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

Merge branch 'master' into codex/skill-system

Browse Source
This commit is contained in:
Yichen Jiang
2026-07-10 22:58:15 +08:00
committed by GitHub
parent e4be19b29e ee15a01f61
commit 386d4d3ec4
9 changed files with 290 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/acp-agent/README.md
View File

@@ -33,7 +33,7 @@ The editor sets each session's `cwd` to the project it opens; both the agent's b
## Snapshot tests (record-once / replay-deterministic)
This example is the home of the harness's **snapshot tests** — they boot this server as a real subprocess, drive it with a deterministic input script, and diff its normalized output against committed golden files. The model is made deterministic by `@deepseek-ai/dsh-llm-replay`, a function/namespace plugin that installs an `llm/stream` waterfall listener and short-circuits it, serving model streams reconstructed from a recorded **session JSONL** fixture (`<scenario>/session.jsonl`) — so replay needs no API key. The fixture IS the persisted session log: its `assistant/chunk` events carry every `StreamChunk`, so grouping them by `(turn, step)` reconstructs each `stream()` call (one model call per loop step). Recording is therefore "run the real agent once and harvest the `.jsonl`". The two failure modes not expressible as logged chunks — a pure throw before any chunk, and cancel/hang — use an optional `<scenario>/replay.override.json` sidecar (a `ReplayEntry[]` that replaces the derived script). A scenario that needs the agent to operate on existing files ships an optional `<scenario>/workspace/` directory — the harness copies its contents into the temp cwd before the run (see `workspace-edit`). See [the ACP snapshot tests RFC](../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md) for the full design.
This example is the home of the harness's **snapshot tests** — they boot this server as a real subprocess, drive it with a deterministic input script, and diff its normalized output against committed golden files. The model is made deterministic by `@deepseek-ai/dsh-llm-replay`, a function/namespace plugin that installs an `llm/stream` waterfall listener and short-circuits it, serving model streams reconstructed from a recorded **session JSONL** fixture (`<scenario>/session.jsonl`) — so replay needs no API key. The fixture IS the persisted session log: its `assistant/chunk` events carry every `StreamChunk`, so grouping them by `(turn, step)` reconstructs each `stream()` call (one model call per loop step). Recording is therefore "run the real agent once and harvest the `.jsonl`"; use `pnpm run test:snapshot:record` when the model transcript itself should change, and `pnpm run test:snapshot:refresh` when the committed model transcript is still the right mock input and only the current replay output/goldens need to be rewritten. The two failure modes not expressible as logged chunks — a pure throw before any chunk, and cancel/hang — use an optional `<scenario>/replay.override.json` sidecar (a `ReplayEntry[]` that replaces the derived script). A scenario that needs the agent to operate on existing files ships an optional `<scenario>/workspace/` directory — the harness copies its contents into the temp cwd before the run (see `workspace-edit`). See [the ACP snapshot tests RFC](../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md) for the full design.
## MVP limitations

28
examples/acp-agent/tests/acp.snapshot.ts
View File

@@ -1,15 +1,16 @@
import { fileURLToPath } from 'node:url'
import { dirname, join } from 'node:path'
import { defineAcpSnapshotSuite, type Scenario } from '@deepseek-ai/dsh-acp-snapshot'
import { defineAcpSnapshotSuite, type Scenario, type SnapshotSuiteOptions } from '@deepseek-ai/dsh-acp-snapshot'
/**
* The acp-agent example's snapshot suite: the scenario table for
* `dsh-acp-snapshot`'s suite factory, which owns every compare/guard mechanic
* (golden + re-persisted-log diffs, record write-back, the pinned-header
* (golden + re-persisted-log diffs, record/refresh write-back, the pinned-header
* uniformity guard, the fixture guards). Fixtures live under `snapshots/<name>/`;
* `pnpm run test:snapshot:record` re-records the `recorded` scenarios against
* the real API. See the package README (packages/support/acp-snapshot) and the
* snapshot RFC, docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md.
* `pnpm run test:snapshot:record` re-records model transcripts against the real
* API; `pnpm run test:snapshot:refresh` rewrites current replay goldens keyless.
* See the package README (packages/support/acp-snapshot) and the snapshot RFC,
* docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md.
*/
// The dsh-acp-agent bin (the demo:acp entry), this example's cordis.yml, and
@@ -26,6 +27,21 @@ const AGENT = {
const CODE_MODE_CONFIG = fileURLToPath(new URL('../code-mode.cordis.yml', import.meta.url))
const BOTH_MODE_CONFIG = fileURLToPath(new URL('../both-mode.cordis.yml', import.meta.url))
function snapshotModeFromEnv(value: string | undefined): SnapshotSuiteOptions['mode'] {
switch (value) {
case undefined:
case '':
case 'replay':
return 'replay'
case 'record':
return 'record'
case 'refresh':
return 'refresh'
default:
throw new Error(`unknown DSH_SNAPSHOT mode: ${value}`)
}
}
const SCENARIOS: Scenario[] = [
{ name: 'handshake', hasModelTurn: false, recorded: false },
{ name: 'reject-extra-dirs', hasModelTurn: false, recorded: false },
@@ -112,5 +128,5 @@ defineAcpSnapshotSuite({
agent: AGENT,
snapshotsDir: join(dirname(fileURLToPath(import.meta.url)), 'snapshots'),
scenarios: SCENARIOS,
mode: process.env.DSH_SNAPSHOT === 'record' ? 'record' : 'replay',
mode: snapshotModeFromEnv(process.env.DSH_SNAPSHOT),
})