docs: trim generated prose

This commit is contained in:
Tianyi Cui
2026-07-12 03:36:43 +08:00
parent 3dca90261c
commit 75838e10b5
323 changed files with 2857 additions and 11833 deletions

View File

@@ -56,12 +56,7 @@ async function setup() {
*/
const fakeAgentDisposers = new Map<Context, (() => Promise<void> | void)[]>()
function registerFakeAgent(ctx: Context, sessionId: string, inject: (...args: unknown[]) => void): Agent {
// The registry KEY (agent.id) is deliberately DIFFERENT from the session
// token (session.header.id) — a config agent has `agentId !== sessionId`. The
// owner token IS the session id, so the notice path must find the agent by
// `session.header.id`, NOT the registry key. Using distinct values here makes
// the test fail if a regression matched on the wrong field (a same-value fake
// would pass either way — the "hits the line but not the scenario" trap).
// Distinct ids ensure notices match the session owner token, not the registry key.
const agent = { id: `agent-${sessionId}`, inject, session: { header: { version: 0, id: sessionId, createdAt: 0 } } } as unknown as Agent
const dispose = ctx.agents.register(agent)
const list = fakeAgentDisposers.get(ctx) ?? []
@@ -416,9 +411,8 @@ describe('background tools', () => {
it('injects a completion notice into the owning agent (found via the registry by session token)', async () => {
const ctx = await setup()
const inject = vi.fn()
// The notice path looks the agent up in ctx.agents by its session token, so
// the agent must be REGISTERED (not merely passed to execute). Mount a
// registry and register a fake whose session.header.id IS the owner token.
// The notice path looks the agent up in ctx.agents by its session token, so the agent must
// be REGISTERED (not merely passed to execute).
const agent = registerFakeAgent(ctx, 'bg', inject)
const started = await ctx.tools.execute({
@@ -481,11 +475,9 @@ describe('background tools', () => {
})
it('drops the notice cleanly when the owning agent is gone from the registry by completion', async () => {
// A bash task (owned by the host-scoped bash-local fiber) can OUTLIVE its
// per-session agent — e.g. the ACP session disconnects and its AgentHandle
// disposes while the background task is still running. The owner token is
// still on the task, but no live agent carries it anymore, so the registry
// lookup finds nothing and the notice is dropped (no throw).
// A bash task (owned by the host-scoped bash-local fiber) can OUTLIVE its per-session agent
// — e.g. the ACP session disconnects and its AgentHandle disposes while the background task
// is still running.
const ctx = await setup()
const inject = vi.fn()
const agent = registerFakeAgent(ctx, 'bg', inject)
@@ -515,11 +507,9 @@ describe('background task ownership (cross-session isolation)', () => {
function callAs(ctx: Context, agent: import('@deepseek-ai/dsh-agent').Agent | undefined, name: string, args: unknown) {
return ctx.tools.execute({ callId: CallId(`own-${++callCounter}`), name, arguments: args, ...agent ? { agent } : {} })
}
// Ownership is by TOKEN (session.header.id), NOT agent object identity — so
// each agent needs a DISTINCT session id, else every fake yields the same
// token and the isolation tests pass for the wrong reason (all tasks owned by
// the same token). The impl reads `session.header.id`, so the fakes MUST carry
// it.
// Ownership is by TOKEN (session.header.id), not agent object identity — so each agent needs
// a DISTINCT session id, else every fake yields the same token and the isolation tests pass
// for the wrong reason (all tasks owned by the same token).
const fakeAgent = (sessionId: string) =>
({ inject: () => undefined, session: { header: { version: 0, id: sessionId, createdAt: 0 } } }) as unknown as import('@deepseek-ai/dsh-agent').Agent
@@ -599,11 +589,8 @@ describe('background task ownership (cross-session isolation)', () => {
})
it('ownership SURVIVES an independent tool-bash HMR reload (token lives on the executor)', async () => {
// The owner token lives on the TASK inside the executor (dsh-bash fiber), NOT
// in a tool-bash plugin-local map. So reloading ONLY tool-bash (executor +
// task survive) preserves ownership. This is the regression guard: a
// plugin-local map would make B accessible after reload, and this test would
// catch it.
// The owner token lives on the TASK inside the executor (dsh-bash fiber), not in a
// tool-bash plugin-local map.
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
@@ -822,11 +809,9 @@ describe('tool-owned UI presentation (presentCall / presentResult)', () => {
it('bash presentResult: a clean exit-0 whose output ENDS in marker-like text is NOT read as a failure', async () => {
const ctx = await setup()
const args = { command: 'printf "[exit code: 5]"', description: 'print' }
// A successful command can print text that looks like a marker. renderResult
// for a clean exit 0 appends NOTHING (and no trailing newline), so the body's
// own tail is `[exit code: 5]`. The parse requires a LEADING newline before
// the marker (renderResult always inserts one before a REAL marker), so this
// no-trailing-newline body is NOT mistaken for a failure → exitCode 0.
// A successful command can print text that looks like a marker. renderResult for a clean
// exit 0 appends NOTHING (and no trailing newline), so the body's own tail is `[exit code:
// 5]`.
const out = ctx.tools.get('bash')!.presentResult!(args, { content: [{ type: 'text', text: '[exit code: 5]' }], isError: false })
expect(out).toEqual({ card: 'terminal', output: '[exit code: 5]', exitCode: 0 })
// Same for a fake signal marker with no leading newline.
@@ -889,26 +874,17 @@ describe('tool-owned UI presentation (presentCall / presentResult)', () => {
it('presentCall validates softly: malformed args (missing required description) return undefined, never throw', async () => {
const ctx = await setup()
// defineTool wraps presentCall to soft-validate against the schema and fall
// back to undefined (a generic UI presentation) rather than throwing on the
// display path — it may run on replay of arbitrary logged args. The
// ToolDefinition.presentCall takes `unknown`, so a malformed shape needs no cast.
// defineTool wraps presentCall to soft-validate against the schema and fall back to
// undefined (a generic UI presentation) rather than throwing on the display path — it may
// run on replay of arbitrary logged args.
expect(ctx.tools.get('bash')?.presentCall?.({ command: 'ls' })).toBeUndefined()
})
})
describe('the model-facing bash tool builds its request from named args only (no {...args} forward)', () => {
/**
* Records every {@link BashExecRequest} the consumer hands to `resolve()`, so a
* test can assert what the model-facing tool DID and DID NOT forward. The `bash`
* tool does not expose `stdin`/`env` as parameters (bash syntax already gives a
* model that power), so it must build its request from named args only and
* never spread unknown tool-call keys into it. This guard's job is to catch a
* future refactor that blindly forwards `...args` — which would silently thread
* model input into the post-scrub `env` merge — NOT to defend a trust boundary
* (the credential scrub in dsh-bash-local is the security control; see the
* bash-stdin-env RFC). Foreground `run()` returns a canned result; `start()` is
* unused here.
* Records every {@link BashExecRequest} the consumer hands to `resolve()`, so a test can
* assert what the model-facing tool DID and DID NOT forward.
*/
class RecordingBashExecutor extends BashExecutor {
readonly requests: BashExecRequest[] = []
@@ -951,12 +927,7 @@ describe('the model-facing bash tool builds its request from named args only (no
it('does not forward env/stdin even when the model includes them as extra arguments', async () => {
const { ctx, bash } = await setupRecording()
// Extra args: the model includes `env` and `stdin` keys hoping they reach the
// executor. The bash tool's schema ignores unknown keys, and execute() builds
// the request from only command/workdir/timeoutMs/signal — so the recorded
// request carries NEITHER. (Not a security wall — the model could set an env
// var or feed stdin via shell syntax anyway; this just keeps the request
// shape honest so a future `...args` spread can't silently forward input.)
// Extra args: the model includes `env` and `stdin` keys hoping they reach the executor.
await ctx.tools.execute({
callId: CallId('no-forward-1'),
name: 'bash',
@@ -1447,11 +1418,8 @@ describe('per-session sandbox mode (the bash/sandbox-mode fold)', () => {
})
it('escalates relative to the session effective mode, not the executor default (narrower override)', async () => {
// The blocker scenario: a workspace-write default with a read-only
// override — the sensible escalation is workspace-write, which a
// default-relative ladder could not even express. The static target
// vocabulary advertises it and the execution check accepts it as
// strictly wider than the CALL's effective (overridden) mode.
// The blocker scenario: a workspace-write default with a read-only override — the sensible
// escalation is workspace-write, which a default-relative ladder could not even express.
const ctx = await setupModal('workspace-write', { approval: true })
ctx.on('approval/request', () => Promise.resolve<ApprovalOutcome>('allowed-once'))
const seen: (string | undefined)[] = []