agent-loop` is the one concrete implementation of the `agent` seam and lives here because it is the harness's default product loop; everything else in `core/` is interface/vocabulary. Plugins depend on the `agent` vocabulary, never on `agent-loop` directly, so the loop stays swappable.
|
||||
|
||||
`agent-core` is the composition counterpart: one bundle plugin that loads the control spine plus selected default capabilities (`timer` + `llm` + sessions + system-prompt + tools + agents + invariants + the local [skill family](../skill/README.md) + `tool-bash` + `agent-loop`) and forwards `agent-loop`'s `agents` list as its own config. App packages (`ui/stdio-agent`, `ui/acp-agent`) consume it and add only a front door; a leaf adds the swappable backends plus any optional product tools it wants to expose. It lives in `core/` because it composes the shared control spine while leaving executors, LLM adapters, alternate skill providers, and UI front doors outside the bundle.
|
||||
The default composition that wires this spine into a runnable agent lives in [`examples/agent-spine-demo`](../examples/agent-spine-demo/README.md): one bundle plugin that loads the control spine plus selected default capabilities (`timer` + `llm` + sessions + system-prompt + tools + agents + invariants + the local [skill family](../skill/README.md) + `tool-bash` + `agent-loop`) and forwards `agent-loop`'s `agents` list as its own config. It sits in `examples/` — ready-to-run demo/reference bundles — not in `core/`: `core/` ships the swappable spine pieces, while a demo bundle picks one concrete composition of them and adds a front door.
|
||||
|
||||
@@ -1,59 +0,0 @@
|
||||
# @deepseek-ai/dsh-agent-core
|
||||
|
||||
The **default executor-less, UI-less agent spine** as ONE Cordis bundle plugin. It loads the fixed set of services every harness agent needs, including the local skill provider, and forwards the loop's `agents` list as its own config — so an app package composes a working agent by adding only a front door and the swappable backends.
|
||||
|
||||
Read this package for the whole plugin tree and its composition order.
|
||||
|
||||
## The tree it loads
|
||||
|
||||
`apply(ctx, config)` mounts each of these as a child of the bundle fiber:
|
||||
|
||||
```
|
||||
@cordisjs/plugin-timer timer service (writes nothing to stdout)
|
||||
@deepseek-ai/dsh-llm abstract LLM service + content-block vocabulary
|
||||
@deepseek-ai/dsh-session event-sourced session log + store
|
||||
@deepseek-ai/dsh-system-prompt prompt-section + tool-schema assembly
|
||||
@deepseek-ai/dsh-tools registry + guarded pre/around/post/final-result pipeline
|
||||
@deepseek-ai/dsh-skill skill provider registry
|
||||
@deepseek-ai/dsh-skill-local local filesystem skill provider
|
||||
@deepseek-ai/dsh-agent agent registry + agent/* event vocabulary
|
||||
@deepseek-ai/dsh-invariants runtime event-contract assertions
|
||||
@deepseek-ai/dsh-tool-bash the model-facing bash/bash_output/bash_kill schemas
|
||||
@deepseek-ai/dsh-tool-skill session-prefix skill catalog + model-facing loader schema
|
||||
@deepseek-ai/dsh-agent-loop THE concrete loop (gets the forwarded `agents`)
|
||||
(dsh-system-prompt gets the forwarded `persona`)
|
||||
```
|
||||
|
||||
## What it deliberately leaves OUTSIDE the bundle
|
||||
|
||||
The spine is everything COMMON to every front door. The swappable and front-door-coupled pieces stay out, picked by whatever loads the bundle:
|
||||
|
||||
- **the LLM adapter** — the bundle ships the abstract `llm` service; the leaf registers a concrete adapter on `ctx.llm` (`llm-deepseek`, `llm-pi-ai`, `llm-replay`).
|
||||
- **the bash executor** — the bundle ships `tool-bash` (the consumer schema); the leaf provides `ctx.bash` (`bash-local` or a sandboxed impl).
|
||||
- **non-local skill providers** — the bundle ships the skill registry, the local filesystem provider, and the `skill` tool; deployments can add other providers such as embedded or remote catalogs as siblings.
|
||||
- **presentation + per-app infra** — the stdio UI / ACP bridge, a console logger, `hmr`. These form the coupled "front-door cluster" that the app packages ([`dsh-stdio-agent`](../../ui/stdio-agent/README.md), [`dsh-acp-agent`](../../ui/acp-agent/README.md)) bake in. `timer` is in the spine (common to both, stdout-silent); a console logger is NOT (it writes to stdout, which the ACP bridge reserves for JSON-RPC).
|
||||
|
||||
This is the [interface/implementation/consumer seam](../../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md) raised to the composition level: the bundle owns the shared spine, the leaf owns the backends, the app package owns the front door.
|
||||
|
||||
## Config
|
||||
|
||||
```ts
|
||||
import type { Config } from '@deepseek-ai/dsh-agent-core'
|
||||
// { agents?, maxParallelToolCalls?, persona?, toolOrder?, tools?, skills? } — the schema
|
||||
// intersects the owner schemas, so validation and defaulting can never drift from the owners.
|
||||
```
|
||||
|
||||
The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates a `main`; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `maxParallelToolCalls` to `agent-loop` as the shared concurrent tool-call cap for every agent it creates; `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; and `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer. Forwarding is exactly why the owners can live in the shared spine even though the apps disagree on what to configure.
|
||||
|
||||
## Why a code bundle, not a shared YAML include
|
||||
|
||||
A YAML include can deduplicate config but cannot own a bin or provide front-door defaults. App packages make stdout-safe ACP wiring the default, though a leaf can still add an unsafe logger. Bundle children register services in the root isolate-keyed store, so injected leaf siblings see them without load-order coupling.
|
||||
|
||||
## Model Experience
|
||||
|
||||
Indirectly, through `dsh-system-prompt`, `dsh-tool-skill`, `dsh-tool-bash`, and `dsh-tools`, which this bundle mounts without adding model-bound wrapper content.
|
||||
|
||||
## Known Limitations and Deferred Work
|
||||
|
||||
- **The spine set is fixed in code** — `apply()` mounts every child unconditionally (including `tool-bash`); no config excludes or replaces one, so swapping the loop or dropping a spine member means composing a different bundle.
|
||||
- **`dsh-invariants` mounts unconditionally** — this bundle has no toggle, so every composition using it pays the dev-mode relational assertions; Session's always-on validation and freezing are separate.
|
||||
@@ -1,57 +0,0 @@
|
||||
{
|
||||
"name": "@deepseek-ai/dsh-agent-core",
|
||||
"description": "The default executor-less/UI-less agent spine as one Cordis bundle plugin (timer + llm + sessions + system-prompt + tools + skills + agents + invariants + tool-bash + tool-skill + agent-loop)",
|
||||
"version": "0.0.1",
|
||||
"private": true,
|
||||
"type": "module",
|
||||
"main": "lib/index.js",
|
||||
"types": "lib/types/index.d.ts",
|
||||
"exports": {
|
||||
".": {
|
||||
"types": "./lib/types/index.d.ts",
|
||||
"default": "./lib/index.js"
|
||||
},
|
||||
"./src/*": "./src/*",
|
||||
"./package.json": "./package.json"
|
||||
},
|
||||
"files": [
|
||||
"lib/index.js",
|
||||
"lib/types/**/*.d.ts",
|
||||
"lib/types/**/*.d.ts.map",
|
||||
"src"
|
||||
],
|
||||
"license": "BSD-3-Clause",
|
||||
"peerDependencies": {
|
||||
"@cordisjs/plugin-timer": "^1.1.2",
|
||||
"@deepseek-ai/dsh-agent": "^0.0.1",
|
||||
"@deepseek-ai/dsh-agent-loop": "^0.0.1",
|
||||
"@deepseek-ai/dsh-invariants": "^0.0.1",
|
||||
"@deepseek-ai/dsh-llm": "^0.0.1",
|
||||
"@deepseek-ai/dsh-session": "^0.0.1",
|
||||
"@deepseek-ai/dsh-skill": "^0.0.1",
|
||||
"@deepseek-ai/dsh-skill-local": "^0.0.1",
|
||||
"@deepseek-ai/dsh-system-prompt": "^0.0.1",
|
||||
"@deepseek-ai/dsh-tool-bash": "^0.0.1",
|
||||
"@deepseek-ai/dsh-tool-skill": "^0.0.1",
|
||||
"@deepseek-ai/dsh-tools": "^0.0.1",
|
||||
"cordis": "^4.0.0-rc.6"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@cordisjs/plugin-timer": "workspace:^",
|
||||
"@deepseek-ai/dsh-agent": "workspace:^",
|
||||
"@deepseek-ai/dsh-agent-loop": "workspace:^",
|
||||
"@deepseek-ai/dsh-invariants": "workspace:^",
|
||||
"@deepseek-ai/dsh-llm": "workspace:^",
|
||||
"@deepseek-ai/dsh-session": "workspace:^",
|
||||
"@deepseek-ai/dsh-skill": "workspace:^",
|
||||
"@deepseek-ai/dsh-skill-local": "workspace:^",
|
||||
"@deepseek-ai/dsh-system-prompt": "workspace:^",
|
||||
"@deepseek-ai/dsh-tool-bash": "workspace:^",
|
||||
"@deepseek-ai/dsh-tool-skill": "workspace:^",
|
||||
"@deepseek-ai/dsh-tools": "workspace:^",
|
||||
"cordis": "^4.0.0-rc.6"
|
||||
},
|
||||
"dependencies": {
|
||||
"schemastery": "^3.18.0"
|
||||
}
|
||||
}
|
||||
@@ -1,107 +0,0 @@
|
||||
/**
|
||||
* Default executor-less, UI-less agent spine. It bundles the common services,
|
||||
* concrete loop, local skill provider, and model-facing bash/skill consumers;
|
||||
* deployments still choose the LLM adapter, bash executor, and presentation.
|
||||
* The plugin intentionally exposes named exports only because Loader default
|
||||
* unwrapping would discard its `Config` schema (see docs/postmortem/0001).
|
||||
* @module @deepseek-ai/dsh-agent-core
|
||||
*/
|
||||
|
||||
import type { Context } from 'cordis'
|
||||
import Timer from '@cordisjs/plugin-timer'
|
||||
import z from 'schemastery'
|
||||
import LlmService from '@deepseek-ai/dsh-llm'
|
||||
import SessionStore from '@deepseek-ai/dsh-session'
|
||||
import SystemPrompt, { type Config as SystemPromptConfig } from '@deepseek-ai/dsh-system-prompt'
|
||||
import ToolRegistry, { type Config as ToolsConfig } from '@deepseek-ai/dsh-tools'
|
||||
import SkillService, { type Config as SkillRegistryConfig } from '@deepseek-ai/dsh-skill'
|
||||
import * as SkillLocal from '@deepseek-ai/dsh-skill-local'
|
||||
import AgentRegistry from '@deepseek-ai/dsh-agent'
|
||||
import * as invariants from '@deepseek-ai/dsh-invariants'
|
||||
import * as toolBash from '@deepseek-ai/dsh-tool-bash'
|
||||
import * as toolSkill from '@deepseek-ai/dsh-tool-skill'
|
||||
import AgentLoop, { type Config as AgentLoopConfig } from '@deepseek-ai/dsh-agent-loop'
|
||||
|
||||
export const name = 'agent-core'
|
||||
|
||||
/** Skill bundle config forwarded to the registry, local provider, and model-facing consumer. */
|
||||
export interface SkillConfig {
|
||||
/** Registry-level discovery cache settings. */
|
||||
registry?: SkillRegistryConfig
|
||||
/** Local filesystem skill provider settings. */
|
||||
local?: SkillLocal.Config
|
||||
/** Model-facing skill catalog and tool settings. */
|
||||
tool?: toolSkill.Config
|
||||
}
|
||||
|
||||
/**
|
||||
* Bundle config: each field forwarded verbatim to the child that owns it — `agents` to the
|
||||
* agent loop (an app that pre-creates no agents, like the ACP bridge, omits it),
|
||||
* `persona` and `toolOrder` to the system-prompt plugin (the deployment's persona section and
|
||||
* the explicit model-facing tool order), the `tools` object to the tool registry (its
|
||||
* presentation `mode`), and `skills` to the skill registry/local provider/tool consumer.
|
||||
* The schema intersects the owners' schemas, which supply defaults for every
|
||||
* optional input and keep validation from drifting.
|
||||
*/
|
||||
export interface Config {
|
||||
/** The agent-loop `agents` list (see dsh-agent-loop's `Config`). */
|
||||
agents?: AgentLoopConfig['agents']
|
||||
/**
|
||||
* Concurrent tool-call cap shared by every agent this bundle's loop creates
|
||||
* (see dsh-agent-loop's `Config.maxParallelToolCalls`).
|
||||
*/
|
||||
maxParallelToolCalls?: AgentLoopConfig['maxParallelToolCalls']
|
||||
/** The deployment persona (see dsh-system-prompt's `Config`). */
|
||||
persona?: SystemPromptConfig['persona']
|
||||
/** The explicit model-facing tool order (see dsh-system-prompt's `Config`). */
|
||||
toolOrder?: SystemPromptConfig['toolOrder']
|
||||
/** The tool registry's config — its presentation `mode` (see dsh-tools' `Config`). */
|
||||
tools?: ToolsConfig
|
||||
/** Skill registry, local provider, and model-facing consumer config. */
|
||||
skills?: SkillConfig
|
||||
}
|
||||
|
||||
/** The skill config schema exported for app packages that forward `skills`. */
|
||||
export const SkillConfigSchema: z<SkillConfig> = z.object({
|
||||
registry: SkillService.Config,
|
||||
local: SkillLocal.Config,
|
||||
tool: toolSkill.Config,
|
||||
})
|
||||
|
||||
/** Intersect the owners' schemas so validation + defaulting stay identical. */
|
||||
export const Config = z.intersect([
|
||||
AgentLoop.Config,
|
||||
SystemPrompt.Config,
|
||||
z.object({ tools: ToolRegistry.Config, skills: SkillConfigSchema }),
|
||||
]) as unknown as z<Config>
|
||||
|
||||
/**
|
||||
* Load the spine. Each `ctx.plugin(...)` mounts one child of the bundle fiber;
|
||||
* `agent-loop` receives the forwarded `agents` list and `system-prompt` the
|
||||
* forwarded `persona` and `toolOrder`. Load order is irrelevant (cordis pends
|
||||
* each fiber on its `inject` until the services it needs exist), but the
|
||||
* listing mirrors the dependency layering for readability: the LLM vocabulary
|
||||
* and core registries first, then the dev tripwire and the bash tool consumer,
|
||||
* then the loop that drives them.
|
||||
*/
|
||||
export function apply(ctx: Context, config: Config): void {
|
||||
ctx.plugin(Timer)
|
||||
ctx.plugin(LlmService)
|
||||
ctx.plugin(SessionStore)
|
||||
// Owner schemas resolve defaults; forward toolOrder only when explicitly set.
|
||||
ctx.plugin(SystemPrompt, {
|
||||
persona: config.persona ?? '',
|
||||
...config.toolOrder !== undefined ? { toolOrder: config.toolOrder } : {},
|
||||
})
|
||||
ctx.plugin(ToolRegistry, config.tools ?? {})
|
||||
ctx.plugin(SkillService, config.skills?.registry ?? {})
|
||||
ctx.plugin(SkillLocal, config.skills?.local ?? {})
|
||||
ctx.plugin(AgentRegistry)
|
||||
ctx.plugin(invariants)
|
||||
ctx.plugin(toolBash)
|
||||
ctx.plugin(toolSkill, config.skills?.tool ?? {})
|
||||
ctx.plugin(AgentLoop, {
|
||||
agents: config.agents ?? [],
|
||||
...config.maxParallelToolCalls !== undefined ? { maxParallelToolCalls: config.maxParallelToolCalls } : {},
|
||||
})
|
||||
}
|
||||
@@ -1,211 +0,0 @@
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { mkdir, mkdtemp, writeFile } from 'node:fs/promises'
|
||||
import { join } from 'node:path'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { Context } from 'cordis'
|
||||
import Loader from '@cordisjs/plugin-loader'
|
||||
import { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt'
|
||||
import * as agentCore from '../src/index.ts'
|
||||
import { AgentId, agentEvents, type Agent } from '@deepseek-ai/dsh-agent'
|
||||
import type { Message } from '@deepseek-ai/dsh-llm'
|
||||
|
||||
async function composePrefix(ctx: Context, cwd: string): Promise<Message[]> {
|
||||
const agent = { session: { header: { cwd } } } as unknown as Agent
|
||||
const empty: Message[] = []
|
||||
return await agentEvents(ctx, agent).waterfall(
|
||||
'agent/session-prefix', empty, new AbortController().signal,
|
||||
() => Promise.resolve(empty),
|
||||
)
|
||||
}
|
||||
|
||||
/**
|
||||
* Unit coverage for the @deepseek-ai/dsh-agent-core bundle: mounting it brings
|
||||
* up the whole default spine in one `ctx.plugin`, and the forwarded
|
||||
* `agents` config reaches the loop (default `[]`, or a pre-created agent).
|
||||
*
|
||||
* The bundle is exercised through `ctx.plugin(agentCore, …)` — the NAMESPACE
|
||||
* import, the same shape the Loader builds from `unwrapExports`. The real
|
||||
* Loader-path guard (export shape, `unwrapExports`) is the app packages' keyless
|
||||
* bin smokes; here we assert the composition + config forwarding.
|
||||
*/
|
||||
async function mount(config?: agentCore.Config): Promise<Context> {
|
||||
const oldDshHome = process.env.DSH_HOME
|
||||
const oldAgentsHome = process.env.DSH_AGENTS_HOME
|
||||
process.env.DSH_HOME = await mkdtemp(join(tmpdir(), 'dsh-agent-core-home-'))
|
||||
process.env.DSH_AGENTS_HOME = await mkdtemp(join(tmpdir(), 'dsh-agent-core-agents-'))
|
||||
const ctx = new Context()
|
||||
try {
|
||||
await ctx.plugin(agentCore, config)
|
||||
// The bundle mounts its children inside apply() (not awaited there); let their
|
||||
// fibers settle so the spine services and any pre-created agent are ready.
|
||||
await new Promise(resolve => setTimeout(resolve, 50))
|
||||
return ctx
|
||||
} finally {
|
||||
if (oldDshHome === undefined) {
|
||||
delete process.env.DSH_HOME
|
||||
} else {
|
||||
process.env.DSH_HOME = oldDshHome
|
||||
}
|
||||
if (oldAgentsHome === undefined) {
|
||||
delete process.env.DSH_AGENTS_HOME
|
||||
} else {
|
||||
process.env.DSH_AGENTS_HOME = oldAgentsHome
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
async function withIsolatedSkillHomes<T>(run: () => Promise<T>): Promise<T> {
|
||||
const oldDshHome = process.env.DSH_HOME
|
||||
const oldAgentsHome = process.env.DSH_AGENTS_HOME
|
||||
process.env.DSH_HOME = await mkdtemp(join(tmpdir(), 'dsh-agent-core-home-'))
|
||||
process.env.DSH_AGENTS_HOME = await mkdtemp(join(tmpdir(), 'dsh-agent-core-agents-'))
|
||||
try {
|
||||
return await run()
|
||||
} finally {
|
||||
if (oldDshHome === undefined) {
|
||||
delete process.env.DSH_HOME
|
||||
} else {
|
||||
process.env.DSH_HOME = oldDshHome
|
||||
}
|
||||
if (oldAgentsHome === undefined) {
|
||||
delete process.env.DSH_AGENTS_HOME
|
||||
} else {
|
||||
process.env.DSH_AGENTS_HOME = oldAgentsHome
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
describe('dsh-agent-core bundle', () => {
|
||||
it('brings up the full default spine', async () => {
|
||||
const ctx = await mount()
|
||||
// One service from each layer of the spine proves the children loaded.
|
||||
expect(ctx.get('timer')).toBeDefined()
|
||||
expect(ctx.get('llm')).toBeDefined()
|
||||
expect(ctx.get('sessions')).toBeDefined()
|
||||
expect(ctx.get('systemPrompt')).toBeDefined()
|
||||
expect(ctx.get('tools')).toBeDefined()
|
||||
expect(ctx.get('skills')).toBeDefined()
|
||||
expect(ctx.get('agents')).toBeDefined()
|
||||
expect(ctx.get('agentLoop')).toBeDefined()
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('includes the skill registry, local provider, and skill tool without builtin skills', async () => {
|
||||
const ctx = await mount()
|
||||
|
||||
expect(ctx.skills).toBeDefined()
|
||||
expect(ctx.tools.schemas().map(tool => tool.name)).toContain('skill')
|
||||
expect(await ctx.skills.list()).toEqual([])
|
||||
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('defaults the agents list to empty (no pre-created agents)', async () => {
|
||||
const ctx = await mount()
|
||||
expect(ctx.get('agents')?.get(AgentId('main'))).toBeUndefined()
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('forwards a pre-created agent to the loop and the persona to system-prompt', async () => {
|
||||
const ctx = await mount({
|
||||
agents: [{ id: AgentId('main'), model: 'mock' }],
|
||||
persona: 'You are main.',
|
||||
})
|
||||
expect(ctx.get('agents')?.get(AgentId('main'))).toBeDefined()
|
||||
const assembly = await ctx.get('systemPrompt')!.assemble()
|
||||
expect(assembly.sections.find(s => s.name === 'deployment:persona')?.text).toBe('You are main.')
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('forwards the global maxParallelToolCalls config to agent-loop', async () => {
|
||||
const ctx = await mount({
|
||||
agents: [{ id: AgentId('main'), model: 'mock' }],
|
||||
maxParallelToolCalls: 3,
|
||||
})
|
||||
expect(ctx.get('agentLoop')?.config.maxParallelToolCalls).toBe(3)
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('tolerates a schema-bypassing direct apply (the ?? fallbacks fire)', async () => {
|
||||
// ctx.plugin validates + defaults the bundle config first; a direct apply
|
||||
// skips the schema, so the forwarding `?? []` / `?? ''` are what fire.
|
||||
const ctx = new Context()
|
||||
agentCore.apply(ctx, {})
|
||||
await new Promise(resolve => setTimeout(resolve, 50))
|
||||
expect(ctx.get('agentLoop')).toBeDefined()
|
||||
expect(ctx.get('agents')?.list()).toHaveLength(0)
|
||||
const assembly = await ctx.get('systemPrompt')!.assemble()
|
||||
expect(assembly.sections.find(s => s.name === 'deployment:persona')?.text).toBe('')
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('forwards skill config to the registry, local provider, and model-facing consumer', async () => {
|
||||
const home = await mkdtemp(join(tmpdir(), 'dsh-agent-core-skill-home-'))
|
||||
const agentsHome = await mkdtemp(join(tmpdir(), 'dsh-agent-core-skill-agents-'))
|
||||
const custom = await mkdtemp(join(tmpdir(), 'dsh-agent-core-skill-custom-'))
|
||||
await mkdir(custom, { recursive: true })
|
||||
await writeFile(join(custom, 'custom-skill.md'), '---\nname: custom-skill\ndescription: Custom skill\n---\n\nCustom body.\n')
|
||||
const ctx = await mount({
|
||||
agents: [],
|
||||
skills: {
|
||||
registry: { collectCacheMaxEntries: 4 },
|
||||
local: {
|
||||
dshHome: join(home, '.dsh'),
|
||||
agentsHome: join(agentsHome, '.agents'),
|
||||
customSkillDirs: [custom],
|
||||
},
|
||||
tool: { catalogDescriptionMaxLength: 6 },
|
||||
},
|
||||
})
|
||||
expect((await ctx.skills.list()).map(skill => skill.name)).toEqual(['custom-skill'])
|
||||
expect(JSON.stringify(await composePrefix(ctx, '/tmp'))).toContain('- `custom-skill`: Cus...')
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('uses the default skill config when apply is called directly without skills', async () => {
|
||||
await withIsolatedSkillHomes(async () => {
|
||||
const ctx = new Context()
|
||||
agentCore.apply(ctx, { agents: [] })
|
||||
await new Promise(resolve => setTimeout(resolve, 50))
|
||||
expect(ctx.skills).toBeDefined()
|
||||
expect(await ctx.skills.list()).toEqual([])
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
})
|
||||
|
||||
it('forwards toolOrder to the system-prompt assembly', async () => {
|
||||
const ctx = await mount({ toolOrder: ['zulu', TOOL_ORDER_REST] })
|
||||
// The bundle's own bash tools pend on the absent `ctx.bash` executor in
|
||||
// this providerless mount, so register two plain tools to order.
|
||||
for (const name of ['alpha', 'zulu']) {
|
||||
ctx.get('tools')!.register({
|
||||
name,
|
||||
description: name,
|
||||
parameters: {},
|
||||
execute: async () => [],
|
||||
})
|
||||
}
|
||||
const assembly = await ctx.get('systemPrompt')!.assemble()
|
||||
expect(assembly.tools.map(tool => tool.name)).toEqual(['zulu', 'alpha', 'skill'])
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('re-exports the loop config schema as its own', () => {
|
||||
expect(agentCore.Config).toBeDefined()
|
||||
expect(agentCore.name).toBe('agent-core')
|
||||
})
|
||||
|
||||
it('has the namespace-plugin export shape (no stray default) so the Loader keeps name/Config/apply', () => {
|
||||
// A default export would make `unwrapExports` collapse this inject-less namespace and silently
|
||||
// drop `name`/`Config`. Apps import the bundle directly, so this is its Loader-shape guard.
|
||||
expect('default' in agentCore).toBe(false)
|
||||
expect(typeof agentCore.apply).toBe('function')
|
||||
|
||||
const loader = Object.create(Loader.prototype) as Loader
|
||||
const unwrapped = loader.unwrapExports(agentCore) as Record<string, unknown>
|
||||
expect(unwrapped).toBe(agentCore)
|
||||
expect(unwrapped.name).toBe('agent-core')
|
||||
expect(unwrapped.Config).toBeDefined()
|
||||
expect(typeof unwrapped.apply).toBe('function')
|
||||
})
|
||||
})
|
||||
@@ -1,445 +0,0 @@
|
||||
/**
|
||||
* Negative-path tests for the config catalog generator (`scripts/gen-config-catalog.ts`).
|
||||
*/
|
||||
|
||||
import { mkdtempSync, mkdirSync, rmSync, writeFileSync } from 'node:fs'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join } from 'node:path'
|
||||
import { afterEach, describe, expect, it } from 'vitest'
|
||||
import { collectConfigCatalog, render } from '../../../../scripts/gen-config-catalog.ts'
|
||||
|
||||
/** Write one fixture package (package.json + src files) under a scan root. */
|
||||
function writePkg(root: string, dir: string, name: string, files: Record<string, string>): void {
|
||||
const pkgDir = join(root, 'packages', dir)
|
||||
mkdirSync(join(pkgDir, 'src'), { recursive: true })
|
||||
writeFileSync(join(pkgDir, 'package.json'), JSON.stringify({ name }))
|
||||
for (const [rel, text] of Object.entries(files)) writeFileSync(join(pkgDir, rel), text)
|
||||
}
|
||||
|
||||
const roots: string[] = []
|
||||
const makeRoot = (): string => {
|
||||
const root = mkdtempSync(join(tmpdir(), 'config-catalog-'))
|
||||
roots.push(root)
|
||||
return root
|
||||
}
|
||||
/** One-package fixture: the common case. */
|
||||
const make = (files: Record<string, string>, name = '@fix/one'): string => {
|
||||
const root = makeRoot()
|
||||
writePkg(root, 'group/one', name, files)
|
||||
return root
|
||||
}
|
||||
|
||||
afterEach(() => {
|
||||
while (roots.length) rmSync(roots.pop()!, { recursive: true, force: true })
|
||||
})
|
||||
|
||||
const DOCUMENTED_CONFIG = `/** Fixture config. */
|
||||
export interface Config {
|
||||
/** A knob. */
|
||||
knob?: string
|
||||
}
|
||||
`
|
||||
|
||||
describe('gen-config-catalog classification', () => {
|
||||
it('classifies an apply plugin with a config parameter and extracts the paste', () => {
|
||||
const entries = collectConfigCatalog(make({
|
||||
'src/index.ts': `import type { Context } from 'cordis'
|
||||
export const inject = ['tools']
|
||||
${DOCUMENTED_CONFIG}
|
||||
/** Load. */
|
||||
export function apply(ctx: Context, config: Config): void {}
|
||||
`,
|
||||
}))
|
||||
expect(entries).toHaveLength(1)
|
||||
expect(entries[0]).toMatchObject({ pkg: '@fix/one', kind: 'config', configTypeName: 'Config', inject: ['tools'] })
|
||||
expect(entries[0]?.pastes?.[0]?.text).toContain('/** A knob. */')
|
||||
})
|
||||
|
||||
it('classifies a default service class, reading its constructor and static inject', () => {
|
||||
const entries = collectConfigCatalog(make({
|
||||
'src/index.ts': `import type { Context } from 'cordis'
|
||||
import z from 'schemastery'
|
||||
${DOCUMENTED_CONFIG}
|
||||
/** Fixture service. */
|
||||
export default class Fix {
|
||||
static inject = ['llm']
|
||||
static Config = z.object({ knob: z.string() }) as unknown as z<Config>
|
||||
constructor(ctx: Context, config: Config) {}
|
||||
}
|
||||
`,
|
||||
}))
|
||||
expect(entries[0]).toMatchObject({ kind: 'config', className: 'Fix', inject: ['llm'], schemaKeys: ['knob'] })
|
||||
})
|
||||
|
||||
it('classifies an abstract default class as a seam', () => {
|
||||
const entries = collectConfigCatalog(make({
|
||||
'src/index.ts': 'export default abstract class FixSeam { abstract run(): void }\n',
|
||||
}))
|
||||
expect(entries[0]).toMatchObject({ kind: 'seam', className: 'FixSeam' })
|
||||
})
|
||||
|
||||
it('classifies a plugin whose apply takes no config as no-config', () => {
|
||||
const entries = collectConfigCatalog(make({
|
||||
'src/index.ts': 'import type { Context } from \'cordis\'\n/** Load. */\nexport function apply(ctx: Context): void {}\n',
|
||||
}))
|
||||
expect(entries[0]?.kind).toBe('no-config')
|
||||
})
|
||||
|
||||
it('classifies a module with neither default export nor apply as a library', () => {
|
||||
const entries = collectConfigCatalog(make({
|
||||
'src/index.ts': 'export const helper = 1\n',
|
||||
}))
|
||||
expect(entries[0]?.kind).toBe('library')
|
||||
})
|
||||
|
||||
it('hard-errors on a package with no entry file', () => {
|
||||
const root = makeRoot()
|
||||
mkdirSync(join(root, 'packages', 'group', 'one'), { recursive: true })
|
||||
writeFileSync(join(root, 'packages', 'group', 'one', 'package.json'), JSON.stringify({ name: '@fix/one' }))
|
||||
expect(() => collectConfigCatalog(root)).toThrow(/entry .* is missing or unreadable/)
|
||||
})
|
||||
|
||||
it('hard-errors on a package.json without a name', () => {
|
||||
const root = makeRoot()
|
||||
mkdirSync(join(root, 'packages', 'group', 'one', 'src'), { recursive: true })
|
||||
writeFileSync(join(root, 'packages', 'group', 'one', 'package.json'), '{}')
|
||||
expect(() => collectConfigCatalog(root)).toThrow(/has no "name"/)
|
||||
})
|
||||
})
|
||||
|
||||
describe('gen-config-catalog config extraction guards', () => {
|
||||
it('hard-errors on a config field with no JSDoc prose', () => {
|
||||
expect(() => collectConfigCatalog(make({
|
||||
'src/index.ts': `import type { Context } from 'cordis'
|
||||
export interface Config {
|
||||
knob?: string
|
||||
}
|
||||
/** Load. */
|
||||
export function apply(ctx: Context, config: Config): void {}
|
||||
`,
|
||||
}))).toThrow(/config field 'Config\.knob' .* has no JSDoc prose/)
|
||||
})
|
||||
|
||||
it('hard-errors on an undocumented field nested in a type literal', () => {
|
||||
expect(() => collectConfigCatalog(make({
|
||||
'src/index.ts': `import type { Context } from 'cordis'
|
||||
/** Fixture config. */
|
||||
export interface Config {
|
||||
/** Entries. */
|
||||
entries: {
|
||||
id: string
|
||||
}[]
|
||||
}
|
||||
/** Load. */
|
||||
export function apply(ctx: Context, config: Config): void {}
|
||||
`,
|
||||
}))).toThrow(/config field 'Config\.entries\.id' .* has no JSDoc prose/)
|
||||
})
|
||||
|
||||
it('pastes a package-local type transitively and records external refs', () => {
|
||||
const entries = collectConfigCatalog(make({
|
||||
'src/index.ts': `import type { Context } from 'cordis'
|
||||
import type { Mode } from './types.ts'
|
||||
import type { Remote } from '@fix/dep'
|
||||
/** Fixture config. */
|
||||
export interface Config {
|
||||
/** The mode. */
|
||||
mode?: Mode
|
||||
/** The remote. */
|
||||
remote?: Remote
|
||||
}
|
||||
/** Load. */
|
||||
export function apply(ctx: Context, config: Config): void {}
|
||||
`,
|
||||
'src/types.ts': '/** Fixture mode. */\nexport type Mode = \'a\' | \'b\'\n',
|
||||
}))
|
||||
expect(entries[0]?.pastes?.map(p => p.source)).toEqual([
|
||||
'packages/group/one/src/index.ts:5',
|
||||
'packages/group/one/src/types.ts:2',
|
||||
])
|
||||
expect(entries[0]?.refs).toEqual([{ alias: 'Remote', imported: 'Remote', specifier: '@fix/dep' }])
|
||||
})
|
||||
|
||||
it('hard-errors on a referenced type name that resolves nowhere', () => {
|
||||
expect(() => collectConfigCatalog(make({
|
||||
'src/index.ts': `import type { Context } from 'cordis'
|
||||
/** Fixture config. */
|
||||
export interface Config {
|
||||
/** The ghost. */
|
||||
ghost?: Ghost
|
||||
}
|
||||
/** Load. */
|
||||
export function apply(ctx: Context, config: Config): void {}
|
||||
`,
|
||||
}))).toThrow(/references 'Ghost' .* neither declared in the package, imported, nor a known global/)
|
||||
})
|
||||
|
||||
it('hard-errors on a config type imported from another package', () => {
|
||||
expect(() => collectConfigCatalog(make({
|
||||
'src/index.ts': `import type { Context } from 'cordis'
|
||||
import type { Config } from '@fix/dep'
|
||||
/** Load. */
|
||||
export function apply(ctx: Context, config: Config): void {}
|
||||
`,
|
||||
}))).toThrow(/config type 'Config' is imported from '@fix\/dep'/)
|
||||
})
|
||||
|
||||
it('hard-errors when one name resolves to two different declarations across the closure', () => {
|
||||
expect(() => collectConfigCatalog(make({
|
||||
'src/index.ts': `import type { Context } from 'cordis'
|
||||
import type { A } from './a.ts'
|
||||
import type { B } from './b.ts'
|
||||
/** Fixture config. */
|
||||
export interface Config {
|
||||
/** A. */
|
||||
a?: A
|
||||
/** B. */
|
||||
b?: B
|
||||
}
|
||||
/** Load. */
|
||||
export function apply(ctx: Context, config: Config): void {}
|
||||
`,
|
||||
'src/a.ts': '/** First Option. */\nexport interface Option {\n /** X. */\n x?: string\n}\n/** A. */\nexport interface A {\n /** O. */\n o?: Option\n}\n',
|
||||
'src/b.ts': '/** Second Option. */\nexport interface Option {\n /** Y. */\n y?: string\n}\n/** B. */\nexport interface B {\n /** O. */\n o?: Option\n}\n',
|
||||
}))).toThrow(/type name 'Option' resolves to two different declarations/)
|
||||
})
|
||||
})
|
||||
|
||||
describe('gen-config-catalog schema cross-check', () => {
|
||||
it('accepts a chained schema whose keys all appear on the config type', () => {
|
||||
const entries = collectConfigCatalog(make({
|
||||
'src/index.ts': `import type { Context } from 'cordis'
|
||||
import z from 'schemastery'
|
||||
${DOCUMENTED_CONFIG}
|
||||
export const Config: z<Config> = z.object({ knob: z.string() }).default({})
|
||||
/** Load. */
|
||||
export function apply(ctx: Context, config: Config): void {}
|
||||
`,
|
||||
}))
|
||||
expect(entries[0]?.schemaKeys).toEqual(['knob'])
|
||||
})
|
||||
|
||||
it('hard-errors on a schema key the config type does not declare', () => {
|
||||
expect(() => collectConfigCatalog(make({
|
||||
'src/index.ts': `import type { Context } from 'cordis'
|
||||
import z from 'schemastery'
|
||||
${DOCUMENTED_CONFIG}
|
||||
export const Config: z<Config> = z.object({ knob: z.string(), hidden: z.number() })
|
||||
/** Load. */
|
||||
export function apply(ctx: Context, config: Config): void {}
|
||||
`,
|
||||
}))).toThrow(/schema validates key 'hidden' but config type 'Config' declares no such member/)
|
||||
})
|
||||
|
||||
it('hard-errors on a NESTED schema key the config type does not declare', () => {
|
||||
expect(() => collectConfigCatalog(make({
|
||||
'src/index.ts': `import type { Context } from 'cordis'
|
||||
import z from 'schemastery'
|
||||
/** Fixture config. */
|
||||
export interface Config {
|
||||
/** Entries. */
|
||||
entries: {
|
||||
/** Id. */
|
||||
id: string
|
||||
}[]
|
||||
}
|
||||
export const Config: z<Config> = z.object({ entries: z.array(z.object({ id: z.string(), ghost: z.string() })) })
|
||||
/** Load. */
|
||||
export function apply(ctx: Context, config: Config): void {}
|
||||
`,
|
||||
}))).toThrow(/schema validates key 'entries\[\]\.ghost'/)
|
||||
})
|
||||
|
||||
it('resolves nested keys through a workspace-imported intersection part (re-export chains included)', () => {
|
||||
const root = makeRoot()
|
||||
writePkg(root, 'group/dep', '@fix/dep', {
|
||||
'src/index.ts': 'export * from \'./types.ts\'\n',
|
||||
'src/types.ts': '/** Shared options. */\nexport interface Opts {\n /** Model. */\n model?: string\n}\n',
|
||||
})
|
||||
writePkg(root, 'group/one', '@fix/one', {
|
||||
'src/index.ts': `import type { Context } from 'cordis'
|
||||
import z from 'schemastery'
|
||||
import type { Opts } from '@fix/dep'
|
||||
/** Fixture config. */
|
||||
export interface Config {
|
||||
/** Entries. */
|
||||
entries: (Opts & {
|
||||
/** Id. */
|
||||
id: string
|
||||
})[]
|
||||
}
|
||||
export const Config: z<Config> = z.object({ entries: z.array(z.object({ id: z.string(), model: z.string() })) })
|
||||
/** Load. */
|
||||
export function apply(ctx: Context, config: Config): void {}
|
||||
`,
|
||||
})
|
||||
expect(() => collectConfigCatalog(root)).not.toThrow()
|
||||
})
|
||||
|
||||
it('resolves nested keys through a Partial<> wrapper', () => {
|
||||
expect(() => collectConfigCatalog(make({
|
||||
'src/index.ts': `import type { Context } from 'cordis'
|
||||
import z from 'schemastery'
|
||||
/** Caps. */
|
||||
export interface Caps {
|
||||
/** X. */
|
||||
x?: boolean
|
||||
}
|
||||
/** Fixture config. */
|
||||
export interface Config {
|
||||
/** Capabilities. */
|
||||
capabilities?: Partial<Caps>
|
||||
}
|
||||
export const Config: z<Config> = z.object({ capabilities: z.object({ x: z.boolean() }) })
|
||||
/** Load. */
|
||||
export function apply(ctx: Context, config: Config): void {}
|
||||
`,
|
||||
}))).not.toThrow()
|
||||
})
|
||||
|
||||
it('leaves a nested key under an external (unresolvable) type unreported', () => {
|
||||
expect(() => collectConfigCatalog(make({
|
||||
'src/index.ts': `import type { Context } from 'cordis'
|
||||
import z from 'schemastery'
|
||||
import type { External } from 'some-external-pkg'
|
||||
/** Fixture config. */
|
||||
export interface Config {
|
||||
/** Options. */
|
||||
options?: External
|
||||
}
|
||||
export const Config: z<Config> = z.object({ options: z.object({ whatever: z.string() }) })
|
||||
/** Load. */
|
||||
export function apply(ctx: Context, config: Config): void {}
|
||||
`,
|
||||
}))).not.toThrow()
|
||||
})
|
||||
|
||||
it('folds an intersected workspace schema into the subset check', () => {
|
||||
const root = makeRoot()
|
||||
writePkg(root, 'group/leaf', '@fix/leaf', {
|
||||
'src/index.ts': `import type { Context } from 'cordis'
|
||||
import z from 'schemastery'
|
||||
/** Leaf config. */
|
||||
export interface Config {
|
||||
/** Leaf knob. */
|
||||
leaf?: string
|
||||
}
|
||||
/** Leaf service. */
|
||||
export default class Leaf {
|
||||
static Config = z.object({ leaf: z.string() }) as unknown as z<Config>
|
||||
constructor(ctx: Context, config: Config) {}
|
||||
}
|
||||
`,
|
||||
})
|
||||
writePkg(root, 'group/bundle', '@fix/bundle', {
|
||||
'src/index.ts': `import type { Context } from 'cordis'
|
||||
import z from 'schemastery'
|
||||
import Leaf from '@fix/leaf'
|
||||
/** Bundle config. */
|
||||
export interface Config {
|
||||
/** Forwarded leaf knob. */
|
||||
leaf?: string
|
||||
}
|
||||
export const Config = z.intersect([Leaf.Config]) as unknown as z<Config>
|
||||
/** Load. */
|
||||
export function apply(ctx: Context, config: Config): void {}
|
||||
`,
|
||||
})
|
||||
const entries = collectConfigCatalog(root)
|
||||
expect(entries.find(e => e.pkg === '@fix/bundle')?.schemaComposes).toEqual(['@fix/leaf'])
|
||||
})
|
||||
|
||||
it('resolves composed nested keys through an indexed-access forwarder', () => {
|
||||
const root = makeRoot()
|
||||
writePkg(root, 'group/leaf', '@fix/leaf', {
|
||||
'src/index.ts': `import type { Context } from 'cordis'
|
||||
import z from 'schemastery'
|
||||
/** Leaf config. */
|
||||
export interface Config {
|
||||
/** Agents. */
|
||||
agents: {
|
||||
/** Id. */
|
||||
id: string
|
||||
}[]
|
||||
}
|
||||
/** Leaf service. */
|
||||
export default class Leaf {
|
||||
static Config = z.object({ agents: z.array(z.object({ id: z.string() })) }) as unknown as z<Config>
|
||||
constructor(ctx: Context, config: Config) {}
|
||||
}
|
||||
`,
|
||||
})
|
||||
writePkg(root, 'group/bundle', '@fix/bundle', {
|
||||
'src/index.ts': `import type { Context } from 'cordis'
|
||||
import z from 'schemastery'
|
||||
import Leaf, { type Config as LeafConfig } from '@fix/leaf'
|
||||
/** Bundle config forwarding the leaf's agents list. */
|
||||
export interface Config {
|
||||
/** Forwarded agents list. */
|
||||
agents?: LeafConfig['agents']
|
||||
}
|
||||
export const Config = z.intersect([Leaf.Config]) as unknown as z<Config>
|
||||
/** Load. */
|
||||
export function apply(ctx: Context, config: Config): void {}
|
||||
`,
|
||||
})
|
||||
expect(() => collectConfigCatalog(root)).not.toThrow()
|
||||
})
|
||||
|
||||
it('hard-errors when an intersected schema key is missing from the bundle config type', () => {
|
||||
const root = makeRoot()
|
||||
writePkg(root, 'group/leaf', '@fix/leaf', {
|
||||
'src/index.ts': `import type { Context } from 'cordis'
|
||||
import z from 'schemastery'
|
||||
/** Leaf config. */
|
||||
export interface Config {
|
||||
/** Leaf knob. */
|
||||
leaf?: string
|
||||
}
|
||||
/** Leaf service. */
|
||||
export default class Leaf {
|
||||
static Config = z.object({ leaf: z.string() }) as unknown as z<Config>
|
||||
constructor(ctx: Context, config: Config) {}
|
||||
}
|
||||
`,
|
||||
})
|
||||
writePkg(root, 'group/bundle', '@fix/bundle', {
|
||||
'src/index.ts': `import type { Context } from 'cordis'
|
||||
import z from 'schemastery'
|
||||
import Leaf from '@fix/leaf'
|
||||
/** Bundle config that forgot to declare the forwarded field. */
|
||||
export interface Config {
|
||||
/** Unrelated. */
|
||||
other?: string
|
||||
}
|
||||
export const Config = z.intersect([Leaf.Config]) as unknown as z<Config>
|
||||
/** Load. */
|
||||
export function apply(ctx: Context, config: Config): void {}
|
||||
`,
|
||||
})
|
||||
expect(() => collectConfigCatalog(root)).toThrow(/schema validates key 'leaf' but config type 'Config' declares no such member/)
|
||||
})
|
||||
})
|
||||
|
||||
describe('gen-config-catalog render', () => {
|
||||
it('renders sections, fences, and the terse classification lists', () => {
|
||||
const root = makeRoot()
|
||||
writePkg(root, 'group/one', '@fix/one', {
|
||||
'src/index.ts': `import type { Context } from 'cordis'
|
||||
${DOCUMENTED_CONFIG}
|
||||
/** Load. */
|
||||
export function apply(ctx: Context, config: Config): void {}
|
||||
`,
|
||||
})
|
||||
writePkg(root, 'group/lib', '@fix/lib', { 'src/index.ts': 'export const helper = 1\n' })
|
||||
writePkg(root, 'group/seam', '@fix/seam', {
|
||||
'src/index.ts': 'export default abstract class Seam { abstract run(): void }\n',
|
||||
})
|
||||
const page = render(collectConfigCatalog(root))
|
||||
expect(page).toContain('## `@fix/one`')
|
||||
expect(page).toContain('```ts config-catalog')
|
||||
expect(page).toContain('/** A knob. */')
|
||||
expect(page).toContain('- `@fix/lib` ([`packages/group/lib/src/index.ts`](../packages/group/lib/src/index.ts))')
|
||||
expect(page).toContain('- `@fix/seam` — abstract `Seam`')
|
||||
})
|
||||
})
|
||||
@@ -1,57 +0,0 @@
|
||||
{
|
||||
"extends": "../../../tsconfig.base.json",
|
||||
"compilerOptions": {
|
||||
"rootDir": "src",
|
||||
"outDir": "lib/types"
|
||||
},
|
||||
"include": [
|
||||
"src"
|
||||
],
|
||||
"references": [
|
||||
{
|
||||
"path": "../../../vendor/cordis"
|
||||
},
|
||||
{
|
||||
"path": "../../../vendor/schemastery"
|
||||
},
|
||||
{
|
||||
"path": "../../../vendor/timer"
|
||||
},
|
||||
{
|
||||
"path": "../../../vendor/schemastery"
|
||||
},
|
||||
{
|
||||
"path": "../../llm/llm"
|
||||
},
|
||||
{
|
||||
"path": "../../core/session"
|
||||
},
|
||||
{
|
||||
"path": "../../core/system-prompt"
|
||||
},
|
||||
{
|
||||
"path": "../../core/tools"
|
||||
},
|
||||
{
|
||||
"path": "../../skill/skill"
|
||||
},
|
||||
{
|
||||
"path": "../../skill/skill-local"
|
||||
},
|
||||
{
|
||||
"path": "../../skill/tool-skill"
|
||||
},
|
||||
{
|
||||
"path": "../../core/agent"
|
||||
},
|
||||
{
|
||||
"path": "../../core/agent-loop"
|
||||
},
|
||||
{
|
||||
"path": "../../support/invariants"
|
||||
},
|
||||
{
|
||||
"path": "../../bash/tool-bash"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -61,7 +61,7 @@ Everything that goes beyond "call the model, run the tools, repeat" belongs to p
|
||||
- Hooks and policy: the relevant `agent/*` checkpoints plus the guarded `tools/pre-execute` → `tools/execute` → `tools/post-execute` → `tools/result` pipeline; exact signatures and modes live in the [generated event catalog](../../../docs/cordis-catalog/events.md)
|
||||
- Compaction: `agent/pre-step`
|
||||
- Sandbox, permission, plan mode: `tools/pre-execute` for extensible deny/ask, `tools.guard()` for monotonic owner policy, `tools/post-execute` for result decisions, and `tools/result` for final observation
|
||||
- Sub-agents: implemented outside the loop as `ctx.subagents` providers; in-process providers use `ctx.agents.create()` and owned `AgentHandle` teardown, while child streaming/progress and background/poll collection remain deferred.
|
||||
- Sub-agents: implemented outside the loop as `ctx.subagents` providers; in-process providers use `ctx.agents.create()` and owned `AgentHandle` teardown, while generic [`ctx.tasks`](../../tasks/tasks/) plus [`dsh-tool-subagent`](../../subagent/tool-subagent/) own background collection.
|
||||
- Persistence: `session/event` + `session/flush`
|
||||
- UI: `session/event` (assistant token stream, boundaries, tool activity) + `agent/*` control events (`agent/status`, `agent/created`/`agent/disposed`)
|
||||
|
||||
|
||||
@@ -28,7 +28,7 @@
|
||||
"@deepseek-ai/dsh-session-persistence": "^0.0.1",
|
||||
"@deepseek-ai/dsh-system-prompt": "^0.0.1",
|
||||
"@deepseek-ai/dsh-tools": "^0.0.1",
|
||||
"cordis": "^4.0.0-rc.6"
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
},
|
||||
"dependencies": {
|
||||
"schemastery": "^3.18.0"
|
||||
@@ -43,6 +43,6 @@
|
||||
"@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^",
|
||||
"@deepseek-ai/dsh-system-prompt": "workspace:^",
|
||||
"@deepseek-ai/dsh-tools": "workspace:^",
|
||||
"cordis": "^4.0.0-rc.6"
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -282,10 +282,8 @@ function appendToolResult(
|
||||
): void {
|
||||
session.append('tool/result', {
|
||||
turn, step,
|
||||
// The correlation id MUST be the loop's authoritative call.id (the
|
||||
// model-transcript id deriveMessages turns into toolCallId), NOT
|
||||
// result.callId — a post-execute listener returning a mismatched id would
|
||||
// otherwise orphan the call↔result pairing in the next model request.
|
||||
// Correlation stays with the loop's authoritative model-transcript call id;
|
||||
// registry results deliberately do not duplicate it.
|
||||
callId: block.id,
|
||||
content: result.content,
|
||||
isError: result.isError,
|
||||
|
||||
@@ -1045,8 +1045,7 @@ describe('tool result call identity', () => {
|
||||
|
||||
// A post-execute listener transforms the result (accept-with-replacement).
|
||||
// The loop must still record the tool/result under the model's authoritative
|
||||
// call.id (the loop ignores result.callId — which the registry always sets to
|
||||
// exec.callId anyway — and uses call.id, the model-transcript id).
|
||||
// call.id, which is the immutable identity carried by the execution input.
|
||||
ctx.on('tools/post-execute', (exec, _result) => {
|
||||
expect(exec.callId).toBe(CallId('c1')) // the loop passed the real id in
|
||||
return Promise.resolve({ kind: 'accept', content: [{ type: 'text', text: 'ok' }] })
|
||||
@@ -1056,8 +1055,7 @@ describe('tool result call identity', () => {
|
||||
send(agent, 'use tool')
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
// The logged tool/result.callId is the originating call.id, NOT the
|
||||
// listener's wrong id.
|
||||
// The logged tool/result.callId is the originating call.id.
|
||||
const resultEvent = [...agent.session.events].find(e => e.type === 'tool/result')
|
||||
expect(resultEvent?.type).toBe('tool/result')
|
||||
if (resultEvent?.type === 'tool/result') {
|
||||
|
||||
@@ -27,7 +27,7 @@
|
||||
"@deepseek-ai/dsh-scope": "^0.0.1",
|
||||
"@deepseek-ai/dsh-session": "^0.0.1",
|
||||
"@deepseek-ai/dsh-system-prompt": "^0.0.1",
|
||||
"cordis": "^4.0.0-rc.6"
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@deepseek-ai/dsh-brand": "workspace:^",
|
||||
@@ -35,6 +35,6 @@
|
||||
"@deepseek-ai/dsh-scope": "workspace:^",
|
||||
"@deepseek-ai/dsh-session": "workspace:^",
|
||||
"@deepseek-ai/dsh-system-prompt": "workspace:^",
|
||||
"cordis": "^4.0.0-rc.6"
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -30,6 +30,22 @@ function fixture(files: Record<string, string>): string {
|
||||
const make = (content: string): string => fixture({ 'index.ts': content })
|
||||
|
||||
describe('verify-export-jsdoc functions and consts', () => {
|
||||
it('limits packages without src/* exports to declarations reachable from package entrypoints', () => {
|
||||
const root = fixture({
|
||||
'index.ts': "export { publicFn } from './internal.ts'\n",
|
||||
'internal.ts': `
|
||||
export function publicFn(value: string): string { return value }
|
||||
export function hiddenFn(value: string): string { return value }
|
||||
`,
|
||||
})
|
||||
writeFileSync(join(root, 'packages/group/fix/package.json'), JSON.stringify({
|
||||
exports: { '.': { types: './lib/types/index.d.ts', default: './lib/index.js' } },
|
||||
}))
|
||||
const violations = collectExportJsdocViolations(root)
|
||||
expect(violations).toHaveLength(1)
|
||||
expect(violations.every(violation => violation.includes('publicFn'))).toBe(true)
|
||||
})
|
||||
|
||||
it('accepts a fully documented surface', () => {
|
||||
expect(collectExportJsdocViolations(make(`
|
||||
/**
|
||||
|
||||
@@ -22,9 +22,9 @@
|
||||
],
|
||||
"license": "BSD-3-Clause",
|
||||
"peerDependencies": {
|
||||
"cordis": "^4.0.0-rc.6"
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
},
|
||||
"devDependencies": {
|
||||
"cordis": "^4.0.0-rc.6"
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -35,7 +35,7 @@ Plain class (not a Cordis Service). Create via `ctx.sessions.create()`.
|
||||
- `session.append(type, data, opts?)` snapshots and freezes durable data and surface metadata, commits synchronously, then notifies observers with independent failure containment. Reentrant attached-session appends reject, and runtime checks cover widened unions and loaded logs.
|
||||
- `session.deriveMessages()` incrementally projects each new surface node once and returns a fresh array over shared frozen messages. A surface rewrite rebuilds the projection; there is no raw-log fallback.
|
||||
- `session.deriveEventMessage(event)` is the canonical per-event projection used by reconstruction and invariants.
|
||||
- `session.surface` lazily folds only new `surfaceOp` markers; `replaceGeneration` changes on every rewrite or invalidation.
|
||||
- `session.surface` lazily folds only new `surfaceOp` markers; `replaceGeneration` changes on every rewrite.
|
||||
- `session.events` is a cached frozen snapshot invalidated by append; accepted events remain deeply frozen.
|
||||
- `session.seq`, `session.id` — current sequence and readonly typed identity.
|
||||
- `session.header: SessionHeader` — detached, deep-frozen creation metadata (`version`, `id`, `createdAt`, optional `cwd`/`parentSession`/`seedLength`). Construction validates the durable record and requires its id to match `session.id`.
|
||||
|
||||
@@ -25,12 +25,12 @@
|
||||
"@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"
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@deepseek-ai/dsh-brand": "workspace:^",
|
||||
"@deepseek-ai/dsh-llm": "workspace:^",
|
||||
"@deepseek-ai/dsh-scope": "workspace:^",
|
||||
"cordis": "^4.0.0-rc.6"
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -41,6 +41,7 @@ declare module 'cordis' {
|
||||
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners
|
||||
* receive only sessions entered through that agent's context.
|
||||
* @param session - the session just entered and announced.
|
||||
* @dshScopeScan unsupported
|
||||
* @mode emit
|
||||
*/
|
||||
'session/created'(this: Scoped<Session>, session: Session): void
|
||||
@@ -50,6 +51,7 @@ declare module 'cordis' {
|
||||
* did not begin. Listener failures are logged and contained.
|
||||
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`) reuses the owner scope.
|
||||
* @param session - the session that is no longer live in the store.
|
||||
* @dshScopeScan unsupported
|
||||
* @mode emit
|
||||
*/
|
||||
'session/disposed'(this: Scoped<Session>, session: Session): void
|
||||
@@ -61,6 +63,7 @@ declare module 'cordis' {
|
||||
* receive only events from sessions entered through that agent's context.
|
||||
* @param session - the session whose log grew.
|
||||
* @param event - the appended event, exactly as recorded.
|
||||
* @dshScopeScan unsupported
|
||||
* @mode emit
|
||||
*/
|
||||
'session/event'(this: Scoped<Session>, session: Session, event: SessionEvent): void
|
||||
@@ -70,6 +73,7 @@ declare module 'cordis' {
|
||||
* {@link SessionStore.flush}. Scope-filtered dispatch
|
||||
* (`@deepseek-ai/dsh-scope`) reuses the session's owner scope.
|
||||
* @param session - the session whose buffered events must reach durable storage.
|
||||
* @dshScopeScan unsupported
|
||||
* @mode parallel
|
||||
*/
|
||||
'session/flush'(this: Scoped<Session>, session: Session): Promise<void> | void
|
||||
|
||||
@@ -193,26 +193,14 @@ export function foldSurface(events: readonly SessionEvent[]): SurfaceFoldResult
|
||||
export class SurfaceManager {
|
||||
/** Incremental state shared with the complete surface fold. */
|
||||
private _state = createFoldState()
|
||||
/** The last processed seq. -1 forces a full rebuild on first access. */
|
||||
/** The last processed seq. -1 folds the seeded log on first access. */
|
||||
private _lastProcessedSeq = -1
|
||||
|
||||
constructor(private log: readonly SessionEvent[]) {}
|
||||
|
||||
/**
|
||||
* Reset to unprocessed state. Call after the log has been replaced
|
||||
* wholesale (e.g. after Session seed). Not needed for normal appends —
|
||||
* those are picked up incrementally.
|
||||
*/
|
||||
invalidate(): void {
|
||||
this._lastProcessedSeq = -1
|
||||
// A wholesale rebuild is a rewrite: bump the generation so incremental
|
||||
// consumers (the session's derived-message cache) discard their view.
|
||||
this._state = createFoldState(this._state.replaceGeneration + 1)
|
||||
}
|
||||
|
||||
/**
|
||||
* The surface's rewrite generation: bumped by every folded `replace` op and
|
||||
* by {@link invalidate}. A replace is the ONE operation that rewrites the
|
||||
* The surface's rewrite generation, bumped by every folded `replace` op.
|
||||
* A replace is the ONE operation that rewrites the
|
||||
* surface non-monotonically, so an incremental consumer of {@link nodes}
|
||||
* (the session's derived-message cache) compares this between visits — an
|
||||
* unchanged generation guarantees every node it has not seen is a pure tail
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
/**
|
||||
* Derived-message cache contract against a scratch oracle: project new nodes
|
||||
* once, rebuild on surface generation changes, return fresh arrays over shared
|
||||
* once, rebuild on surface replacements, return fresh arrays over shared
|
||||
* frozen messages, and remain value-equal to replay at every step.
|
||||
*/
|
||||
|
||||
@@ -61,16 +61,6 @@ describe('derived-message cache', () => {
|
||||
expect(Object.isFrozen(first[0])).toBe(true)
|
||||
})
|
||||
|
||||
it('rebuilds after surface.invalidate() (the generation covers wholesale rebuilds too)', () => {
|
||||
const session = new Session(SessionId('cache-invalidate'))
|
||||
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
|
||||
userText(session, 'one')
|
||||
const before = session.deriveMessages()
|
||||
session.surface.invalidate()
|
||||
const after = session.deriveMessages()
|
||||
expect(after).toEqual(before)
|
||||
expect(after[0]).not.toBe(before[0])
|
||||
})
|
||||
})
|
||||
|
||||
describe('Session.deriveEventMessage — the per-event projection', () => {
|
||||
|
||||
@@ -81,14 +81,6 @@ describe('SurfaceManager', () => {
|
||||
expect(nodes[1]!.next).toBeNull()
|
||||
})
|
||||
|
||||
it('invalidate resets to full rebuild', () => {
|
||||
const s = surfaceSession()
|
||||
expect(s.surface.nodes.length).toBe(2)
|
||||
// After invalidate, the surface should rebuild from scratch on next access.
|
||||
;(s.surface).invalidate()
|
||||
expect(s.surface.nodes.length).toBe(2) // same result, but rebuilt
|
||||
})
|
||||
|
||||
it('empty surface yields empty nodes', () => {
|
||||
const s = new Session(SessionId('empty'))
|
||||
// Only turn boundaries, no surface nodes.
|
||||
@@ -386,7 +378,7 @@ describe('surface type guards', () => {
|
||||
})
|
||||
|
||||
describe('SurfaceManager.replaceGeneration', () => {
|
||||
it('folds the pending log delta on access and counts replaces and invalidations', () => {
|
||||
it('folds the pending log delta on access and counts replaces', () => {
|
||||
const s = new Session(SessionId('gen'))
|
||||
s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
|
||||
s.append('user/message', { content: [{ type: 'text', text: 'one' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
|
||||
@@ -400,10 +392,5 @@ describe('SurfaceManager.replaceGeneration', () => {
|
||||
content: [{ type: 'text', text: 'summary' }], source: { kind: 'plugin', plugin: 'compact' },
|
||||
}, { surfaceOp: { op: 'replace', start: nodes[0]!.seq, end: nodes[1]!.seq }, sourceEventSeqs: [nodes[0]!.seq, nodes[1]!.seq] })
|
||||
expect(s.surface.replaceGeneration).toBe(1)
|
||||
|
||||
// invalidate() is a rewrite too: the generation moves forward (and the
|
||||
// refold re-counts the replace), never backwards.
|
||||
s.surface.invalidate()
|
||||
expect(s.surface.replaceGeneration).toBeGreaterThan(1)
|
||||
})
|
||||
})
|
||||
|
||||
@@ -24,7 +24,7 @@
|
||||
"peerDependencies": {
|
||||
"@deepseek-ai/dsh-llm": "^0.0.1",
|
||||
"@deepseek-ai/dsh-scope": "^0.0.1",
|
||||
"cordis": "^4.0.0-rc.6"
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
},
|
||||
"dependencies": {
|
||||
"schemastery": "^3.18.0"
|
||||
@@ -32,6 +32,6 @@
|
||||
"devDependencies": {
|
||||
"@deepseek-ai/dsh-llm": "workspace:^",
|
||||
"@deepseek-ai/dsh-scope": "workspace:^",
|
||||
"cordis": "^4.0.0-rc.6"
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -65,10 +65,6 @@ export interface PromptSection {
|
||||
export interface AssembledSection {
|
||||
/** The contributing section's unique name. */
|
||||
name: string
|
||||
// TODO(assembled-section-order): drop this output field; registry order has
|
||||
// already sorted the array, and no production renderer/listener reads it.
|
||||
/** The contributing section's order (sections arrive sorted ascending). */
|
||||
order: number
|
||||
/** The resolved (but not yet interpolated) section text. */
|
||||
text: string
|
||||
}
|
||||
@@ -226,7 +222,7 @@ export class SystemPrompt extends Service {
|
||||
private scopedVariableProviders = new Map<ScopeKey, Map<string, (context: AssembleContext) => string | undefined>>()
|
||||
private readonly toolOrder: string[] | undefined
|
||||
|
||||
constructor(ctx: Context, public config: Config) {
|
||||
constructor(ctx: Context, config: Config) {
|
||||
super(ctx, 'systemPrompt')
|
||||
this.toolOrder = validateToolOrder(config.toolOrder)
|
||||
// Keep harness-owned openers independent of the selected loop plugin.
|
||||
@@ -403,12 +399,11 @@ export class SystemPrompt extends Service {
|
||||
}
|
||||
const assembly: PromptAssembly = {
|
||||
sections: [...sectionByName.values()]
|
||||
.sort((a, b) => a.order - b.order)
|
||||
.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(collected, this.toolOrder, knownNames),
|
||||
variables,
|
||||
}
|
||||
|
||||
@@ -139,7 +139,7 @@ describe('scoped assemble dispatch', () => {
|
||||
scope.ctx.on('system-prompt/assemble', async (_assembly: PromptAssembly, context, next: () => Promise<PromptAssembly>) => {
|
||||
shaped.push(context.scope)
|
||||
const result = await next()
|
||||
result.sections.push({ name: 'listener:extra', order: 999, text: 'listener text' })
|
||||
result.sections.push({ name: 'listener:extra', text: 'listener text' })
|
||||
return result
|
||||
})
|
||||
|
||||
|
||||
@@ -21,9 +21,9 @@ describe('SystemPrompt', () => {
|
||||
await ctx.plugin(SystemPrompt, { persona: 'You are DeepSeek Harness SDK.' })
|
||||
|
||||
const assembly = await ctx.systemPrompt.assemble()
|
||||
expect(assembly.sections.map(s => [s.name, s.order])).toEqual([
|
||||
['harness:identity', -100],
|
||||
['deployment:persona', 0],
|
||||
expect(assembly.sections.map(s => s.name)).toEqual([
|
||||
'harness:identity',
|
||||
'deployment:persona',
|
||||
])
|
||||
expect(renderPrompt(assembly)).toBe(`${IDENTITY}\n\nYou are DeepSeek Harness SDK.`)
|
||||
// The names are reserved by the plugin — one owner per section.
|
||||
@@ -183,7 +183,7 @@ describe('SystemPrompt', () => {
|
||||
const contexts: AssembleContext[] = []
|
||||
ctx.on('system-prompt/assemble', async (assembly: PromptAssembly, context, next) => {
|
||||
contexts.push(context)
|
||||
assembly.sections.push({ name: 'from-a', order: 100, text: 'a' })
|
||||
assembly.sections.push({ name: 'from-a', text: 'a' })
|
||||
return next()
|
||||
})
|
||||
// Listener B (registered later, runs after A) sees A's contribution.
|
||||
@@ -235,8 +235,8 @@ describe('SystemPrompt', () => {
|
||||
it('filters out empty section text from renderPrompt', () => {
|
||||
const result = renderPrompt({
|
||||
sections: [
|
||||
{ name: 'empty', order: 0, text: '' },
|
||||
{ name: 'real', order: 1, text: 'content' },
|
||||
{ name: 'empty', text: '' },
|
||||
{ name: 'real', text: 'content' },
|
||||
],
|
||||
tools: [],
|
||||
variables: {},
|
||||
@@ -356,13 +356,13 @@ describe('SystemPrompt', () => {
|
||||
})
|
||||
|
||||
it('names "(none)" when no variables are registered at all', () => {
|
||||
expect(() => renderPrompt({ sections: [{ name: 's', order: 0, text: '{{x}}' }], tools: [], variables: {} }))
|
||||
expect(() => renderPrompt({ sections: [{ name: 's', text: '{{x}}' }], tools: [], variables: {} }))
|
||||
.toThrow('unknown prompt variable "{{x}}" in section "s"; registered variables: (none)')
|
||||
})
|
||||
|
||||
it('throws when a referenced variable has no value for this assembly', () => {
|
||||
expect(() => renderPrompt({
|
||||
sections: [{ name: 'persona', order: 0, text: 'in {{cwd}}' }],
|
||||
sections: [{ name: 'persona', text: 'in {{cwd}}' }],
|
||||
tools: [],
|
||||
variables: { cwd: undefined },
|
||||
})).toThrow('prompt variable "{{cwd}}" has no value for this assembly (section "persona")')
|
||||
@@ -370,7 +370,7 @@ describe('SystemPrompt', () => {
|
||||
|
||||
it('throws on a malformed complete reference, e.g. inner spaces', () => {
|
||||
expect(() => renderPrompt({
|
||||
sections: [{ name: 's', order: 0, text: 'on {{ model }}' }],
|
||||
sections: [{ name: 's', text: 'on {{ model }}' }],
|
||||
tools: [],
|
||||
variables: { model: 'm' },
|
||||
})).toThrow('malformed prompt variable reference "{{ model }}" in section "s"')
|
||||
@@ -378,7 +378,7 @@ describe('SystemPrompt', () => {
|
||||
|
||||
it('leaves a lone {{ verbatim only when NO }} follows anywhere after it', () => {
|
||||
const text = renderPrompt({
|
||||
sections: [{ name: 's', order: 0, text: 'shell ${X:-{{fallback} stays' }],
|
||||
sections: [{ name: 's', text: 'shell ${X:-{{fallback} stays' }],
|
||||
tools: [],
|
||||
variables: {},
|
||||
})
|
||||
@@ -390,7 +390,7 @@ describe('SystemPrompt', () => {
|
||||
{ text: 'x {{a{b}} y {{model}}', label: 'nested brace inside a would-be group' },
|
||||
])('throws on a mangled reference with a }} still following ($label)', ({ text }) => {
|
||||
expect(() => renderPrompt({
|
||||
sections: [{ name: 's', order: 0, text }],
|
||||
sections: [{ name: 's', text }],
|
||||
tools: [],
|
||||
variables: { model: 'm' },
|
||||
})).toThrow('malformed prompt variable reference at')
|
||||
@@ -400,7 +400,7 @@ describe('SystemPrompt', () => {
|
||||
// `in` would find Object.prototype.constructor and splice function
|
||||
// source into the prompt; Object.hasOwn must reject it instead.
|
||||
expect(() => renderPrompt({
|
||||
sections: [{ name: 's', order: 0, text: 'on {{constructor}}' }],
|
||||
sections: [{ name: 's', text: 'on {{constructor}}' }],
|
||||
tools: [],
|
||||
variables: { model: 'm' },
|
||||
})).toThrow('unknown prompt variable "{{constructor}}"')
|
||||
@@ -416,7 +416,7 @@ describe('SystemPrompt', () => {
|
||||
|
||||
it('never re-scans substituted values (a value containing {{sneaky}} stays literal)', () => {
|
||||
const text = renderPrompt({
|
||||
sections: [{ name: 's', order: 0, text: 'v = {{model}}!' }],
|
||||
sections: [{ name: 's', text: 'v = {{model}}!' }],
|
||||
tools: [],
|
||||
variables: { model: 'literal {{sneaky}} inside' },
|
||||
})
|
||||
|
||||
@@ -37,7 +37,7 @@ The live registry pipeline has three transformable waterfalls followed by the ob
|
||||
- `ToolExecutionInput` — the caller-supplied call description: `{ callId, name, arguments, agent?, parent?, signal? }`; callers may pass an enclosing execution's opaque token as `parent` but never choose the new execution's own token.
|
||||
- `ToolExecutionToken` — a fresh branded `Symbol` assigned by the registry. It supports equality correlation only and never crosses a model, log, or worker boundary.
|
||||
- `ToolExecution` — the pipeline-owned call: immutable `{ token, callId, name, arguments, agent?, parent? }` identity plus optional operational `signal`, which an around wrapper may add, replace, remove, and restore. A nested call's `parent` is a `ToolExecutionToken`, not an execution object.
|
||||
- `ToolExecutionResult` — losslessly JSON-serializable outcome: `{ callId, content, isError, error?, additionalContext?, meta? }`. The registry materializes and freezes the complete post-policy value before final observation. On failure with a `HarnessError`, `error: { name, code }` carries the structured failure class alongside the model-facing text.
|
||||
- `ToolExecutionResult` — losslessly JSON-serializable outcome: `{ content, isError, error?, additionalContext?, meta? }`. Call identity stays on the immutable `ToolExecution` supplied alongside the result instead of being duplicated on the outcome. The registry materializes and freezes the complete post-policy value before final observation. On failure with a `HarnessError`, `error: { name, code }` carries the structured failure class alongside the model-facing text.
|
||||
- `PreToolDecision` — `{kind:'allow'}` | `{kind:'deny', reason}` | `{kind:'ask', reason?}`. Input rewrite is deliberately not offered; `ask` is serviced by [`ctx.approval`](../../ui/user-approval/README.md) when mounted and otherwise degrades to deny.
|
||||
- `PostToolDecision` — `{kind:'accept', content?, additionalContext?}` (keep the call successful, optionally replacing the model-facing content) | `{kind:'block', feedback, additionalContext?}` (turn it into an `isError` whose content is the corrective feedback). Output replacement is clean because `tool/result` is logged AFTER `execute()` returns.
|
||||
- `ToolGuard` — `(execution) => string | undefined`; the returned string is a final monotonic denial reason evaluated after the reorderable pre-execute waterfall and before dispatch.
|
||||
|
||||
@@ -29,7 +29,7 @@
|
||||
"@deepseek-ai/dsh-scope": "^0.0.1",
|
||||
"@deepseek-ai/dsh-session": "^0.0.1",
|
||||
"@deepseek-ai/dsh-system-prompt": "^0.0.1",
|
||||
"cordis": "^4.0.0-rc.6"
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
},
|
||||
"dependencies": {
|
||||
"schemastery": "^3.18.0"
|
||||
@@ -42,6 +42,6 @@
|
||||
"@deepseek-ai/dsh-scope": "workspace:^",
|
||||
"@deepseek-ai/dsh-session": "workspace:^",
|
||||
"@deepseek-ai/dsh-system-prompt": "workspace:^",
|
||||
"cordis": "^4.0.0-rc.6"
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -108,14 +108,13 @@ function renderValue(value: unknown): string {
|
||||
/** The run_code result's `meta` payload (JSON-serializable; `presentResult` narrows it back). */
|
||||
interface RunCodeMeta {
|
||||
logs: CodeRunResult['logs']
|
||||
dispatches: number
|
||||
}
|
||||
|
||||
/** Soft-narrow a result `meta` back to {@link RunCodeMeta} (replay may carry older shapes; presentation must not throw). */
|
||||
function asRunCodeMeta(meta: unknown): RunCodeMeta | undefined {
|
||||
if (typeof meta !== 'object' || meta === null) return undefined
|
||||
const m = meta as Record<string, unknown>
|
||||
if (!Array.isArray(m.logs) || typeof m.dispatches !== 'number') return undefined
|
||||
if (!Array.isArray(m.logs) || !m.logs.every(log => typeof log === 'string')) return undefined
|
||||
return m as unknown as RunCodeMeta
|
||||
}
|
||||
|
||||
@@ -251,12 +250,12 @@ export function createRunCodeTool(registry: ToolRegistry, requireRuntime: () =>
|
||||
}
|
||||
|
||||
if (result.error) {
|
||||
const logsText = result.logs.length > 0 ? `\nCaptured output:\n${result.logs.map(entry => entry.text).join('\n')}` : ''
|
||||
const logsText = result.logs.length > 0 ? `\nCaptured output:\n${result.logs.join('\n')}` : ''
|
||||
throw new CodeRunFailedError(`code run failed (${result.error.kind}): ${result.error.message}${logsText}`)
|
||||
}
|
||||
const rendered = renderValue(result.value)
|
||||
const parts = [result.logs.map(entry => entry.text).join('\n'), rendered].filter(part => part.length > 0)
|
||||
const meta: RunCodeMeta = { logs: result.logs, dispatches }
|
||||
const parts = [result.logs.join('\n'), rendered].filter(part => part.length > 0)
|
||||
const meta: RunCodeMeta = { logs: result.logs }
|
||||
return {
|
||||
content: [{ type: 'text', text: parts.length > 0 ? parts.join('\n') : '(run_code completed with no output)' }],
|
||||
meta,
|
||||
@@ -278,7 +277,7 @@ export function createRunCodeTool(registry: ToolRegistry, requireRuntime: () =>
|
||||
presentResult: (_args, result) => {
|
||||
const meta = asRunCodeMeta(result.meta)
|
||||
if (!meta) return undefined
|
||||
const output = meta.logs.map(entry => entry.text).join('\n')
|
||||
const output = meta.logs.join('\n')
|
||||
return {
|
||||
card: 'generic',
|
||||
...output.length > 0 ? { content: [{ type: 'text' as const, text: output }] } : {},
|
||||
|
||||
@@ -301,7 +301,7 @@ export interface ToolErrorInfo {
|
||||
* distinguish it from a tool body's own error.
|
||||
*/
|
||||
export class ToolNotFoundError extends HarnessError {
|
||||
constructor(public readonly toolName: string) {
|
||||
constructor(toolName: string) {
|
||||
super(`unknown tool "${toolName}"`, 'UNKNOWN_TOOL')
|
||||
this.name = 'ToolNotFoundError'
|
||||
}
|
||||
@@ -309,7 +309,6 @@ export class ToolNotFoundError extends HarnessError {
|
||||
|
||||
/** The outcome of one tool call. */
|
||||
export interface ToolExecutionResult {
|
||||
callId: CallId
|
||||
content: ContentBlock[]
|
||||
isError: boolean
|
||||
/**
|
||||
@@ -789,7 +788,11 @@ export class ToolRegistry extends Service {
|
||||
* @returns the materialized final result.
|
||||
*/
|
||||
async execute(exec: ToolExecutionInput): Promise<ToolExecutionResult> {
|
||||
const prepared = await this.prepareScheduledExecution(exec)
|
||||
return this.prepareExecution(exec, prepared => this.completeScheduledExecution(prepared))
|
||||
}
|
||||
|
||||
/** Complete every remaining stage for the public one-call execution path. */
|
||||
private async completeScheduledExecution(prepared: ScheduledToolPreparation): Promise<ToolExecutionResult> {
|
||||
switch (prepared.kind) {
|
||||
case 'dispatch': {
|
||||
const dispatched = await this.dispatchScheduledExecution(prepared.exec)
|
||||
@@ -831,7 +834,7 @@ export class ToolRegistry extends Service {
|
||||
return { kind: 'ready', exec: { ...base, arguments: deepFreeze(detached) } }
|
||||
} catch (error: unknown) {
|
||||
const execution: ToolExecution = { ...base, arguments: undefined }
|
||||
return { kind: 'final-result', exec: execution, result: toolErrorResult(callId, error) }
|
||||
return { kind: 'final-result', exec: execution, result: toolErrorResult(error) }
|
||||
}
|
||||
}
|
||||
|
||||
@@ -842,8 +845,16 @@ export class ToolRegistry extends Service {
|
||||
* @internal
|
||||
*/
|
||||
private async prepareScheduledExecution(input: ToolExecutionInput): Promise<ScheduledToolPreparation> {
|
||||
return this.prepareExecution(input, prepared => prepared)
|
||||
}
|
||||
|
||||
/** Run preparation and hand its outcome directly to the selected continuation. */
|
||||
private async prepareExecution<T>(
|
||||
input: ToolExecutionInput,
|
||||
next: (prepared: ScheduledToolPreparation) => T | PromiseLike<T>,
|
||||
): Promise<T> {
|
||||
const created = this.createExecution(input)
|
||||
if (created.kind !== 'ready') return created
|
||||
if (created.kind !== 'ready') return next(created)
|
||||
const exec = created.exec
|
||||
try {
|
||||
const carrier = scopeTarget(this, exec.agent)
|
||||
@@ -856,19 +867,18 @@ export class ToolRegistry extends Service {
|
||||
? this.guardReason(exec)
|
||||
: decision.reason
|
||||
if (denialReason !== undefined) {
|
||||
return {
|
||||
return await next({
|
||||
kind: 'post-result',
|
||||
exec,
|
||||
result: {
|
||||
callId: exec.callId,
|
||||
content: [{ type: 'text', text: `Error: ${denialReason}` }],
|
||||
isError: true,
|
||||
},
|
||||
}
|
||||
})
|
||||
}
|
||||
return { kind: 'dispatch', exec }
|
||||
return await next({ kind: 'dispatch', exec })
|
||||
} catch (error: unknown) {
|
||||
return { kind: 'final-result', exec, result: toolErrorResult(exec.callId, error) }
|
||||
return next({ kind: 'final-result', exec, result: toolErrorResult(error) })
|
||||
}
|
||||
}
|
||||
|
||||
@@ -892,18 +902,15 @@ export class ToolRegistry extends Service {
|
||||
const returned = await tool.execute(exec.arguments, exec)
|
||||
const content = Array.isArray(returned) ? returned : returned.content
|
||||
const meta = Array.isArray(returned) ? undefined : returned.meta
|
||||
return { callId: exec.callId, content, isError: false, ...meta !== undefined ? { meta } : {} }
|
||||
return { content, isError: false, ...meta !== undefined ? { meta } : {} }
|
||||
} catch (error: unknown) {
|
||||
return toolErrorResult(exec.callId, error)
|
||||
return toolErrorResult(error)
|
||||
}
|
||||
},
|
||||
)
|
||||
if (result.callId !== exec.callId) {
|
||||
throw new TypeError(`tools/execute returned callId "${String(result.callId)}" for authoritative call "${exec.callId}"`)
|
||||
}
|
||||
return { kind: 'post-result', result }
|
||||
} catch (error: unknown) {
|
||||
return { kind: 'final-result', result: toolErrorResult(exec.callId, error) }
|
||||
return { kind: 'final-result', result: toolErrorResult(error) }
|
||||
}
|
||||
}
|
||||
|
||||
@@ -918,7 +925,7 @@ export class ToolRegistry extends Service {
|
||||
try {
|
||||
return this.finishScheduledExecution(exec, await this.postExecute(exec, result))
|
||||
} catch (error: unknown) {
|
||||
return this.finishScheduledExecution(exec, toolErrorResult(exec.callId, error))
|
||||
return this.finishScheduledExecution(exec, toolErrorResult(error))
|
||||
}
|
||||
}
|
||||
|
||||
@@ -934,7 +941,7 @@ export class ToolRegistry extends Service {
|
||||
try {
|
||||
finalResult = this.materializeFinalResult(result)
|
||||
} catch (error: unknown) {
|
||||
finalResult = this.materializeFinalResult(toolErrorResult(exec.callId, error))
|
||||
finalResult = this.materializeFinalResult(toolErrorResult(error))
|
||||
}
|
||||
this.notifyResult(exec, finalResult)
|
||||
return finalResult
|
||||
@@ -942,6 +949,8 @@ export class ToolRegistry extends Service {
|
||||
|
||||
/** Notify final-result observers without giving them a mutation/error channel into the outcome. */
|
||||
private notifyResult(exec: ToolExecution, result: ToolExecutionResult): void {
|
||||
// Freeze the remaining mutable signal slot before observers receive the
|
||||
// shared WeakMap-keyable execution object.
|
||||
Object.freeze(exec)
|
||||
const callbacks = this.ctx.events.dispatch('emit', [
|
||||
scopeTarget(this, exec.agent), 'tools/result', exec, result,
|
||||
@@ -1009,7 +1018,6 @@ export class ToolRegistry extends Service {
|
||||
const additionalContext = decision.additionalContext
|
||||
if (decision.kind === 'block') {
|
||||
return {
|
||||
callId: result.callId,
|
||||
content: decision.feedback,
|
||||
isError: true,
|
||||
...additionalContext ? { additionalContext } : {},
|
||||
@@ -1038,10 +1046,9 @@ function createExecutionToken(): ToolExecutionToken {
|
||||
return Symbol('dsh.tool.execution') as ToolExecutionToken
|
||||
}
|
||||
|
||||
function toolErrorResult(callId: ToolExecution['callId'], error: unknown): ToolExecutionResult {
|
||||
function toolErrorResult(error: unknown): ToolExecutionResult {
|
||||
const info = errorInfo(error)
|
||||
return {
|
||||
callId,
|
||||
content: [{ type: 'text', text: `Error: ${errorMessage(error)}` }],
|
||||
isError: true,
|
||||
...info ? { error: info } : {},
|
||||
|
||||
@@ -328,7 +328,7 @@ describe('the run_code dispatch bridge', () => {
|
||||
const tools = request.bindings[0]!.functions
|
||||
const first = await tools.echo!({ value: 'one' })
|
||||
const second = await tools.echo!({ value: 'two' })
|
||||
return { logs: [{ source: 'console', level: 'log', text: `saw ${String(first)}` }], value: second }
|
||||
return { logs: [`saw ${String(first)}`], value: second }
|
||||
}
|
||||
const result = await runCode(ctx, 'const …: string = …', { agent })
|
||||
expect(result.isError).toBe(false)
|
||||
@@ -339,7 +339,7 @@ describe('the run_code dispatch bridge', () => {
|
||||
{ parentCallId: 'call-1', subCallId: 'call-1:code:1', name: 'echo', arguments: { value: 'one' }, isError: false, resultSummary: 'echo:one' },
|
||||
{ parentCallId: 'call-1', subCallId: 'call-1:code:2', name: 'echo', arguments: { value: 'two' }, isError: false, resultSummary: 'echo:two' },
|
||||
])
|
||||
expect(result.meta).toEqual({ logs: [{ source: 'console', level: 'log', text: 'saw echo:one' }], dispatches: 2 })
|
||||
expect(result.meta).toEqual({ logs: ['saw echo:one'] })
|
||||
})
|
||||
|
||||
it('exposes only an opaque parent token to nested result observers', async () => {
|
||||
@@ -503,7 +503,7 @@ describe('the run_code dispatch bridge', () => {
|
||||
it('converts a failed run into a structured isError result carrying kind, message, and captured logs', async () => {
|
||||
const { ctx, runtime } = await setup({ mode: 'code' })
|
||||
runtime.behavior = () => Promise.resolve({
|
||||
logs: [{ source: 'console', level: 'log', text: 'got this far' }],
|
||||
logs: ['got this far'],
|
||||
error: { kind: 'timeout', message: 'compute budget exhausted (300ms busy)' },
|
||||
})
|
||||
const result = await runCode(ctx, 'program')
|
||||
@@ -627,7 +627,7 @@ describe('the run_code dispatch bridge', () => {
|
||||
const view = tool.presentResult?.({ code: 'return 1' }, {
|
||||
content: [{ type: 'text', text: 'model-facing' }],
|
||||
isError: false,
|
||||
meta: { logs: [{ source: 'console', level: 'log', text: 'printed' }], dispatches: 1 },
|
||||
meta: { logs: ['printed'] },
|
||||
})
|
||||
// The result omits the title — an update replaces only provided fields,
|
||||
// so the pending card's program title persists through completion.
|
||||
@@ -636,9 +636,10 @@ describe('the run_code dispatch bridge', () => {
|
||||
content: [{ type: 'text', text: 'printed' }],
|
||||
})
|
||||
// No captured output → no content either; everything pending persists.
|
||||
expect(tool.presentResult?.({ code: 'x' }, { content: [], isError: false, meta: { logs: [], dispatches: 2 } }))
|
||||
expect(tool.presentResult?.({ code: 'x' }, { content: [], isError: false, meta: { logs: [] } }))
|
||||
.toEqual({ card: 'generic' })
|
||||
// Replay with an unrecognizable meta falls back to the generic rendering.
|
||||
expect(tool.presentResult?.({ code: 'x' }, { content: [], isError: false, meta: { logs: [{ text: 'legacy' }], dispatches: 1 } })).toBeUndefined()
|
||||
expect(tool.presentResult?.({ code: 'x' }, { content: [], isError: false, meta: { other: true } })).toBeUndefined()
|
||||
expect(tool.presentResult?.({ code: 'x' }, { content: [], isError: false })).toBeUndefined()
|
||||
})
|
||||
|
||||
@@ -23,7 +23,7 @@ describe('gen-tool-catalog collectToolCatalog', () => {
|
||||
it('boots every shipped tool package and harvests its model-facing schemas', async () => {
|
||||
const catalog = await collectToolCatalog()
|
||||
const names = catalog.flatMap(entry => entry.schemas.map(s => s.name)).sort()
|
||||
expect(names).toEqual(['ask_user_question', 'bash', 'bash_kill', 'bash_output', 'cordis_inspect', 'cordis_mount', 'cordis_unmount', 'edit', 'read', 'run_code', 'skill', 'subagent', 'todo_write', 'web_fetch', 'web_search', 'workflow', 'write'])
|
||||
expect(names).toEqual(['ask_user_question', 'bash', 'cordis_inspect', 'cordis_mount', 'cordis_unmount', 'edit', 'read', 'run_code', 'skill', 'subagent', 'task_kill', 'task_list', 'task_output', 'todo_write', 'web_fetch', 'web_search', 'workflow', 'write'])
|
||||
// Every tool carries a JSON-Schema `parameters` object (what the model sees).
|
||||
for (const entry of catalog) {
|
||||
for (const schema of entry.schemas) {
|
||||
|
||||
@@ -548,7 +548,6 @@ describe('scoped execution dispatch', () => {
|
||||
|
||||
expect(reads).toBe(1)
|
||||
expect(result).toEqual({
|
||||
callId: CallId('unstable-arguments'),
|
||||
content: [{ type: 'text', text: 'ran:t' }],
|
||||
isError: false,
|
||||
})
|
||||
@@ -564,10 +563,9 @@ describe('scoped execution dispatch', () => {
|
||||
ctx.on('internal/dispatch', (mode, name) => {
|
||||
if (name === 'tools/result') dispatchModes.push(mode)
|
||||
})
|
||||
ctx.on('tools/execute', async (exec, next) => {
|
||||
ctx.on('tools/execute', async (_exec, next) => {
|
||||
await next()
|
||||
return {
|
||||
callId: exec.callId,
|
||||
content: [{ type: 'text', text: 'outer failure' }],
|
||||
isError: true,
|
||||
}
|
||||
|
||||
@@ -80,7 +80,7 @@ describe('ToolRegistry', () => {
|
||||
const ctx = await setup()
|
||||
ctx.tools.register(echoTool)
|
||||
const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'echo', arguments: { text: 'hi' } })
|
||||
expect(result).toEqual({ callId: CallId('c1'), content: [{ type: 'text', text: 'hi' }], isError: false })
|
||||
expect(result).toEqual({ content: [{ type: 'text', text: 'hi' }], isError: false })
|
||||
})
|
||||
|
||||
it('threads a tool-attached meta (object return form) onto the result', async () => {
|
||||
@@ -94,7 +94,6 @@ describe('ToolRegistry', () => {
|
||||
})
|
||||
const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'meta-tool', arguments: {} })
|
||||
expect(result).toEqual({
|
||||
callId: CallId('c1'),
|
||||
content: [{ type: 'text', text: 'ok' }],
|
||||
isError: false,
|
||||
meta: { diffs: [{ path: 'a', oldText: null, newText: 'x' }] },
|
||||
@@ -111,7 +110,7 @@ describe('ToolRegistry', () => {
|
||||
},
|
||||
})
|
||||
const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'no-meta-tool', arguments: {} })
|
||||
expect(result).toEqual({ callId: CallId('c1'), content: [{ type: 'text', text: 'ok' }], isError: false })
|
||||
expect(result).toEqual({ content: [{ type: 'text', text: 'ok' }], isError: false })
|
||||
expect('meta' in result).toBe(false)
|
||||
})
|
||||
|
||||
@@ -178,13 +177,12 @@ describe('ToolRegistry', () => {
|
||||
})
|
||||
})
|
||||
|
||||
it('ToolNotFoundError carries the tool name and a stable code', async () => {
|
||||
it('ToolNotFoundError carries a stable message and code', async () => {
|
||||
const { HarnessError } = await import('@deepseek-ai/dsh-llm')
|
||||
const err = new ToolNotFoundError('ghost')
|
||||
expect(err).toBeInstanceOf(HarnessError)
|
||||
expect(err.name).toBe('ToolNotFoundError')
|
||||
expect(err.code).toBe('UNKNOWN_TOOL')
|
||||
expect(err.toolName).toBe('ghost')
|
||||
expect(err.message).toBe('unknown tool "ghost"')
|
||||
})
|
||||
|
||||
@@ -425,7 +423,7 @@ describe('ToolRegistry', () => {
|
||||
ctx.on('tools/post-execute', async (_exec, _result, next) => { order.push('post'); return next() })
|
||||
|
||||
const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'traced', arguments: { text: 'hi' } })
|
||||
expect(result).toEqual({ callId: CallId('c1'), content: [{ type: 'text', text: 'hi' }], isError: false })
|
||||
expect(result).toEqual({ content: [{ type: 'text', text: 'hi' }], isError: false })
|
||||
// The around seam wraps dispatch; pre gates before it, post runs over its result.
|
||||
expect(order).toEqual(['pre', 'execute:before', 'dispatch', 'execute:after', 'post'])
|
||||
})
|
||||
@@ -526,8 +524,8 @@ describe('ToolRegistry', () => {
|
||||
async execute() { dispatched = true; return [] },
|
||||
})
|
||||
|
||||
ctx.on('tools/execute', async (exec: ToolExecution, _next: () => Promise<ToolExecutionResult>): Promise<ToolExecutionResult> =>
|
||||
({ callId: exec.callId, content: [{ type: 'text', text: 'short-circuited' }], isError: false }))
|
||||
ctx.on('tools/execute', async (_exec: ToolExecution, _next: () => Promise<ToolExecutionResult>): Promise<ToolExecutionResult> =>
|
||||
({ content: [{ type: 'text', text: 'short-circuited' }], isError: false }))
|
||||
|
||||
const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'never-runs', arguments: {} })
|
||||
expect(dispatched).toBe(false) // returning without next() skips core dispatch
|
||||
@@ -537,8 +535,7 @@ describe('ToolRegistry', () => {
|
||||
it('preserves additionalContext supplied by an around-dispatch result', async () => {
|
||||
const ctx = await setup()
|
||||
ctx.tools.register(echoTool)
|
||||
ctx.on('tools/execute', async exec => ({
|
||||
callId: exec.callId,
|
||||
ctx.on('tools/execute', async () => ({
|
||||
content: [{ type: 'text', text: 'short-circuited with context' }],
|
||||
isError: false,
|
||||
additionalContext: {
|
||||
@@ -556,20 +553,6 @@ describe('ToolRegistry', () => {
|
||||
})
|
||||
})
|
||||
|
||||
it('normalizes a tools/execute result with the wrong call id', async () => {
|
||||
const ctx = await setup()
|
||||
ctx.tools.register(echoTool)
|
||||
ctx.on('tools/execute', async () => ({ callId: CallId('other'), content: [], isError: false }))
|
||||
|
||||
const result = await ctx.tools.execute({
|
||||
callId: CallId('malformed-shape'), name: 'echo', arguments: {},
|
||||
})
|
||||
expect(result.isError).toBe(true)
|
||||
expect(result.content[0]).toMatchObject({
|
||||
text: 'Error: tools/execute returned callId "other" for authoritative call "malformed-shape"',
|
||||
})
|
||||
})
|
||||
|
||||
it('returns an isError result when a tools/execute listener throws', async () => {
|
||||
const ctx = await setup()
|
||||
ctx.tools.register(echoTool)
|
||||
@@ -577,7 +560,6 @@ describe('ToolRegistry', () => {
|
||||
|
||||
const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'echo', arguments: { text: 'hi' } })
|
||||
expect(result).toEqual({
|
||||
callId: CallId('c1'),
|
||||
content: [{ type: 'text', text: 'Error: wrapper broke' }],
|
||||
isError: true,
|
||||
})
|
||||
@@ -593,7 +575,6 @@ describe('ToolRegistry', () => {
|
||||
const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'echo', arguments: { text: 'hi' } })
|
||||
|
||||
expect(result).toEqual({
|
||||
callId: CallId('c1'),
|
||||
content: [{ type: 'text', text: 'Error: permission hook broke' }],
|
||||
isError: true,
|
||||
})
|
||||
@@ -609,7 +590,6 @@ describe('ToolRegistry', () => {
|
||||
const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'echo', arguments: { text: 'hi' } })
|
||||
|
||||
expect(result).toEqual({
|
||||
callId: CallId('c1'),
|
||||
content: [{ type: 'text', text: 'Error: post hook broke' }],
|
||||
isError: true,
|
||||
})
|
||||
@@ -625,7 +605,6 @@ describe('ToolRegistry', () => {
|
||||
const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'echo', arguments: { text: 'hi' } })
|
||||
|
||||
expect(result).toMatchObject({
|
||||
callId: CallId('c1'),
|
||||
isError: true,
|
||||
error: { name: 'HarnessError', code: 'DENIED' },
|
||||
})
|
||||
@@ -1254,7 +1233,7 @@ describe('defineTool validation (the runtime-validation RFC, part 1)', () => {
|
||||
},
|
||||
}))
|
||||
const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'reader', arguments: { path: '/x' } })
|
||||
expect(result).toEqual({ callId: CallId('c1'), content: [{ type: 'text', text: 'read /x' }], isError: false })
|
||||
expect(result).toEqual({ content: [{ type: 'text', text: 'read /x' }], isError: false })
|
||||
})
|
||||
|
||||
it('ToolArgsError carries a stable code and the violation list', () => {
|
||||
|
||||
Reference in New Issue
Block a user