mirror of
https://github.com/stablyai/orca.git
synced 2026-10-13 00:02:54 +00:00
Audit sweep over `src/relay`, `src/preload` and `src/shared` (1,087 test files reviewed). 101 case declarations removed across 40 files, 6 test files deleted outright, 1,143 lines gone. Executed-case count falls further, since several removals were `it.each` tables. Dominant patterns, by frequency: - Self-comparisons that cannot fail: `expect(f(x)).toBe(f(x))`, `JSON.parse(JSON.stringify(literal))` deep-equalling the literal for a type with no codec, and `normalizeKeyToken(t) === normalizeKeyToken(t)` presented as proof of memoization. - Object literals asserting their own fields back, where the guarantee comes from the type annotation and the runtime assertion cannot fail. - Copied inventories: constants compared to their own initializers, and a function returning a copy of an exported constant checked against that constant's literal contents. - Duplicate invocations of a contract owned at a stronger boundary, including provider-local replays of a shared helper. - Table rows varying a field production never reads, so every row runs one path. - Names promising more than the input exercises: a "Windows launch" case in a module with no platform input, and a case whose named branch is never entered. Two production symbols go with them, each a test-only export whose sole caller was a deleted case: - `getGitHubProjectRefInputByteLength` — a one-line forward to `getClipboardTextByteLength`. The real bound (`GITHUB_PROJECT_REF_INPUT_MAX_BYTES`) and its guard stay. - `GRAB_STYLE_PROPERTIES` — an intended shared source of truth that nothing ever consulted; the property set is hand-enumerated at three independent sites. One case was deliberately restored and strengthened rather than dropped. The relay integration suite is the only place the real `SshChannelMultiplexer` is wired to `RelayDispatcher`, so it reaches transport behavior the handler suites cannot (they use `createMockDispatcher`). Its `fs.writeFile` roundtrip is the one case producing a void result, and `JSON.stringify` drops an absent `result` member — a shape no other surviving case exercises. Restored with an assertion pinning what the client actually observes: `null`, not `undefined`. That assertion failed on first run, so the fact was previously unasserted anywhere. One deletion was reverted mid-audit. A case asserting that optional fields stay invisible to "old attach and ready decoders" builds those decoders from `z.object` schemas declared in the test file, so it demonstrates zod's unknown-key stripping rather than anything shipped. It is nonetheless the only forward-compatibility coverage these envelopes have, and `reliability-gates.jsonc:6232` names it as evidence verbatim, so it stays. Note that `check-reliability-gates.mjs` passed both with and without it: the script resolves manifest paths and commands, and does not check that a named assertion still corresponds to a live case. Kept deliberately: everything a reliability gate cites as evidence; the three `registers all expected handlers` RPC manifests (a dropped registration is a silent wire break no type checker catches, and one carries the STA-4571 `pty.ackData` ratchet); the `child-process` direct-import ratchet; and prototype-spy cases paired with a `.repeat(10_000)` input, which assert a real memory bound rather than merely forbidding a technique. Verified: `pnpm test src/shared src/relay src/preload` (1073 files, 11996 passed, 1 pre-existing `it.fails`, 131 skipped), `pnpm tc` after clearing `.tsbuildinfo`, `check-reliability-gates.mjs` (140 gates), `check:code-quality:changed` (0 new findings).
123 lines
5.0 KiB
TypeScript
123 lines
5.0 KiB
TypeScript
import { describe, expect, it } from 'vitest'
|
|
import {
|
|
AGENT_HOOK_INSTALL_PLUGINS_METHOD,
|
|
AGENT_HOOK_NOTIFICATION_METHOD,
|
|
AGENT_HOOK_REQUEST_REPLAY_METHOD,
|
|
AGENT_HOOK_SHED_FIELDS_KEY,
|
|
ORCA_FEATURE_REMOTE_AGENT_HOOKS_ENV,
|
|
createShedSubagentsField,
|
|
isAgentHookSource,
|
|
isRemoteAgentHooksEnabled,
|
|
restoreShedStatusFields
|
|
} from './agent-hook-relay'
|
|
import type { ParsedAgentStatusPayload } from './agent-status-types'
|
|
|
|
describe('agent-hook-relay wire shape', () => {
|
|
it('exposes stable JSON-RPC method names', () => {
|
|
expect(AGENT_HOOK_NOTIFICATION_METHOD).toBe('agent.hook')
|
|
expect(AGENT_HOOK_REQUEST_REPLAY_METHOD).toBe('agent_hook.requestReplay')
|
|
expect(AGENT_HOOK_INSTALL_PLUGINS_METHOD).toBe('agent_hook.installPlugins')
|
|
})
|
|
|
|
it('validates hook sources crossing persisted and relay trust boundaries', () => {
|
|
expect(isAgentHookSource('claude')).toBe(true)
|
|
expect(isAgentHookSource('kimi')).toBe(true)
|
|
expect(isAgentHookSource('prime-agent')).toBe(true)
|
|
expect(isAgentHookSource('claude\0codex')).toBe(false)
|
|
expect(isAgentHookSource('unknown')).toBe(false)
|
|
expect(isAgentHookSource({ source: 'claude' })).toBe(false)
|
|
})
|
|
})
|
|
|
|
describe('isRemoteAgentHooksEnabled', () => {
|
|
it('is on when the env var is absent', () => {
|
|
expect(isRemoteAgentHooksEnabled({})).toBe(true)
|
|
})
|
|
|
|
it('is off for empty / "0"', () => {
|
|
expect(isRemoteAgentHooksEnabled({ [ORCA_FEATURE_REMOTE_AGENT_HOOKS_ENV]: '' })).toBe(false)
|
|
expect(isRemoteAgentHooksEnabled({ [ORCA_FEATURE_REMOTE_AGENT_HOOKS_ENV]: '0' })).toBe(false)
|
|
expect(isRemoteAgentHooksEnabled({ [ORCA_FEATURE_REMOTE_AGENT_HOOKS_ENV]: ' ' })).toBe(false)
|
|
})
|
|
|
|
it('is on for any other non-empty value', () => {
|
|
expect(isRemoteAgentHooksEnabled({ [ORCA_FEATURE_REMOTE_AGENT_HOOKS_ENV]: '1' })).toBe(true)
|
|
expect(isRemoteAgentHooksEnabled({ [ORCA_FEATURE_REMOTE_AGENT_HOOKS_ENV]: 'on' })).toBe(true)
|
|
expect(isRemoteAgentHooksEnabled({ [ORCA_FEATURE_REMOTE_AGENT_HOOKS_ENV]: 'true' })).toBe(true)
|
|
})
|
|
})
|
|
|
|
describe('restoreShedStatusFields', () => {
|
|
const roster = [{ id: 'child-1', agentType: 'reviewer', state: 'working' as const, startedAt: 1 }]
|
|
const cached: ParsedAgentStatusPayload = {
|
|
state: 'working',
|
|
prompt: 'p',
|
|
agentType: 'claude',
|
|
subagents: roster,
|
|
lastAssistantMessage: 'cached message',
|
|
interactivePrompt: '{"questions":["old"]}'
|
|
}
|
|
const shed: ParsedAgentStatusPayload = { state: 'done', prompt: 'p', agentType: 'claude' }
|
|
|
|
it('restores a matching shed roster, so a done pane is not falsely hibernation-eligible', () => {
|
|
const restored = restoreShedStatusFields(shed, [createShedSubagentsField(roster)], cached)
|
|
expect(restored.subagents).toEqual(roster)
|
|
expect(restored.state).toBe('done')
|
|
// Only the named field comes back.
|
|
expect(restored.lastAssistantMessage).toBeUndefined()
|
|
})
|
|
|
|
it('does not restore a shed roster across a prompt identity change', () => {
|
|
expect(AGENT_HOOK_SHED_FIELDS_KEY).toBe('shedFields')
|
|
const nextTurn = { ...shed, prompt: 'next prompt' }
|
|
const restored = restoreShedStatusFields(
|
|
nextTurn,
|
|
['lastAssistantMessage', createShedSubagentsField(roster)],
|
|
cached
|
|
)
|
|
expect(restored.lastAssistantMessage).toBeUndefined()
|
|
expect(restored.subagents).toBeUndefined()
|
|
expect(restored).toBe(nextTurn)
|
|
})
|
|
|
|
it('does not restore the cached roster when the shed roster digest changed', () => {
|
|
const changedRoster = [
|
|
{ id: 'child-2', agentType: 'reviewer', state: 'working' as const, startedAt: 2 }
|
|
]
|
|
const restored = restoreShedStatusFields(
|
|
shed,
|
|
[createShedSubagentsField(changedRoster)],
|
|
cached
|
|
)
|
|
expect(restored.subagents).toBeUndefined()
|
|
expect(restored).toBe(shed)
|
|
})
|
|
|
|
it('never restores interactivePrompt — a stale answerable card is worse than none', () => {
|
|
const restored = restoreShedStatusFields(shed, ['interactivePrompt'], cached)
|
|
expect(restored.interactivePrompt).toBeUndefined()
|
|
expect(restored).toBe(shed)
|
|
})
|
|
|
|
it('leaves an intentional lastAssistantMessage clear intact when the relay shed nothing', () => {
|
|
expect(restoreShedStatusFields(shed, undefined, cached)).toBe(shed)
|
|
expect(restoreShedStatusFields(shed, [], cached)).toBe(shed)
|
|
expect(restoreShedStatusFields(shed, [], cached).lastAssistantMessage).toBeUndefined()
|
|
// A hostile/garbled marker must not throw or restore.
|
|
expect(restoreShedStatusFields(shed, 'subagents', cached)).toBe(shed)
|
|
expect(restoreShedStatusFields(shed, ['subagents'], cached)).toBe(shed)
|
|
expect(restoreShedStatusFields(shed, [{ toString: () => 'subagents' }], cached)).toBe(shed)
|
|
})
|
|
|
|
it('does not overwrite a value the envelope still carries', () => {
|
|
const fresh: ParsedAgentStatusPayload = { ...shed, lastAssistantMessage: 'fresh' }
|
|
expect(
|
|
restoreShedStatusFields(fresh, ['lastAssistantMessage'], cached).lastAssistantMessage
|
|
).toBe('fresh')
|
|
})
|
|
|
|
it('is a no-op with no cached payload for the pane', () => {
|
|
expect(restoreShedStatusFields(shed, ['subagents'], undefined)).toBe(shed)
|
|
})
|
|
})
|