Merge remote-tracking branch 'origin/master' into cross-family-fs-sandbox

# Conflicts:
#	docs/config-catalog.md
#	docs/cordis-catalog/events.md
#	docs/cordis-catalog/services.md
#	docs/event-producer-consumer.md
#	docs/persistence-catalog.md
#	examples/acp-agent/cordis.yml
#	examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
#	examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
#	examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl
#	examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/permission-switching/session.jsonl
#	examples/acp-agent/tests/snapshots/skill-load/session.jsonl
#	examples/acp-agent/tests/snapshots/text-turn/session.jsonl
#	packages/bash/bash-sandbox/src/index.ts
#	packages/bash/bash/src/types.ts
#	packages/bash/tool-bash/src/index.ts
#	packages/fs/fs/src/index.ts
#	packages/sandbox/sandbox-policy/src/session-mode.ts
#	packages/ui/permission/src/index.ts
#	packages/ui/permission/tests/permission.spec.ts
#	scripts/doc-budgets.manifest.json
This commit is contained in:
kingwl
2026-07-14 21:25:36 +08:00
608 changed files with 7195 additions and 12508 deletions

View File

@@ -10,20 +10,13 @@ import { SandboxPolicyService } from '@deepseek-ai/dsh-sandbox-policy'
import { SandboxBashExecutor } from '@deepseek-ai/dsh-bash-sandbox'
/**
* KEYLESS consumer-integration proof under bwrap: the REAL
* `LocalSandboxProvider` (nothing forced — bwrap is the ladder's first rung,
* so a passing probe selects it) underneath the REAL `SandboxBashExecutor`,
* driven through the executor's public run/start paths. Verifies the WORLD
* (files exist or don't) plus the stamped result facts — in particular that
* bwrap's EROFS denial text classifies as `denied: true` through the
* wrap-carried dialect; the backend-only confinement proofs live with
* `@deepseek-ai/dsh-sandbox-local`.
* Keyless integration of the real provider and executor through public run/start paths. With
* no rung forced, a passing bwrap probe selects the ladder's first rung. The tests check world
* effects and stamped facts, including EROFS classification through the wrap-carried dialect;
* backend-only confinement is covered by `@deepseek-ai/dsh-sandbox-local`.
*
* Self-skips wherever the functional probe fails — no `bwrap` on PATH, or a
* host that denies unprivileged user namespaces.
*
* HOME-based dirs on purpose: bwrap's `/tmp` is an ephemeral mount, so only
* paths outside it prove the workspace-root boundary.
* Skips when bwrap or unprivileged user namespaces are unavailable. HOME-based paths are
* intentional because bwrap replaces `/tmp`, which cannot prove the workspace-root boundary.
*/
const probe = spawnSync('bwrap', [...bwrapProfileArgs({ mode: 'read-only', workspaceRoot: '/' }), '--', 'true'], { timeout: 5_000, stdio: 'ignore' })

View File

@@ -1,11 +1,8 @@
/**
* SandboxBashExecutor tests: the CONSUMER side of the sandbox seam. A fake
* `ctx.sandbox` provider (injected as a real cordis service) makes wrapping,
* policy hand-off, fail-closed propagation, classification, and fact
* stamping all deterministic without any real runner; the real-provider
* integration proof lives in `tests/landlock.e2e.ts`. Denials are produced
* with plain unix permissions (a 0555 directory), which exercises the same
* stderr signature the classifier keys on.
* Consumer-side `SandboxBashExecutor` tests. A fake Cordis sandbox service makes wrapping,
* policy hand-off, fail-closed propagation, classification, and fact stamping deterministic;
* real-provider integration lives in `tests/landlock.e2e.ts`. A mode-0555 directory supplies
* the Unix denial signature used by the classifier without requiring a real sandbox runner.
*/
import { chmodSync, mkdirSync, mkdtempSync } from 'node:fs'
@@ -297,10 +294,9 @@ describe('background sandbox facts', () => {
})
it('overlapping background tasks keep their OWN wrap facts (per-task, not latest-wrap)', async () => {
// The seam returns facts PER WRAP — a legal provider may vary them
// between calls. The slow task settles AFTER the quick one started, so a
// latest-wrap field would classify its denial against the quick task's
// dialect (missing it) and stamp the wrong enforcement.
// Facts belong to each wrap and may vary between calls. The slow task settles after the
// quick task starts; a shared latest-wrap field would classify and stamp it with the wrong
// task's dialect and enforcement.
const wraps: Array<Pick<ConfinedArgv, 'enforcement' | 'denialSignatures'>> = [
{ enforcement: 'partial', denialSignatures: ['permission denied'] },
{ enforcement: 'full', denialSignatures: ['read-only file system'] },

View File

@@ -10,16 +10,11 @@ import { SandboxPolicyService } from '@deepseek-ai/dsh-sandbox-policy'
import { SandboxBashExecutor } from '@deepseek-ai/dsh-bash-sandbox'
/**
* KEYLESS consumer-integration proof on macOS: the REAL `LocalSandboxProvider`
* (Linux rungs forced off, so `sandbox-exec`/Seatbelt confines) underneath
* the REAL `SandboxBashExecutor`, driven through the executor's public
* run/start paths. Verifies the WORLD (files exist or don't) plus the
* stamped result facts — in particular that Seatbelt's EPERM denial text
* classifies as `denied: true` through the wrap-carried dialect; the
* backend-only confinement proofs live with `@deepseek-ai/dsh-sandbox-local`.
*
* Self-skips wherever the functional probe fails — every non-macOS host, or
* a macOS whose `sandbox-exec` refuses the profile.
* Keyless macOS integration of the real provider and executor through public run/start paths.
* Linux rungs are forced off so Seatbelt is selected. The tests check world effects and stamped
* facts, including EPERM classification through the wrap-carried dialect; backend-only
* confinement is covered by `@deepseek-ai/dsh-sandbox-local`. Skips off macOS or when
* `sandbox-exec` rejects the profile.
*/
const probe = spawnSync('sandbox-exec', [...seatbeltProfileArgs({ mode: 'read-only', workspaceRoot: '/' }), '--', 'true'], { timeout: 5_000, stdio: 'ignore' })