Files
deepseek-harness/packages/llm/llm/tests/assembler.spec.ts
T
Tianyi Cui 2745879132 refactor(llm): drop the image content block until a path can honor it
ImageBlock had no production producer and every consumer dropped it:
the deepseek serializer skipped it, the pi-ai converter skipped it as
unrepresentable, the ACP bridge neither advertises image prompt
capability nor forwards image blocks, and compact-basic charged a flat
85-token estimate and rendered an [image] placeholder. A block
constructed today would silently vanish from the wire — the vocabulary
advertised a capability no path honors, the silent-data-loss shape the
defensive patterns warn against. The only constructors were tests
pinning the skip/estimate branches.

Remove ImageBlock and its ContentBlockMap entry (its cache?: CacheHint
field leaves with it; CacheHint itself and the other two cache? fields
are out of scope). compact-basic loses its explicit image estimate and
placeholder arms (the merge-extensible default arms absorb the case);
the deepseek serializer, pi-ai converter, and ACP codec already handled
image in their default arms, so only their image-naming comments
change. The codec's inbound rejection of ACP-protocol image prompt
content stays — that guards wire content a client can send regardless
of our vocabulary.

Tests that constructed harness image blocks to pin the removed branches
are dropped (the 85-token estimate pin) or retargeted onto plugin-added
block types / other non-text blocks, which the surviving default arms
own. Docs, the type-equiv pastes, and the content-block vocabulary
RFC's block list and multimodal-home consequence are updated in the
same change; the RFC moves to implemented/ and the index is
regenerated. A real multimodal feature reintroduces image via
declaration merging together with the adapter mapping, ACP
advertisement, and compaction pricing that honor it.
2026-07-04 17:21:13 +08:00

172 lines
8.6 KiB
TypeScript

import { describe, expect, it } from 'vitest'
import { BlockAssembler, CallId, type StreamChunk } from '@deepseek-ai/dsh-llm'
describe('BlockAssembler', () => {
it('assembles interleaved text, reasoning, and tool-call deltas', () => {
const chunks: StreamChunk[] = [
{ type: 'block-start', index: 0, blockType: 'reasoning' },
{ type: 'reasoning-delta', index: 0, text: 'thinking…' },
{ type: 'block-end', index: 0, block: { type: 'reasoning', text: 'thinking…' } },
{ type: 'block-start', index: 1, blockType: 'text' },
{ type: 'text-delta', index: 1, text: 'Hello' },
{ type: 'text-delta', index: 1, text: ' world' },
{ type: 'block-start', index: 2, blockType: 'tool-call' },
{ type: 'tool-call-delta', index: 2, id: CallId('call-1'), name: 'echo', argumentsDelta: '{"text":' },
{ type: 'tool-call-delta', index: 2, id: CallId('call-1'), argumentsDelta: '"hi"}' },
{ type: 'usage', usage: { inputTokens: 10, outputTokens: 5 } },
{ type: 'finish', reason: { kind: 'tool-calls' } },
]
const assembler = new BlockAssembler()
for (const chunk of chunks) assembler.push(chunk)
expect(assembler.blocks()).toEqual([
{ type: 'reasoning', text: 'thinking…' },
{ type: 'text', text: 'Hello world' },
{ type: 'tool-call', id: CallId('call-1'), name: 'echo', arguments: '{"text":"hi"}' },
])
expect(assembler.usage).toEqual({ inputTokens: 10, outputTokens: 5 })
expect(assembler.finish).toEqual({ kind: 'tool-calls' })
expect(assembler.message().role).toBe('assistant')
})
it('returns the completed block from push() on block-end', () => {
const assembler = new BlockAssembler()
expect(assembler.push({ type: 'block-start', index: 0, blockType: 'text' })).toBeUndefined()
expect(assembler.push({ type: 'text-delta', index: 0, text: 'hi' })).toBeUndefined()
const block = assembler.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'hi' } })
expect(block).toEqual({ type: 'text', text: 'hi' })
})
it('tolerates deltas without explicit block-start/end', () => {
const assembler = new BlockAssembler()
assembler.push({ type: 'text-delta', index: 0, text: 'implicit' })
expect(assembler.blocks()).toEqual([{ type: 'text', text: 'implicit' }])
expect(assembler.finish).toEqual({ kind: 'stop' })
})
it('returns undefined usage when no usage chunk was received', () => {
const assembler = new BlockAssembler()
assembler.push({ type: 'text-delta', index: 0, text: 'no usage' })
expect(assembler.usage).toBeUndefined()
})
it('reuses an existing partial when ensure() is called with a tracked index', () => {
const assembler = new BlockAssembler()
// block-start creates the partial; block-end calls ensure() on the same index
assembler.push({ type: 'block-start', index: 0, blockType: 'text' })
// push a delta first to guarantee the partial exists
assembler.push({ type: 'text-delta', index: 0, text: 'hi' })
// block-end's ensure() must find the existing partial (the second branch path)
const block = assembler.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'hi' } })
expect(block).toEqual({ type: 'text', text: 'hi' })
})
it('throws from assemble() when a partial has an unhandled blockType', () => {
const assembler = new BlockAssembler()
// A partial whose blockType is not text/reasoning/tool-call cannot be
// assembled without its block-end. A plugin-added block type (here
// 'video', via the merge-extensible ContentBlockMap) opened by a
// block-start with no closing block-end exercises that throw.
assembler.push({ type: 'block-start', index: 0, blockType: 'video' } as unknown as StreamChunk)
expect(() => assembler.blocks()).toThrow('cannot assemble incomplete block of type "video"')
})
it('mustGet throws when an index is missing from the partials map (invariant violation)', () => {
const assembler = new BlockAssembler()
// Force the invariant violation: manually corrupt the data structures.
/* eslint-disable */
const hack = assembler as any
hack.order.push(99)
/* eslint-enable */
expect(() => assembler.blocks()).toThrow('BlockAssembler invariant violated')
})
it('ignores duplicate block-start for the same index', () => {
const assembler = new BlockAssembler()
assembler.push({ type: 'block-start', index: 0, blockType: 'text' })
assembler.push({ type: 'text-delta', index: 0, text: 'one' })
// duplicate block-start — should be no-op (false branch of has check)
assembler.push({ type: 'block-start', index: 0, blockType: 'text' })
assembler.push({ type: 'text-delta', index: 0, text: ' two' })
assembler.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'one two' } })
expect(assembler.blocks()).toEqual([{ type: 'text', text: 'one two' }])
})
it('ignores tool-call-delta stragglers after block-end', () => {
const assembler = new BlockAssembler()
assembler.push({ type: 'block-start', index: 0, blockType: 'tool-call' })
assembler.push({ type: 'tool-call-delta', index: 0, id: CallId('c1'), name: 'echo', argumentsDelta: '{}' })
assembler.push({ type: 'block-end', index: 0, block: { type: 'tool-call', id: CallId('c1'), name: 'echo', arguments: '{}' } })
// straggler after block-end — partial.block is set, so early return
assembler.push({ type: 'tool-call-delta', index: 0, id: CallId('c1'), name: 'evil', argumentsDelta: 'oops' })
expect(assembler.blocks()).toEqual([{ type: 'tool-call', id: CallId('c1'), name: 'echo', arguments: '{}' }])
})
it('assembles tool-call with generated id fallback when no id provided', () => {
const assembler = new BlockAssembler()
assembler.push({ type: 'tool-call-delta', index: 0, argumentsDelta: '{}' } as StreamChunk)
// No id and no name provided — uses fallback id `call-{index}` and empty name
const blocks = assembler.blocks()
expect(blocks).toEqual([
{ type: 'tool-call', id: CallId('call-0'), name: '', arguments: '{}' },
])
})
it('exposes usage via the getter when a usage chunk was received', () => {
const assembler = new BlockAssembler()
assembler.push({ type: 'text-delta', index: 0, text: 'msg' })
assembler.push({ type: 'usage', usage: { inputTokens: 5, outputTokens: 3 } })
expect(assembler.usage).toEqual({ inputTokens: 5, outputTokens: 3 })
})
})
describe('assertNever', () => {
it('throws with diagnostics when a value escapes a closed union at runtime', async () => {
const { assertNever } = await import('@deepseek-ai/dsh-llm')
expect(() => assertNever({ type: 'rogue' } as never, 'test-context'))
.toThrow('unreachable variant in test-context: {"type":"rogue"}')
expect(() => assertNever(undefined as never)).toThrow('unreachable variant: undefined')
})
it('BlockAssembler.push rejects chunks outside the closed StreamChunk union', () => {
const assembler = new BlockAssembler()
expect(() => assembler.push({ type: 'rogue-chunk' } as unknown as StreamChunk))
.toThrow('unreachable variant in BlockAssembler.push')
})
})
describe('BlockAssembler regressions (property-test findings)', () => {
it('first block-end wins: a duplicate block-end for a closed index is ignored', () => {
// Found by fast-check (the property-testing RFC): two block-ends at the same index made the
// streamed prefix (first block) disagree with final blocks() (second
// block). The first close must win — same straggler rule as post-close
// deltas — so the prefix returned incrementally by push() and the final
// blocks() stay identical.
const chunks: StreamChunk[] = [
{ type: 'block-end', index: 0, block: { type: 'reasoning', text: 'first' } },
{ type: 'block-end', index: 0, block: { type: 'text', text: 'second' } },
]
const streaming = new BlockAssembler()
const closed = []
for (const chunk of chunks) {
const block = streaming.push(chunk)
if (block) closed.push(block)
}
const oneShot = new BlockAssembler()
for (const chunk of chunks) oneShot.push(chunk)
expect(closed).toEqual([{ type: 'reasoning', text: 'first' }])
expect(oneShot.blocks()).toEqual([{ type: 'reasoning', text: 'first' }])
expect(closed).toEqual(oneShot.blocks())
})
it('push returns undefined for a duplicate block-end (it closed nothing)', () => {
const a = new BlockAssembler()
expect(a.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'x' } }))
.toEqual({ type: 'text', text: 'x' })
expect(a.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'y' } }))
.toBeUndefined()
})
})