feat(pwsh): mirror the bash sandbox surface — denial rendering, escalation, and the ConstrainedLanguage contract

tool-pwsh now renders sandbox denial facts (denial marker + same-turn escalation hint, runner-failed notice on background reads) and advertises the sandbox_permissions/justification escalation pair resolved through ctx.approval before execution — the shared fail-closed sequence from dsh-sandbox, with the tool name 'pwsh'. The description teaches the ConstrainedLanguage contract under the Windows sandbox (both confined modes run pwsh in CLM: Add-Type, non-core .NET statics, COM, and reflection fail; the mode cannot be lifted — probe-verified, pinned by LANGMODE assertions in the runner suite and description assertions in the tool suite). The stale pwsh-sandbox JSDoc ('the tool owns approval') and the parity notes' superseded 'minus sandbox' claims are corrected.
This commit is contained in:
Huanqi Cao
2026-08-08 20:11:21 +08:00
parent 2dd9af6f4b
commit 83f835e4cb
18 changed files with 471 additions and 82 deletions

View File

@@ -1138,7 +1138,7 @@ export type Config = LocalConfig
Depends on: [`LocalConfig`](#deepseek-aidsh-pwsh-local)
Source: [`packages/bash/pwsh-sandbox/src/index.ts:39`](../packages/bash/pwsh-sandbox/src/index.ts)
Source: [`packages/bash/pwsh-sandbox/src/index.ts:40`](../packages/bash/pwsh-sandbox/src/index.ts)
## `@deepseek-ai/dsh-repeat-tool-guard`
@@ -2057,7 +2057,7 @@ export interface Config {
}
```
Source: [`packages/bash/tool-pwsh/src/index.ts:47`](../packages/bash/tool-pwsh/src/index.ts)
Source: [`packages/bash/tool-pwsh/src/index.ts:52`](../packages/bash/tool-pwsh/src/index.ts)
## `@deepseek-ai/dsh-tool-ralph`

View File

@@ -988,6 +988,7 @@ flowchart TD
pkg_tool_pwsh --> pkg_system_prompt
pkg_tool_pwsh --> pkg_tasks
pkg_tool_pwsh --> pkg_tools
pkg_tool_pwsh --> pkg_user_approval
pkg_subagent_acp --> pkg_agent
pkg_subagent_acp --> pkg_invariants
pkg_subagent_acp --> pkg_llm
@@ -1342,7 +1343,7 @@ flowchart TD
| [`session-telemetry-otel`](../packages/telemetry/session-telemetry-otel) | `telemetry` | [`brand`](../packages/util/brand), [`command-feedback`](../packages/feedback/command-feedback), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`paths`](../packages/util/paths), [`session`](../packages/core/session), [`session-telemetry`](../packages/telemetry/session-telemetry) |
| [`tool-workflow`](../packages/workflow/tool-workflow) | `workflow` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) |
| [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`bash-env`](../packages/bash/bash-env), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) |
| [`tool-pwsh`](../packages/bash/tool-pwsh) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`bash-env`](../packages/bash/bash-env), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) |
| [`tool-pwsh`](../packages/bash/tool-pwsh) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`bash-env`](../packages/bash/bash-env), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) |
| [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subprocess`](../packages/subprocess/subprocess), [`timeout`](../packages/util/timeout) |
| [`subagent-claude-code`](../packages/subagent/subagent-claude-code) | `subagent` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subprocess`](../packages/subprocess/subprocess), [`timeout`](../packages/util/timeout) |
| [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | `subagent` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) |

View File

@@ -212,7 +212,7 @@ The bash tool is the model-facing consumer of the bash executor seam. A `run_in_
### `pwsh`
Execute a PowerShell command (`pwsh -Command`) and return its stdout/stderr. Each call runs in a fresh pwsh process: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Paths use native Windows form (`C:\...`); read environment variables with `$env:NAME`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$env:DSH_*` variables; inspect them when needed. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. On Windows a force-killed command settles as `[exit code: 1]` without a signal marker — treat it as an interruption, not a command failure. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`.
Execute a PowerShell command (`pwsh -Command`) and return its stdout/stderr. Each call runs in a fresh pwsh process: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Paths use native Windows form (`C:\...`); read environment variables with `$env:NAME`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$env:DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. On Windows a force-killed command settles as `[exit code: 1]` without a signal marker — treat it as an interruption, not a command failure. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`.
```json
{