Pine/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases 1 Wiki Activity

Resolve compaction policy per routed model

Browse Source
This commit is contained in:
Yichen Jiang
2026-07-20 15:34:00 +08:00
parent b877ede82d
commit cfa180c127
54 changed files with 1210 additions and 319 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/llm/llm-deepseek/README.md
+5 -1
View File
@@ -19,11 +19,15 @@ The package root exposes the Cordis plugin contract and `DeepSeekAdapter`; wire
models: # optional; defaults to V4 Flash and V4 Pro
- id: deepseek-v4-flash
name: DeepSeek V4 Flash
contextWindow: 128000
- id: private-reasoner
description: Company-hosted reasoning model
contextWindow: 64000
```
The plugin registers the single provider route `deepseek`. A request selects it with `provider: deepseek`; its `model` is passed through as the wire `model` string, so changing DeepSeek models does not require lifecycle-time registration. Omitting `models` advertises `deepseek-v4-flash` and `deepseek-v4-pro`; an explicit list replaces those defaults, while `models: []` advertises none. Catalog entries are exposed through `ctx.llm.listModels('deepseek')` for clients such as ACP editors, but remain advisory: unlisted model ids still pass through unchanged. An omitted entry name defaults to its id. Registering another adapter for `deepseek` throws `LlmError('DUPLICATE_ADAPTER')`.
The plugin registers the single provider route `deepseek`. A request selects it with `provider: deepseek`; its `model` is passed through as the wire `model` string, so changing DeepSeek models does not require lifecycle-time registration. Omitting `models` advertises `deepseek-v4-flash` and `deepseek-v4-pro`, each with a 128,000-token context window; an explicit list replaces those defaults, while `models: []` advertises none. Catalog entries are exposed through `ctx.llm.listModels('deepseek')` for clients such as ACP editors, but remain advisory: unlisted model ids still pass through unchanged. An omitted entry name defaults to its id.
`contextWindow` is optional per configured model and is not exposed through the advisory catalog. `ctx.llm.resolveModelContext('deepseek', model)` returns it only for an exact configured id; omission or an unlisted pass-through model returns `undefined` without invalidating routing. Pressure-sensitive plugins therefore get deployment-owned capacity without treating the model selector as authoritative. Registering another adapter for `deepseek` throws `LlmError('DUPLICATE_ADAPTER')`.
`reasoningEffort` is **omitted by default** — when unset, the `reasoning_effort` wire field is not sent and the server applies its own default for the model. The only accepted values are `high` and `max` (DeepSeek's official effort levels). It is meaningful only with thinking enabled (the provider default).
packages/llm/llm-deepseek/src/adapter.ts
+17 -1
View File
@@ -6,7 +6,13 @@
*/
import { attributionHeaders, CONTEXT_WINDOW_EXCEEDED_CODE, isContextWindowExceededError, LlmAdapter, LlmError } from '@deepseek-ai/dsh-llm'
import type { GenerateOptions, LlmModelInfo, LlmProviderInfo, StreamChunk } from '@deepseek-ai/dsh-llm'
import type {
GenerateOptions,
LlmModelContext,
LlmModelInfo,
LlmProviderInfo,
StreamChunk,
} from '@deepseek-ai/dsh-llm'
import { serializeRequest } from './serialize.ts'
import type { RequestDefaults } from './serialize.ts'
import { parseSse } from './sse.ts'
@@ -21,6 +27,8 @@ export interface DeepSeekCatalogModel {
name?: string
/** Optional selector detail for deployments with similar model variants. */
description?: string
/** Known combined request/response context capacity; omitted when deployment metadata is unavailable. */
contextWindow?: number
}
/** Constructor options for {@link DeepSeekAdapter}; the plugin's `apply` resolves them from Config + environment. */
@@ -79,6 +87,14 @@ export class DeepSeekAdapter extends LlmAdapter {
})))
}
override resolveModelContext(
_provider: string,
model: string,
): Promise<LlmModelContext | undefined> {
const contextWindow = this.options.models?.find(entry => entry.id === model)?.contextWindow
return Promise.resolve(contextWindow === undefined ? undefined : { contextWindow })
}
async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
const body = serializeRequest(options, this.options.defaults ?? {})
packages/llm/llm-deepseek/src/index.ts
+10 -2
View File
@@ -20,8 +20,8 @@ export const name = 'llm-deepseek'
export const inject = ['llm']
const DEFAULT_MODELS: DeepSeekCatalogModel[] = [
{ id: 'deepseek-v4-flash' },
{ id: 'deepseek-v4-pro' },
{ id: 'deepseek-v4-flash', contextWindow: 128_000 },
{ id: 'deepseek-v4-pro', contextWindow: 128_000 },
]
/**
@@ -47,6 +47,7 @@ const catalogModel: z<DeepSeekCatalogModel> = z.object({
id: z.string().required(),
name: z.string(),
description: z.string(),
contextWindow: z.number().step(1).min(1),
})
export const Config: z<Config> = z.object({
@@ -68,12 +69,19 @@ function resolveModels(models: readonly DeepSeekCatalogModel[] | undefined): Dee
if (model.name !== undefined && model.name.length === 0) {
throw new Error(`llm-deepseek: catalog model "${model.id}" has an empty name`)
}
if (model.contextWindow !== undefined
&& (!Number.isInteger(model.contextWindow) || model.contextWindow <= 0)) {
throw new Error(
`llm-deepseek: catalog model "${model.id}" contextWindow must be a positive integer`,
)
}
if (seen.has(model.id)) throw new Error(`llm-deepseek: duplicate catalog model "${model.id}"`)
seen.add(model.id)
return {
id: model.id,
...model.name === undefined ? {} : { name: model.name },
...model.description === undefined ? {} : { description: model.description },
...model.contextWindow === undefined ? {} : { contextWindow: model.contextWindow },
}
})
}
packages/llm/llm-deepseek/tests/adapter.spec.ts
+28 -2
View File
@@ -312,6 +312,8 @@ describe('plugin registration and config', () => {
{ provider: 'deepseek', id: 'deepseek-v4-flash', name: 'deepseek-v4-flash' },
{ provider: 'deepseek', id: 'deepseek-v4-pro', name: 'deepseek-v4-pro' },
])
await expect(ctx.llm.resolveModelContext('deepseek', 'deepseek-v4-flash'))
.resolves.toEqual({ contextWindow: 128_000 })
})
it('uses the default model catalog when apply is called directly', async () => {
@@ -331,14 +333,23 @@ describe('plugin registration and config', () => {
apiKey: 'k',
baseURL: 'http://127.0.0.1:1',
models: [
{ id: 'private-fast' },
{ id: 'private-reasoner', name: 'Private Reasoner', description: 'Higher reasoning budget' },
{ id: 'private-fast', contextWindow: 32_000 },
{
id: 'private-reasoner',
name: 'Private Reasoner',
description: 'Higher reasoning budget',
contextWindow: 64_000,
},
],
})
await expect(ctx.llm.listModels('deepseek')).resolves.toEqual([
{ provider: 'deepseek', id: 'private-fast', name: 'private-fast' },
{ provider: 'deepseek', id: 'private-reasoner', name: 'Private Reasoner', description: 'Higher reasoning budget' },
])
await expect(ctx.llm.resolveModelContext('deepseek', 'private-fast'))
.resolves.toEqual({ contextWindow: 32_000 })
await expect(ctx.llm.resolveModelContext('deepseek', 'arbitrary-unlisted'))
.resolves.toBeUndefined()
})
it('allows an explicit empty model catalog', async () => {
@@ -355,6 +366,8 @@ describe('plugin registration and config', () => {
it.each([
[[{ id: '' }], /ids must be non-empty/],
[[{ id: 'm', name: '' }], /empty name/],
[[{ id: 'm', contextWindow: 0 }], /contextWindow/],
[[{ id: 'm', contextWindow: 1.5 }], /contextWindow/],
[[{ id: 'm' }, { id: 'm' }], /duplicate catalog model/],
] as const)('rejects invalid advisory model config', async (models, message) => {
const ctx = new Context()
@@ -367,6 +380,19 @@ describe('plugin registration and config', () => {
expect(ctx.llm.listProviders()).toEqual([])
})
it('rejects invalid context capacity when apply is called directly', async () => {
const ctx = new Context()
await ctx.plugin(LlmService)
expect(() => {
LlmDeepSeek.apply(ctx, {
apiKey: 'k',
baseURL: 'http://127.0.0.1:1',
models: [{ id: 'invalid-context', contextWindow: 0 }],
})
}).toThrow(/contextWindow must be a positive integer/)
expect(ctx.llm.listProviders()).toEqual([])
})
it('falls back to DEEPSEEK_API_KEY and DEEPSEEK_BASE_URL env vars', async () => {
vi.stubEnv('DEEPSEEK_API_KEY', 'env-key')
vi.stubEnv('DEEPSEEK_BASE_URL', 'http://127.0.0.1:1')