The ShellDialect marker on BashExecutor and the load-time rejection in
tool-bash/tool-pwsh force every test and example fake executor to declare
a dialect for a guard with no in-repo or plausible deployment to catch
(shipped compositions always pair the tool with its matching executor),
and they break the example composition suites that stub ctx.bash without
a dialect (agent-spine-demo/cli-demo/acp-demo lost the bash tool).
Keep the non-dialect doc fixes that landed with the attempt: the tool-bash
README bashEnv contract trim with the stale example import removed, the
acp-snapshot suite.ts 'usable pwsh' JSDoc, and the pwsh.cordis.yml comment
indent. The parity note records the attempt and revert under Alternatives.
The seam gains ShellDialect ('bash' | 'powershell' - concrete shells, not
families: zsh or fish would be their own values, never 'bash'); bash-local
declares bash (bash-sandbox inherits), pwsh-local declares powershell, and
both tools throw at load when the mounted executor speaks another dialect -
previously tool-pwsh over bash-local handed PowerShell text to bash -c and
the deployment error surfaced as ordinary nonzero exits. Pinned by mismatch
tests on both tools; the parity note records the contract (both languages).
Also from the review round: the tool-bash README's managed-environment
section becomes a summary linking the owning dsh-bash-env contract (the
duplicated prose carried a stale owner in its example import), the
pwshOnly JSDoc drops the stale 'on PATH' phrasing, and the task-tools
contract comment in the two pwsh compositions is indented into its block.
Review feedback (tianyicui, PR #657 inline): the missing-service message
should mention dsh-tasks, which defines ctx.tasks, rather than promoting a
specific backend. The seam's own surfaces (README, the direct-mount fence)
keep pointing at implementations, so the pointer chain still lands on
dsh-tasks-local without the producer strings going stale when another
backend becomes the recommended default. Agent Note updated accordingly
(en+zh, re-recorded).
The tasks/ family now matches the capability-seam shape: @deepseek-ai/dsh-tasks
keeps the abstract TaskService (ctx.tasks contract, vocabulary types, snapshot
invariant companion) and the new @deepseek-ai/dsh-tasks-local carries the
process-local registry (LocalTaskService: in-memory store, settlement,
owner-cleanup effects, teardown, TASK_WAIT_TIMEOUT). Compositions and test
harnesses now load dsh-tasks-local; producers, TaskKindMap merges, and
dsh-tool-tasks keep importing the seam only.
Producer misconfiguration diagnostics name dsh-tasks-local because loading the
implementation is the fix. The registry behavior suite moves to tasks-local;
the seam keeps a stub-subclass registration test and the probe-based invariant
suite.
Delete @deepseek-ai/dsh-home and make dsh-paths the sole owner of the
single-root harness home ($DSH_HOME || ~/.dsh). Migrate tool-bash,
skill-local, and agent-spine-demo off dsh-home, and fold telemetry's
divergent globalConfigDir onto the shared resolver, dropping its second
XDG/APPDATA policy and the deepseek-harness namespace so the anonymous
id lives under the harness home. Add dshHomeDisplay() for symbolic
user-facing paths, replacing workspace-context's bespoke check.
The background-task change repeated its lifecycle design across implemented RFCs, package READMEs, JSDoc, test commentary, and model-visible schemas. That repetition obscured the contracts that maintainers must preserve and added avoidable prompt tokens.
Rewrite the implemented RFCs around the current design, keep authorization, exact-owner cleanup, wait/abort ordering, producer quiescence, and teardown-failure guarantees at their owning surfaces, and remove peer surveys, review history, control-flow narration, and emphatic restatement.
Shorten the task and subagent schema wording, synchronize the bilingual tool cookbook, and regenerate the config, service, RFC, tool, and replay snapshot derivatives. Runtime behavior is unchanged; test edits update prose-only assertions and descriptions.
The managed DSH_* runtime path was correct, but its public extension and documentation contracts were incomplete. A contributor following the README could access ctx.bashEnv without declaring an injection, the new environment types had no drift-checked catalog entries, and the capability graph omitted three packages that now query sessionPersistence.
Declare the README injection, catalog DshEnvironmentKey and DshEnvironment, and add tool-bash plus both hook bridges to the generated persistence consumer graph. Keep BashEnvRegistry.list() contributor-only for now because no production caller treats it as exhaustive, but record the built-in enumeration gap before diagnostics, prompt, or UI code depends on it.
Validated on the exact resulting tree with typecheck, lint, coverage, snapshot, documentation, module-graph, build, hygiene, demo-smoke, and built-artifact checks.
A background spawn failure currently resembles a signal-less kill, while a sandbox-runner failure resembles a completed wrapper exit. The generic task adapter cannot mark both as failed without a distinct infrastructure-failure fact on BashProcess. Mapping the existing states differently would also risk treating ordinary nonzero command exits as infrastructure failures.
Keep the current truthful model-visible diagnostics and record a scoped TODO at processOutcome. The eventual fix must widen the BashProcess seam first, then map spawn and runner failures to TaskOutcome failed while preserving completed for real command exits.
Extend SandboxMode enforcement from bash to the filesystem tools, the sandbox
RFC's deferred cross-family phase.
- dsh-sandbox-policy (new, ctx.sandboxPolicy): the single home for the
deployment default mode + workspaceRoot and the per-session override event,
renamed bash/sandbox-mode -> sandbox/mode and moved here with its fold/setter.
Decouples the bash seam from dsh-session.
- dsh-fs-sandbox (new): SandboxedFileSystem extends LocalFileSystem and fences
write/edit by the per-call mode (read-only denies, workspace-write contains to
the workspace + temp roots via the shared writableRoots, danger passes
through); reads pass through. Structured FS_SANDBOX_DENIED; in-lock parent
re-canonicalization. A policy fence in trusted code, not a kernel boundary.
- dsh-sandbox: the shared escalation kit (writableRoots, the strictly-wider
ladder, denial/hint markers, approveEscalation) both tool families use;
approveEscalation takes a structural approver so dsh-sandbox gains no
approval/agent dependency, and both tools stay duplication-free.
- tool-fs: write/edit advertise sandbox_permissions/justification under a
confining ctx.fs, map FS_SANDBOX_DENIED to the shared [sandbox: ...] marker,
and resolve the same one-approved-wider retry.
- examples/acp-agent: composes sandbox-policy + fs-sandbox, drops the gating
that disabled the fs stack under confined modes.
RFC docs/rfc/implemented/feature/2026-07-14-cross-family-fs-sandbox.md; the old
sandbox RFC's In-process/deferred/FAQ sections updated to shipped fact.
Huanqi Cao
Tianyi Cui
NI0317
Turtle
kingwl
Yichen Jiang