docs(sandbox): satisfy the doc-sync gates for the Windows ACL packages

JSDoc every sandbox-windows-acl export (the 138 verify-export-jsdoc violations); fix the sandbox-windows-acl README code block (undeclared workspaceRoot), bring its stale claims current (the provider wiring and kill-on-close are live), add the canonical Model Experience sections to both new packages, audited the backend's indirect Model Experience sentence, and regenerate docs/config-catalog.md.
This commit is contained in:
Huanqi Cao
2026-08-08 02:26:26 +08:00
parent bec3cba084
commit dcd5a50374
14 changed files with 292 additions and 37 deletions
+12 -2
View File
@@ -15,9 +15,19 @@ The executor inherits [`@deepseek-ai/dsh-pwsh-local`](../pwsh-local/)'s process
### Confinement works, denial surfaces as command failure
The model sees the confined command's own stderr (e.g. `Access to the path '...' is denied.` under the Windows ACL runner); the tool layer converts classified denials into the standard permission-denied surface exactly as it does for the bash tool.
#### What the model sees
## Known Limitations
The confined command's own stderr (e.g. `Access to the path '...' is denied.` under the Windows ACL runner); the tool layer converts classified denials into the standard permission-denied surface exactly as it does for the bash tool.
#### Token effect
No model-visible text beyond the command's stderr and the tool layer's standard denial surface.
#### KV Cache effect
None directly; the denial surface belongs to the tool layer.
## Known Limitations and Deferred Work
- **Reads are unrestricted** on Windows (the ACL runner restricts writes only); the read boundary is documented in `@deepseek-ai/dsh-sandbox-windows-acl`.
- **The Windows workspace-write temp area is the real temp directory** (`GetTempPathW`). This is a deliberate backend-defined choice, the same decision Landlock makes (`readWrite: ['/tmp', ...]`): the seam's "backend-defined temp area" permits it, and the escape probe in `tests/acl.e2e.ts` lives outside the temp tree for exactly that reason. A per-run private temp (bwrap's `--tmpfs /tmp` semantics) would additionally need an environment-block rewrite in the runner; it is an optional future hardening, not a correctness gap.