From 6ca8c3b99a672d12b84ebff6443f98d26451f27e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 21 Jun 2026 03:00:07 +0800 Subject: [PATCH] fix review findings: stale get/list in proposed RFCs + doneFor double-await Second Codex pass caught two proposed RFCs that describe the bash seam as it WAS (with get/list) and would read stale once this prune lands, plus a latent test-helper edge: - docs/rfc/proposed/architecture/2026-06-20-branded-ids.md and 2026-06-20-generic-long-running-tool-runtime.md: drop get/list from the BashExecutor seam description (surviving: resolve/run/start/ownerOf/ readOutput/kill/onTaskDone). branded-ids will be further updated when it is implemented; this keeps it accurate in the meantime. - trackCompletions now records every completion to `done` unconditionally (and also wakes a parked waiter), so a second doneFor(id) after completion resolves instead of hanging. --- docs/rfc/proposed/architecture/2026-06-20-branded-ids.md | 4 ++-- .../2026-06-20-generic-long-running-tool-runtime.md | 2 +- packages/bash/tool-bash/tests/tools.spec.ts | 5 +++-- 3 files changed, 6 insertions(+), 5 deletions(-) diff --git a/docs/rfc/proposed/architecture/2026-06-20-branded-ids.md b/docs/rfc/proposed/architecture/2026-06-20-branded-ids.md index 93a4bf6cda..d69eb8f8c6 100644 --- a/docs/rfc/proposed/architecture/2026-06-20-branded-ids.md +++ b/docs/rfc/proposed/architecture/2026-06-20-branded-ids.md @@ -6,7 +6,7 @@ Status: proposed The harness already brands three identifiers — `CallId` (`packages/llm/llm/src/brand.ts`), `SessionId` (`packages/core/session/src/types.ts`), and `AgentId` (`packages/core/agent/src/types.ts`) — using the `Branded = string & { readonly [BRAND]: B }` machinery and a zero-cost cast factory per type. `brand.ts` also states the governing policy: *"Branding is for IDs that cross package boundaries and could plausibly be confused; not every string needs a brand."* That policy is right; the problem is that it is only half-applied. Two gaps let a structurally-identical-but-semantically-wrong string slip through the type checker today. -**Gap 1 — unbranded cross-boundary IDs in the bash seam.** The background-task id is a plain `string`: `BashTask.id: string` (`packages/bash/bash/src/types.ts`), carried as `string` through the whole executor seam (`BashExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)` in `packages/bash/bash/src/index.ts`) and validated/passed as `string` by the model-facing tools (`validateTaskId`, `assertTaskAccess`, the `task_id` schema arg in `packages/bash/tool-bash/src/index.ts`). It is generated by a per-executor counter — `` `bash-${this.nextTaskId++}` `` in `packages/bash/bash-local/src/index.ts` — which gives it **exactly the same `name-N` shape as `SessionId`'s default** (`` `session-${++counter}` `` in `packages/core/session/src/index.ts`). A bash task id and a session id are trivially swappable at a call site and the compiler says nothing. This is the headline case the user asked about, and it is a model-facing id (the model passes `task_id` back to `bash_output`/`bash_kill`), so a confusion here is reachable from untrusted input. +**Gap 1 — unbranded cross-boundary IDs in the bash seam.** The background-task id is a plain `string`: `BashTask.id: string` (`packages/bash/bash/src/types.ts`), carried as `string` through the whole executor seam (`BashExecutor.ownerOf`/`readOutput`/`kill(id: string)` in `packages/bash/bash/src/index.ts`) and validated/passed as `string` by the model-facing tools (`validateTaskId`, `assertTaskAccess`, the `task_id` schema arg in `packages/bash/tool-bash/src/index.ts`). It is generated by a per-executor counter — `` `bash-${this.nextTaskId++}` `` in `packages/bash/bash-local/src/index.ts` — which gives it **exactly the same `name-N` shape as `SessionId`'s default** (`` `session-${++counter}` `` in `packages/core/session/src/index.ts`). A bash task id and a session id are trivially swappable at a call site and the compiler says nothing. This is the headline case the user asked about, and it is a model-facing id (the model passes `task_id` back to `bash_output`/`bash_kill`), so a confusion here is reachable from untrusted input. The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias that the [unify-the-agent-id-and-the-session-id](../simplification/2026-06-20-unify-agent-and-session-id.md) proposal calls the "bash owner-token alias hole". @@ -16,7 +16,7 @@ The bash **owner token** is the related sub-case: `BashExecRequest.owner?: strin A type-only change. Brands are zero-cost casts; nothing about runtime behavior, serialization, comparison, or the wire format changes. The work is in three parts, all honoring the existing "not every string" policy. -- **Brand the bash task id.** Add `BashTaskId = Branded<'BashTaskId'>` plus its same-named factory in `packages/bash/bash/src/types.ts` (the package that *owns* the id), importing `Branded` from `@deepseek-ai/dsh-llm` exactly as `SessionId`/`AgentId` already do. Thread it through `BashTask.id`, the `BashExecutor` seam methods (`get`/`ownerOf`/`readOutput`/`kill`), the generation site in `dsh-bash-local` (brand the counter output once, at creation), and the `dsh-tool-bash` validate/access surface (`validateTaskId` returns a `BashTaskId`; `task_id` is branded at the tool boundary where the model's string arrives). +- **Brand the bash task id.** Add `BashTaskId = Branded<'BashTaskId'>` plus its same-named factory in `packages/bash/bash/src/types.ts` (the package that *owns* the id), importing `Branded` from `@deepseek-ai/dsh-llm` exactly as `SessionId`/`AgentId` already do. Thread it through `BashTask.id`, the `BashExecutor` seam methods (`ownerOf`/`readOutput`/`kill`), the generation site in `dsh-bash-local` (brand the counter output once, at creation), and the `dsh-tool-bash` validate/access surface (`validateTaskId` returns a `BashTaskId`; `task_id` is branded at the tool boundary where the model's string arrives). - **Mint a distinct `OwnerToken` brand.** Add `OwnerToken = Branded<'OwnerToken'>` in `packages/bash/bash/src/types.ts`; type `BashExecRequest.owner` / `BashExecSpec.owner` / `BashExecutor.ownerOf` as `OwnerToken | undefined`. The `dsh-tool-bash` consumer casts the agent's `session.header.id` (a `SessionId`) into an `OwnerToken` at the boundary — the one place the two vocabularies meet. The bash seam never imports `dsh-session`. (Rationale in the next section.) diff --git a/docs/rfc/proposed/architecture/2026-06-20-generic-long-running-tool-runtime.md b/docs/rfc/proposed/architecture/2026-06-20-generic-long-running-tool-runtime.md index 4f034e3020..d17224c46f 100644 --- a/docs/rfc/proposed/architecture/2026-06-20-generic-long-running-tool-runtime.md +++ b/docs/rfc/proposed/architecture/2026-06-20-generic-long-running-tool-runtime.md @@ -4,7 +4,7 @@ Status: proposed ## Problem -The bash capability seam supports both foreground commands and long-running background tasks. Background support is large: the abstract executor exposes `start`, `get`, `ownerOf`, `list`, `readOutput`, `kill`, and `onTaskDone`; the local executor tracks tasks, incremental reads, owner tokens, process cleanup, and completion listeners; the model sees three tools (`bash`, `bash_output`, `bash_kill`); the tool plugin injects completion notices back into the owning agent's session. The local executor fences task access behind owner tokens because predictable global task ids are a cross-session read/kill hazard. +The bash capability seam supports both foreground commands and long-running background tasks. Background support is large: the abstract executor exposes `start`, `ownerOf`, `readOutput`, `kill`, and `onTaskDone`; the local executor tracks tasks, incremental reads, owner tokens, process cleanup, and completion listeners; the model sees three tools (`bash`, `bash_output`, `bash_kill`); the tool plugin injects completion notices back into the owning agent's session. The local executor fences task access behind owner tokens because predictable global task ids are a cross-session read/kill hazard. The [tool cookbook](../../../cookbook/adding-a-tool.md) already points at the real design smell: background bash is really generic long-running-tool infrastructure living inside one tool. If future tools need background execution, polling, kill, ownership, and completion notices, those semantics should not be hidden in `dsh-bash`. diff --git a/packages/bash/tool-bash/tests/tools.spec.ts b/packages/bash/tool-bash/tests/tools.spec.ts index b7429ff9bb..e0cc1165e3 100644 --- a/packages/bash/tool-bash/tests/tools.spec.ts +++ b/packages/bash/tool-bash/tests/tools.spec.ts @@ -85,12 +85,13 @@ function trackCompletions(ctx: Context): void { const state = { done: new Map(), waiters: new Map void>() } completions.set(ctx, state) ctx.bash.onTaskDone((task) => { + // Always record the completion so a later doneFor(id) still resolves; also + // wake any waiter already parked on this id. + state.done.set(task.id, task) const waiter = state.waiters.get(task.id) if (waiter) { state.waiters.delete(task.id) waiter(task) - } else { - state.done.set(task.id, task) } }) }