Files
zero/internal/cli/auth_propagation_test.go
KRATOS 6e0a665118 fix(auth): propagate credentials to every provider-build surface and pin children to the live provider (#366)
* fix(auth): propagate credentials to every provider-build surface and pin children to the live provider

Sub-agents, swarm members, ACP sessions, and mid-run escalation switches
could build providers without the credentials the parent was running with.
This consolidates credential resolution so every surface gets the same auth:

- Wrap deps.newProvider once in fillAppDeps to fold the stored API key in
  centrally; ACP, exec escalation, and buildProvider no longer patch it
  per call site (an apiKeyStored profile previously went out keyless on
  those paths and 401'd).
- Export ZERO_PROVIDER at startup (buildProvider) and keep exporting on
  every runtime switch (wizard, onboarding, /model, /provider), so spawned
  children resolve the parent's live provider instead of whatever another
  process last persisted to config.json. Injected via appDeps so tests
  never mutate the process environment.
- Share one OAuth login selection end to end: ProviderProfile.
  OAuthLoginCandidates (name, then catalog-ID fallback; nothing for a
  profile with its own configured credential) + oauth.FirstStored resolve
  the login ONCE, and the bound store key is threaded through
  providers.Options.OAuthLoginKey so the Codex account-id header always
  reads the same login that issued the bearer token. A renamed profile
  (name != catalog ID) now finds its login; an explicit API key is never
  silently overridden by a same-name or catalog-shared OAuth login.
- Export ProviderProfile.HasConfiguredCredential as the single "profile is
  key-authed" predicate (cli/tui/config previously had three copies).
- applyProviderWizard commits live state (provider, profile, name, env
  export) only after BOTH the build and the config persist succeed, so a
  persist failure no longer leaves the chat running on a provider the
  status line and children disagree with.

Covered by red-green tests for each path: stored-key wrap, escalation
switch, catalog-ID fallback (incl. case-variant names), explicit-key
protection, same-login account selection, wizard persist-failure rollback,
onboarding/startup env export.

* test: isolate OAuth/config test storage and fix the flaky MCP response-id test

Review + CI fixes, all test-only:

- factory/cli OAuth tests: pin ZERO_OAUTH_STORAGE=file next to the temp
  ZERO_OAUTH_TOKENS_PATH — an inherited "keyring" value sends NewStore to
  the OS keychain and ignores the temp path entirely, so the tests could
  read (or clobber) the developer's real logins. newOAuthStoreForTest now
  owns both pins so a future call site can't forget them.
- TestApplyProviderWizardExportsActiveProviderEnv: point m.userConfigPath
  at a temp config and stub newProvider, so the SUCCESS path exercises the
  full build+persist+commit sequence in isolation (the default empty path
  silently skipped persist; a changed default must never reach the real
  user config).
- TestClientRequestWaitsForMatchingResponseID (ubuntu smoke flake): the
  responses were pre-loaded into a bytes.Buffer, so the client's reader
  goroutine could consume the matching response — and hit EOF — before
  request() registered its pending id, failing with "request() error =
  EOF" on fast runners. The fake server now sits on pipes and responds
  only after reading the outgoing request, matching production ordering;
  survives -race -count=50.
2026-07-02 12:21:27 +05:30

181 lines
7.3 KiB
Go

package cli
import (
"bytes"
"errors"
"os"
"path/filepath"
"testing"
"github.com/Gitlawb/zero/internal/config"
"github.com/Gitlawb/zero/internal/zeroruntime"
)
// seedStoredProviderKey writes key into a credential store rooted beside the
// returned config path, and returns deps fields wired at that path — the same
// layout applyStoredProviderKey resolves through in production.
func seedStoredProviderKey(t *testing.T, providerName, key string) (userConfigPath string) {
t.Helper()
t.Setenv("ZERO_CRED_STORAGE", "encrypted-file") // never touch the real OS keychain in tests
dir := t.TempDir()
store, err := config.ProviderKeyStoreAt(dir)
if err != nil {
t.Fatalf("ProviderKeyStoreAt: %v", err)
}
if err := store.Set(providerName, key); err != nil {
t.Fatalf("seed stored key: %v", err)
}
return filepath.Join(dir, "config.json")
}
// applyStoredProviderKeyAt must fill APIKey from the credential store for an
// apiKeyStored profile — the single central helper the newProvider wrapper uses.
func TestApplyStoredProviderKeyAtFillsFromCredstore(t *testing.T) {
configPath := seedStoredProviderKey(t, "echo", "sk-stored-test")
ucp := func() (string, error) { return configPath, nil }
stored := applyStoredProviderKeyAt(config.ProviderProfile{Name: "echo", APIKeyStored: true}, ucp)
if stored.APIKey != "sk-stored-test" {
t.Fatalf("APIKey = %q, want the stored key", stored.APIKey)
}
// A profile that did NOT opt into stored-key auth must be left unchanged —
// a stale store entry must not silently reactivate credentials.
plain := applyStoredProviderKeyAt(config.ProviderProfile{Name: "echo"}, ucp)
if plain.APIKey != "" {
t.Fatalf("non-stored profile APIKey = %q, want empty", plain.APIKey)
}
}
// fillAppDeps wraps newProvider so EVERY surface that builds a runtime provider
// (buildProvider, the ACP builder — which is just deps.newProvider — and exec's
// escalation switcher) gets the stored key applied. Passing the raw resolved
// profile previously sent unauthenticated requests for apiKeyStored profiles,
// the default onboarding outcome. Testing the wrap covers all those surfaces.
func TestFillAppDepsWrapsNewProviderWithStoredKey(t *testing.T) {
configPath := seedStoredProviderKey(t, "echo", "sk-stored-wrap")
var captured config.ProviderProfile
deps := fillAppDeps(appDeps{
userConfigPath: func() (string, error) { return configPath, nil },
newProvider: func(profile config.ProviderProfile) (zeroruntime.Provider, error) {
captured = profile
return nil, nil // only the captured profile matters here
},
})
if _, err := deps.newProvider(config.ProviderProfile{Name: "echo", APIKeyStored: true}); err != nil {
t.Fatalf("wrapped newProvider: %v", err)
}
if captured.APIKey != "sk-stored-wrap" {
t.Fatalf("wrapped newProvider built with APIKey = %q, want the stored key (unauthenticated regression)", captured.APIKey)
}
}
// buildProvider (the TUI/exec STARTUP construction site) must export
// ZERO_PROVIDER so children spawned at any point in the run are pinned to the
// parent's provider from launch — not only after an in-session switch. Without
// this, a provider switch persisted by another zero process mid-session moves
// new children onto a different provider (and credentials) than the parent.
func TestBuildProviderExportsActiveProviderEnv(t *testing.T) {
t.Setenv(config.ActiveProviderEnv, "stale-from-elsewhere")
// The exporter is injected (defaultAppDeps wires config.SetActiveProviderEnv;
// fillAppDeps deliberately leaves it nil so ordinary tests never mutate the
// process env). Inject the real one here to assert the actual env effect.
deps := appDeps{
exportActiveProvider: config.SetActiveProviderEnv,
newProvider: func(config.ProviderProfile) (zeroruntime.Provider, error) {
return nil, nil
},
}
resolved := config.ResolvedConfig{Provider: config.ProviderProfile{Name: "pinned", ProviderKind: config.ProviderKindAnthropic, Model: "m"}}
if _, err := buildProvider(resolved, deps); err != nil {
t.Fatalf("buildProvider: %v", err)
}
if got := os.Getenv(config.ActiveProviderEnv); got != "pinned" {
t.Fatalf("%s = %q after startup build, want %q (children would spawn on the stale provider)", config.ActiveProviderEnv, got, "pinned")
}
// A FAILED build must not move the pin: the process never committed to the
// new provider, so children must keep resolving whatever was in effect.
t.Setenv(config.ActiveProviderEnv, "still-current")
failing := appDeps{
exportActiveProvider: config.SetActiveProviderEnv,
newProvider: func(config.ProviderProfile) (zeroruntime.Provider, error) {
return nil, errors.New("boom")
},
}
if _, err := buildProvider(resolved, failing); err == nil {
t.Fatal("expected build error")
}
if got := os.Getenv(config.ActiveProviderEnv); got != "still-current" {
t.Fatalf("%s = %q after failed build, want it untouched", config.ActiveProviderEnv, got)
}
// No provider profile at all → no provider, no pin change.
if _, err := buildProvider(config.ResolvedConfig{}, deps); err != nil {
t.Fatalf("buildProvider(empty): %v", err)
}
if got := os.Getenv(config.ActiveProviderEnv); got != "still-current" {
t.Fatalf("%s = %q after profile-less build, want it untouched", config.ActiveProviderEnv, got)
}
}
// A mid-run --allow-escalation model switch previously rebuilt the provider
// from the PURE resolved profile (the stored key lives only in buildProvider's
// local copy), so the escalated provider was keyless and the next completion
// call 401'd mid-run. Every profile handed to newProvider on this path must
// carry the stored key.
func TestRunExecEscalationSwitchKeepsStoredKey(t *testing.T) {
dataHome := t.TempDir()
t.Setenv("XDG_DATA_HOME", dataHome)
cwd := t.TempDir()
if _, ok := mustUpgradeTarget(t, "claude-haiku-4.5"); !ok {
t.Skip("registry has no upgrade target for claude-haiku-4.5")
}
configPath := seedStoredProviderKey(t, "echo", "sk-stored-escalation")
var builtProfiles []config.ProviderProfile
var stdout, stderr bytes.Buffer
exitCode := runWithDeps([]string{
"exec",
"--allow-escalation",
"--model", "claude-haiku-4.5",
"--init-session-id", "escalation_stored_key_run",
"escalate please",
}, &stdout, &stderr, appDeps{
getwd: func() (string, error) { return cwd, nil },
userConfigPath: func() (string, error) { return configPath, nil },
resolveConfig: func(_ string, overrides config.Overrides) (config.ResolvedConfig, error) {
model := "claude-haiku-4.5"
if overrides.Provider.Model != "" {
model = overrides.Provider.Model
}
cfg := execResolvedConfig()
cfg.Provider.ProviderKind = config.ProviderKindAnthropic
cfg.Provider.Model = model
cfg.Provider.APIKeyStored = true // key lives ONLY in the credstore
cfg.MaxTurns = 3
return cfg, nil
},
newProvider: func(profile config.ProviderProfile) (zeroruntime.Provider, error) {
builtProfiles = append(builtProfiles, profile)
return &usageEmittingEscalatingProvider{escalate: len(builtProfiles) == 1}, nil
},
})
if exitCode != exitSuccess {
t.Fatalf("exit = %d, want success; stderr=%s", exitCode, stderr.String())
}
if len(builtProfiles) < 2 {
t.Fatalf("want at least 2 provider builds (initial + escalated), got %d", len(builtProfiles))
}
for i, profile := range builtProfiles {
if profile.APIKey != "sk-stored-escalation" {
t.Fatalf("provider build %d APIKey = %q, want the stored key (escalated build went out keyless)", i, profile.APIKey)
}
}
}