Monitoring coverage was 3 of 89 active entities. Three bugs, each hidden by discarded errors in checkdefaults: - writeCheck generated a fresh uuid, inserted the check entity ON CONFLICT (slug) DO NOTHING, then wrote a check_defs row referencing it. On any re-seed the slug already existed, the entity insert no-oped, and the FK violated — aborting the ingest transaction and surfacing as an unrelated failure several entities later. Re-seeding has been broken since; prod's coverage was frozen at its first successful seed. This is what TestSeedIngestIdempotentAndNoDuplicateEdges had been reporting. - shortSlug truncated to the last 8 chars, so all 21 ingress routes collapsed to ".network" and overwrote each other; service:jellyfin collided with lxc:jellyfin. - The ssh-script checker never read the `args` config checkdefaults wrote, so process_check.sh always ran without its unit name and returned "unknown". Coverage is now 75/89. Monitoring is declared per entity type in seeds/ontology.yaml and resolved through the is-a hierarchy, so a type can say it warrants nothing (site, lan, mesh, cluster) and never be reported as a gap. coverageSweep raises an `unmonitored` signal only where a type declares monitoring it lacks — 8 real gaps, no false positives. Also: - entity_types.attribute_schema was never ingested: the seed loader read "attribute_schema" but the YAML says "attributes", so all 60 types stored JSON null. - ListExecutions ignored its declared target/action/correlation_id filters and paginated on a non-unique target slug, dropping and repeating rows. - started_at was captured but only written at terminal state, so a running execution reported NULL for its whole life. The three MCP auto-run copies wrote no timing at all; they are now one autoRun helper. - SSH output was buffered to completion and discarded entirely on timeout. Both sshExec copies now stream through a shared execlog sink into execution_logs, and keep partial output when a command is cancelled. - executions.correlation_id was a random per-execution uuid that correlated nothing; it is now the chat session id, which is what lets the chat tail live output. - reversible_low had no auto-run branch despite policy declaring it unattended. Since computeCommandRisk never returns it, the class only arises when an agent declares it over a read_only command — so gating it penalised candor without adding safety. - backup-target gains a backup-freshness checker (portable find -mmin, since the first target is on macOS), resolving its host by walking backs-up-to backwards. The pre-deploy pg_dump is now a tracked backup target. UI: an Executions section on entity detail with live output tailing, and streamed output under a running `run` call in the chat timeline. Migrations 022-024. Ops.svelte and context.ts exclude execution.output from their refetch triggers, which would otherwise fire once a second per command. Co-Authored-By: Claude <noreply@anthropic.com>
138 lines
4.2 KiB
TypeScript
138 lines
4.2 KiB
TypeScript
import { describe, it, expect, beforeEach, vi } from 'vitest'
|
|
import { get, writable } from 'svelte/store'
|
|
import type { OikosEvent } from './events'
|
|
|
|
// The store is driven entirely by SSE events plus a log fetch, so both are
|
|
// mocked. What matters is the correlation logic: an execution.output event is
|
|
// matched to a chat session by correlation_id, which MCP-initiated executions
|
|
// now carry (it used to be a random per-execution UUID that correlated
|
|
// nothing).
|
|
|
|
const liveEvents = writable<OikosEvent[]>([])
|
|
const subscribeEvents = vi.fn(() => () => {})
|
|
const fetchExecutionLogs = vi.fn(async (id: string) => ({
|
|
items: [],
|
|
combined: `output-for-${id}`
|
|
}))
|
|
|
|
vi.mock('./events', () => ({
|
|
liveEvents,
|
|
subscribeEvents
|
|
}))
|
|
vi.mock('$lib/api', () => ({
|
|
fetchExecutionLogs: (id: string) => fetchExecutionLogs(id)
|
|
}))
|
|
|
|
let mod: typeof import('./execstream')
|
|
|
|
function event(partial: Partial<OikosEvent>): OikosEvent {
|
|
return {
|
|
id: Math.floor(Math.random() * 1e9),
|
|
ts: new Date().toISOString(),
|
|
type: 'execution.output',
|
|
entity_id: 'exec-1',
|
|
severity: 'info',
|
|
source: 'actuator',
|
|
data: {},
|
|
correlation_id: 'session-1',
|
|
...partial
|
|
} as OikosEvent
|
|
}
|
|
|
|
// The store fetches asynchronously; let the microtask queue drain.
|
|
const settle = () => new Promise((r) => setTimeout(r, 0))
|
|
|
|
beforeEach(async () => {
|
|
liveEvents.set([])
|
|
fetchExecutionLogs.mockClear()
|
|
vi.resetModules()
|
|
mod = await import('./execstream')
|
|
})
|
|
|
|
describe('liveExecutionOutputFor', () => {
|
|
it('picks up output for its own session', async () => {
|
|
const store = mod.liveExecutionOutputFor('session-1')
|
|
const stop = store.subscribe(() => {})
|
|
|
|
liveEvents.set([event({ entity_id: 'exec-1', correlation_id: 'session-1' })])
|
|
await settle()
|
|
|
|
expect(fetchExecutionLogs).toHaveBeenCalledWith('exec-1')
|
|
expect(get(store)).toEqual({ executionId: 'exec-1', output: 'output-for-exec-1' })
|
|
stop()
|
|
})
|
|
|
|
// Without this every open chat window would tail every other session's
|
|
// commands.
|
|
it('ignores output belonging to a different session', async () => {
|
|
const store = mod.liveExecutionOutputFor('session-1')
|
|
const stop = store.subscribe(() => {})
|
|
|
|
liveEvents.set([event({ entity_id: 'exec-9', correlation_id: 'session-2' })])
|
|
await settle()
|
|
|
|
expect(fetchExecutionLogs).not.toHaveBeenCalled()
|
|
expect(get(store)).toBeNull()
|
|
stop()
|
|
})
|
|
|
|
it('ignores unrelated event types', async () => {
|
|
const store = mod.liveExecutionOutputFor('session-1')
|
|
const stop = store.subscribe(() => {})
|
|
|
|
liveEvents.set([event({ type: 'signal.raised' })])
|
|
await settle()
|
|
|
|
expect(fetchExecutionLogs).not.toHaveBeenCalled()
|
|
stop()
|
|
})
|
|
|
|
// A session runs commands one after another; the second must not inherit
|
|
// the first one's output.
|
|
it('resets when a new execution starts in the same session', async () => {
|
|
const store = mod.liveExecutionOutputFor('session-1')
|
|
const stop = store.subscribe(() => {})
|
|
|
|
liveEvents.set([event({ entity_id: 'exec-1' })])
|
|
await settle()
|
|
expect(get(store)?.executionId).toBe('exec-1')
|
|
|
|
liveEvents.set([event({ entity_id: 'exec-2' })])
|
|
await settle()
|
|
expect(get(store)).toEqual({ executionId: 'exec-2', output: 'output-for-exec-2' })
|
|
stop()
|
|
})
|
|
|
|
// Once the command finishes its output belongs to the tool_result, not to a
|
|
// still-"running" entry — leaving it set would show stale output against
|
|
// the next command.
|
|
it('clears on a terminal execution event', async () => {
|
|
const store = mod.liveExecutionOutputFor('session-1')
|
|
const stop = store.subscribe(() => {})
|
|
|
|
liveEvents.set([event({ entity_id: 'exec-1' })])
|
|
await settle()
|
|
expect(get(store)).not.toBeNull()
|
|
|
|
liveEvents.set([event({ type: 'execution.completed', entity_id: 'exec-1' })])
|
|
await settle()
|
|
expect(get(store)).toBeNull()
|
|
stop()
|
|
})
|
|
|
|
it('does not clear on another session completing', async () => {
|
|
const store = mod.liveExecutionOutputFor('session-1')
|
|
const stop = store.subscribe(() => {})
|
|
|
|
liveEvents.set([event({ entity_id: 'exec-1' })])
|
|
await settle()
|
|
|
|
liveEvents.set([
|
|
event({ type: 'execution.completed', entity_id: 'exec-5', correlation_id: 'session-2' })
|
|
])
|
|
await settle()
|
|
expect(get(store)).not.toBeNull()
|
|
stop()
|
|
})
|
|
})
|