Compare commits
5 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| b8583ef019 | |||
| 231dfcf523 | |||
| e740ffe23f | |||
| 283ebd5b47 | |||
| 0d6b61bfff |
@@ -3,16 +3,24 @@ import { useState, useCallback, useRef, useEffect } from 'react';
|
||||
import type { Secret, SecretGroup } from '@/types/secrets';
|
||||
import { useSecretsStore } from '@/stores/secrets-store';
|
||||
import { StatusBadge } from '@/components/ui/StatusBadge';
|
||||
import { RevealToggle } from '@/components/ui/RevealToggle';
|
||||
import { KeyValueField } from '@/components/ui/KeyValueField';
|
||||
import { ValidationHint } from '@/components/ui/ValidationHint';
|
||||
import { TestConnectionButton } from '@/components/ui/TestConnectionButton';
|
||||
import { validateSecretValue } from '@/lib/validation/secret-formats';
|
||||
import { SERVICES } from '@/lib/services';
|
||||
|
||||
const AUTO_HIDE_MS = 30_000;
|
||||
const VALIDATION_DEBOUNCE_MS = 400;
|
||||
|
||||
// Secret values are write-only from the browser: the server List endpoint
|
||||
// "Never exposes values", there is no per-secret decrypt route, and the
|
||||
// only decrypted path (GET /secrets/values) is bulk + token-gated for
|
||||
// remote agents. The old eye/RevealToggle was a dead affordance — it
|
||||
// flipped its own icon but could never reveal anything, which read as
|
||||
// "this doesn't work" (esp. once clicked → eye-with-slash). We show an
|
||||
// honest static indicator instead; rotation is via Edit.
|
||||
const WRITE_ONLY_TITLE =
|
||||
'Value is write-only and cannot be revealed — use Edit to replace/rotate it';
|
||||
|
||||
interface SecretRowProps {
|
||||
secret: Secret;
|
||||
workspaceId: string;
|
||||
@@ -31,28 +39,12 @@ export function SecretRow({ secret, workspaceId }: SecretRowProps) {
|
||||
const setSecretStatus = useSecretsStore((s) => s.setSecretStatus);
|
||||
|
||||
const isEditing = editingKey === secret.name;
|
||||
const [revealed, setRevealed] = useState(false);
|
||||
const [editValue, setEditValue] = useState('');
|
||||
const [validationError, setValidationError] = useState<string | null>(null);
|
||||
const [isSaving, setIsSaving] = useState(false);
|
||||
const [saveError, setSaveError] = useState<string | null>(null);
|
||||
const debounceRef = useRef<ReturnType<typeof setTimeout>>(undefined);
|
||||
const editBtnRef = useRef<HTMLButtonElement>(null);
|
||||
const revealTimerRef = useRef<ReturnType<typeof setTimeout>>(undefined);
|
||||
|
||||
// Auto-hide revealed value after 30s
|
||||
useEffect(() => {
|
||||
if (revealed) {
|
||||
clearTimeout(revealTimerRef.current);
|
||||
revealTimerRef.current = setTimeout(() => setRevealed(false), AUTO_HIDE_MS);
|
||||
return () => clearTimeout(revealTimerRef.current);
|
||||
}
|
||||
}, [revealed]);
|
||||
|
||||
// Reset revealed state when panel closes (session-only)
|
||||
useEffect(() => {
|
||||
return () => setRevealed(false);
|
||||
}, []);
|
||||
|
||||
// Debounced validation
|
||||
useEffect(() => {
|
||||
@@ -133,11 +125,15 @@ export function SecretRow({ secret, workspaceId }: SecretRowProps) {
|
||||
{secret.masked_value}
|
||||
</span>
|
||||
<div className="secret-row__actions">
|
||||
<RevealToggle
|
||||
revealed={revealed}
|
||||
onToggle={() => setRevealed((r) => !r)}
|
||||
label={`Toggle reveal ${secret.name}`}
|
||||
/>
|
||||
<span
|
||||
data-testid="write-only-indicator"
|
||||
className="secret-row__write-only"
|
||||
role="img"
|
||||
aria-label={`${secret.name} value is write-only and cannot be revealed; use Edit to replace it`}
|
||||
title={WRITE_ONLY_TITLE}
|
||||
>
|
||||
🔒
|
||||
</span>
|
||||
<StatusBadge status={secret.status} />
|
||||
<button
|
||||
type="button"
|
||||
|
||||
@@ -138,14 +138,54 @@ describe("SecretRow — display mode", () => {
|
||||
expect(document.querySelector('[role="row"]')).toBeTruthy();
|
||||
});
|
||||
|
||||
it("has Reveal, Copy, Edit, Delete buttons", () => {
|
||||
it("has Copy, Edit, Delete buttons", () => {
|
||||
render(<SecretRow secret={GITHUB_SECRET} workspaceId="ws-1" />);
|
||||
expect(screen.getByTestId("reveal-toggle")).toBeTruthy();
|
||||
expect(screen.getByRole("button", { name: /copy/i })).toBeTruthy();
|
||||
expect(screen.getByRole("button", { name: /edit/i })).toBeTruthy();
|
||||
expect(screen.getByRole("button", { name: /delete/i })).toBeTruthy();
|
||||
});
|
||||
|
||||
// Regression: the reveal/eye control was a dead affordance. Clicking it
|
||||
// flipped its own icon (eye → eye-with-slash) but never revealed the value,
|
||||
// because secret values are write-only from the browser (server List
|
||||
// "Never exposes values"; there is no per-secret decrypt endpoint and the
|
||||
// client has no plaintext-fetch function). The honest fix removes the
|
||||
// toggle and shows a static "write-only / cannot be revealed" indicator.
|
||||
// See internal tracking issue + internal#210/#211.
|
||||
it("does NOT render a reveal/eye toggle (values are write-only)", () => {
|
||||
render(<SecretRow secret={GITHUB_SECRET} workspaceId="ws-1" />);
|
||||
expect(screen.queryByTestId("reveal-toggle")).toBeNull();
|
||||
expect(
|
||||
screen.queryByRole("button", { name: /toggle reveal/i }),
|
||||
).toBeNull();
|
||||
});
|
||||
|
||||
it("shows a write-only indicator explaining the value cannot be revealed", () => {
|
||||
render(<SecretRow secret={ANTHROPIC_SECRET} workspaceId="ws-1" />);
|
||||
const indicator = screen.getByTestId("write-only-indicator");
|
||||
expect(indicator).toBeTruthy();
|
||||
// Affordance must be honest: explain it cannot be revealed and that
|
||||
// Edit is the rotate path. It must not be a clickable button.
|
||||
const title = indicator.getAttribute("title") ?? "";
|
||||
expect(title.toLowerCase()).toMatch(/write-only|cannot be revealed/);
|
||||
expect(indicator.tagName).not.toBe("BUTTON");
|
||||
});
|
||||
|
||||
it("write-only indicator is present for the Anthropic/OAuth-token row too", () => {
|
||||
// The reported bug singled out CLAUDE_CODE_OAUTH_TOKEN (anthropic group);
|
||||
// the fix is group-agnostic — every row gets the same honest affordance.
|
||||
const OAUTH_SECRET = {
|
||||
name: "CLAUDE_CODE_OAUTH_TOKEN",
|
||||
masked_value: "••••••••••••••••9d2a",
|
||||
group: "anthropic" as const,
|
||||
status: "unverified" as const,
|
||||
updated_at: "2024-01-04",
|
||||
};
|
||||
render(<SecretRow secret={OAUTH_SECRET} workspaceId="ws-1" />);
|
||||
expect(screen.queryByTestId("reveal-toggle")).toBeNull();
|
||||
expect(screen.getByTestId("write-only-indicator")).toBeTruthy();
|
||||
});
|
||||
|
||||
it("shows invalid status correctly", () => {
|
||||
render(<SecretRow secret={CUSTOM_SECRET} workspaceId="ws-1" />);
|
||||
expect(screen.getByTestId("status-badge").getAttribute("data-status")).toBe("invalid");
|
||||
|
||||
@@ -399,7 +399,21 @@ func (h *WorkspaceHandler) proxyA2ARequest(ctx context.Context, workspaceID stri
|
||||
// (no Do(), no maybeMarkContainerDead). The response is a synthetic
|
||||
// {status:"queued"} envelope so the caller (canvas, another workspace)
|
||||
// knows delivery is acknowledged but pending consumption.
|
||||
if lookupDeliveryMode(ctx, workspaceID) == models.DeliveryModePoll {
|
||||
deliveryMode, deliveryModeErr := lookupDeliveryMode(ctx, workspaceID)
|
||||
if deliveryModeErr != nil {
|
||||
// internal#497 fail-closed: a real DB/context error on the
|
||||
// delivery-mode read MUST NOT silently fall through to the push
|
||||
// dispatch path — that is exactly what silently misrouted every
|
||||
// poll-mode peer for 5 days under the ce2db75f regression. Surface
|
||||
// a structured error so the delegation is marked failed (loud +
|
||||
// retryable) instead of dispatched to the wrong path.
|
||||
log.Printf("ProxyA2A: delivery-mode lookup failed for %s: %v — failing closed", workspaceID, deliveryModeErr)
|
||||
return 0, nil, &proxyA2AError{
|
||||
Status: http.StatusServiceUnavailable,
|
||||
Response: gin.H{"error": "delivery-mode lookup failed; refusing to dispatch to avoid silent misrouting"},
|
||||
}
|
||||
}
|
||||
if deliveryMode == models.DeliveryModePoll {
|
||||
if logActivity {
|
||||
h.logA2AReceiveQueued(ctx, workspaceID, callerID, body, a2aMethod)
|
||||
}
|
||||
|
||||
@@ -468,40 +468,64 @@ func parseUsageFromA2AResponse(body []byte) (inputTokens, outputTokens int64) {
|
||||
return 0, 0
|
||||
}
|
||||
|
||||
// lookupDeliveryMode returns the workspace's delivery_mode. On any DB
|
||||
// error or missing row it returns DeliveryModePush — the fail-closed
|
||||
// default. "Closed" here means "fall back to today's behavior (synchronous
|
||||
// dispatch)" rather than "fall back to drop the request silently into
|
||||
// activity_logs where the agent might never see it." A poll-mode workspace
|
||||
// that briefly reads as push will get its A2A request dispatched to the
|
||||
// stored URL (or a 502 if no URL); a push-mode workspace that briefly
|
||||
// reads as poll would get its request silently queued with no dispatch.
|
||||
// The first failure is loud + recoverable; the second is silent.
|
||||
// lookupDeliveryMode returns the workspace's delivery_mode.
|
||||
//
|
||||
// internal#497 / RFC#497 fail-closed (SURGICAL scope): the *specific*
|
||||
// failure mode that hid the ce2db75f regression for 5 days is now
|
||||
// propagated instead of silently swallowed — a CONTEXT error
|
||||
// (context.Canceled / context.DeadlineExceeded). Under ce2db75f the
|
||||
// detached delegation goroutine ran on a cancelled request context, every
|
||||
// `SELECT delivery_mode` failed `context canceled`, this function returned
|
||||
// push, the poll-mode short-circuit in proxyA2ARequest was skipped, and
|
||||
// poll-mode peers (e.g. an operator laptop on molecule-mcp-claude-channel)
|
||||
// silently never got their a2a_receive inbox row. A transient,
|
||||
// systematic-once-triggered context cancellation became permanent
|
||||
// invisible misrouting. Returning that error lets the caller fail loud
|
||||
// (mark the delegation failed) instead of mis-dispatching.
|
||||
//
|
||||
// Scope is deliberately narrow: only ctx errors propagate. Other DB
|
||||
// errors retain the long-standing documented "fall back to push (today's
|
||||
// synchronous behavior)" contract — that path is loud + recoverable
|
||||
// (502 / SSRF reject / restart), unlike the silent poll-mode drop, and
|
||||
// the surrounding proxy (incl. the sibling checkWorkspaceBudget) is
|
||||
// intentionally built around that fail-open-to-push behavior. Widening
|
||||
// further is an RFC#497 follow-up, not part of this P0 fix.
|
||||
//
|
||||
// A genuinely *absent* configuration is NOT an error and still resolves to
|
||||
// push (the safe synchronous default): sql.ErrNoRows, a NULL/empty column,
|
||||
// or an unrecognised value all return (push, nil).
|
||||
//
|
||||
// The function is intentionally lookup-only — it never mutates the row.
|
||||
// The register handler (registry.go) is the only writer for delivery_mode.
|
||||
//
|
||||
// See #2339 PR 1 for the column + register-flow side; this is the
|
||||
// proxy-side read used for the short-circuit in proxyA2ARequest.
|
||||
func lookupDeliveryMode(ctx context.Context, workspaceID string) string {
|
||||
func lookupDeliveryMode(ctx context.Context, workspaceID string) (string, error) {
|
||||
var mode sql.NullString
|
||||
err := db.DB.QueryRowContext(ctx,
|
||||
`SELECT delivery_mode FROM workspaces WHERE id = $1`, workspaceID,
|
||||
).Scan(&mode)
|
||||
if err != nil {
|
||||
if !errors.Is(err, sql.ErrNoRows) {
|
||||
log.Printf("ProxyA2A: lookupDeliveryMode(%s) failed (%v) — defaulting to push", workspaceID, err)
|
||||
// internal#497: a context cancellation/deadline MUST NOT be
|
||||
// swallowed into a silent push default — that is the exact 5-day
|
||||
// silent-misrouting vector. Propagate so the caller fails closed.
|
||||
if errors.Is(err, context.Canceled) || errors.Is(err, context.DeadlineExceeded) {
|
||||
log.Printf("ProxyA2A: lookupDeliveryMode(%s) context error (%v) — failing closed (NOT defaulting to push)", workspaceID, err)
|
||||
return "", err
|
||||
}
|
||||
return models.DeliveryModePush
|
||||
if !errors.Is(err, sql.ErrNoRows) {
|
||||
log.Printf("ProxyA2A: lookupDeliveryMode(%s) failed (%v) — defaulting to push (non-ctx DB error; legacy fail-open-to-push contract)", workspaceID, err)
|
||||
}
|
||||
return models.DeliveryModePush, nil
|
||||
}
|
||||
if !mode.Valid || mode.String == "" {
|
||||
return models.DeliveryModePush
|
||||
return models.DeliveryModePush, nil
|
||||
}
|
||||
if !models.IsValidDeliveryMode(mode.String) {
|
||||
log.Printf("ProxyA2A: workspace %s has invalid delivery_mode=%q — defaulting to push", workspaceID, mode.String)
|
||||
return models.DeliveryModePush
|
||||
return models.DeliveryModePush, nil
|
||||
}
|
||||
return mode.String
|
||||
return mode.String, nil
|
||||
}
|
||||
|
||||
// logA2AReceiveQueued records a poll-mode "queued" A2A receive into
|
||||
|
||||
@@ -1,59 +0,0 @@
|
||||
package handlers
|
||||
|
||||
import (
|
||||
"testing"
|
||||
"time"
|
||||
)
|
||||
|
||||
// =============================================================================
|
||||
// parseIdleTimeoutEnv
|
||||
// =============================================================================
|
||||
|
||||
// parseIdleTimeoutEnv is the only untested pure helper in a2a_proxy.go.
|
||||
// Covered in the full proxy path via idleTimeoutDuration package var, but
|
||||
// the unit itself had no direct tests until this file.
|
||||
|
||||
func TestParseIdleTimeoutEnv_Valid(t *testing.T) {
|
||||
tests := []struct {
|
||||
input string
|
||||
want time.Duration
|
||||
}{
|
||||
{"30", 30 * time.Second},
|
||||
{"60", 60 * time.Second},
|
||||
{"300", 5 * time.Minute},
|
||||
{"3600", 1 * time.Hour},
|
||||
}
|
||||
for _, tt := range tests {
|
||||
got := parseIdleTimeoutEnv(tt.input)
|
||||
if got != tt.want {
|
||||
t.Errorf("parseIdleTimeoutEnv(%q) = %v; want %v", tt.input, got, tt.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestParseIdleTimeoutEnv_Empty(t *testing.T) {
|
||||
got := parseIdleTimeoutEnv("")
|
||||
if got != defaultIdleTimeoutDuration {
|
||||
t.Errorf("parseIdleTimeoutEnv(%q) = %v; want defaultIdleTimeoutDuration (%v)", "", got, defaultIdleTimeoutDuration)
|
||||
}
|
||||
}
|
||||
|
||||
func TestParseIdleTimeoutEnv_InvalidInteger(t *testing.T) {
|
||||
cases := []string{"abc", "12.5", "1e3"}
|
||||
for _, v := range cases {
|
||||
got := parseIdleTimeoutEnv(v)
|
||||
if got != defaultIdleTimeoutDuration {
|
||||
t.Errorf("parseIdleTimeoutEnv(%q) = %v; want defaultIdleTimeoutDuration", v, got)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestParseIdleTimeoutEnv_NonPositive(t *testing.T) {
|
||||
cases := []string{"0", "-1", "-30"}
|
||||
for _, v := range cases {
|
||||
got := parseIdleTimeoutEnv(v)
|
||||
if got != defaultIdleTimeoutDuration {
|
||||
t.Errorf("parseIdleTimeoutEnv(%q) = %v; want defaultIdleTimeoutDuration", v, got)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -2228,12 +2228,18 @@ func TestProxyA2A_PushMode_NoShortCircuit(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// TestProxyA2A_PollMode_FailsClosedToPush verifies the safety contract:
|
||||
// a DB error reading delivery_mode must default to push (the existing
|
||||
// behavior), NOT poll. Failing to push means a poll-mode workspace
|
||||
// briefly attempts a real dispatch — visible failure (502 / SSRF
|
||||
// rejection / restart cascade), not a silent drop into activity_logs
|
||||
// where the agent might never look. Loud > silent, recoverable > lost.
|
||||
// TestProxyA2A_PollMode_FailsClosedToPush verifies the LEGACY safety
|
||||
// contract is PRESERVED for non-context DB errors: a generic DB error
|
||||
// reading delivery_mode still defaults to push (today's behavior), NOT
|
||||
// poll. Failing to push means a poll-mode workspace briefly attempts a
|
||||
// real dispatch — visible failure (502 / SSRF rejection / restart
|
||||
// cascade), not a silent drop into activity_logs where the agent might
|
||||
// never look. Loud > silent, recoverable > lost.
|
||||
//
|
||||
// internal#497 narrows the fail-closed change to *context* errors only
|
||||
// (the actual ce2db75f regression vector); generic DB errors keep this
|
||||
// long-standing fail-open-to-push contract. The ctx-error fail-closed is
|
||||
// covered by TestLookupDeliveryMode_ContextCanceled_FailsClosed.
|
||||
func TestProxyA2A_PollMode_FailsClosedToPush(t *testing.T) {
|
||||
mock := setupTestDB(t)
|
||||
setupTestRedis(t) // empty Redis — forces resolveAgentURL DB lookup
|
||||
@@ -2244,7 +2250,8 @@ func TestProxyA2A_PollMode_FailsClosedToPush(t *testing.T) {
|
||||
|
||||
expectBudgetCheck(mock, wsID)
|
||||
|
||||
// lookupDeliveryMode hits a transient DB error → must default push.
|
||||
// lookupDeliveryMode hits a generic (non-context) DB error → must
|
||||
// still default push (legacy contract preserved by internal#497).
|
||||
mock.ExpectQuery("SELECT delivery_mode FROM workspaces WHERE id").
|
||||
WithArgs(wsID).
|
||||
WillReturnError(sql.ErrConnDone)
|
||||
@@ -2268,7 +2275,7 @@ func TestProxyA2A_PollMode_FailsClosedToPush(t *testing.T) {
|
||||
var resp map[string]interface{}
|
||||
_ = json.Unmarshal(w.Body.Bytes(), &resp)
|
||||
if resp["status"] == "queued" {
|
||||
t.Errorf("DB error on delivery_mode lookup silently queued the request — must fail-closed-to-push, got body: %s", w.Body.String())
|
||||
t.Errorf("generic DB error on delivery_mode lookup silently queued the request — must fail-open-to-push, got body: %s", w.Body.String())
|
||||
}
|
||||
}
|
||||
|
||||
@@ -2277,6 +2284,37 @@ func TestProxyA2A_PollMode_FailsClosedToPush(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// TestLookupDeliveryMode_ContextCanceled_FailsClosed is the internal#497
|
||||
// regression test for the SECONDARY defect. It pins the exact invariant
|
||||
// that hid the ce2db75f regression for 5 days: when the delivery_mode read
|
||||
// fails because the context was cancelled (precisely what happened in the
|
||||
// detached delegation goroutine running on a returned request context),
|
||||
// lookupDeliveryMode MUST return an error and MUST NOT silently return
|
||||
// "push". Returning push there is what skipped the poll-mode short-circuit
|
||||
// and silently dropped 100% of poll-mode peer deliveries.
|
||||
//
|
||||
// A pre-cancelled context makes QueryRowContext fail with
|
||||
// context.Canceled deterministically — no DB rows are mocked because the
|
||||
// query never reaches a result.
|
||||
func TestLookupDeliveryMode_ContextCanceled_FailsClosed(t *testing.T) {
|
||||
mock := setupTestDB(t)
|
||||
// The query fails on the cancelled ctx before matching; provide a
|
||||
// permissive expectation so sqlmock doesn't complain about the attempt.
|
||||
mock.ExpectQuery("SELECT delivery_mode FROM workspaces WHERE id").
|
||||
WillReturnError(context.Canceled)
|
||||
|
||||
ctx, cancel := context.WithCancel(context.Background())
|
||||
cancel() // simulate the HTTP handler having returned (request ctx dead)
|
||||
|
||||
mode, err := lookupDeliveryMode(ctx, "ws-poll-peer")
|
||||
if err == nil {
|
||||
t.Fatalf("internal#497 regression: lookupDeliveryMode swallowed a context error and returned mode=%q with nil err — this is the exact 5-day silent-misrouting vector", mode)
|
||||
}
|
||||
if mode == models.DeliveryModePush {
|
||||
t.Errorf("internal#497 regression: context error must NOT default to push (got mode=%q)", mode)
|
||||
}
|
||||
}
|
||||
|
||||
// ==================== a2aClient ResponseHeaderTimeout config ====================
|
||||
|
||||
func TestA2AClientResponseHeaderTimeout(t *testing.T) {
|
||||
|
||||
@@ -162,8 +162,32 @@ func (h *DelegationHandler) Delegate(c *gin.Context) {
|
||||
},
|
||||
})
|
||||
|
||||
// Fire-and-forget: send A2A in background goroutine
|
||||
go h.executeDelegation(ctx, sourceID, body.TargetID, delegationID, a2aBody)
|
||||
// Fire-and-forget: send A2A in a background goroutine.
|
||||
//
|
||||
// internal#497 — the goroutine MUST NOT inherit the HTTP request's
|
||||
// cancellation. `ctx` here is c.Request.Context(); the handler returns
|
||||
// 202 a few lines below, which cancels that context immediately. Before
|
||||
// this fix (regression ce2db75f) executeDelegation ran on the
|
||||
// request-scoped ctx, so every DB op + proxy call in the detached
|
||||
// goroutine failed `context canceled` the instant the 202 was written.
|
||||
// That silently broke 100% of A2A peer delegations fleet-wide since
|
||||
// 2026-05-12 (poll-mode peers never got their a2a_receive inbox row;
|
||||
// lookupDeliveryMode swallowed the ctx error and defaulted to push).
|
||||
//
|
||||
// context.WithoutCancel detaches cancellation/deadline while PRESERVING
|
||||
// all context values (trace/correlation/tenant ids that proxyA2ARequest
|
||||
// and the broadcaster read off ctx) — this is the established pattern in
|
||||
// this package (a2a_proxy.go:850, a2a_proxy_helpers.go:525,
|
||||
// registry.go:822). The 30-minute ceiling matches the prior internal
|
||||
// budget executeDelegation used before ce2db75f and the proxy's own
|
||||
// absolute agent-dispatch ceiling (a2a_proxy.go forwardCtx).
|
||||
delegationCtx, cancelDelegation := context.WithTimeout(
|
||||
context.WithoutCancel(ctx), 30*time.Minute,
|
||||
)
|
||||
go func() {
|
||||
defer cancelDelegation()
|
||||
h.executeDelegation(delegationCtx, sourceID, body.TargetID, delegationID, a2aBody)
|
||||
}()
|
||||
|
||||
// Broadcast event so canvas shows delegation in real-time
|
||||
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventDelegationSent), sourceID, map[string]interface{}{
|
||||
|
||||
@@ -16,6 +16,65 @@ import (
|
||||
"github.com/gin-gonic/gin"
|
||||
)
|
||||
|
||||
// ---------- internal#497 regression: detached goroutine ctx must outlive the handler ----------
|
||||
|
||||
// TestDelegate_DetachedContext_SurvivesRequestCancellation pins the
|
||||
// load-bearing invariant that regression ce2db75f violated: the context
|
||||
// handed to executeDelegation in the fire-and-forget goroutine must NOT be
|
||||
// cancelled when the HTTP handler returns 202 (which cancels
|
||||
// c.Request.Context()). Before the fix, executeDelegation ran on the
|
||||
// request-scoped ctx, so every DB op + proxy call failed `context
|
||||
// canceled` the instant the 202 was written — silently breaking 100% of
|
||||
// A2A peer delegations fleet-wide since 2026-05-12.
|
||||
//
|
||||
// This test asserts the exact ctx-derivation contract used by Delegate
|
||||
// (context.WithoutCancel(parent) + a timeout budget): the derived context
|
||||
// (a) stays alive after the parent is cancelled, and (b) still carries
|
||||
// parent values (trace/correlation/tenant ids the downstream proxy +
|
||||
// broadcaster read off ctx). It is intentionally DB-free and fast.
|
||||
func TestDelegate_DetachedContext_SurvivesRequestCancellation(t *testing.T) {
|
||||
type ctxKey string
|
||||
const traceKey ctxKey = "trace-id"
|
||||
|
||||
// Simulate c.Request.Context() carrying a correlation value.
|
||||
parent, cancelParent := context.WithCancel(
|
||||
context.WithValue(context.Background(), traceKey, "trace-abc-123"),
|
||||
)
|
||||
|
||||
// Exact derivation Delegate uses for the detached goroutine.
|
||||
delegationCtx, cancelDelegation := context.WithTimeout(
|
||||
context.WithoutCancel(parent), 30*time.Minute,
|
||||
)
|
||||
defer cancelDelegation()
|
||||
|
||||
// The HTTP handler "returns 202" → request context is cancelled.
|
||||
cancelParent()
|
||||
|
||||
if err := parent.Err(); err == nil {
|
||||
t.Fatal("precondition: parent context should be cancelled after the handler returns")
|
||||
}
|
||||
|
||||
// (a) Cancellation MUST NOT propagate to the detached context.
|
||||
select {
|
||||
case <-delegationCtx.Done():
|
||||
t.Fatalf("regression: detached delegation ctx was cancelled by the handler returning (err=%v) — executeDelegation would fail every DB op with `context canceled`", delegationCtx.Err())
|
||||
default:
|
||||
// alive — correct
|
||||
}
|
||||
|
||||
// (b) Parent values MUST still be readable (WithoutCancel preserves
|
||||
// values; trace/correlation/tenant ids the proxy + broadcaster use).
|
||||
if got, _ := delegationCtx.Value(traceKey).(string); got != "trace-abc-123" {
|
||||
t.Errorf("detached ctx lost the parent trace value: got %q, want %q", got, "trace-abc-123")
|
||||
}
|
||||
|
||||
// And it still has a real deadline (the 30m budget), so it is not an
|
||||
// unbounded background context.
|
||||
if _, hasDeadline := delegationCtx.Deadline(); !hasDeadline {
|
||||
t.Error("detached ctx must carry the 30-minute timeout budget, but has no deadline")
|
||||
}
|
||||
}
|
||||
|
||||
// ---------- Delegate: missing target_id → 400 ----------
|
||||
|
||||
func TestDelegate_MissingTargetID(t *testing.T) {
|
||||
|
||||
@@ -0,0 +1,141 @@
|
||||
package handlers
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
|
||||
"github.com/gin-gonic/gin"
|
||||
)
|
||||
|
||||
func TestListRegistry_EmptyDir(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
h := NewPluginsHandler(dir, nil, nil)
|
||||
|
||||
got := h.listRegistryFiltered("")
|
||||
if len(got) != 0 {
|
||||
t.Errorf("expected empty list, got %d plugins", len(got))
|
||||
}
|
||||
}
|
||||
|
||||
func TestListRegistry_IgnoresFiles(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
if err := os.WriteFile(filepath.Join(dir, "not-a-plugin.txt"), []byte("x"), 0600); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
h := NewPluginsHandler(dir, nil, nil)
|
||||
|
||||
got := h.listRegistryFiltered("")
|
||||
if len(got) != 0 {
|
||||
t.Errorf("expected empty list (files ignored), got %d", len(got))
|
||||
}
|
||||
}
|
||||
|
||||
func TestListRegistry_SinglePlugin(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
pluginDir := filepath.Join(dir, "my-plugin")
|
||||
if err := os.Mkdir(pluginDir, 0755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := os.WriteFile(filepath.Join(pluginDir, "plugin.yaml"), []byte("name: my-plugin\nversion: 1.0.0\n"), 0600); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
h := NewPluginsHandler(dir, nil, nil)
|
||||
|
||||
got := h.listRegistryFiltered("")
|
||||
if len(got) != 1 {
|
||||
t.Fatalf("expected 1 plugin, got %d", len(got))
|
||||
}
|
||||
if got[0].Name != "my-plugin" {
|
||||
t.Errorf("expected name 'my-plugin', got %q", got[0].Name)
|
||||
}
|
||||
}
|
||||
|
||||
func TestListRegistry_FiltersByRuntime(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
for _, spec := range []struct{ name, yaml string }{
|
||||
{"runtime-a", "name: runtime-a\nruntimes:\n - claude-code\n"},
|
||||
{"runtime-b", "name: runtime-b\nruntimes:\n - hermes\n"},
|
||||
{"universal", "name: universal\nversion: 1.0.0\n"},
|
||||
} {
|
||||
pd := filepath.Join(dir, spec.name)
|
||||
if err := os.Mkdir(pd, 0755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := os.WriteFile(filepath.Join(pd, "plugin.yaml"), []byte(spec.yaml), 0600); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
h := NewPluginsHandler(dir, nil, nil)
|
||||
|
||||
// Filter to claude-code: runtime-a matches, universal (no runtimes field)
|
||||
// is always included per supportsRuntime semantics.
|
||||
got := h.listRegistryFiltered("claude-code")
|
||||
if len(got) != 2 {
|
||||
t.Fatalf("expected 2 (runtime-a + universal), got %d: %v", len(got), func() []string {
|
||||
ns := make([]string, len(got))
|
||||
for i, p := range got { ns[i] = p.Name }
|
||||
return ns
|
||||
}())
|
||||
}
|
||||
}
|
||||
|
||||
func TestListRegistry_PluginWithNoRuntimeDeclarations_AlwaysIncluded(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
pd := filepath.Join(dir, "universal-plugin")
|
||||
if err := os.Mkdir(pd, 0755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := os.WriteFile(filepath.Join(pd, "plugin.yaml"), []byte("name: universal-plugin\nversion: 1.0.0\n"), 0600); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
h := NewPluginsHandler(dir, nil, nil)
|
||||
|
||||
// When plugin declares no runtimes, it should always be included (try-it).
|
||||
got := h.listRegistryFiltered("any-runtime")
|
||||
if len(got) != 1 {
|
||||
t.Errorf("expected 1 plugin (unspecified runtime), got %d", len(got))
|
||||
}
|
||||
}
|
||||
|
||||
func TestListRegistry_ReadDirError_ReturnsEmpty(t *testing.T) {
|
||||
h := NewPluginsHandler("/nonexistent/path/for/plugins", nil, nil)
|
||||
got := h.listRegistryFiltered("")
|
||||
if len(got) != 0 {
|
||||
t.Errorf("expected empty list on ReadDir error, got %d", len(got))
|
||||
}
|
||||
}
|
||||
|
||||
func TestListRegistry_HTTPEndpoint(t *testing.T) {
|
||||
dir := t.TempDir()
|
||||
pd := filepath.Join(dir, "test-plugin")
|
||||
if err := os.Mkdir(pd, 0755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := os.WriteFile(filepath.Join(pd, "plugin.yaml"), []byte("name: test-plugin\nversion: 2.0.0\n"), 0600); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
h := NewPluginsHandler(dir, nil, nil)
|
||||
|
||||
w := httptest.NewRecorder()
|
||||
c, _ := gin.CreateTestContext(w)
|
||||
c.Request = httptest.NewRequest("GET", "/plugins", nil)
|
||||
h.ListRegistry(c)
|
||||
|
||||
if w.Code != http.StatusOK {
|
||||
t.Errorf("expected 200, got %d: %s", w.Code, w.Body.String())
|
||||
}
|
||||
var plugins []pluginInfo
|
||||
if err := json.Unmarshal(w.Body.Bytes(), &plugins); err != nil {
|
||||
t.Fatalf("failed to parse JSON: %v", err)
|
||||
}
|
||||
if len(plugins) != 1 {
|
||||
t.Errorf("expected 1 plugin, got %d", len(plugins))
|
||||
}
|
||||
if plugins[0].Name != "test-plugin" {
|
||||
t.Errorf("expected name 'test-plugin', got %q", plugins[0].Name)
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user