diff --git a/examples/tui-agent/tests/fixtures/tui-scripted-llm.ts b/examples/tui-agent/tests/fixtures/tui-scripted-llm.ts index 020394ebe3..2806e205a4 100644 --- a/examples/tui-agent/tests/fixtures/tui-scripted-llm.ts +++ b/examples/tui-agent/tests/fixtures/tui-scripted-llm.ts @@ -1,5 +1,5 @@ import type { Context } from 'cordis' -import type { GenerateOptions, LlmModelInfo, StreamChunk } from '@deepseek-ai/dsh-llm' +import type { GenerateOptions, LlmModelContext, LlmModelInfo, StreamChunk } from '@deepseek-ai/dsh-llm' import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm' const CONTROL_PROBE = '\u001b]2;MODEL_CONTROLLED\u0007\u001b[999CMODEL_CURSOR\u009b31mMODEL_C1' @@ -25,6 +25,10 @@ class ScriptedTuiAdapter extends LlmAdapter { ]) } + override resolveModelContext(_provider: string, _model: string): Promise { + return Promise.resolve({ contextWindow: 128_000 }) + } + override async * stream(options: GenerateOptions): AsyncIterable { if (options.model !== 'tui-scripted-model-pro' || !options.system?.includes('tui-scripted-model-pro')) { throw new Error('the scripted TUI request did not apply the selected model to routing and prompt variables') diff --git a/examples/tui-agent/tests/tui.snapshot.ts b/examples/tui-agent/tests/tui.snapshot.ts index cc8e9847cb..1ac3f5b55e 100644 --- a/examples/tui-agent/tests/tui.snapshot.ts +++ b/examples/tui-agent/tests/tui.snapshot.ts @@ -33,7 +33,7 @@ import { HeadlessTerminal } from '../../../packages/ui/tui/tests/headless-termin const SNAPSHOTS_DIR = join(dirname(fileURLToPath(import.meta.url)), 'snapshots') // Keep pre-normalization layout widths identical across macOS and Linux. const SNAPSHOT_TMP_ROOT = process.platform === 'win32' ? tmpdir() : '/tmp' -const PROVIDERS = [{ id: 'deepseek', models: [{ id: 'deepseek-v4-flash' }] }] +const PROVIDERS = [{ id: 'deepseek', models: [{ id: 'deepseek-v4-flash', contextWindow: 128_000 }] }] const UUID_RE = /[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12}/gi type SnapshotMode = 'replay' | 'record' | 'refresh' diff --git a/packages/support/llm-replay/README.md b/packages/support/llm-replay/README.md index 4c8966333b..0d89d4337d 100644 --- a/packages/support/llm-replay/README.md +++ b/packages/support/llm-replay/README.md @@ -23,7 +23,7 @@ Replay keys every call by its calling session id (`GenerateOptions.sessionId`, s | `file` | string | `$DSH_SNAPSHOT_FILE` | Path to the primary (parent) `session.jsonl` fixture. Required (config or env). | | `overrideFile` | string | `$DSH_SNAPSHOT_OVERRIDE` | Optional path to a `ReplayEntry[]` sidecar that replaces the PRIMARY session's derived script. | | `childFiles` | string[] | `$DSH_SNAPSHOT_CHILD_FILES` (path-delimited) | Recorded subagent child-session logs for a nested scenario; empty for a single-session scenario. | -| `providers` | `ReplayProviderConfig[]` | — | Optional replay-only provider and model catalog. Configured routes dispatch through the replay adapter and never perform provider I/O. | +| `providers` | `ReplayProviderConfig[]` | — | Optional replay-only provider and model catalog. Each model may publish `contextWindow`; configured routes dispatch through the replay adapter and never perform provider I/O. | ```yaml - id: llm-replay @@ -34,6 +34,7 @@ Replay keys every call by its calling session id (`GenerateOptions.sessionId`, s name: DeepSeek models: - id: deepseek-v4-flash + contextWindow: 128000 - id: deepseek-v4-pro # file/overrideFile/childFiles default to $DSH_SNAPSHOT_FILE / # $DSH_SNAPSHOT_OVERRIDE / $DSH_SNAPSHOT_CHILD_FILES, set by the snapshot diff --git a/packages/support/llm-replay/src/index.ts b/packages/support/llm-replay/src/index.ts index 3299905a07..5a254cca2d 100644 --- a/packages/support/llm-replay/src/index.ts +++ b/packages/support/llm-replay/src/index.ts @@ -10,7 +10,7 @@ import { existsSync, readFileSync } from 'node:fs' import { delimiter as pathDelimiter } from 'node:path' import type { Context } from 'cordis' import type { SessionEvent } from '@deepseek-ai/dsh-session' -import type { GenerateOptions, LlmModelInfo, LlmProviderInfo, StreamChunk } from '@deepseek-ai/dsh-llm' +import type { GenerateOptions, LlmModelContext, LlmModelInfo, LlmProviderInfo, StreamChunk } from '@deepseek-ai/dsh-llm' import { LlmAdapter, LlmError, assertNever } from '@deepseek-ai/dsh-llm' /** @@ -31,6 +31,8 @@ export interface ReplayModelConfig { name?: string /** Optional selector description. */ description?: string + /** Optional positive integer context capacity published by the replay adapter. */ + contextWindow?: number } /** One provider route exposed by the replay adapter. */ @@ -260,6 +262,14 @@ class ReplayAdapter extends LlmAdapter { }))) } + override resolveModelContext(provider: string, model: string): Promise { + const configured = this.providers.get(provider) + /* v8 ignore next -- LlmService only asks about routes registered from this same map. */ + if (configured === undefined) return Promise.resolve(undefined) + const contextWindow = configured.models?.find(candidate => candidate.id === model)?.contextWindow + return Promise.resolve(contextWindow === undefined ? undefined : { contextWindow }) + } + override stream(options: GenerateOptions): AsyncIterable { return this.replay(options) } diff --git a/packages/support/llm-replay/tests/llm-replay.spec.ts b/packages/support/llm-replay/tests/llm-replay.spec.ts index 846085deec..b9a05e47ea 100644 --- a/packages/support/llm-replay/tests/llm-replay.spec.ts +++ b/packages/support/llm-replay/tests/llm-replay.spec.ts @@ -228,7 +228,7 @@ describe('installLlmReplay (through the real LlmService)', () => { id: 'deepseek', name: 'DeepSeek', models: [ - { id: 'flash' }, + { id: 'flash', contextWindow: 128_000 }, { id: 'pro', name: 'Pro', description: 'Larger model' }, ], }, @@ -245,6 +245,10 @@ describe('installLlmReplay (through the real LlmService)', () => { { provider: 'deepseek', id: 'pro', name: 'Pro', description: 'Larger model' }, ]) await expect(ctx.llm.listModels('empty')).resolves.toEqual([]) + await expect(ctx.llm.resolveModelContext('deepseek', 'flash')).resolves.toEqual({ contextWindow: 128_000 }) + await expect(ctx.llm.resolveModelContext('deepseek', 'pro')).resolves.toBeUndefined() + await expect(ctx.llm.resolveModelContext('deepseek', 'unlisted')).resolves.toBeUndefined() + await expect(ctx.llm.resolveModelContext('empty', 'unlisted')).resolves.toBeUndefined() expect(await drain(ctx.llm.stream({ provider: 'deepseek', model: 'pro', messages: [] }))).toEqual(TEXT_CHUNKS) dispose()