Files
felhom-agent/cmd/felhom-agent/restoretest_due_wiring_test.go
T
admin 7581f8140a
gates / gates (push) Successful in 7s
v0.122.0: three ways the signals lied about themselves (R-189, R-188, R-186)
All three are the reporting and release path misreporting its own work. No
customer machine, no backup, no restore, no data. The restore-test itself and
when it runs are unchanged.

R-189 — a passing restore-test no longer vanishes on a restart. restore_tests[]
came only from the in-memory store, whose comment ("lost on restart; the cadence
re-populates") was true under a timer and stopped being true when R-86 made the
agent refuse to re-test a proven archive: the proof is then not repeated for a
whole archive generation. Observed live — a 14.5 GB offsite PASS reached no
host-report because the agent was restarted 2m43s later. RestoreTestState now
carries tier + verified beside the archive and renders reportable entries; the
collector merges them, one per tier, newest by TestedAt. It refuses to lie: a
record missing archive-or-tier produces no entry, and run mechanics are not
re-invented. Only successes are persisted, and the asymmetry is now written where
it will be read.

R-188 — a correct release stops emailing a failure. Only the tag PUSH moved
(build -> tag locally -> publish -> push tag): the push wakes CI, and a tag
visible before its package made the gate correctly fail a correct release about
half the time. The old order's invariant is asserted directly instead — the gate
now refuses a published version with no tag, as a bounded probe that prints its
own coverage, because the package listing api is still 401 without a token.

R-186 — a released binary can be verified by rebuilding it. -trimpath
-buildvcs=false: same source, same bytes, tag or no tag. Measured. publish-agent's
fallback also forced CGO_ENABLED=0 and produced a 74 KB different binary for the
same version; both paths now build identically. CLAUDE.md records the command.
2026-08-03 16:40:18 +02:00

157 lines
5.3 KiB
Go

package main
import (
"go/ast"
"go/parser"
"go/token"
"testing"
)
// R-86 Scenario I — the seam-discipline test for the due-check.
//
// A due-check is worth nothing if the daemon still wires the OLD picker: every unit test in
// internal/backup would stay green (they inject the seam directly), the scheduler would ask for the
// newest archive with no settle cutoff, and the per-archive rule would run against a candidate that
// changes every time a backup lands. That is the same shape as the v0.91.0 inert seam — built,
// tested, never called — and this repo has shipped it four times.
//
// It walks main.go's AST rather than grepping: a commented-out call still satisfies a substring
// match, and a comment is not a caller.
func TestMainWiresTheSettleAwareTierPicker(t *testing.T) {
f := parseMainForWiring(t)
var settlePicker, oldPicker, settleWired, evalInterval bool
ast.Inspect(f, func(n ast.Node) bool {
switch node := n.(type) {
case *ast.SelectorExpr:
// runner.PickSettledRestoreCandidateOn passed as a value (not called).
switch node.Sel.Name {
case "PickSettledRestoreCandidateOn":
settlePicker = true
case "PickRestoreCandidateOn":
oldPicker = true
}
case *ast.KeyValueExpr:
key, ok := node.Key.(*ast.Ident)
if !ok {
return true
}
if key.Name == "Settle" {
settleWired = true
}
case *ast.CallExpr:
if sel, ok := node.Fun.(*ast.SelectorExpr); ok && sel.Sel.Name == "RestoreTestEvalInterval" {
evalInterval = true
}
}
return true
})
if !settlePicker {
t.Error("main.go never passes runner.PickSettledRestoreCandidateOn as the scheduler's TierPick — " +
"the due-check would run without a settle cutoff, i.e. against an archive that may still be being written")
}
if oldPicker {
t.Error("main.go still wires the pre-R-86 PickRestoreCandidateOn as a tier picker — " +
"two pickers means the one under test is not the one running")
}
if !settleWired {
t.Error("main.go never sets SchedulerOptions.Settle — the settle lag would default to 0 in the daemon " +
"and every freshly-landed archive would be an immediate candidate")
}
if !evalInterval {
t.Error("main.go never calls cfg.Backup.RestoreTestEvalInterval() — the scheduler would be driven by " +
"the retired cadence knob")
}
}
// The two R-85 guarantees the due-check must not have quietly dropped: the spec is still built PER
// RUN, and the shared heavy-operation gate is still handed to the scheduler.
func TestMainStillWiresTheHeavyOperationGateAndPerRunSpec(t *testing.T) {
f := parseMainForWiring(t)
var inFlightWired, specIsAFunc bool
ast.Inspect(f, func(n ast.Node) bool {
kv, ok := n.(*ast.KeyValueExpr)
if !ok {
return true
}
key, ok := kv.Key.(*ast.Ident)
if !ok {
return true
}
switch key.Name {
case "InFlight":
inFlightWired = true
case "Spec":
// A FuncLit means it is evaluated per run; anything else is a frozen value.
if _, isFunc := kv.Value.(*ast.FuncLit); isFunc {
specIsAFunc = true
}
}
return true
})
if !inFlightWired {
t.Error("main.go no longer hands the scheduler the shared InFlight gate — a restore-test could pull a " +
"multi-GB archive over the same tunnel an offsite backup is pushing one over (Scenario F)")
}
if !specIsAFunc {
t.Error("SchedulerOptions.Spec is no longer a function literal — a frozen spec is the R-85 defect " +
"(the tier and its timeout evaluated once at daemon start, forever)")
}
}
func parseMainForWiring(t *testing.T) *ast.File {
t.Helper()
fset := token.NewFileSet()
f, err := parser.ParseFile(fset, "main.go", nil, 0)
if err != nil {
t.Fatalf("parse main.go: %v", err)
}
return f
}
// R-189 Scenario I — the DURABLE proof source must actually be wired into the collector.
//
// This test exists because the method it feeds is the project's own cautionary tale:
// `RestoreTestState.Snapshot` carried the doc comment "for the host-report gauge" from the day it
// was written and **had no caller at all** — a seam built, documented and never connected, found
// only when a live restore-test's PASS reached no host-report. The fix must not become the next
// instance, so the wiring is asserted rather than trusted.
//
// AST, not grep: a commented-out call still contains the string (proven yesterday, when commenting
// out the tier-picker line failed this test while a `strings.Contains` check would have passed).
func TestMainWiresTheDurableRestoreTestProof(t *testing.T) {
f := parseMainForWiring(t)
var wired, feedsState bool
ast.Inspect(f, func(n ast.Node) bool {
call, ok := n.(*ast.CallExpr)
if !ok {
return true
}
sel, ok := call.Fun.(*ast.SelectorExpr)
if !ok || sel.Sel.Name != "SetProvenRestoreTests" {
return true
}
wired = true
// ...and it must be fed the PERSISTED state, not the in-memory store.
if len(call.Args) == 1 {
if id, ok := call.Args[0].(*ast.Ident); ok && id.Name == "rtState" {
feedsState = true
}
}
return true
})
if !wired {
t.Error("main.go never calls collector.SetProvenRestoreTests — the persisted proof would never " +
"reach the hub, which is the R-189 defect exactly: a passing restore-test that vanishes on restart")
}
if wired && !feedsState {
t.Error("collector.SetProvenRestoreTests is not fed rtState — the in-memory store is the thing " +
"that does NOT survive a restart, so wiring it here would fix nothing")
}
}