Files
deepseek-harness/packages/core/system-prompt/tests/system-prompt.spec.ts
Tianyi Cui e85e21c8b0 fix(review): close interpolation strictness holes; make tool-subagent mirror provider lifecycle
Codex round-1 findings, both confirmed:

- renderPrompt: variable lookup now uses Object.hasOwn (an unregistered
  {{constructor}} previously resolved through Object.prototype and spliced
  function source into the prompt), and a {{ that opens no complete group
  while a }} still follows ({{{model}}}, {{a{b}}) now throws instead of
  passing or partially interpolating. A lone {{ with no }} after it stays
  verbatim; substituted values are never re-scanned.
- tool-subagent: the apply-time provider lookup assumed a load order the
  cordis Loader does not guarantee (siblings start concurrently). The seam
  now announces subagent/provider-added/-removed and the tool mirrors the
  provider's lifecycle: registers when the provider is (or becomes)
  available, unregisters when it goes away, re-derives wording on reload.
  No load-order requirement remains.
- loop.spec containment test now proves live continuation: after the
  contained render failure, a waterfall listener rescues {{cwd}} and the
  same agent completes a real model turn.

RFC/READMEs updated to the shipped contract; cordis catalog regenerated.
2026-07-05 02:42:48 +08:00

376 lines
16 KiB
TypeScript

import { describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import SystemPrompt, { AssembleContext, PromptAssembly, renderPrompt } from '@deepseek-ai/dsh-system-prompt'
describe('SystemPrompt', () => {
it('assembles sections in order with context-resolved text and collected tools', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
ctx.systemPrompt.section({ name: 'persona', order: 0, text: 'You are DeepSeek Code.' })
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: {} }])
const assembly = await ctx.systemPrompt.assemble()
expect(assembly.sections.map(s => s.name)).toEqual(['persona', 'rules', 'cwd'])
expect(assembly.sections.map(s => s.text)).toEqual(['You are DeepSeek Code.', 'Be precise.', 'cwd: /tmp'])
expect(assembly.tools).toEqual([{ name: 'echo', description: 'echo back', parameters: {} }])
expect(assembly.variables).toEqual({})
expect(renderPrompt(assembly)).toBe('You are DeepSeek Code.\n\nBe precise.\n\ncwd: /tmp')
})
it('resolves section text providers against the assemble context, at each assemble call', async () => {
// The context is HOW per-agent sections work (the loop passes { agent });
// this spec stays agent-agnostic and smuggles a marker through a plain field.
const ctx = new Context()
await ctx.plugin(SystemPrompt)
let calls = 0
ctx.systemPrompt.section({
name: 'dynamic',
order: 0,
text: (context: AssembleContext) => `call ${++calls} for ${(context as { who?: string }).who ?? 'nobody'}`,
})
expect((await ctx.systemPrompt.assemble({ who: 'alice' } as AssembleContext)).sections[0]!.text).toBe('call 1 for alice')
expect((await ctx.systemPrompt.assemble()).sections[0]!.text).toBe('call 2 for nobody')
})
it('removes contributions when the contributing fiber is disposed (HMR safety)', async () => {
const ctx = new Context()
await ctx.plugin(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.variable('scoped_var', () => 'v')
}, { inject: ['systemPrompt'] }))
const before = await ctx.systemPrompt.assemble()
expect(before.sections).toHaveLength(1)
expect(before.variables).toEqual({ scoped_var: 'v' })
await fiber.dispose()
const assembly = await ctx.systemPrompt.assemble()
expect(assembly.sections).toHaveLength(0)
expect(assembly.tools).toHaveLength(0)
expect(assembly.variables).toEqual({})
})
it('rejects a duplicate section name (a double-loaded plugin must fail, not double its text)', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
ctx.systemPrompt.section({ name: 'dup', order: 0, text: 'first' })
expect(() => ctx.systemPrompt.section({ name: 'dup', order: 1, text: 'second' }))
.toThrow('prompt section "dup" is already registered')
// The failed registration leaked nothing; the original stays intact.
const assembly = await ctx.systemPrompt.assemble()
expect(assembly.sections.map(s => s.text)).toEqual(['first'])
})
it('rolls back a section when a system-prompt/change listener throws (P1-1)', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
// Throw on the first emit only. Note the rollback path itself emits
// system-prompt/change, so a multi-shot guard would also fire on rollback;
// a single-shot guard isolates the register's own emit.
let threw = false
const off = ctx.on('system-prompt/change', () => {
if (!threw) { threw = true; throw new Error('boom change listener') }
})
expect(() => ctx.systemPrompt.section({ name: 'p', order: 0, text: 'persona' })).toThrow('boom change listener')
expect((await ctx.systemPrompt.assemble()).sections).toHaveLength(0) // nothing leaked
// Subsequent listener-free register contributes exactly once.
off()
ctx.systemPrompt.section({ name: 'p', order: 0, text: 'persona' })
expect((await ctx.systemPrompt.assemble()).sections.map(s => s.name)).toEqual(['p'])
})
it('rolls back a tool provider when a system-prompt/change listener throws (P1-1)', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
let threw = false
const off = ctx.on('system-prompt/change', () => {
if (!threw) { threw = true; throw new Error('boom change listener') }
})
expect(() => ctx.systemPrompt.tools(() => [{ 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: {} }])
expect((await ctx.systemPrompt.assemble()).tools.map(t => t.name)).toEqual(['t'])
})
it('rolls back a variable when a system-prompt/change listener throws (P1-1)', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
let threw = false
const off = ctx.on('system-prompt/change', () => {
if (!threw) { threw = true; throw new Error('boom change listener') }
})
expect(() => ctx.systemPrompt.variable('v', () => 'x')).toThrow('boom change listener')
expect((await ctx.systemPrompt.assemble()).variables).toEqual({}) // nothing leaked
off()
ctx.systemPrompt.variable('v', () => 'x')
expect((await ctx.systemPrompt.assemble()).variables).toEqual({ v: 'x' })
})
it('composes multiple system-prompt/assemble waterfall listeners in order, with the context', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
ctx.systemPrompt.section({ name: 'base', order: 0, text: 'base' })
// Listener A appends a section, then delegates.
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' })
return next()
})
// Listener B (registered later, runs after A) sees A's contribution.
const seen: string[][] = []
ctx.on('system-prompt/assemble', async (assembly: PromptAssembly, _context, next) => {
seen.push(assembly.sections.map(s => s.name))
return next()
})
const passed: AssembleContext = {}
const assembly = await ctx.systemPrompt.assemble(passed)
expect(seen).toEqual([['base', 'from-a']])
expect(assembly.sections.map(s => s.name)).toEqual(['base', 'from-a'])
expect(contexts[0]).toBe(passed) // the caller's context reaches listeners
})
it('lets a waterfall listener short-circuit by not calling next()', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
ctx.systemPrompt.section({ name: 'real', order: 0, text: 'real' })
ctx.on('system-prompt/assemble', async () => {
return { sections: [], tools: [], variables: {} } satisfies PromptAssembly
})
const assembly = await ctx.systemPrompt.assemble()
expect(assembly.sections).toHaveLength(0)
})
it('assembles snapshots so one-step mutations do not leak into future assemblies', async () => {
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: {} } }])
const first = await ctx.systemPrompt.assemble()
first.sections[0]!.name = 'mutated'
first.sections[0]!.text = 'mutated'
first.tools[0]!.description = 'mutated'
const firstParameters = first.tools[0]!.parameters as { properties: Record<string, unknown> }
firstParameters.properties['leak'] = { type: 'string' }
const second = await ctx.systemPrompt.assemble()
expect(second.sections.map(section => section.name)).toEqual(['base'])
expect(second.sections.map(section => section.text)).toEqual(['base'])
expect(second.tools).toEqual([{ name: 't', description: 'tool', parameters: { type: 'object', properties: {} } }])
})
it('filters out empty section text from renderPrompt', () => {
const result = renderPrompt({
sections: [
{ name: 'empty', order: 0, text: '' },
{ name: 'real', order: 1, text: 'content' },
],
tools: [],
variables: {},
})
expect(result).toBe('content')
})
it('emits system-prompt/change when a tool provider is registered and disposed', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
let changeCount = 0
ctx.on('system-prompt/change', () => void changeCount++)
const dispose = ctx.systemPrompt.tools(() => [])
// registration emits change
expect(changeCount).toBe(1)
dispose()
// disposal emits change again
expect(changeCount).toBe(2)
})
it('cleans up tool providers on fiber dispose', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
inner.systemPrompt.tools(() => [{ name: 'fiber-tool', description: '', parameters: {} }])
}, { inject: ['systemPrompt'] }))
expect((await ctx.systemPrompt.assemble()).tools).toHaveLength(1)
await fiber.dispose()
expect((await ctx.systemPrompt.assemble()).tools).toHaveLength(0)
})
it('removes section when returned disposer is called directly', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
const dispose = ctx.systemPrompt.section({ name: 'direct', order: 0, text: 'direct section' })
expect((await ctx.systemPrompt.assemble()).sections).toHaveLength(1)
dispose()
expect((await ctx.systemPrompt.assemble()).sections).toHaveLength(0)
})
it('removes tool provider when returned disposer is called directly', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
const dispose = ctx.systemPrompt.tools(() => [{ name: 'direct-tool', description: '', parameters: {} }])
expect((await ctx.systemPrompt.assemble()).tools).toHaveLength(1)
dispose()
expect((await ctx.systemPrompt.assemble()).tools).toHaveLength(0)
})
describe('prompt variables', () => {
it('resolves each variable against the assemble context and emits change on register/unregister', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
let changeCount = 0
ctx.on('system-prompt/change', () => void changeCount++)
const dispose = ctx.systemPrompt.variable('who', context => (context as { who?: string }).who)
expect(changeCount).toBe(1)
expect((await ctx.systemPrompt.assemble({ who: 'alice' } as AssembleContext)).variables).toEqual({ who: 'alice' })
// A provider returning undefined records "registered but no value here".
expect((await ctx.systemPrompt.assemble()).variables).toEqual({ who: undefined })
dispose()
expect(changeCount).toBe(2)
expect((await ctx.systemPrompt.assemble()).variables).toEqual({})
})
it('rejects a duplicate variable name and an unreferenceable name', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
ctx.systemPrompt.variable('model', () => 'm1')
expect(() => ctx.systemPrompt.variable('model', () => 'm2'))
.toThrow('prompt variable "model" is already registered')
expect(() => ctx.systemPrompt.variable('Not Valid', () => 'x'))
.toThrow('invalid prompt variable name "Not Valid"')
// Neither failed registration leaked.
expect((await ctx.systemPrompt.assemble()).variables).toEqual({ model: 'm1' })
})
it('interpolates {{name}} references in section text at render', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
ctx.systemPrompt.section({ name: 'persona', order: 0, text: 'You run on {{model}} in {{cwd}}.' })
ctx.systemPrompt.variable('model', () => 'deepseek-v4')
ctx.systemPrompt.variable('cwd', () => '/work')
expect(renderPrompt(await ctx.systemPrompt.assemble())).toBe('You run on deepseek-v4 in /work.')
})
it('lets a waterfall listener add or override variables before render', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
ctx.systemPrompt.section({ name: 's', order: 0, text: '{{extra}}' })
ctx.on('system-prompt/assemble', async (assembly: PromptAssembly, _context, next) => {
assembly.variables['extra'] = 'from-waterfall'
return next()
})
expect(renderPrompt(await ctx.systemPrompt.assemble())).toBe('from-waterfall')
})
it('throws on a reference to an unregistered variable, listing what exists', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
ctx.systemPrompt.section({ name: 'persona', order: 0, text: 'on {{modle}}' })
ctx.systemPrompt.variable('model', () => 'm')
await expect(async () => renderPrompt(await ctx.systemPrompt.assemble()))
.rejects.toThrow('unknown prompt variable "{{modle}}" in section "persona"; registered variables: model')
})
it('names "(none)" when no variables are registered at all', () => {
expect(() => renderPrompt({ sections: [{ name: 's', order: 0, 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}}' }],
tools: [],
variables: { cwd: undefined },
})).toThrow('prompt variable "{{cwd}}" has no value for this assembly (section "persona")')
})
it('throws on a malformed complete reference, e.g. inner spaces', () => {
expect(() => renderPrompt({
sections: [{ name: 's', order: 0, text: 'on {{ model }}' }],
tools: [],
variables: { model: 'm' },
})).toThrow('malformed prompt variable reference "{{ model }}" in section "s"')
})
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' }],
tools: [],
variables: {},
})
expect(text).toBe('shell ${X:-{{fallback} stays')
})
it.each([
{ text: '{{{model}}}', label: 'extra outer braces' },
{ text: 'x {{a{b}} y {{model}}', label: 'nested brace inside a would-be group' },
])('throws on a mangled reference with a }} still following ($label)', ({ text }) => {
expect(() => renderPrompt({
sections: [{ name: 's', order: 0, text }],
tools: [],
variables: { model: 'm' },
})).toThrow('malformed prompt variable reference at')
})
it('rejects {{constructor}} as UNKNOWN — prototype properties are not variables', () => {
// `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}}' }],
tools: [],
variables: { model: 'm' },
})).toThrow('unknown prompt variable "{{constructor}}"')
})
it('a variable NAMED like a prototype property works once actually registered', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
ctx.systemPrompt.section({ name: 's', order: 0, text: '{{constructor}}' })
ctx.systemPrompt.variable('constructor', () => 'own-value')
expect(renderPrompt(await ctx.systemPrompt.assemble())).toBe('own-value')
})
it('never re-scans substituted values (a value containing {{sneaky}} stays literal)', () => {
const text = renderPrompt({
sections: [{ name: 's', order: 0, text: 'v = {{model}}!' }],
tools: [],
variables: { model: 'literal {{sneaky}} inside' },
})
expect(text).toBe('v = literal {{sneaky}} inside!')
})
})
})