refactor(chat): route browser chat through one runtime
Co-Authored-By: Claude Opus 4.8 <[email protected]> Claude-Session: https://claude.ai/code/session_01ESFAnh2t9HmLwng8oW95St
This commit is contained in:
@@ -15,6 +15,9 @@ import type {
|
||||
CommandManifest,
|
||||
CommandManifestPayload,
|
||||
ErrorPayload,
|
||||
HarnessSelection,
|
||||
HarnessTurnAckPayload,
|
||||
HarnessTurnSendPayload,
|
||||
MessageAckPayload,
|
||||
RoutingDecisionInfo,
|
||||
ServerToClientEvents,
|
||||
@@ -42,6 +45,9 @@ export type {
|
||||
CommandManifest,
|
||||
CommandManifestPayload,
|
||||
ErrorPayload,
|
||||
HarnessSelection,
|
||||
HarnessTurnAckPayload,
|
||||
HarnessTurnSendPayload,
|
||||
MessageAckPayload,
|
||||
RoutingDecisionInfo,
|
||||
ServerToClientEvents,
|
||||
|
||||
@@ -1,8 +1,14 @@
|
||||
import { useState, type KeyboardEvent, type ReactElement } from 'react';
|
||||
import type { HarnessSelection } from '@/lib/types';
|
||||
import type { HarnessSelectionValue } from './use-harness-selection';
|
||||
|
||||
interface ComposerProps {
|
||||
onSend: (input: { content: string; provider?: string; modelId?: string }) => void;
|
||||
onSend: (input: {
|
||||
content: string;
|
||||
provider?: string;
|
||||
modelId?: string;
|
||||
selection: HarnessSelection;
|
||||
}) => boolean;
|
||||
onStop: () => void;
|
||||
streaming: boolean;
|
||||
/** True from local send time through server turn startup/ack and
|
||||
@@ -44,11 +50,23 @@ export function Composer({
|
||||
if (busy) return;
|
||||
// Send is gated on a validated, persisted catalog tuple — a draft or unset
|
||||
// selection can never emit, so provider/model never travel as free text.
|
||||
if (!harness.canSend) return;
|
||||
if (!harness.canSend || harness.persistedSelection === null) return;
|
||||
const trimmed = content.trim();
|
||||
if (!trimmed) return;
|
||||
onSend({ content: trimmed, ...harness.projection });
|
||||
setContent('');
|
||||
// Pass BOTH the nested selection tuple (the turn-runtime contract) and the
|
||||
// flat provider/modelId (the legacy first-send that creates the conversation)
|
||||
// — both derived from the same validated persisted tuple. The hook decides
|
||||
// which path applies from whether a conversation is already established.
|
||||
const selection = harness.persistedSelection;
|
||||
const ok = onSend({
|
||||
content: trimmed,
|
||||
selection,
|
||||
provider: selection.providerId,
|
||||
modelId: selection.modelId,
|
||||
});
|
||||
// Clear the input only when the send was accepted — a refused turn (e.g. a
|
||||
// failed idempotency mint) must retain the user's text so it is not lost.
|
||||
if (ok) setContent('');
|
||||
}
|
||||
|
||||
function handleKeyDown(event: KeyboardEvent<HTMLTextAreaElement>): void {
|
||||
|
||||
@@ -21,6 +21,7 @@ vi.mock('@/lib/socket', () => ({
|
||||
destroySocket: destroySocketMock,
|
||||
}));
|
||||
|
||||
import type { HarnessSelection } from '@mosaicstack/types';
|
||||
import { useChatConnection, type ChatConnectionValue } from './use-chat-connection';
|
||||
|
||||
let fake: ReturnType<typeof createFakeChatSocket>;
|
||||
@@ -33,6 +34,111 @@ function Harness(): null {
|
||||
return null;
|
||||
}
|
||||
|
||||
/**
|
||||
* Task Five, Step Two (web send path) red-first support. These probe the FUTURE
|
||||
* pi-rpc send contract against the CURRENT implementation, so the desired API is
|
||||
* expressed here as a localized cast — production types stay untouched until Step
|
||||
* Three. The reds fail on behaviour (legacy `message` emitted instead of
|
||||
* `turn:send`; no nested selection; no idempotency key; void return; no
|
||||
* conversation-id gating), never on a missing module or type.
|
||||
*/
|
||||
interface HarnessTurnSendInput {
|
||||
readonly content: string;
|
||||
readonly selection: HarnessSelection;
|
||||
}
|
||||
type HarnessSendMessage = (input: HarnessTurnSendInput) => boolean;
|
||||
|
||||
function harnessSend(): HarnessSendMessage {
|
||||
return latest?.actions.sendMessage as unknown as HarnessSendMessage;
|
||||
}
|
||||
|
||||
/**
|
||||
* Install a controllable `crypto.randomUUID` on the global crypto object and
|
||||
* return a restore fn. Uses defineProperty on the instance so it works whether
|
||||
* or not the native method is configurable (it lives on the prototype, so an own
|
||||
* property simply shadows it).
|
||||
*/
|
||||
function installRandomUUID(fn: () => string): () => void {
|
||||
const g = globalThis as { crypto?: { randomUUID?: () => string } };
|
||||
if (!g.crypto) {
|
||||
Object.defineProperty(g, 'crypto', { configurable: true, writable: true, value: {} });
|
||||
}
|
||||
const cryptoObj = g.crypto as { randomUUID?: () => string };
|
||||
const original = Object.getOwnPropertyDescriptor(cryptoObj, 'randomUUID');
|
||||
Object.defineProperty(cryptoObj, 'randomUUID', {
|
||||
configurable: true,
|
||||
writable: true,
|
||||
value: fn,
|
||||
});
|
||||
return () => {
|
||||
if (original) {
|
||||
Object.defineProperty(cryptoObj, 'randomUUID', original);
|
||||
} else {
|
||||
Reflect.deleteProperty(cryptoObj, 'randomUUID');
|
||||
}
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Force `crypto.randomUUID` to read as ABSENT by shadowing it with an own
|
||||
* `undefined` property. The native method lives on `Crypto.prototype`, so a
|
||||
* bare delete of the (non-existent) own property would leave the inherited
|
||||
* method visible — the shadow is what actually makes the call site see no
|
||||
* secure generator. Returns a restore fn.
|
||||
*/
|
||||
function removeRandomUUID(): () => void {
|
||||
const g = globalThis as { crypto?: { randomUUID?: () => string } };
|
||||
if (!g.crypto) {
|
||||
Object.defineProperty(g, 'crypto', { configurable: true, writable: true, value: {} });
|
||||
}
|
||||
const cryptoObj = g.crypto as { randomUUID?: () => string };
|
||||
const original = Object.getOwnPropertyDescriptor(cryptoObj, 'randomUUID');
|
||||
Object.defineProperty(cryptoObj, 'randomUUID', {
|
||||
configurable: true,
|
||||
writable: true,
|
||||
value: undefined,
|
||||
});
|
||||
return () => {
|
||||
if (original) {
|
||||
Object.defineProperty(cryptoObj, 'randomUUID', original);
|
||||
} else {
|
||||
Reflect.deleteProperty(cryptoObj, 'randomUUID');
|
||||
}
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Task Five, Step Two group 4/5 support — the FUTURE `turn:ack` receipt surface
|
||||
* and the FUTURE fixed idempotency/rejection notice, expressed as a localized
|
||||
* read-only view over `state`. Production `ChatConnectionState` gains
|
||||
* `turnReceipt` at Step Three; the cast keeps production types untouched until
|
||||
* then, so a success assertion against it fails on BEHAVIOUR (no turn:ack
|
||||
* handler runs), never on a missing module. `error` already exists on state.
|
||||
*/
|
||||
interface HarnessTurnReceiptView {
|
||||
readonly idempotencyKey: string;
|
||||
readonly receiptId: string;
|
||||
readonly selection: HarnessSelection;
|
||||
}
|
||||
interface HarnessTurnStateView {
|
||||
readonly turnReceipt: HarnessTurnReceiptView | null | undefined;
|
||||
readonly error: string | null;
|
||||
}
|
||||
function harnessTurnState(): HarnessTurnStateView {
|
||||
return latest?.state as unknown as HarnessTurnStateView;
|
||||
}
|
||||
|
||||
/**
|
||||
* Emit a server `turn:ack` the CURRENT hook has no listener for — a safe no-op
|
||||
* today (the fake iterates an empty handler set), so the group-4 reds fail
|
||||
* because nothing is surfaced, not because this throws. The event name is cast
|
||||
* past the compile-time `ServerToClientEvents` contract exactly as the
|
||||
* `turn:send` client cast is; the typed event map lands at Step Three.
|
||||
*/
|
||||
function serverEmitTurnAck(payload: unknown): void {
|
||||
fake.serverEmitRaw('turn:ack' as unknown as Parameters<typeof fake.serverEmitRaw>[0], payload);
|
||||
}
|
||||
|
||||
beforeAll(() => {
|
||||
Object.defineProperty(globalThis, 'IS_REACT_ACT_ENVIRONMENT', {
|
||||
configurable: true,
|
||||
@@ -373,6 +479,371 @@ describe('useChatConnection', () => {
|
||||
});
|
||||
});
|
||||
|
||||
describe('turn:send harness routing (Task Five, Step Two red-first)', () => {
|
||||
const selection: HarnessSelection = {
|
||||
harnessId: 'pi',
|
||||
providerId: 'anthropic',
|
||||
modelId: 'claude',
|
||||
};
|
||||
const UUID = 'aaaaaaaa-aaaa-4aaa-8aaa-aaaaaaaaaaaa';
|
||||
|
||||
async function establishConversation(): Promise<void> {
|
||||
await act(async () => {
|
||||
fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
|
||||
});
|
||||
}
|
||||
|
||||
it('emits a single turn:send with the nested selection tuple and a UUID idempotencyKey — never the legacy message event', async () => {
|
||||
const restore = installRandomUUID(() => UUID);
|
||||
try {
|
||||
await establishConversation();
|
||||
await act(async () => {
|
||||
harnessSend()({ content: 'hello', selection });
|
||||
});
|
||||
} finally {
|
||||
restore();
|
||||
}
|
||||
|
||||
const sends = fake.emitted.filter((e) => e.event === 'turn:send');
|
||||
expect(sends).toHaveLength(1);
|
||||
expect(sends[0]?.payload).toEqual({
|
||||
conversationId: 'c1',
|
||||
content: 'hello',
|
||||
selection,
|
||||
idempotencyKey: UUID,
|
||||
});
|
||||
// The pi-rpc sender must not fall back to the embedded `message` event.
|
||||
expect(fake.emitted.some((e) => e.event === 'message')).toBe(false);
|
||||
});
|
||||
|
||||
it('generates the idempotencyKey with exactly one crypto.randomUUID() call per accepted send', async () => {
|
||||
const gen = vi.fn(() => UUID);
|
||||
const restore = installRandomUUID(gen);
|
||||
try {
|
||||
await establishConversation();
|
||||
await act(async () => {
|
||||
harnessSend()({ content: 'first', selection });
|
||||
});
|
||||
await act(async () => {
|
||||
harnessSend()({ content: 'second', selection });
|
||||
});
|
||||
} finally {
|
||||
restore();
|
||||
}
|
||||
|
||||
expect(gen).toHaveBeenCalledTimes(2);
|
||||
const keys = fake.emitted
|
||||
.filter((e) => e.event === 'turn:send')
|
||||
.map((e) => (e.payload as { idempotencyKey: string }).idempotencyKey);
|
||||
expect(keys).toEqual([UUID, UUID]);
|
||||
});
|
||||
|
||||
it('does not send before an active conversation id exists (no first-send auto-create)', async () => {
|
||||
const restore = installRandomUUID(() => UUID);
|
||||
let returned: boolean | undefined;
|
||||
try {
|
||||
await act(async () => {
|
||||
returned = harnessSend()({ content: 'too early', selection });
|
||||
});
|
||||
} finally {
|
||||
restore();
|
||||
}
|
||||
|
||||
expect(returned).toBe(false);
|
||||
expect(fake.emitted.some((e) => e.event === 'turn:send')).toBe(false);
|
||||
expect(fake.emitted.some((e) => e.event === 'message')).toBe(false);
|
||||
// Nothing optimistically appended when the send is refused.
|
||||
expect(latest?.state.messages.some((m) => m.text === 'too early')).toBe(false);
|
||||
});
|
||||
|
||||
it('returns true when it emits and false when the send is refused', async () => {
|
||||
const restore = installRandomUUID(() => UUID);
|
||||
let refusedEarly: boolean | undefined;
|
||||
let acceptedAfter: boolean | undefined;
|
||||
try {
|
||||
await act(async () => {
|
||||
refusedEarly = harnessSend()({ content: 'early', selection });
|
||||
});
|
||||
await establishConversation();
|
||||
await act(async () => {
|
||||
acceptedAfter = harnessSend()({ content: 'now', selection });
|
||||
});
|
||||
} finally {
|
||||
restore();
|
||||
}
|
||||
|
||||
expect(refusedEarly).toBe(false);
|
||||
expect(acceptedAfter).toBe(true);
|
||||
});
|
||||
|
||||
it('when secure UUID generation throws: emits nothing, appends nothing, releases the lock, and a later send succeeds', async () => {
|
||||
await establishConversation();
|
||||
|
||||
const failing = installRandomUUID(() => {
|
||||
throw new Error('secure random unavailable');
|
||||
});
|
||||
let firstReturn: boolean | undefined;
|
||||
try {
|
||||
await act(async () => {
|
||||
firstReturn = harnessSend()({ content: 'blocked', selection });
|
||||
});
|
||||
} finally {
|
||||
failing();
|
||||
}
|
||||
|
||||
expect(firstReturn).toBe(false);
|
||||
expect(fake.emitted.some((e) => e.event === 'turn:send')).toBe(false);
|
||||
expect(latest?.state.messages.some((m) => m.text === 'blocked')).toBe(false);
|
||||
|
||||
// The send lock must have been released, so a subsequent valid send works.
|
||||
const restore = installRandomUUID(() => UUID);
|
||||
let secondReturn: boolean | undefined;
|
||||
try {
|
||||
await act(async () => {
|
||||
secondReturn = harnessSend()({ content: 'retry', selection });
|
||||
});
|
||||
} finally {
|
||||
restore();
|
||||
}
|
||||
|
||||
expect(secondReturn).toBe(true);
|
||||
expect(fake.emitted.some((e) => e.event === 'turn:send')).toBe(true);
|
||||
});
|
||||
});
|
||||
|
||||
describe('turn:ack receipt + rejection contract (Task Five, Step Two group 4)', () => {
|
||||
const selection: HarnessSelection = {
|
||||
harnessId: 'pi',
|
||||
providerId: 'anthropic',
|
||||
modelId: 'claude',
|
||||
};
|
||||
const UUID = 'aaaaaaaa-aaaa-4aaa-8aaa-aaaaaaaaaaaa';
|
||||
|
||||
// Establish the conversation and send one accepted turn under a controlled
|
||||
// idempotency key. Returns the crypto restore fn so callers unwind it.
|
||||
async function establishAndSend(): Promise<() => void> {
|
||||
const restore = installRandomUUID(() => UUID);
|
||||
await act(async () => {
|
||||
fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
|
||||
});
|
||||
await act(async () => {
|
||||
harnessSend()({ content: 'hello', selection });
|
||||
});
|
||||
return restore;
|
||||
}
|
||||
|
||||
it('surfaces a turn:ack receipt echoing the exact idempotencyKey, server receiptId, and requested selection tuple', async () => {
|
||||
const restore = await establishAndSend();
|
||||
try {
|
||||
await act(async () => {
|
||||
serverEmitTurnAck({
|
||||
conversationId: 'c1',
|
||||
idempotencyKey: UUID,
|
||||
receiptId: 'r1',
|
||||
selection,
|
||||
});
|
||||
});
|
||||
} finally {
|
||||
restore();
|
||||
}
|
||||
|
||||
// RED anchor: no turn:ack handler exists, so nothing is recorded. Green
|
||||
// only when Step Three echoes the exact tuple back into state — never a
|
||||
// substituted or fabricated one.
|
||||
expect(harnessTurnState().turnReceipt).toEqual({
|
||||
idempotencyKey: UUID,
|
||||
receiptId: 'r1',
|
||||
selection,
|
||||
});
|
||||
});
|
||||
|
||||
it('on a rejected turn:ack surfaces a visible safe notice, never the raw internal error, and fabricates no receipt tuple', async () => {
|
||||
const restore = await establishAndSend();
|
||||
try {
|
||||
await act(async () => {
|
||||
serverEmitTurnAck({
|
||||
conversationId: 'c1',
|
||||
idempotencyKey: UUID,
|
||||
ok: false,
|
||||
code: 'runtime_unsupported',
|
||||
error: 'ADAPTER_BOOM internal stack: pi adapter unavailable at 0xdeadbeef',
|
||||
});
|
||||
});
|
||||
} finally {
|
||||
restore();
|
||||
}
|
||||
|
||||
// RED anchor: a rejected ack must surface a visible notice; today no
|
||||
// handler runs, so state.error stays null.
|
||||
expect(harnessTurnState().error).toBeTruthy();
|
||||
// The raw internal exception text must never reach the browser surface.
|
||||
expect(harnessTurnState().error ?? '').not.toContain('ADAPTER_BOOM');
|
||||
expect(harnessTurnState().error ?? '').not.toContain('0xdeadbeef');
|
||||
// A rejection must not fabricate a success receipt tuple.
|
||||
expect(harnessTurnState().turnReceipt ?? null).toBeNull();
|
||||
});
|
||||
|
||||
it('uses one fixed safe rejection notice regardless of the internal cause (frozen union, not a passthrough)', async () => {
|
||||
const firstRestore = await establishAndSend();
|
||||
try {
|
||||
await act(async () => {
|
||||
serverEmitTurnAck({
|
||||
conversationId: 'c1',
|
||||
idempotencyKey: UUID,
|
||||
ok: false,
|
||||
code: 'runtime_unsupported',
|
||||
error: 'cause-ALPHA adapter_unavailable',
|
||||
});
|
||||
});
|
||||
} finally {
|
||||
firstRestore();
|
||||
}
|
||||
const firstNotice = harnessTurnState().error;
|
||||
|
||||
// A fresh turn on the same conversation, rejected for a DIFFERENT internal
|
||||
// reason, must surface the identical fixed notice.
|
||||
const secondRestore = installRandomUUID(() => UUID);
|
||||
try {
|
||||
await act(async () => {
|
||||
harnessSend()({ content: 'again', selection });
|
||||
});
|
||||
await act(async () => {
|
||||
serverEmitTurnAck({
|
||||
conversationId: 'c1',
|
||||
idempotencyKey: UUID,
|
||||
ok: false,
|
||||
code: 'runtime_unsupported',
|
||||
error: 'cause-BRAVO conversation_service_unavailable',
|
||||
});
|
||||
});
|
||||
} finally {
|
||||
secondRestore();
|
||||
}
|
||||
const secondNotice = harnessTurnState().error;
|
||||
|
||||
// RED anchor: both are null today; green requires a single frozen safe
|
||||
// string surfaced for both distinct internal causes.
|
||||
expect(firstNotice).toBeTruthy();
|
||||
expect(secondNotice).toBeTruthy();
|
||||
expect(firstNotice).toBe(secondNotice);
|
||||
expect(firstNotice ?? '').not.toContain('ALPHA');
|
||||
expect(secondNotice ?? '').not.toContain('BRAVO');
|
||||
});
|
||||
});
|
||||
|
||||
describe('idempotency-key failure semantics (Task Five, Step Two group 5)', () => {
|
||||
const selection: HarnessSelection = {
|
||||
harnessId: 'pi',
|
||||
providerId: 'anthropic',
|
||||
modelId: 'claude',
|
||||
};
|
||||
const UUID_A = '11111111-1111-4111-8111-111111111111';
|
||||
const UUID_B = '22222222-2222-4222-9222-222222222222';
|
||||
const UUID_V4 = /^[0-9a-f]{8}-[0-9a-f]{4}-4[0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$/i;
|
||||
|
||||
async function establish(): Promise<void> {
|
||||
await act(async () => {
|
||||
fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
|
||||
});
|
||||
}
|
||||
|
||||
it('mints a DISTINCT UUID-v4 idempotencyKey for each of two accepted turns — a key is never reused across turns', async () => {
|
||||
const keys = [UUID_A, UUID_B];
|
||||
let call = 0;
|
||||
const restore = installRandomUUID(() => keys[call++] ?? UUID_A);
|
||||
try {
|
||||
await establish();
|
||||
await act(async () => {
|
||||
harnessSend()({ content: 'first', selection });
|
||||
});
|
||||
await act(async () => {
|
||||
harnessSend()({ content: 'second', selection });
|
||||
});
|
||||
} finally {
|
||||
restore();
|
||||
}
|
||||
|
||||
const sent = fake.emitted
|
||||
.filter((e) => e.event === 'turn:send')
|
||||
.map((e) => (e.payload as { idempotencyKey: string }).idempotencyKey);
|
||||
// RED anchor: current sendMessage emits the legacy `message`, so no
|
||||
// turn:send keys exist at all.
|
||||
expect(sent).toHaveLength(2);
|
||||
expect(sent[0]).toMatch(UUID_V4);
|
||||
expect(sent[1]).toMatch(UUID_V4);
|
||||
expect(sent[0]).not.toBe(sent[1]);
|
||||
});
|
||||
|
||||
it('when crypto.randomUUID is ABSENT: surfaces a visible fixed idempotency-unavailable notice, emits nothing, appends nothing, releases the lock synchronously, and a later valid send succeeds', async () => {
|
||||
await establish();
|
||||
|
||||
const restoreCrypto = removeRandomUUID();
|
||||
let firstReturn: boolean | undefined;
|
||||
try {
|
||||
await act(async () => {
|
||||
firstReturn = harnessSend()({ content: 'no-secure-random', selection });
|
||||
});
|
||||
} finally {
|
||||
restoreCrypto();
|
||||
}
|
||||
|
||||
// RED anchors: a refused send returns false and surfaces a visible notice.
|
||||
expect(firstReturn).toBe(false);
|
||||
expect(harnessTurnState().error).toBeTruthy();
|
||||
expect(fake.emitted.some((e) => e.event === 'turn:send')).toBe(false);
|
||||
expect(latest?.state.messages.some((m) => m.text === 'no-secure-random')).toBe(false);
|
||||
|
||||
// The lock released synchronously (no server event needed): a later valid
|
||||
// send goes through.
|
||||
const restore = installRandomUUID(() => UUID_A);
|
||||
let secondReturn: boolean | undefined;
|
||||
try {
|
||||
await act(async () => {
|
||||
secondReturn = harnessSend()({ content: 'recovered', selection });
|
||||
});
|
||||
} finally {
|
||||
restore();
|
||||
}
|
||||
expect(secondReturn).toBe(true);
|
||||
expect(fake.emitted.some((e) => e.event === 'turn:send')).toBe(true);
|
||||
});
|
||||
|
||||
it('surfaces the SAME fixed idempotency-unavailable notice whether randomUUID is absent or throws, never leaking the thrown message', async () => {
|
||||
// Case 1: absent.
|
||||
await establish();
|
||||
const restoreAbsent = removeRandomUUID();
|
||||
try {
|
||||
await act(async () => {
|
||||
harnessSend()({ content: 'absent', selection });
|
||||
});
|
||||
} finally {
|
||||
restoreAbsent();
|
||||
}
|
||||
const absentNotice = harnessTurnState().error;
|
||||
|
||||
// Case 2: throws with a distinctive internal message.
|
||||
const failing = installRandomUUID(() => {
|
||||
throw new Error('SECURE_RANDOM_BOOM entropy pool drained');
|
||||
});
|
||||
try {
|
||||
await act(async () => {
|
||||
harnessSend()({ content: 'throws', selection });
|
||||
});
|
||||
} finally {
|
||||
failing();
|
||||
}
|
||||
const throwNotice = harnessTurnState().error;
|
||||
|
||||
// RED anchor: both are null today.
|
||||
expect(absentNotice).toBeTruthy();
|
||||
expect(throwNotice).toBeTruthy();
|
||||
expect(absentNotice).toBe(throwNotice);
|
||||
// The thrown internal detail must never reach the browser surface.
|
||||
expect(throwNotice ?? '').not.toContain('SECURE_RANDOM_BOOM');
|
||||
expect(throwNotice ?? '').not.toContain('entropy pool');
|
||||
});
|
||||
});
|
||||
|
||||
it('abort emits abort with the active conversationId', async () => {
|
||||
await act(async () => {
|
||||
fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
|
||||
|
||||
@@ -12,6 +12,7 @@ import {
|
||||
import {
|
||||
asConversationId,
|
||||
asFiniteNumber,
|
||||
asHarnessSelection,
|
||||
asString,
|
||||
asStringArray,
|
||||
isRecord,
|
||||
@@ -25,6 +26,8 @@ import type {
|
||||
CommandManifest,
|
||||
CommandManifestPayload,
|
||||
ErrorPayload,
|
||||
HarnessSelection,
|
||||
HarnessTurnAckPayload,
|
||||
MessageAckPayload,
|
||||
SessionInfoPayload,
|
||||
SessionUsagePayload,
|
||||
@@ -130,6 +133,34 @@ const CONVERSATION_START_FAILURE = 'Unable to start this conversation. Please tr
|
||||
* dropped. */
|
||||
const APPROVAL_LIMIT_MESSAGE = 'Approval limit reached for this session. This command was not run.';
|
||||
|
||||
/** Fixed, browser-safe notice surfaced when the harness runtime rejects a turn
|
||||
* (`turn:ack` with `ok:false`). It is deliberately generic: the raw server
|
||||
* `code`/`message`/`error` can carry adapter internals or entropy-source detail,
|
||||
* so no rejection ever leaks its cause into the UI — every distinct rejection
|
||||
* shows this same string. */
|
||||
const TURN_REJECTED_NOTICE = 'This turn could not be sent. Please try again.';
|
||||
|
||||
/** Fixed, browser-safe notice surfaced when a turn is refused because the
|
||||
* idempotency-key mint failed closed (`crypto.randomUUID` absent or throwing).
|
||||
* Like {@link TURN_REJECTED_NOTICE}, it never carries the thrown message. */
|
||||
const IDEMPOTENCY_UNAVAILABLE_NOTICE = 'This turn could not be sent. Please try again.';
|
||||
|
||||
/** Mints a single idempotency key for one accepted `turn:send`, fail-closed.
|
||||
* Returns a fresh RFC-4122 UUID from `crypto.randomUUID`, or `null` when that
|
||||
* source is absent (not a function) or throws — the caller then refuses the turn
|
||||
* rather than falling back to any non-cryptographic source (Math.random, a
|
||||
* clock, or a counter would all be forgeable/collision-prone). Never throws. */
|
||||
function mintIdempotencyKey(): string | null {
|
||||
try {
|
||||
const c: unknown = globalThis.crypto;
|
||||
if (!isRecord(c) || typeof c.randomUUID !== 'function') return null;
|
||||
const key = (c.randomUUID as () => unknown)();
|
||||
return typeof key === 'string' && key.length > 0 ? key : null;
|
||||
} catch {
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
/** True only for the narrow case a malformed-conversationId `error`/`agent:end`
|
||||
* must be treated as a terminal startup failure: no conversation has ever been
|
||||
* established yet, and a send is still pending one. Once a conversation is
|
||||
@@ -236,6 +267,14 @@ export interface PendingApproval {
|
||||
args?: string;
|
||||
}
|
||||
|
||||
/** Receipt captured from an accepted harness `turn:ack` — the minimal record proving the
|
||||
* server accepted this exact turn under its minted idempotency key and selection tuple. */
|
||||
export interface HarnessTurnReceipt {
|
||||
idempotencyKey: string;
|
||||
receiptId: string;
|
||||
selection: HarnessSelection;
|
||||
}
|
||||
|
||||
export interface ChatConnectionState {
|
||||
conversationId: string | null;
|
||||
/** True once a message has been sent while no conversation is active yet, so the
|
||||
@@ -268,6 +307,10 @@ export interface ChatConnectionState {
|
||||
approvalRequestPending: boolean;
|
||||
systemReload: SystemReloadPayload | null;
|
||||
error: string | null;
|
||||
/** Receipt from the most recently accepted harness `turn:ack`, or null before any
|
||||
* turn has been accepted. A rejected turn:ack surfaces via `error` and leaves this
|
||||
* untouched (a prior accepted receipt is not erased by a later rejection). */
|
||||
turnReceipt: HarnessTurnReceipt | null;
|
||||
messages: ChatTranscriptMessage[];
|
||||
/** Monotonically increasing counter used to mint transcript message ids —
|
||||
* never reset while retained messages remain, so ids stay unique across the
|
||||
@@ -308,7 +351,12 @@ export interface ChatConnectionState {
|
||||
}
|
||||
|
||||
export interface ChatConnectionActions {
|
||||
sendMessage: (input: { content: string; provider?: string; modelId?: string }) => void;
|
||||
sendMessage: (input: {
|
||||
content: string;
|
||||
provider?: string;
|
||||
modelId?: string;
|
||||
selection?: HarnessSelection;
|
||||
}) => boolean;
|
||||
abort: () => void;
|
||||
setThinking: (level: string) => void;
|
||||
executeCommand: (input: { command: string; args?: string }) => void;
|
||||
@@ -341,6 +389,7 @@ const initialState: ChatConnectionState = {
|
||||
approvalRequestPending: false,
|
||||
systemReload: null,
|
||||
error: null,
|
||||
turnReceipt: null,
|
||||
messages: [],
|
||||
messageSeq: 0,
|
||||
toolSeq: 0,
|
||||
@@ -361,7 +410,9 @@ type Action =
|
||||
| { type: 'server/command:approval'; payload: SlashCommandApprovalResultPayload }
|
||||
| { type: 'server/system:reload'; payload: SystemReloadPayload }
|
||||
| { type: 'server/error'; payload: ErrorPayload }
|
||||
| { type: 'server/turn:ack'; payload: HarnessTurnAckPayload }
|
||||
| { type: 'local/send'; content: string }
|
||||
| { type: 'local/turn-idempotency-unavailable' }
|
||||
| { type: 'local/approve-request'; command: string; args?: string }
|
||||
| { type: 'local/consume-approval' }
|
||||
| { type: 'local/approval-saturated' }
|
||||
@@ -778,6 +829,30 @@ function reduce(state: ChatConnectionState, action: Action): ChatConnectionState
|
||||
};
|
||||
}
|
||||
|
||||
case 'server/turn:ack': {
|
||||
// The harness runtime's turn acknowledgement. The success shape carries a
|
||||
// receipt id + minted idempotencyKey + echoed selection; the failure shape
|
||||
// is discriminated on `ok === false`. Every field is runtime-untrusted (the
|
||||
// top-of-reducer guard already rejected a non-object payload).
|
||||
const record = action.payload as Record<string, unknown>;
|
||||
if (record.ok === false) {
|
||||
// A rejected turn surfaces a FIXED browser-safe notice — never the raw
|
||||
// server `message`/`error`/`code`, which can carry adapter internals — and
|
||||
// does not disturb any previously accepted receipt.
|
||||
return { ...state, error: TURN_REJECTED_NOTICE };
|
||||
}
|
||||
const idempotencyKey = asString(record.idempotencyKey);
|
||||
// The web ack uses `receiptId`; fall back to the frozen contract's `turnId`.
|
||||
const receiptId = asString(record.receiptId) || asString(record.turnId);
|
||||
const selection = asHarnessSelection(record.selection);
|
||||
if (idempotencyKey.length === 0 || receiptId.length === 0 || selection === null) {
|
||||
// A malformed success frame is ignored outright rather than recorded as a
|
||||
// half-populated receipt.
|
||||
return state;
|
||||
}
|
||||
return { ...state, turnReceipt: { idempotencyKey, receiptId, selection } };
|
||||
}
|
||||
|
||||
case 'local/send': {
|
||||
const message: ChatTranscriptMessage = {
|
||||
// Sourced from the reducer-owned `messageSeq` counter — see the
|
||||
@@ -802,6 +877,14 @@ function reduce(state: ChatConnectionState, action: Action): ChatConnectionState
|
||||
};
|
||||
}
|
||||
|
||||
case 'local/turn-idempotency-unavailable': {
|
||||
// The idempotency-key mint failed closed (crypto.randomUUID absent or
|
||||
// throwing), so the turn was refused before emit. Surface a FIXED notice —
|
||||
// never the underlying thrown message, which can leak entropy-source
|
||||
// internals.
|
||||
return { ...state, error: IDEMPOTENCY_UNAVAILABLE_NOTICE };
|
||||
}
|
||||
|
||||
case 'local/disconnect': {
|
||||
// A transient socket disconnect must not leave the UI stuck waiting on
|
||||
// a turn/approval/send that will never resolve on this connection.
|
||||
@@ -913,6 +996,8 @@ export function useChatConnection(): ChatConnectionValue {
|
||||
const onError = (payload: ErrorPayload): void => {
|
||||
dispatch({ type: 'server/error', payload });
|
||||
};
|
||||
const onTurnAck = (payload: HarnessTurnAckPayload): void =>
|
||||
dispatch({ type: 'server/turn:ack', payload });
|
||||
const onDisconnect = (): void => {
|
||||
dispatch({ type: 'local/disconnect' });
|
||||
};
|
||||
@@ -930,6 +1015,7 @@ export function useChatConnection(): ChatConnectionValue {
|
||||
socket.on('command:approval', onCommandApproval);
|
||||
socket.on('system:reload', onSystemReload);
|
||||
socket.on('error', onError);
|
||||
socket.on('turn:ack', onTurnAck);
|
||||
socket.on('disconnect', onDisconnect);
|
||||
|
||||
if (!socket.connected) {
|
||||
@@ -950,14 +1036,44 @@ export function useChatConnection(): ChatConnectionValue {
|
||||
socket.off('command:approval', onCommandApproval);
|
||||
socket.off('system:reload', onSystemReload);
|
||||
socket.off('error', onError);
|
||||
socket.off('turn:ack', onTurnAck);
|
||||
socket.off('disconnect', onDisconnect);
|
||||
destroySocket();
|
||||
};
|
||||
}, []);
|
||||
|
||||
const actions: ChatConnectionActions = {
|
||||
sendMessage: ({ content, provider, modelId }) => {
|
||||
if (sendLockRef.current || state.streaming || state.sending) return;
|
||||
sendMessage: ({ content, provider, modelId, selection }) => {
|
||||
// Turn-runtime path: a selection tuple against an already-established
|
||||
// conversation routes through the exclusive `turn:send` contract. It is
|
||||
// lock-independent by design — it does not engage the send lock, does not
|
||||
// dispatch `local/send` (no optimistic append), and mints exactly one
|
||||
// idempotency key per accepted turn. A failed mint fails the turn closed.
|
||||
if (selection != null && state.conversationId !== null) {
|
||||
const idempotencyKey = mintIdempotencyKey();
|
||||
if (idempotencyKey === null) {
|
||||
dispatch({ type: 'local/turn-idempotency-unavailable' });
|
||||
return false;
|
||||
}
|
||||
const socket = getSocket();
|
||||
if (!socket.connected) socket.connect();
|
||||
socket.emit('turn:send', {
|
||||
conversationId: state.conversationId,
|
||||
content,
|
||||
selection,
|
||||
idempotencyKey,
|
||||
});
|
||||
return true;
|
||||
}
|
||||
// A selection tuple with no active conversation and no flat provider/model
|
||||
// is a bare harness call that cannot create a conversation — refuse it,
|
||||
// emitting nothing and appending nothing.
|
||||
if (selection != null && provider === undefined && modelId === undefined) {
|
||||
return false;
|
||||
}
|
||||
// Legacy `message` path (first send that creates the conversation, and every
|
||||
// pre-turn-runtime send) — unchanged behavior, now reporting acceptance.
|
||||
if (sendLockRef.current || state.streaming || state.sending) return false;
|
||||
sendLockRef.current = true;
|
||||
const socket = getSocket();
|
||||
if (!socket.connected) socket.connect();
|
||||
@@ -968,6 +1084,7 @@ export function useChatConnection(): ChatConnectionValue {
|
||||
provider,
|
||||
modelId,
|
||||
});
|
||||
return true;
|
||||
},
|
||||
|
||||
abort: () => {
|
||||
|
||||
@@ -226,7 +226,10 @@ describe('useHarnessSelection', () => {
|
||||
modelId: 'gpt-5',
|
||||
});
|
||||
expect(value().canSend).toBe(true);
|
||||
expect(value().projection).toEqual({ provider: 'openai', modelId: 'gpt-5' });
|
||||
// Task Five: the composer sends the nested `persistedSelection` tuple directly.
|
||||
// The Task-Four compat flat `projection` ({provider, modelId}) is removed — the
|
||||
// harnessId must never be dropped on the way to the wire.
|
||||
expect('projection' in value()).toBe(false);
|
||||
});
|
||||
|
||||
it('keeps a stale/unavailable persisted selection visibly displayed rather than silently dropping it', async () => {
|
||||
@@ -386,7 +389,8 @@ describe('useHarnessSelection', () => {
|
||||
providerId: 'anthropic',
|
||||
modelId: 'claude',
|
||||
});
|
||||
expect(value().projection).toEqual({ provider: 'anthropic', modelId: 'claude' });
|
||||
// Task Five: no compat flat projection — the nested persistedSelection is the wire tuple.
|
||||
expect('projection' in value()).toBe(false);
|
||||
});
|
||||
|
||||
it('does not enable send on a model pick until the PUT for that exact new tuple resolves', async () => {
|
||||
@@ -420,7 +424,8 @@ describe('useHarnessSelection', () => {
|
||||
});
|
||||
await flush();
|
||||
expect(value().canSend).toBe(true);
|
||||
expect(value().projection).toEqual({ provider: 'anthropic', modelId: 'claude' });
|
||||
// Task Five: no compat flat projection — the nested persistedSelection is the wire tuple.
|
||||
expect('projection' in value()).toBe(false);
|
||||
});
|
||||
|
||||
it('never requests any /api/providers* endpoint across the whole flow', async () => {
|
||||
|
||||
@@ -42,10 +42,6 @@ export interface HarnessSelectionValue {
|
||||
* resolves the composite option identity to the real entry and passes both
|
||||
* ids, so a bare model id is never combined with ambient provider state. */
|
||||
selectModel: (providerId: string, modelId: string) => void;
|
||||
/** The compatibility `{provider, modelId}` projection for the legacy socket
|
||||
* send path — derived ONLY from the validated persisted tuple, never from any
|
||||
* free-text or unpersisted draft. Empty when nothing is sendable. */
|
||||
projection: { provider?: string; modelId?: string };
|
||||
}
|
||||
|
||||
/** A tuple is a currently-usable catalog option only when the catalog holds a
|
||||
@@ -193,9 +189,6 @@ export function useHarnessSelection(): HarnessSelectionValue {
|
||||
!catalogUnavailable &&
|
||||
tuplesEqual(draft, persistedSelection) &&
|
||||
isAvailableInCatalog(persistedSelection, catalog);
|
||||
const projection: { provider?: string; modelId?: string } = canSend
|
||||
? { provider: persistedSelection.providerId, modelId: persistedSelection.modelId }
|
||||
: {};
|
||||
|
||||
return {
|
||||
harnesses,
|
||||
@@ -211,6 +204,5 @@ export function useHarnessSelection(): HarnessSelectionValue {
|
||||
selectHarness,
|
||||
selectProvider,
|
||||
selectModel,
|
||||
projection,
|
||||
};
|
||||
}
|
||||
|
||||
@@ -108,6 +108,33 @@ async function flushAsync(times = 5): Promise<void> {
|
||||
}
|
||||
}
|
||||
|
||||
/** Deterministic idempotency key for the Task Five red-first page send test. */
|
||||
const PAGE_UUID = 'bbbbbbbb-bbbb-4bbb-8bbb-bbbbbbbbbbbb';
|
||||
|
||||
/** Install a controllable `crypto.randomUUID` and return a restore fn. Uses
|
||||
* defineProperty on the crypto instance so it works whether or not the native
|
||||
* method is configurable (it lives on the prototype; an own property shadows it). */
|
||||
function installRandomUUID(fn: () => string): () => void {
|
||||
const g = globalThis as { crypto?: { randomUUID?: () => string } };
|
||||
if (!g.crypto) {
|
||||
Object.defineProperty(g, 'crypto', { configurable: true, writable: true, value: {} });
|
||||
}
|
||||
const cryptoObj = g.crypto as { randomUUID?: () => string };
|
||||
const original = Object.getOwnPropertyDescriptor(cryptoObj, 'randomUUID');
|
||||
Object.defineProperty(cryptoObj, 'randomUUID', {
|
||||
configurable: true,
|
||||
writable: true,
|
||||
value: fn,
|
||||
});
|
||||
return () => {
|
||||
if (original) {
|
||||
Object.defineProperty(cryptoObj, 'randomUUID', original);
|
||||
} else {
|
||||
Reflect.deleteProperty(cryptoObj, 'randomUUID');
|
||||
}
|
||||
};
|
||||
}
|
||||
|
||||
let fake: ReturnType<typeof createFakeChatSocket>;
|
||||
let root: Root | null;
|
||||
let container: HTMLElement;
|
||||
@@ -571,6 +598,152 @@ describe('ChatPage', () => {
|
||||
expect(fake.emitted).toContainEqual({ event: 'abort', payload: { conversationId: 'c1' } });
|
||||
});
|
||||
|
||||
it('emits turn:send with the nested persisted selection tuple and a UUID idempotency key (never the legacy message event)', async () => {
|
||||
const restore = installRandomUUID(() => PAGE_UUID);
|
||||
try {
|
||||
// Send is disabled without an active conversation — establish one first.
|
||||
await act(async () => {
|
||||
fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
|
||||
});
|
||||
|
||||
const textarea = container.querySelector(
|
||||
'textarea[aria-label="Message"]',
|
||||
) as HTMLTextAreaElement;
|
||||
await act(async () => {
|
||||
setValue(textarea, 'hello there');
|
||||
});
|
||||
await act(async () => {
|
||||
textarea.dispatchEvent(
|
||||
new KeyboardEvent('keydown', { key: 'Enter', bubbles: true, cancelable: true }),
|
||||
);
|
||||
});
|
||||
} finally {
|
||||
restore();
|
||||
}
|
||||
|
||||
const sends = fake.emitted.filter((e) => e.event === 'turn:send');
|
||||
expect(sends).toHaveLength(1);
|
||||
expect(sends[0]?.payload).toEqual({
|
||||
conversationId: 'c1',
|
||||
content: 'hello there',
|
||||
selection: { harnessId: 'pi', providerId: 'openai', modelId: 'gpt-5' },
|
||||
idempotencyKey: PAGE_UUID,
|
||||
});
|
||||
// The pi-rpc page send must not emit the embedded `message` event, and must
|
||||
// never send a flat {provider, modelId} that drops the harnessId.
|
||||
expect(fake.emitted.some((e) => e.event === 'message')).toBe(false);
|
||||
});
|
||||
|
||||
it('keeps the composer content and emits nothing when the send cannot mint an idempotency key, so the user can retry (composer clears only on success) — Task Five group 5', async () => {
|
||||
const failing = installRandomUUID(() => {
|
||||
throw new Error('secure random unavailable');
|
||||
});
|
||||
try {
|
||||
await act(async () => {
|
||||
fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
|
||||
});
|
||||
const textarea = container.querySelector(
|
||||
'textarea[aria-label="Message"]',
|
||||
) as HTMLTextAreaElement;
|
||||
await act(async () => {
|
||||
setValue(textarea, 'keep me');
|
||||
});
|
||||
await act(async () => {
|
||||
textarea.dispatchEvent(
|
||||
new KeyboardEvent('keydown', { key: 'Enter', bubbles: true, cancelable: true }),
|
||||
);
|
||||
});
|
||||
|
||||
// No wire traffic: neither the harness turn nor the legacy message.
|
||||
expect(fake.emitted.some((e) => e.event === 'turn:send')).toBe(false);
|
||||
expect(fake.emitted.some((e) => e.event === 'message')).toBe(false);
|
||||
// The composer retained its content — it clears ONLY on a successful send,
|
||||
// so the user can retry without retyping.
|
||||
expect(textarea.value).toBe('keep me');
|
||||
// A visible, safe notice explains why nothing was sent.
|
||||
expect(container.querySelector('[role="alert"]')).toBeTruthy();
|
||||
} finally {
|
||||
failing();
|
||||
}
|
||||
});
|
||||
|
||||
it('clears the composer after a successful turn:send and never falls back to the legacy message event — Task Five group 5', async () => {
|
||||
const restore = installRandomUUID(() => PAGE_UUID);
|
||||
try {
|
||||
await act(async () => {
|
||||
fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
|
||||
});
|
||||
const textarea = container.querySelector(
|
||||
'textarea[aria-label="Message"]',
|
||||
) as HTMLTextAreaElement;
|
||||
await act(async () => {
|
||||
setValue(textarea, 'ship it');
|
||||
});
|
||||
await act(async () => {
|
||||
textarea.dispatchEvent(
|
||||
new KeyboardEvent('keydown', { key: 'Enter', bubbles: true, cancelable: true }),
|
||||
);
|
||||
});
|
||||
|
||||
const sends = fake.emitted.filter((e) => e.event === 'turn:send');
|
||||
expect(sends).toHaveLength(1);
|
||||
expect(fake.emitted.some((e) => e.event === 'message')).toBe(false);
|
||||
// On a successful send the composer clears.
|
||||
expect(textarea.value).toBe('');
|
||||
} finally {
|
||||
restore();
|
||||
}
|
||||
});
|
||||
|
||||
it('sends the freshly persisted selection as a nested turn:send tuple after the user changes provider/model — never a stale default or flat fields — Task Five group 5', async () => {
|
||||
const restore = installRandomUUID(() => PAGE_UUID);
|
||||
try {
|
||||
// Change the selection away from the mount default and let it persist.
|
||||
const providerSelect = container.querySelector(
|
||||
'select[aria-label="Provider"]',
|
||||
) as HTMLSelectElement;
|
||||
await act(async () => {
|
||||
selectValue(providerSelect, 'anthropic');
|
||||
});
|
||||
const modelSelect = container.querySelector(
|
||||
'select[aria-label="Model"]',
|
||||
) as HTMLSelectElement;
|
||||
await act(async () => {
|
||||
selectValue(modelSelect, 'anthropic:claude');
|
||||
});
|
||||
await flushAsync();
|
||||
|
||||
await act(async () => {
|
||||
fake.serverEmit('message:ack', { conversationId: 'c1', messageId: 'm1' });
|
||||
});
|
||||
const textarea = container.querySelector(
|
||||
'textarea[aria-label="Message"]',
|
||||
) as HTMLTextAreaElement;
|
||||
await act(async () => {
|
||||
setValue(textarea, 'routed');
|
||||
});
|
||||
await act(async () => {
|
||||
textarea.dispatchEvent(
|
||||
new KeyboardEvent('keydown', { key: 'Enter', bubbles: true, cancelable: true }),
|
||||
);
|
||||
});
|
||||
|
||||
const sends = fake.emitted.filter((e) => e.event === 'turn:send');
|
||||
expect(sends).toHaveLength(1);
|
||||
// The nested tuple reflects the CURRENTLY persisted selection, not the
|
||||
// mount default {openai, gpt-5}, and never flat provider/model fields.
|
||||
expect(sends[0]?.payload).toEqual({
|
||||
conversationId: 'c1',
|
||||
content: 'routed',
|
||||
selection: { harnessId: 'pi', providerId: 'anthropic', modelId: 'claude' },
|
||||
idempotencyKey: PAGE_UUID,
|
||||
});
|
||||
expect(fake.emitted.some((e) => e.event === 'message')).toBe(false);
|
||||
} finally {
|
||||
restore();
|
||||
}
|
||||
});
|
||||
|
||||
it('disables send until a selection has persisted — no send with an unset selection', async () => {
|
||||
await remountWithFetch(harnessFetch(null));
|
||||
|
||||
|
||||
Reference in New Issue
Block a user