mirror of https://github.com/deepseek-ai/deepseek-harness synced 2026-08-15 21:04:50 +00:00

Files

Tianyi Cui 13c6e847a2 feat(bash): add stdin + extra env to the executor seam as a trusted-plugin surface

The hooks subsystem runs external hook commands the Claude Code / Codex way:
JSON payload on stdin, context in CLAUDE_PROJECT_DIR / CLAUDE_PLUGIN_ROOT env.
Reusing the ctx.bash seam for that needs two new inputs — but stdin and arbitrary
env are exactly what dsh-bash-local's credential scrub exists to keep away from
model-driven commands. So this adds them as a TRUSTED-PLUGIN surface:

- BashExecRequest + BashExecSpec gain optional `stdin` and `env`. They are plain
  optionals on the resolved spec (not required-but-nullable like `owner`): a
  missing one means "none", the safe default, not a security footgun.
- dsh-bash-local threads them through resolve/run/start. `env` merges AFTER the
  credential scrub, so a trusted caller's explicit entry wins even on a
  credential-shaped name — the scrub guards the harness's OWN ambient creds from
  model-driven commands, not a trusted plugin. stdin is always a pipe, closed
  immediately (with bytes when supplied, empty otherwise — EOF as before); an
  EPIPE from a child that exits without reading is swallowed.
- The model-facing dsh-tool-bash NEVER forwards model input into stdin/env (its
  request is command/workdir/timeoutMs/signal/owner only). A regression guard
  drives the real tool with adversarial args and asserts the request carries
  neither field — proven to go red if the consumer ever forwards them.

Configurable scrub (in an earlier sketch) is dropped as speculative: the explicit
`env` field already gives a trusted caller full control, and no caller needs to
broaden the ambient scrub. Documented in a new architecture RFC, the bash.md
type-equiv blocks, and the three bash READMEs.

2026-06-30 13:52:25 +08:00

src

feat(bash): add stdin + extra env to the executor seam as a trusted-plugin surface

2026-06-30 13:52:25 +08:00

tests

feat(bash): add stdin + extra env to the executor seam as a trusted-plugin surface

2026-06-30 13:52:25 +08:00

package.json

Merge remote-tracking branch 'origin/master' into feat/adr0016-type-build-check

2026-06-22 00:35:51 +08:00

README.md

feat(bash): add stdin + extra env to the executor seam as a trusted-plugin surface

2026-06-30 13:52:25 +08:00

tsconfig.json

Merge remote-tracking branch 'origin/master' into feat/adr0016-type-build-check

2026-06-22 00:35:51 +08:00

README.md

@deepseek-ai/dsh-bash-local

Local-subprocess implementation of the @deepseek-ai/dsh-bash executor seam: LocalBashExecutor spawns bash -c <command> per call in its own process group, collects bounded output with full-stream spill files, and escalates kills SIGTERM→SIGKILL across the whole group.

Config

- id: bash
  name: '@deepseek-ai/dsh-bash-local'
  config:
    cwd: /path/to/workspace   # default: process.cwd()
    timeoutMs: 120000          # default foreground timeout
    maxTimeoutMs: 600000       # cap for per-call overrides
    maxOutputBytes: 64000      # per-stream in-memory cap; overflow spills to disk

Behavior (and where it came from)

Design surveyed against the bash tools of Claude Code, OpenCode, Codex, and pi; the notable choices:

Spawn per call, no shell state — every call is a fresh non-login bash -c (deterministic; no rc files). All four surveyed tools spawn per call. XXX(stateful-shell) in src/run.ts records the two proven stateful designs (Claude Code's cwd-only persistence; Codex's PTY exec sessions) for when real workflows demand them.
Process-group kills with escalation — children are spawned detached (own process group); kills send SIGTERM to the group, then SIGKILL after a 3s grace (OpenCode's escalation; pipelines and subshells die with the parent). ESRCH is tolerated; daemons that re-parent away from the group can still survive — same caveat as the surveyed tools.
Tail-keep truncation + spill files — output beyond maxOutputBytes keeps the in-memory TAIL (errors/results cluster at the end — pi/OpenCode rationale) while the FULL stream is appended to a temp file whose path is reported when available. If the final spill close reports a delayed writeback failure, the executor still returns the tail but withholds the path rather than advertising a possibly incomplete file.
Model-friendly env + credential scrub — process.env minus credential-shaped vars (*KEY*/*SECRET*/*TOKEN*), then NO_COLOR=1 TERM=dumb PAGER=cat GIT_PAGER=cat (Codex's hardcoded set) so pagers and ANSI color don't garble results. A spec's trusted-plugin env is merged LAST (after the scrub), so an in-process plugin's explicit entry wins even on a credential-shaped name — the scrub guards the harness's ambient credentials from model-driven commands, not a trusted caller. The spec's stdin (also trusted-plugin) is written to the child and closed; with none supplied, stdin is an immediately-closed empty pipe (EOF, as before). See the trusted-plugin RFC.
Background tasks — start() returns immediately, no timeout applies (Claude Code detaches timeouts when backgrounding), readOutput() is incremental with whole-stream byte offsets, and disposal kills everything. The spec's opaque owner token is stored on the tracked task and returned by ownerOf(id) — the executor never interprets it (the consumer's access policy does), and because it lives with the task here it survives a tool-bash HMR reload.

Sandboxing

TODO(permissions/sandbox): execution policy does NOT belong in this package. Wrap the tools/execute waterfall (veto/ask) or implement a sandboxing BashExecutor — see docs/architecture.md § plugin checklist. Reference points: Claude Code wraps commands in sandbox-exec/bubblewrap; Codex applies seatbelt/landlock plus an execpolicy prefix-rule engine.