Merge remote-tracking branch 'origin/master' into jsonl-packed-chunk-rows

Conflicts: the four generated catalog docs (regenerated over merged sources), session index.ts exports (keep chunk-rows exports + master's SessionSurface re-export), stdio/acp demo config schema and persistence wiring (thread packChunks through master's DEFAULT_PERSISTENCE_ROOT/UI shape), stdio README config table, and the jsonl spec import line. The packed-chunk fixture also gains the provenance field master made required on assistant/message.
2026-07-20 15:24:58 +08:00
parent 79f1ca5f6e b877ede82d
commit d85d2a4be3
1331 changed files with 74129 additions and 16289 deletions
--- a/packages/support/llm-replay/README.md
+++ b/packages/support/llm-replay/README.md
@@ -1,8 +1,8 @@
 # @deepseek-ai/dsh-llm-replay

-A replay LLM plugin for keyless snapshot tests. It installs a single `llm/stream` waterfall listener that short-circuits the waterfall (never calls `next()`) and yields model streams reconstructed from a recorded **session JSONL** fixture — so a test can boot the real agent against a fixed model transcript with no API key.
+A replay LLM plugin for keyless snapshot tests. It yields model streams reconstructed from a recorded **session JSONL** fixture, so a test can boot the real agent against a fixed model transcript with no API key. With `providers` configured it registers a replay-only adapter whose catalog is visible to clients such as ACP editors; without `providers` it installs the catch-all `llm/stream` waterfall used by tests that do not need discovery.

-Its consumer is the ACP snapshot harness in `examples/acp-agent`, which loads this plugin (via `cordis.snapshot.yml`) in place of a real LLM adapter. The package exists so its derive/parse/replay logic falls under the per-file 100% coverage gate on `packages/*/src` (the same logic, while it lived under `examples/`, was outside the gate).
+Its consumers are the ACP snapshot harness in `examples/acp-agent` and the `stream-json` snapshot in `examples/headless-agent`; each loads this plugin in place of a real LLM adapter. Keeping derivation and replay here places that logic under the per-file 100% coverage gate on `packages/*/src`.

 ## How the fixture works

@@ -23,10 +23,18 @@ 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. |

 ```yaml
 - id: llm-replay
  name: '@deepseek-ai/dsh-llm-replay'
+  config:
+    providers:
+      - id: deepseek
+        name: DeepSeek
+        models:
+          - id: deepseek-v4-flash
+          - id: deepseek-v4-pro
  # file/overrideFile/childFiles default to $DSH_SNAPSHOT_FILE /
  # $DSH_SNAPSHOT_OVERRIDE / $DSH_SNAPSHOT_CHILD_FILES, set by the snapshot
  # harness per scenario.
@@ -34,11 +42,11 @@ Replay keys every call by its calling session id (`GenerateOptions.sessionId`, s

 ## Exports

- `installLlmReplay(ctx, config)` — install the `llm/stream` listener; returns the disposer (HMR safety). Use this in tests to drive replay without the Loader or env vars.
+- `installLlmReplay(ctx, config)` — install the configured replay adapter or catch-all `llm/stream` listener; returns the disposer (HMR safety). Use this in tests to drive replay without the Loader or env vars.
 - `loadSessionScripts(config)` — resolve the ordered `SessionScript[]` (primary + children) for a scenario, ready to bind to live sessions in first-call order.
 - `loadReplayScript(config)` — resolve the `ReplayEntry[]` for the PRIMARY session only (sidecar override if present, else derived from the JSONL; fail-loud if the fixture is missing).
 - `deriveReplayScript(events)` / `parseSessionLog(text)` / `parseSessionHeader(text)` — the pure helpers that turn a recorded session log into a script and read its header `id`/`createdAt`. A derived group must end in a `finish` chunk; a group without one is the fingerprint of a thrown `stream()` and must instead be expressed via an override sidecar.
- Types `ReplayEntry` / `SessionScript` / `ReplayConfig` / `Config`.
+- Types `ReplayEntry` / `SessionScript` / `ReplayConfig` / `ReplayProviderConfig` / `ReplayModelConfig` / `Config`.

 ## Plugin export shape

@@ -48,6 +56,10 @@ Named `name` / `inject` / `Config` / `apply`, with **no default export**: the co

 None, as this keyless test adapter sends no request to a provider model; it only replays recorded assistant chunks into the test loop.

+#### KV Cache effect
+
+None; this package neither assembles nor sends a provider request.
+
 ## Known Limitations and Deferred Work

 - **First-call-order script binding assumes sequential delegation** — a cut that runs sibling subagents concurrently (or a compaction summarize call landing mid-run) would bind live sessions to recorded scripts non-deterministically; a stronger keying is deferred until such a scenario exists (`XXX(concurrent-subagents)`).
--- a/packages/support/llm-replay/src/index.ts
+++ b/packages/support/llm-replay/src/index.ts
@@ -11,8 +11,8 @@ import { delimiter as pathDelimiter } from 'node:path'
 import type { Context } from 'cordis'
 import { decodeStorageRecord } from '@deepseek-ai/dsh-session'
 import type { SessionEvent } from '@deepseek-ai/dsh-session'
-import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm'
-import { LlmError, assertNever } from '@deepseek-ai/dsh-llm'
+import type { GenerateOptions, LlmModelInfo, LlmProviderInfo, StreamChunk } from '@deepseek-ai/dsh-llm'
+import { LlmAdapter, LlmError, assertNever } from '@deepseek-ai/dsh-llm'

 /**
 * One recorded model call. `throw` may replay prefix chunks before failing;
@@ -21,9 +21,29 @@ import { LlmError, assertNever } from '@deepseek-ai/dsh-llm'
 */
 export type ReplayEntry =
  | { kind: 'chunks'; chunks: StreamChunk[] }
-  | { kind: 'throw'; chunks: StreamChunk[]; message: string; code: string; status?: number }
+  | { kind: 'throw'; chunks: StreamChunk[]; message: string; code: string }
  | { kind: 'hang' }

+/** One model exposed by a replay-only provider catalog. */
+export interface ReplayModelConfig {
+  /** Model id used for replay requests. */
+  id: string
+  /** Selector label; defaults to {@link id}. */
+  name?: string
+  /** Optional selector description. */
+  description?: string
+}
+
+/** One provider route exposed by the replay adapter. */
+export interface ReplayProviderConfig {
+  /** Provider route used for replay requests. */
+  id: string
+  /** Selector label; defaults to {@link id}. */
+  name?: string
+  /** Advisory models exposed to clients such as ACP editors. */
+  models?: ReplayModelConfig[]
+}
+
 /** Resolved plugin configuration. */
 export interface ReplayConfig {
  /**
@@ -46,6 +66,12 @@ export interface ReplayConfig {
   * for a single-session scenario.
   */
  childFiles?: string[]
+  /**
+   * Optional provider catalog. When non-empty, replay registers an adapter for
+   * these routes; when absent or empty, it retains the catch-all waterfall used
+   * by tests that do not need discovery.
+   */
+  providers?: ReplayProviderConfig[]
 }

 /**
@@ -205,6 +231,42 @@ export function loadSessionScripts(config: ReplayConfig): SessionScript[] {
  return [primary, ...children]
 }

+/** Replay adapter that makes a configured provider catalog discoverable without provider I/O. */
+class ReplayAdapter extends LlmAdapter {
+  private readonly providers: ReadonlyMap<string, ReplayProviderConfig>
+
+  constructor(
+    providers: readonly ReplayProviderConfig[],
+    private readonly replay: (options: GenerateOptions) => AsyncIterable<StreamChunk>,
+  ) {
+    super()
+    this.providers = new Map(providers.map(provider => [provider.id, provider]))
+  }
+
+  override providerInfo(provider: string): LlmProviderInfo {
+    const configured = this.providers.get(provider)
+    /* v8 ignore next -- LlmService only asks about routes registered from this same map. */
+    if (configured === undefined) return super.providerInfo(provider)
+    return { id: provider, name: configured.name ?? provider }
+  }
+
+  override listModels(provider: string): Promise<readonly LlmModelInfo[]> {
+    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([])
+    return Promise.resolve((configured.models ?? []).map(model => ({
+      provider,
+      id: model.id,
+      name: model.name ?? model.id,
+      ...model.description === undefined ? {} : { description: model.description },
+    })))
+  }
+
+  override stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
+    return this.replay(options)
+  }
+}
+
 /** Yield a recorded stream back, honoring abort like a real adapter. */
 async function* replayEntry(entry: ReplayEntry, signal: AbortSignal | undefined): AsyncIterable<StreamChunk> {
  switch (entry.kind) {
@@ -223,7 +285,7 @@ async function* replayEntry(entry: ReplayEntry, signal: AbortSignal | undefined)
        if (signal?.aborted) throw new Error('aborted')
        yield chunk
      }
-      throw new LlmError(entry.message, entry.code, entry.status)
+      throw new LlmError(entry.message, entry.code)
    case 'hang':
      // Replay a stream that stalls until cancelled (mirrors MockAdapter): one
      // chunk, then wait for abort and surface it as the consumer expects.
@@ -245,12 +307,14 @@ async function* replayEntry(entry: ReplayEntry, signal: AbortSignal | undefined)
 /**
 * Install per-session positional replay. A newly seen live session takes the
 * next ordered recorded script, then advances its own cursor synchronously at
- * invocation time; calls without `sessionId` share one anonymous session.
- * Returns the effect disposer for HMR-safe removal.
+ * invocation time; calls without `sessionId` share one anonymous session. A
+ * non-empty provider catalog registers a routed replay adapter; otherwise a
+ * catch-all waterfall intercepts requests. Returns the effect disposer for
+ * HMR-safe removal.
 *
- * @param ctx - the context whose `llm/stream` waterfall the listener short-circuits.
+ * @param ctx - the context whose LLM service receives the replay route or waterfall.
 * @param config - the resolved fixture paths (env-var defaulting is `apply`'s job).
- * @returns the `ctx.on` disposer that removes the listener.
+ * @returns the disposer that removes the registered adapter or listener.
 */
 export function installLlmReplay(ctx: Context, config: ReplayConfig): () => void {
  const scripts = loadSessionScripts(config)
@@ -260,7 +324,7 @@ export function installLlmReplay(ctx: Context, config: ReplayConfig): () => void
  const bound = new Map<string, { entries: ReplayEntry[]; cursor: number }>()
  let nextScript = 0
  const ANON = '\0anon\0' // the key for a call that carries no sessionId
-  return ctx.on('llm/stream', (options: GenerateOptions, _next) => {
+  const replay = (options: GenerateOptions): AsyncIterable<StreamChunk> => {
    const key = options.sessionId ?? ANON
    let state = bound.get(key)
    let unrecorded = false
@@ -298,7 +362,12 @@ export function installLlmReplay(ctx: Context, config: ReplayConfig): () => void
      }
      yield* replayEntry(entry, options.signal)
    })()
-  })
+  }
+  const providers = config.providers ?? []
+  if (providers.length > 0) {
+    return ctx.llm.registerAdapter(providers.map(provider => provider.id), new ReplayAdapter(providers, replay))
+  }
+  return ctx.on('llm/stream', (options: GenerateOptions, _next) => replay(options))
 }

 export const name = 'llm-replay'
@@ -316,6 +385,8 @@ export interface Config {
   * a nested-agent scenario; absent/empty for a single-session scenario.
   */
  childFiles?: string[]
+  /** Optional replay-only provider catalog; absent or empty selects catch-all waterfall replay. */
+  providers?: ReplayProviderConfig[]
 }

 export function apply(ctx: Context, config: Config = {}): void {
@@ -331,5 +402,6 @@ export function apply(ctx: Context, config: Config = {}): void {
    file,
    ...overrideFile !== undefined && overrideFile.length > 0 ? { overrideFile } : {},
    ...childFiles.length > 0 ? { childFiles } : {},
+    ...config.providers !== undefined ? { providers: config.providers } : {},
  })
 }
--- a/packages/support/llm-replay/tests/llm-replay.spec.ts
+++ b/packages/support/llm-replay/tests/llm-replay.spec.ts
@@ -188,7 +188,7 @@ describe('loadReplayScript', () => {
  it('uses the sidecar override when present, ignoring the JSONL', () => {
    writeFileSync(file, sessionJsonl([]), 'utf8')
    const overrideFile = join(dir, 'replay.override.json')
-    const override: ReplayEntry[] = [{ kind: 'throw', chunks: [], message: '401', code: 'AUTH', status: 401 }]
+    const override: ReplayEntry[] = [{ kind: 'throw', chunks: [], message: '401', code: 'AUTH' }]
    writeFileSync(overrideFile, JSON.stringify(override), 'utf8')
    expect(loadReplayScript({ file, overrideFile })).toEqual(override)
  })
@@ -211,7 +211,7 @@ describe('loadReplayScript', () => {
  })
 })

-describe('installLlmReplay (through the real waterfall)', () => {
+describe('installLlmReplay (through the real LlmService)', () => {
  function writeLog(...calls: StreamChunk[][]): void {
    let seq = 1
    const events: SessionEvent[] = []
@@ -227,7 +227,41 @@ describe('installLlmReplay (through the real waterfall)', () => {
    await ctx.plugin(LlmService)
    // No adapter registered for 'm' — replay must not reach it.
    installLlmReplay(ctx, { file })
-    expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS)
+    expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS)
+  })
+
+  it('registers a replay-only provider catalog when configured', async () => {
+    writeLog(TEXT_CHUNKS)
+    const ctx = new Context()
+    await ctx.plugin(LlmService)
+    const dispose = installLlmReplay(ctx, {
+      file,
+      providers: [
+        {
+          id: 'deepseek',
+          name: 'DeepSeek',
+          models: [
+            { id: 'flash' },
+            { id: 'pro', name: 'Pro', description: 'Larger model' },
+          ],
+        },
+        { id: 'empty' },
+      ],
+    })
+
+    expect(ctx.llm.listProviders()).toEqual([
+      { id: 'deepseek', name: 'DeepSeek' },
+      { id: 'empty', name: 'empty' },
+    ])
+    await expect(ctx.llm.listModels('deepseek')).resolves.toEqual([
+      { provider: 'deepseek', id: 'flash', name: 'flash' },
+      { provider: 'deepseek', id: 'pro', name: 'Pro', description: 'Larger model' },
+    ])
+    await expect(ctx.llm.listModels('empty')).resolves.toEqual([])
+    expect(await drain(ctx.llm.stream({ provider: 'deepseek', model: 'pro', messages: [] }))).toEqual(TEXT_CHUNKS)
+
+    dispose()
+    expect(ctx.llm.listProviders()).toEqual([])
  })

  it('serves the Nth call the Nth derived entry (positional)', async () => {
@@ -240,16 +274,16 @@ describe('installLlmReplay (through the real waterfall)', () => {
    const ctx = new Context()
    await ctx.plugin(LlmService)
    installLlmReplay(ctx, { file })
-    expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS)
-    expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(second)
+    expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS)
+    expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(second)
  })

-  it('replays a sidecar throw-entry as an LlmError with code/status, after its prefix chunks', async () => {
+  it('replays a sidecar throw-entry as an LlmError with its stable code, after its prefix chunks', async () => {
    writeFileSync(file, sessionJsonl([]), 'utf8')
    const overrideFile = join(dir, 'replay.override.json')
    const partial: StreamChunk[] = [{ type: 'block-start', index: 0, blockType: 'text' }]
    writeFileSync(overrideFile, JSON.stringify([
-      { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH', status: 401 },
+      { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH' },
    ]), 'utf8')
    const ctx = new Context()
    await ctx.plugin(LlmService)
@@ -257,8 +291,8 @@ describe('installLlmReplay (through the real waterfall)', () => {

    const seen: StreamChunk[] = []
    await expect((async () => {
-      for await (const c of ctx.llm.stream({ model: 'm', messages: [] })) seen.push(c)
-    })()).rejects.toMatchObject({ message: 'unauthorized', code: 'AUTH', status: 401 })
+      for await (const c of ctx.llm.stream({ provider: 'm', model: 'm', messages: [] })) seen.push(c)
+    })()).rejects.toMatchObject({ message: 'unauthorized', code: 'AUTH' })
    expect(seen).toEqual(partial)
  })

@@ -271,7 +305,7 @@ describe('installLlmReplay (through the real waterfall)', () => {
    installLlmReplay(ctx, { file, overrideFile })

    const controller = new AbortController()
-    const iterator = ctx.llm.stream({ model: 'm', messages: [], signal: controller.signal })[Symbol.asyncIterator]()
+    const iterator = ctx.llm.stream({ provider: 'm', model: 'm', messages: [], signal: controller.signal })[Symbol.asyncIterator]()
    // Deterministically consume the two pre-hang chunks (no sleep), then abort
    // and assert the next pull rejects — event-driven, per the no-sleeps rule.
    expect((await iterator.next()).value).toMatchObject({ type: 'block-start' })
@@ -285,8 +319,8 @@ describe('installLlmReplay (through the real waterfall)', () => {
    const ctx = new Context()
    await ctx.plugin(LlmService)
    installLlmReplay(ctx, { file })
-    await drain(ctx.llm.stream({ model: 'm', messages: [] }))
-    await expect(drain(ctx.llm.stream({ model: 'm', messages: [] }))).rejects.toThrow(/exhausted/)
+    await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))
+    await expect(drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).rejects.toThrow(/exhausted/)
  })

  it('aborts mid-replay when the signal is already set', async () => {
@@ -296,7 +330,7 @@ describe('installLlmReplay (through the real waterfall)', () => {
    installLlmReplay(ctx, { file })
    const controller = new AbortController()
    controller.abort()
-    await expect(drain(ctx.llm.stream({ model: 'm', messages: [], signal: controller.signal })))
+    await expect(drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [], signal: controller.signal })))
      .rejects.toThrow('aborted')
  })

@@ -318,11 +352,11 @@ describe('installLlmReplay (through the real waterfall)', () => {
    }, { inject: ['llm'] }))

    // While installed, replay short-circuits to the derived fixture ('hi').
-    expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS)
+    expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS)

    await fiber.dispose()
    // After dispose the listener is gone; the call reaches the real adapter.
-    expect(await drain(ctx.llm.stream({ model: 'm', messages: [] })))
+    expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] })))
      .toEqual([{ type: 'finish', reason: { kind: 'stop' } }])
  })

@@ -334,7 +368,7 @@ describe('installLlmReplay (through the real waterfall)', () => {
    const ctx = new Context()
    await ctx.plugin(LlmService)
    installLlmReplay(ctx, { file, overrideFile })
-    await expect(drain(ctx.llm.stream({ model: 'm', messages: [] })))
+    await expect(drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] })))
      .rejects.toThrow(/llm-replay replay entry/)
  })

@@ -346,7 +380,7 @@ describe('installLlmReplay (through the real waterfall)', () => {
    await ctx.plugin(LlmService)
    installLlmReplay(ctx, { file, overrideFile })
    const controller = new AbortController()
-    const iterator = ctx.llm.stream({ model: 'm', messages: [], signal: controller.signal })[Symbol.asyncIterator]()
+    const iterator = ctx.llm.stream({ provider: 'm', model: 'm', messages: [], signal: controller.signal })[Symbol.asyncIterator]()
    // Consume the two pre-hang chunks, then start the third pull so the generator
    // is parked inside the await (signal NOT yet aborted — exercises the
    // addEventListener('abort') registration), and only THEN abort.
@@ -363,7 +397,7 @@ describe('installLlmReplay (through the real waterfall)', () => {
    const overrideFile = join(dir, 'replay.override.json')
    const partial: StreamChunk[] = [{ type: 'block-start', index: 0, blockType: 'text' }]
    writeFileSync(overrideFile, JSON.stringify([
-      { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH', status: 401 },
+      { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH' },
    ]), 'utf8')
    const ctx = new Context()
    await ctx.plugin(LlmService)
@@ -372,7 +406,7 @@ describe('installLlmReplay (through the real waterfall)', () => {
    controller.abort()
    // Already aborted: the throw-entry's prefix loop surfaces 'aborted' before
    // it can reach the recorded LlmError.
-    await expect(drain(ctx.llm.stream({ model: 'm', messages: [], signal: controller.signal })))
+    await expect(drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [], signal: controller.signal })))
      .rejects.toThrow('aborted')
  })

@@ -386,7 +420,7 @@ describe('installLlmReplay (through the real waterfall)', () => {
    const controller = new AbortController()
    controller.abort()
    // The two pre-hang chunks still flow; the abort surfaces at the await.
-    const iterator = ctx.llm.stream({ model: 'm', messages: [], signal: controller.signal })[Symbol.asyncIterator]()
+    const iterator = ctx.llm.stream({ provider: 'm', model: 'm', messages: [], signal: controller.signal })[Symbol.asyncIterator]()
    await iterator.next()
    await iterator.next()
    await expect(iterator.next()).rejects.toThrow('aborted')
@@ -516,7 +550,7 @@ describe('installLlmReplay (per-session keying)', () => {
  ]

  const live = (id: string): GenerateOptions =>
-    ({ model: 'm', messages: [], sessionId: id as NonNullable<GenerateOptions['sessionId']> })
+    ({ provider: 'm', model: 'm', messages: [], sessionId: id as NonNullable<GenerateOptions['sessionId']> })

  it('routes each live session to its own script by FIRST-CALL order', async () => {
    const parentFile = writeSession('session.jsonl', { id: 'rec-parent', createdAt: 100 }, [TEXT_CHUNKS])
@@ -553,7 +587,7 @@ describe('installLlmReplay (per-session keying)', () => {
    await ctx.plugin(LlmService)
    installLlmReplay(ctx, { file: parentFile })
    // No sessionId at all — the legacy single-session path.
-    expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS)
+    expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS)
  })

  it('fails loud when more distinct live sessions call than were recorded', async () => {
@@ -587,12 +621,13 @@ describe('apply (the plugin entry)', () => {
    expect(inject).toEqual(['llm'])
  })

-  it('installs replay from an explicit config.file', async () => {
+  it('installs replay and its catalog from explicit config', async () => {
    writeFileSync(file, sessionJsonl(TEXT_CHUNKS.map((c, i) => chunkEvent(i + 1, 1, 1, c))), 'utf8')
    const ctx = new Context()
    await ctx.plugin(LlmService)
-    apply(ctx, { file })
-    expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS)
+    apply(ctx, { file, providers: [{ id: 'm', models: [{ id: 'm' }] }] })
+    expect(ctx.llm.listProviders()).toEqual([{ id: 'm', name: 'm' }])
+    expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS)
  })

  it('falls back to $DSH_SNAPSHOT_FILE / $DSH_SNAPSHOT_OVERRIDE when config is empty', async () => {
@@ -604,7 +639,7 @@ describe('apply (the plugin entry)', () => {
    const ctx = new Context()
    await ctx.plugin(LlmService)
    apply(ctx)
-    expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS)
+    expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS)
  })

  it('uses only the file when no override path is configured or in the env', async () => {
@@ -614,7 +649,7 @@ describe('apply (the plugin entry)', () => {
    const ctx = new Context()
    await ctx.plugin(LlmService)
    apply(ctx)
-    expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS)
+    expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS)
  })

  it('throws when no fixture path is given by config or env', async () => {
@@ -644,7 +679,7 @@ describe('apply (the plugin entry)', () => {
    await ctx.plugin(LlmService)
    apply(ctx, { file, childFiles: [childFile] })
    const live = (id: string): GenerateOptions =>
-      ({ model: 'm', messages: [], sessionId: id as NonNullable<GenerateOptions['sessionId']> })
+      ({ provider: 'm', model: 'm', messages: [], sessionId: id as NonNullable<GenerateOptions['sessionId']> })
    expect(await drain(ctx.llm.stream(live('A')))).toEqual(TEXT_CHUNKS)
    expect(await drain(ctx.llm.stream(live('B')))).toEqual(childSecond)
  })
@@ -664,7 +699,7 @@ describe('apply (the plugin entry)', () => {
    await ctx.plugin(LlmService)
    apply(ctx)
    const live = (id: string): GenerateOptions =>
-      ({ model: 'm', messages: [], sessionId: id as NonNullable<GenerateOptions['sessionId']> })
+      ({ provider: 'm', model: 'm', messages: [], sessionId: id as NonNullable<GenerateOptions['sessionId']> })
    expect(await drain(ctx.llm.stream(live('A')))).toEqual(TEXT_CHUNKS)
    expect(await drain(ctx.llm.stream(live('B')))).toEqual(childChunks)
  })
@@ -676,6 +711,6 @@ describe('apply (the plugin entry)', () => {
    const ctx = new Context()
    await ctx.plugin(LlmService)
    apply(ctx)
-    expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS)
+    expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS)
  })
 })