DeepSeek/deepseek-harness
1
0
Fork 0
mirror of https://github.com/deepseek-ai/deepseek-harness synced 2026-08-15 21:04:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/master' into codex/simp-share-loader-smoke-harness

Browse Source 
# Conflicts:
#	examples/AGENTS.md
#	examples/coding-agent/tests/code-mode-keyless-smoke.e2e.ts
#	examples/coding-agent/tests/keyless-smoke.e2e.ts
#	examples/cordis-agent/tests/keyless-smoke.e2e.ts
#	examples/echo-agent/tests/echo.e2e.ts
This commit is contained in:
Tianyi Cui
2026-07-14 18:30:10 +08:00
parent 4cea4979c6 fb126e164a
commit dbf4bebe83
558 changed files with 4400 additions and 12476 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
examples/coding-agent/tests/code-mode.e2e.ts
View File

@@ -16,14 +16,9 @@ import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
import { WorkerCodeRuntime } from '@deepseek-ai/dsh-code-runtime-worker'
/**
* The Code Mode with-key proof (the RFC's e2e tier): a REAL model under
* `mode: 'code'`, a task that requires composing two tool calls, verified
* against the WORLD — the persisted request header carried exactly
* `[run_code]` as the wire tool list, each sub-call landed as a
* `tool/code-dispatch` event, the file the program wrote exists on disk, and
* the final answer is the program's curated output. Key-gated (see
* vitest.e2e.config.ts); the keyless Loader-path smoke of the overlay lives
* in `code-mode-keyless-smoke.e2e.ts`.
* With-key Code Mode proof: a real model receives only `run_code`, composes two
* sub-calls, writes a file, and returns curated output while the log records
* each `tool/code-dispatch`. The keyless Loader smoke is in the sibling test.
*/
const PERSONA = 'You are coding-agent. You work by writing TypeScript programs for run_code: '

31
examples/coding-agent/tests/compaction.e2e.ts
View File

@@ -7,25 +7,11 @@ import { AgentId } from '@deepseek-ai/dsh-agent'
import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts'
/**
* The compaction smoke test: a real model runs a multi-step bash task with a
* deliberately tiny context window, so the auto-compaction listener fires
* MID-SESSION and summarizes the older history into a checkpoint. This is the
* first end-to-end exercise of the compaction seam (it is wired nowhere else),
* and the runaway-survival regression net — it proves a session that grows past
* the window keeps running rather than overflowing. Key-gated.
*
* Verifies the WORLD, not the agent's self-report: a compact/start…end pair
* landed in the real session log, the surface actually shrank (a replace node
* exists and shadowed older nodes), and the agent still produced a final answer
* after compaction (so the summarized history did not break the conversation).
*
* FIXME(compaction-snapshot): this key-gated e2e is the ONLY coverage of runaway
* compaction — there is no keyless full-transcript snapshot of it. dsh-llm-replay
* reconstructs one model call per (turn, step) from `assistant/chunk` events, but
* `summarize()` assembles its stream into a local BlockAssembler and appends no
* `assistant/chunk`, so the interleaved summarization call is unreplayable. A
* snapshot needs replay-harness work to serve that call; deferred as a follow-up.
* Key-gated smoke for mid-session compaction. It verifies the compact event
* pair, replacement of older surface nodes, and a final answer after compaction.
*/
// FIXME(compaction-snapshot): this is the only full compaction coverage because
// replay cannot serve the summarizer's unlogged model call.
let workdir: string | undefined
let ctx: Context | undefined
@@ -40,18 +26,11 @@ afterEach(async () => {
describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compacts mid-flight and keeps running', () => {
it('summarizes older history into a checkpoint without breaking the task', async () => {
workdir = await mkdtemp(join(tmpdir(), 'dsh-compaction-'))
// A handful of files for the model to read, so multiple bash steps
// accumulate surface nodes (tool calls + results) and grow the history past
// the (deliberately tiny) window.
for (let i = 1; i <= 4; i++) {
await writeFile(join(workdir, `file${i}.txt`), `This is file number ${i}. `.repeat(50))
}
// Tiny window so a couple of steps crosses the threshold. The generation
// cap is deliberately larger than the final checkpoint because
// reasoning-capable APIs count reasoning tokens against the provider output
// budget even though those blocks are stripped before the checkpoint is
// stored.
// Reasoning tokens require a larger generation cap than the retained checkpoint.
ctx = await codingHarness(workdir, {
persona: SYSTEM_PROMPT,
compact: {