Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/worktree-hooks-b-bash-seam' into worktree-hooks-c-interception

Browse Source 
# Conflicts:
#	docs/architecture.md
#	packages/core/agent-loop/README.md
This commit is contained in:
Tianyi Cui
2026-07-01 15:37:54 +08:00
parent 60418a5779 7097e4fb50
commit 5bdb40ff34
27 changed files with 158 additions and 98 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md
View File

@@ -6,7 +6,7 @@ Status: implemented (accepted 2026-06-30)
## Context
The hooks subsystem (stack PR-A…PR-F) runs external hook commands the way Claude Code and Codex do: a hook is a shell command that receives its event payload as **JSON on stdin** and reads context from a handful of **environment variables** (`CLAUDE_PROJECT_DIR`, `CLAUDE_PLUGIN_ROOT`, `PLUGIN_ROOT`, …). The harness already has a perfectly good command runner behind the `ctx.bash` capability seam ([dsh-bash](../../../../packages/bash/bash) → [dsh-bash-local](../../../../packages/bash/bash-local)), with process-group kills, output truncation/spill, and a credential scrub. Reusing it for hook execution means the bridges do not re-implement subprocess plumbing — but the seam had no way to write stdin or set extra env.
The hooks subsystem runs external hook commands the way Claude Code and Codex do: a hook is a shell command that receives its event payload as **JSON on stdin** and reads context from a handful of **environment variables** (`CLAUDE_PROJECT_DIR`, `CLAUDE_PLUGIN_ROOT`, `PLUGIN_ROOT`, …). The harness already has a perfectly good command runner behind the `ctx.bash` capability seam ([dsh-bash](../../../../packages/bash/bash) → [dsh-bash-local](../../../../packages/bash/bash-local)), with process-group kills, output truncation/spill, and a credential scrub. Reusing it for hook execution means a hook bridge does not re-implement subprocess plumbing — but the seam had no way to write stdin or set extra env.
The friction is that those two inputs are **dangerous in exactly the way the seam was built to prevent**. [dsh-bash-local](../../../../packages/bash/bash-local)'s `childEnv()` deliberately scrubs `*KEY*`/`*SECRET*`/`*TOKEN*` from the child environment so the harness's own `DEEPSEEK_API_KEY` cannot leak into model-driven command output (see [AGENTS.md](../../../../AGENTS.md) § Defensive patterns, "Never hand untrusted/model output the ambient environment or predictable paths"). An arbitrary-env / arbitrary-stdin capability is the opposite of that guarantee. So the question this RFC answers is not "can we add stdin/env" — it is "who is allowed to use them, and how is that boundary enforced".
@@ -30,4 +30,4 @@ An earlier sketch of this work also proposed making `SENSITIVE_ENV_PATTERN` conf
## Consequences
The hooks bridges (PR-F) build a `BashExecRequest` with the hook's JSON payload as `stdin` and its `CLAUDE_*`/`PLUGIN_ROOT` vars as `env`, and run it through the same `ctx.bash` everything else uses — no bespoke subprocess code, and the full process-group-kill / truncation / spill machinery for free. The model-facing attack surface is unchanged: the consumer's request-building is the single boundary, guarded by a test that fails if it regresses. The vocabulary addition is documented in [docs/core-data-structures/bash.md](../../../core-data-structures/bash.md) (the `type-equiv` request/spec blocks) and the three bash-package READMEs; the trusted-plugin rule mirrors the existing scrub/predictable-path discipline in [AGENTS.md](../../../../AGENTS.md) § Defensive patterns.
A hook bridge builds a `BashExecRequest` with the hook's JSON payload as `stdin` and its `CLAUDE_*`/`PLUGIN_ROOT` vars as `env`, and runs it through the same `ctx.bash` everything else uses — no bespoke subprocess code, and the full process-group-kill / truncation / spill machinery for free. The model-facing attack surface is unchanged: the consumer's request-building is the single boundary, guarded by a test that fails if it regresses. The vocabulary addition is documented in [docs/core-data-structures/bash.md](../../../core-data-structures/bash.md) (the `type-equiv` request/spec blocks) and the three bash-package READMEs; the trusted-plugin rule mirrors the existing scrub/predictable-path discipline in [AGENTS.md](../../../../AGENTS.md) § Defensive patterns.