docs: trim generated prose

This commit is contained in:
Tianyi Cui
2026-07-12 03:36:43 +08:00
parent 3dca90261c
commit 75838e10b5
323 changed files with 2857 additions and 11833 deletions

View File

@@ -3,54 +3,20 @@ import { fileURLToPath } from 'node:url'
import { defineAcpSnapshotSuite, type Scenario, type SnapshotSuiteOptions } from '@deepseek-ai/dsh-acp-snapshot'
/**
* Snapshot suite for the SANDBOXED composition (`../cordis.yml`, swapped to
* the sibling `cordis.snapshot.yml` replay overlay by the bin under
* `DSH_SNAPSHOT=replay`). Replay swaps only the MODEL for the recorded
* transcript — every bash call re-executes for real under the host's actual
* runner (Seatbelt on macOS, bwrap on Linux CI: ci.yml's snapshot lane
* installs bubblewrap for exactly this), so the recorded scenarios double as
* cross-backend confinement regression: an allowed command a runner change
* starts denying fails replay outright. Their commands are limited to
* `cat`/`printf` shapes whose bytes are identical across those backends and
* across GNU/BSD userlands.
*
* Deliberately ABSENT: a scenario whose transcript carries a real sandbox
* DENIAL. The harness-authored `[sandbox: file access denied …]` marker is
* byte-stable, but the denied command's own stderr is the backend's dialect
* (bwrap EROFS "Read-only file system", Landlock EACCES "Permission
* denied", Seatbelt EPERM "Operation not permitted", GNU vs BSD phrasing on
* top), and stderr reaches both compared surfaces — such a fixture replays
* only on the platform that recorded it. The denial→marker path stays on
* dsh-tool-bash's unit tests and the real-kernel sandbox e2e legs
* (.github/workflows/sandbox.yml); the escalation scenarios below sidestep
* it by having the USER assert the prior denial, so the recorded model
* escalates without a platform-variant denial in the log.
* Snapshot suite for the sandboxed composition (`../cordis.yml`, swapped to the sibling
* `cordis.snapshot.yml` replay overlay by the bin under `DSH_SNAPSHOT=replay`).
*/
const SCENARIOS: Scenario[] = [
// Protocol-only (keyless, authored): the session config-option surface
// this composition adds — both advertised selects on session/new, the
// complete refreshed state every session/set_config_option answers with,
// and both rejection shapes — as committed wire bytes. No bash runs, so
// this one still replays on runner-less hosts.
// Protocol-only (keyless, authored): the session config-option surface this composition adds
// — both advertised selects on session/new, the complete refreshed state every
// session/set_config_option answers with, and both rejection shapes — as committed wire
// bytes.
{ name: 'config-options', hasModelTurn: false, recorded: false },
// The runtime mode-switching arc, and NECESSARILY the pinned-header
// scenario: an approval-policy switch rewrites its prompt section, and the
// resulting request/header-delta is legal only in the pinning scenario
// (the factory's uniformity guard). The pin commits this composition's
// full header — persona, tool schemas WITH the escalation fields — plus
// the approval delta and its "changed by the user" notice verbatim. The
// SANDBOX switch is deliberately silent (no section, no notice — the
// sandbox RFC's visibility asymmetry): the recorded arc proves it by
// BEHAVIOR, a confined write landing under the switched mode with no
// header change.
// The runtime mode-switching arc, and NECESSARILY the pinned-header scenario: an
// approval-policy switch rewrites its prompt section, and the resulting request/header-delta
// is legal only in the pinning scenario (the factory's uniformity guard).
{ name: 'mode-switching', hasModelTurn: true, recorded: true, pinsHeader: true, expectedHeaderDeltas: 1 },
// The approval wire end-to-end, under the DEFAULT read-only/ask (a switch
// would emit a header-delta the uniformity guard forbids here): the
// escalating bash call streams, session/request_permission attaches to it
// (allow-once / reject-once), and the scripted answer drives each branch —
// an approved run executes CONFINED under the granted workspace-write; a
// rejected one executes nothing and fails with the deterministic
// rejection text.
// Pin both approval branches under the default read-only/ask policy.
{ name: 'escalation-approved', hasModelTurn: true, recorded: true },
{ name: 'escalation-rejected', hasModelTurn: true, recorded: true },
]

View File

@@ -18,21 +18,6 @@ import {
/**
* examples/sandbox-acp-agent end to end.
*
* Keyless smoke: boot the REAL `cordis.yml` through the `dsh-acp-agent` bin as
* an ACP subprocess and drive initialize + session/new — the real-Loader-path
* guard (postmortem 0001) for THIS tree's export shapes, which now include the
* sandbox executor AND the approval service. No prompt is sent, so neither the
* model nor a sandbox runner is ever exercised.
*
* With-key escalation flow (self-skips without DEEPSEEK_API_KEY or a usable
* platform runner): a scripted ACP client plays the human. The real model is
* denied under `read-only`, escalates with `sandbox_permissions` +
* `justification`, the bridge prompts THIS client over
* `session/request_permission`, the client answers `allow-once`, and the
* retried write must land ON DISK (world-verified). The session cwd is a temp
* dir under the platform temp area, which `workspace-write` grants — so either
* escalation target the model picks can land the write.
*/
const binScript = fileURLToPath(new URL('../../../packages/ui/acp-agent/src/bin.ts', import.meta.url))
@@ -42,10 +27,8 @@ const tsxLoader = fileURLToPath(import.meta.resolve('tsx'))
// tsconfig so the unbuilt `paths` map resolves (see examples/AGENTS.md).
const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
// A usable confining runner, probed the same way the executor suites do:
// bwrap on Linux, Seatbelt's sandbox-exec on macOS. Without one the strict
// attempt would fail closed (SANDBOX_UNAVAILABLE) instead of producing the
// denial this flow starts from.
// A usable confining runner, probed the same way the executor suites do: bwrap on Linux,
// Seatbelt's sandbox-exec on macOS.
const hasBwrap = spawnSync('bwrap', ['--ro-bind', '/', '/', '--dev', '/dev', '--proc', '/proc', '--die-with-parent', '--', 'true'], {
timeout: 5_000,
stdio: 'ignore',
@@ -121,9 +104,8 @@ describe('sandbox-acp-agent keyless smoke (real cordis.yml via the Loader)', ()
workdir = await mkdtemp(join(tmpdir(), 'sandbox-acp-smoke-'))
spawned = spawnSandboxAcpAgent(workdir, 'reject-once')
const { client } = spawned
// A dummy key boots the adapter; no prompt is ever sent, so no model call
// and no sandbox runner probe happen. This drives the fiber tree the same
// way an editor would, which is what catches a broken export/inject shape.
// A dummy key boots the adapter; no prompt is ever sent, so no model call and no sandbox
// runner probe happen.
const init = await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
expect(init.protocolVersion).toBe(PROTOCOL_VERSION)
const { sessionId } = await client.newSession({ cwd: workdir, mcpServers: [] })