mirror of
https://github.com/Kaelio/ktx.git
synced 2026-06-28 08:49:38 +02:00
feat: add codex llm backend for ktx runtime work (#253)
* feat: add codex sdk runner foundation * feat: parse codex runtime events * feat: expose codex runtime mcp tools * feat: add codex llm runtime * feat: wire codex llm backend * test: avoid Array.fromAsync in codex runner test * docs: document codex llm backend * fix: tighten codex runtime config ownership * fix: use codex sdk env and thread options * fix: parse codex sdk event shapes * test: add codex backend live smoke * docs: clarify codex backend isolation * fix: drive codex loop metrics from mcp events * fix: enforce codex local step budget * docs: disclose codex isolation limits * fix: count all codex agent steps and stream step callbacks live The agent-loop step budget only counted completed mcp_tool_call items, so built-in command_execution steps (which the public Codex SDK/CLI surface can still expose) never decremented the budget, letting ingest/reconciliation run past stepBudget until Codex stopped on its own. onStepFinish was also replayed only after the whole stream drained, so live work_unit_step / reconciliation progress appeared stuck until the Codex process exited. collectEvents is now the single live step accumulator: it counts every completed agent-action item via a shared isCompletedAgentStep predicate (command_execution, mcp_tool_call, file_change, web_search), fires onStepFinish as each step completes, and enforces the budget on that broader count. A no-tool turn still counts as one step. toolFailures stays MCP-specific, since a non-zero command exit is normal agent exploration, not a loop failure. * test: align ingest llm-guard assertions with codex backend The skip-llm ingest guard message now lists codex as a valid backend and mentions a Claude Code/Codex session plus a codex setup hint, but this slow suite test still asserted the pre-codex wording. Update it to match the production message (already covered by the local-bundle-runtime unit test) and add the codex setup-line assertion. * fix: treat codex error:null tool calls as success The Codex SDK serializes error: null on successful mcp_tool_call items, so the failure check (item.error !== undefined) flagged every successful tool call as failed with the empty-payload default "Codex turn failed". This killed every ingest work unit under the codex backend before it could produce a patch. Key on status === 'failed' (authoritative, always set) and only treat a populated error object as a failure. Add a regression test built from a verbatim real-SDK event capture. * fix: default codex backend to gpt-5.5 and report real probe errors The previous default gpt-5.3-codex is an API-key-only model that the OpenAI API rejects under ChatGPT-account (subscription) auth, so codex status/setup failed with a misleading "authentication is not usable" message even though auth was fine. - Default codex model is now gpt-5.5 (works on both subscription and API-key auth); the curated setup picker offers gpt-5.5 / gpt-5.4 / gpt-5.4-mini and keeps free-form entry for account-specific ids (e.g. gpt-5.3-codex-spark). - runCodexAuthProbe now distinguishes "model not available" from an auth failure and surfaces the real API error: collectEvents retains stream events when the SDK throws on a non-zero exit, and the API error JSON envelope is unwrapped to its human-readable message. - The Codex isolation warning now renders inside the clack setup frame. - Docs updated to gpt-5.5 with a note that *-codex ids require API-key auth. * fix: require llm.models.default in status and match codex probe remediation Status reported a project ready when a non-none LLM backend was configured without llm.models.default, but the runtime (resolveModelSlots) hard-requires it, so ingest/scan/memory threw after `ktx status` said the project was usable. buildLlmStatus now fails for any non-none backend missing models.default and no longer invents a fallback model for claude-code/codex. Codex probe failures now carry a category-matched fix: a model-access failure steers the user at llm.models.default instead of the auth/install remediation. runCodexAuthProbe returns the fix and status consumes it; the message stays self-sufficient so setup output is unchanged. Docs: README now lists the codex backend and local Codex auth; ktx-setup.mdx states --llm-model only accepts codex/default or gpt-*/codex-* ids. Repaired four doctor fixtures that configured a backend without models.default (the now-correctly-blocked config) and added coverage for the new behavior.
This commit is contained in:
Andrey Avtomonov
GitHub
parent
74c6076b72
commit
494618ab14
41 changed files with 2544 additions and 30 deletions
|
|
@ -56,6 +56,7 @@
|
|||
"@looker/sdk-rtl": "^21.6.5",
|
||||
"@modelcontextprotocol/sdk": "^1.29.0",
|
||||
"@notionhq/client": "^5.22.0",
|
||||
"@openai/codex-sdk": "^0.133.0",
|
||||
"ai": "^6.0.188",
|
||||
"better-sqlite3": "^12.10.0",
|
||||
"commander": "14.0.3",
|
||||
|
|
|
|||
|
|
@ -29,7 +29,7 @@ function embeddingBackend(value: string): 'openai' | 'sentence-transformers' {
|
|||
}
|
||||
|
||||
function llmBackend(value: string): KtxSetupLlmBackend {
|
||||
if (value === 'anthropic' || value === 'vertex' || value === 'claude-code') {
|
||||
if (value === 'anthropic' || value === 'vertex' || value === 'claude-code' || value === 'codex') {
|
||||
return value;
|
||||
}
|
||||
throw new InvalidArgumentError(`invalid choice '${value}'`);
|
||||
|
|
|
|||
|
|
@ -611,9 +611,10 @@ function nextLocalJobId(): string {
|
|||
|
||||
function localIngestLlmProviderGuardMessage(projectDir: string): string {
|
||||
return [
|
||||
'ktx ingest requires llm.provider.backend: anthropic, vertex, gateway, or claude-code, or an injected agentRunner.',
|
||||
'Configure a local Claude Code session or API-backed LLM, then rerun ingest:',
|
||||
'ktx ingest requires llm.provider.backend: anthropic, vertex, gateway, claude-code, or codex, or an injected agentRunner.',
|
||||
'Configure a local Claude Code/Codex session or API-backed LLM, then rerun ingest:',
|
||||
` ktx setup --project-dir ${projectDir} --llm-backend claude-code --no-input`,
|
||||
` ktx setup --project-dir ${projectDir} --llm-backend codex --llm-model gpt-5.5 --no-input`,
|
||||
` ktx setup --project-dir ${projectDir} --llm-backend anthropic --anthropic-api-key-env ANTHROPIC_API_KEY --llm-model claude-sonnet-4-6 --no-input`,
|
||||
].join('\n');
|
||||
}
|
||||
|
|
|
|||
194
packages/cli/src/context/llm/codex-exec-events.ts
Normal file
194
packages/cli/src/context/llm/codex-exec-events.ts
Normal file
|
|
@ -0,0 +1,194 @@
|
|||
import type { LlmTokenUsage, RunLoopStopReason } from './runtime-port.js';
|
||||
|
||||
export interface CodexExecEventSummary {
|
||||
finalText: string;
|
||||
stopReason: RunLoopStopReason;
|
||||
usage: LlmTokenUsage;
|
||||
stepCount: number;
|
||||
stepBoundariesMs: number[];
|
||||
toolCallCount: number;
|
||||
toolFailures: string[];
|
||||
error?: Error;
|
||||
}
|
||||
|
||||
interface CodexEventParseOptions {
|
||||
startedAt?: number;
|
||||
now?: () => number;
|
||||
}
|
||||
|
||||
function record(value: unknown): Record<string, unknown> | undefined {
|
||||
return value && typeof value === 'object' ? (value as Record<string, unknown>) : undefined;
|
||||
}
|
||||
|
||||
/**
|
||||
* Codex thread items that represent a discrete agent action consuming one loop
|
||||
* step. The step budget caps the total number of these regardless of which
|
||||
* capability the agent reaches for, so built-in `command_execution` (and any
|
||||
* file/web action the public Codex surface still exposes) count alongside our
|
||||
* own `mcp_tool_call` items rather than only the MCP ones.
|
||||
*/
|
||||
const AGENT_STEP_ITEM_TYPES = new Set(['command_execution', 'mcp_tool_call', 'file_change', 'web_search']);
|
||||
|
||||
export function isCompletedAgentStep(event: unknown): boolean {
|
||||
const eventRecord = record(event);
|
||||
if (eventRecord?.type !== 'item.completed') {
|
||||
return false;
|
||||
}
|
||||
const itemType = record(eventRecord.item)?.type;
|
||||
return typeof itemType === 'string' && AGENT_STEP_ITEM_TYPES.has(itemType);
|
||||
}
|
||||
|
||||
function text(value: unknown): string | undefined {
|
||||
return typeof value === 'string' && value.trim().length > 0 ? value : undefined;
|
||||
}
|
||||
|
||||
function numberValue(value: unknown): number | undefined {
|
||||
return typeof value === 'number' && Number.isFinite(value) ? value : undefined;
|
||||
}
|
||||
|
||||
function usageFrom(value: unknown): LlmTokenUsage {
|
||||
const usage = record(value);
|
||||
if (!usage) {
|
||||
return {};
|
||||
}
|
||||
const inputTokens = numberValue(usage.input_tokens ?? usage.inputTokens);
|
||||
const outputTokens = numberValue(usage.output_tokens ?? usage.outputTokens);
|
||||
const explicitTotalTokens = numberValue(usage.total_tokens ?? usage.totalTokens);
|
||||
const totalTokens =
|
||||
explicitTotalTokens ??
|
||||
(inputTokens !== undefined && outputTokens !== undefined ? inputTokens + outputTokens : undefined);
|
||||
return {
|
||||
...(inputTokens !== undefined ? { inputTokens } : {}),
|
||||
...(outputTokens !== undefined ? { outputTokens } : {}),
|
||||
...(totalTokens !== undefined ? { totalTokens } : {}),
|
||||
};
|
||||
}
|
||||
|
||||
function stopReasonFrom(value: unknown): RunLoopStopReason {
|
||||
const reason = text(value)?.toLowerCase();
|
||||
if (reason && /(budget|max_turn|max-turn|limit)/.test(reason)) {
|
||||
return 'budget';
|
||||
}
|
||||
return 'natural';
|
||||
}
|
||||
|
||||
function errorMessageFrom(value: unknown): string {
|
||||
if (value instanceof Error) {
|
||||
return value.message;
|
||||
}
|
||||
const asRecord = record(value);
|
||||
const message = text(asRecord?.message);
|
||||
return message ?? text(value) ?? 'Codex turn failed';
|
||||
}
|
||||
|
||||
/**
|
||||
* Codex serializes API failures as a JSON envelope inside the event message
|
||||
* (e.g. `{"type":"error","status":400,"error":{"message":"…"}}`). Surface the
|
||||
* human-readable inner message so callers don't leak raw JSON; pass plain
|
||||
* strings through unchanged.
|
||||
*/
|
||||
function unwrapCodexApiErrorMessage(raw: string): string {
|
||||
const trimmed = raw.trim();
|
||||
if (!trimmed.startsWith('{')) {
|
||||
return raw;
|
||||
}
|
||||
try {
|
||||
const parsed = record(JSON.parse(trimmed));
|
||||
return text(record(parsed?.error)?.message) ?? text(parsed?.message) ?? raw;
|
||||
} catch {
|
||||
return raw;
|
||||
}
|
||||
}
|
||||
|
||||
/** @internal */
|
||||
export function parseCodexExecEventLine(line: string): unknown {
|
||||
try {
|
||||
return JSON.parse(line) as unknown;
|
||||
} catch (error) {
|
||||
throw new Error(`Codex JSONL event stream was malformed: ${error instanceof Error ? error.message : String(error)}`);
|
||||
}
|
||||
}
|
||||
|
||||
export function summarizeCodexExecEvents(
|
||||
events: Iterable<unknown>,
|
||||
options: CodexEventParseOptions = {},
|
||||
): CodexExecEventSummary {
|
||||
const startedAt = options.startedAt ?? Date.now();
|
||||
const now = options.now ?? Date.now;
|
||||
let finalText = '';
|
||||
let stopReason: RunLoopStopReason = 'natural';
|
||||
let usage: LlmTokenUsage = {};
|
||||
let turnCount = 0;
|
||||
let completedStepCount = 0;
|
||||
const stepBoundariesMs: number[] = [];
|
||||
let toolCallCount = 0;
|
||||
const toolFailures: string[] = [];
|
||||
let error: Error | undefined;
|
||||
|
||||
for (const event of events) {
|
||||
const eventRecord = record(event);
|
||||
const eventType = text(eventRecord?.type);
|
||||
if (!eventRecord || !eventType) {
|
||||
continue;
|
||||
}
|
||||
|
||||
if (eventType === 'turn.started') {
|
||||
turnCount += 1;
|
||||
continue;
|
||||
}
|
||||
|
||||
const item = record(eventRecord.item);
|
||||
const itemType = text(item?.type);
|
||||
|
||||
if (eventType === 'item.started' && itemType === 'mcp_tool_call') {
|
||||
toolCallCount += 1;
|
||||
continue;
|
||||
}
|
||||
|
||||
if (isCompletedAgentStep(event)) {
|
||||
completedStepCount += 1;
|
||||
stepBoundariesMs.push(now() - startedAt);
|
||||
// Only MCP tool calls fail the loop: a non-zero `command_execution` exit
|
||||
// is normal agent exploration, not a runtime error. `status` is the
|
||||
// authoritative signal (the SDK always sets it); the SDK also serializes
|
||||
// `error: null` on successful calls, so an explicit-null `error` must NOT
|
||||
// be read as a failure — only a populated error object counts.
|
||||
if (itemType === 'mcp_tool_call' && (item?.status === 'failed' || (item?.error !== undefined && item?.error !== null))) {
|
||||
const name = text(item?.name) ?? text(item?.tool) ?? text(item?.tool_name) ?? 'unknown';
|
||||
toolFailures.push(`${name}: ${errorMessageFrom(item?.error)}`);
|
||||
}
|
||||
continue;
|
||||
}
|
||||
|
||||
if (eventType === 'item.completed' && itemType === 'agent_message') {
|
||||
finalText = text(item?.text) ?? finalText;
|
||||
continue;
|
||||
}
|
||||
|
||||
if (eventType === 'turn.completed') {
|
||||
usage = usageFrom(eventRecord.usage);
|
||||
if (completedStepCount === 0) {
|
||||
stepBoundariesMs.push(now() - startedAt);
|
||||
}
|
||||
stopReason = stopReasonFrom(eventRecord.reason ?? eventRecord.stop_reason ?? eventRecord.terminal_reason);
|
||||
continue;
|
||||
}
|
||||
|
||||
if (eventType === 'turn.failed' || eventType === 'error') {
|
||||
stopReason = 'error';
|
||||
error = new Error(unwrapCodexApiErrorMessage(errorMessageFrom(eventRecord.error ?? eventRecord.message)));
|
||||
continue;
|
||||
}
|
||||
}
|
||||
|
||||
return {
|
||||
finalText,
|
||||
stopReason,
|
||||
usage,
|
||||
stepCount: completedStepCount > 0 ? completedStepCount : turnCount,
|
||||
stepBoundariesMs,
|
||||
toolCallCount,
|
||||
toolFailures,
|
||||
...(error ? { error } : {}),
|
||||
};
|
||||
}
|
||||
9
packages/cli/src/context/llm/codex-isolation.ts
Normal file
9
packages/cli/src/context/llm/codex-isolation.ts
Normal file
|
|
@ -0,0 +1,9 @@
|
|||
export const CODEX_ISOLATION_WARNING =
|
||||
'Codex backend isolation is limited by the public Codex SDK/CLI surface: ktx restricts the runtime MCP server to the current ktx tool set, disables Codex web search, asks for a read-only sandbox, and sets approval_policy=never, but Codex may still load user Codex config and built-in command execution or read-only file capabilities.';
|
||||
|
||||
export const CODEX_ISOLATION_WARNING_FIX =
|
||||
'Use llm.provider.backend: claude-code when you need stricter Claude-Code-style runtime tool isolation, or remove host Codex MCP/tool config before running untrusted prompts through the codex backend.';
|
||||
|
||||
export function formatCodexIsolationWarning(): string {
|
||||
return `${CODEX_ISOLATION_WARNING} ${CODEX_ISOLATION_WARNING_FIX}`;
|
||||
}
|
||||
87
packages/cli/src/context/llm/codex-mcp-runtime-server.ts
Normal file
87
packages/cli/src/context/llm/codex-mcp-runtime-server.ts
Normal file
|
|
@ -0,0 +1,87 @@
|
|||
import { randomBytes } from 'node:crypto';
|
||||
import type { Server } from 'node:http';
|
||||
import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
|
||||
import type { KtxMcpServerLike } from '../mcp/types.js';
|
||||
import { runKtxMcpHttpServer, type KtxMcpHttpServerHandle } from '../../mcp-http-server.js';
|
||||
import type { KtxRuntimeToolSet } from './runtime-port.js';
|
||||
import { normalizeKtxRuntimeToolOutput } from './runtime-tools.js';
|
||||
|
||||
/** @internal */
|
||||
export interface CreateCodexRuntimeMcpServerInput {
|
||||
server?: KtxMcpServerLike;
|
||||
toolSet: KtxRuntimeToolSet;
|
||||
}
|
||||
|
||||
export interface CodexRuntimeMcpServerHandle {
|
||||
url: string;
|
||||
bearerTokenEnvVar: 'KTX_CODEX_RUNTIME_MCP_TOKEN';
|
||||
bearerToken: string;
|
||||
close(): Promise<void>;
|
||||
}
|
||||
|
||||
type RunServer = typeof runKtxMcpHttpServer;
|
||||
|
||||
export interface StartCodexRuntimeMcpServerInput {
|
||||
projectDir: string;
|
||||
toolSet: KtxRuntimeToolSet;
|
||||
runServer?: RunServer;
|
||||
}
|
||||
|
||||
/** @internal */
|
||||
export function createCodexRuntimeMcpServer(input: CreateCodexRuntimeMcpServerInput): KtxMcpServerLike {
|
||||
const server =
|
||||
input.server ??
|
||||
(new McpServer({
|
||||
name: 'ktx-runtime',
|
||||
version: '0.0.0',
|
||||
}) as KtxMcpServerLike);
|
||||
|
||||
for (const descriptor of Object.values(input.toolSet)) {
|
||||
server.registerTool(
|
||||
descriptor.name,
|
||||
{
|
||||
description: descriptor.description,
|
||||
inputSchema: descriptor.inputSchema.shape,
|
||||
},
|
||||
async (toolInput) => {
|
||||
const normalized = normalizeKtxRuntimeToolOutput(await descriptor.execute(toolInput));
|
||||
return {
|
||||
content: [{ type: 'text', text: normalized.markdown }],
|
||||
...(normalized.structured !== undefined && normalized.structured !== null && typeof normalized.structured === 'object'
|
||||
? { structuredContent: normalized.structured as object }
|
||||
: {}),
|
||||
};
|
||||
},
|
||||
);
|
||||
}
|
||||
|
||||
return server;
|
||||
}
|
||||
|
||||
function serverPort(server: Server, fallback: number): number {
|
||||
const address = server.address();
|
||||
return typeof address === 'object' && address ? address.port : fallback;
|
||||
}
|
||||
|
||||
export async function startCodexRuntimeMcpServer(
|
||||
input: StartCodexRuntimeMcpServerInput,
|
||||
): Promise<CodexRuntimeMcpServerHandle> {
|
||||
const bearerToken = randomBytes(32).toString('hex');
|
||||
const runServer = input.runServer ?? runKtxMcpHttpServer;
|
||||
const handle = (await runServer({
|
||||
projectDir: input.projectDir,
|
||||
host: '127.0.0.1',
|
||||
port: 0,
|
||||
token: bearerToken,
|
||||
allowedHosts: ['127.0.0.1', 'localhost'],
|
||||
allowedOrigins: [],
|
||||
createMcpServer: () => createCodexRuntimeMcpServer({ toolSet: input.toolSet }) as McpServer,
|
||||
})) as KtxMcpHttpServerHandle;
|
||||
const port = serverPort(handle.server, 0);
|
||||
return {
|
||||
url: `http://127.0.0.1:${port}/mcp`,
|
||||
bearerTokenEnvVar: 'KTX_CODEX_RUNTIME_MCP_TOKEN',
|
||||
bearerToken,
|
||||
close: () => handle.close(),
|
||||
};
|
||||
}
|
||||
20
packages/cli/src/context/llm/codex-models.ts
Normal file
20
packages/cli/src/context/llm/codex-models.ts
Normal file
|
|
@ -0,0 +1,20 @@
|
|||
export const DEFAULT_CODEX_MODEL = 'gpt-5.5';
|
||||
|
||||
const CODEX_MODEL_ALIASES: Record<string, string> = {
|
||||
codex: DEFAULT_CODEX_MODEL,
|
||||
default: DEFAULT_CODEX_MODEL,
|
||||
};
|
||||
|
||||
const EXPLICIT_CODEX_MODEL_ID = /^(?:gpt|codex)-[a-z0-9][a-z0-9._-]*$/i;
|
||||
|
||||
export function resolveCodexModel(model: string): string {
|
||||
const normalized = model.trim();
|
||||
const alias = CODEX_MODEL_ALIASES[normalized];
|
||||
if (alias) {
|
||||
return alias;
|
||||
}
|
||||
if (EXPLICIT_CODEX_MODEL_ID.test(normalized)) {
|
||||
return normalized;
|
||||
}
|
||||
throw new Error(`Unsupported Codex model "${model}". Use codex, default, or a gpt-* / codex-* model id.`);
|
||||
}
|
||||
38
packages/cli/src/context/llm/codex-runtime-config.ts
Normal file
38
packages/cli/src/context/llm/codex-runtime-config.ts
Normal file
|
|
@ -0,0 +1,38 @@
|
|||
interface CodexRuntimeMcpConfig {
|
||||
url: string;
|
||||
bearerTokenEnvVar: string;
|
||||
bearerToken: string;
|
||||
toolNames: string[];
|
||||
}
|
||||
|
||||
export interface BuildCodexRuntimeConfigInput {
|
||||
model: string;
|
||||
mcp?: CodexRuntimeMcpConfig;
|
||||
}
|
||||
|
||||
export interface CodexRuntimeConfig {
|
||||
configOverrides: Record<string, unknown>;
|
||||
env: Record<string, string>;
|
||||
}
|
||||
|
||||
export function buildCodexRuntimeConfig(input: BuildCodexRuntimeConfigInput): CodexRuntimeConfig {
|
||||
const configOverrides: Record<string, unknown> = {
|
||||
history: { persistence: 'none' },
|
||||
};
|
||||
const env: Record<string, string> = {};
|
||||
|
||||
if (input.mcp) {
|
||||
configOverrides.mcp_servers = {
|
||||
ktx: {
|
||||
url: input.mcp.url,
|
||||
bearer_token_env_var: input.mcp.bearerTokenEnvVar,
|
||||
enabled_tools: input.mcp.toolNames,
|
||||
default_tools_approval_mode: 'approve',
|
||||
required: true,
|
||||
},
|
||||
};
|
||||
env[input.mcp.bearerTokenEnvVar] = input.mcp.bearerToken;
|
||||
}
|
||||
|
||||
return { configOverrides, env };
|
||||
}
|
||||
371
packages/cli/src/context/llm/codex-runtime.ts
Normal file
371
packages/cli/src/context/llm/codex-runtime.ts
Normal file
|
|
@ -0,0 +1,371 @@
|
|||
import { z } from 'zod';
|
||||
import { noopLogger, type KtxLogger } from '../core/config.js';
|
||||
import { isCompletedAgentStep, summarizeCodexExecEvents, type CodexExecEventSummary } from './codex-exec-events.js';
|
||||
import {
|
||||
startCodexRuntimeMcpServer,
|
||||
type CodexRuntimeMcpServerHandle,
|
||||
} from './codex-mcp-runtime-server.js';
|
||||
import { resolveCodexModel } from './codex-models.js';
|
||||
import { buildCodexRuntimeConfig } from './codex-runtime-config.js';
|
||||
import { CodexSdkCliRunner, type CodexSdkRunner } from './codex-sdk-runner.js';
|
||||
import type {
|
||||
KtxGenerateObjectInput,
|
||||
KtxGenerateTextInput,
|
||||
KtxLlmRuntimePort,
|
||||
KtxRuntimeToolSet,
|
||||
LlmTokenUsage,
|
||||
RunLoopParams,
|
||||
RunLoopResult,
|
||||
} from './runtime-port.js';
|
||||
|
||||
export interface CodexKtxLlmRuntimeDeps {
|
||||
projectDir: string;
|
||||
modelSlots: { default: string } & Partial<Record<string, string>>;
|
||||
runner?: CodexSdkRunner;
|
||||
startMcpServer?: (input: { projectDir: string; toolSet: KtxRuntimeToolSet }) => Promise<CodexRuntimeMcpServerHandle>;
|
||||
logger?: KtxLogger;
|
||||
}
|
||||
|
||||
function modelForRole(modelSlots: CodexKtxLlmRuntimeDeps['modelSlots'], role: string): string {
|
||||
return resolveCodexModel(modelSlots[role] ?? modelSlots.default);
|
||||
}
|
||||
|
||||
function promptWithSystem(system: string | undefined, prompt: string): string {
|
||||
return [system, prompt].filter(Boolean).join('\n\n');
|
||||
}
|
||||
|
||||
interface CollectCodexEventsOptions {
|
||||
stepBudget?: number;
|
||||
abortController?: AbortController;
|
||||
onStep?: (stepIndex: number) => void | Promise<void>;
|
||||
}
|
||||
|
||||
interface CollectCodexEventsResult {
|
||||
events: unknown[];
|
||||
budgetExceeded: boolean;
|
||||
streamError?: Error;
|
||||
}
|
||||
|
||||
function eventRecord(value: unknown): Record<string, unknown> | undefined {
|
||||
return value && typeof value === 'object' ? (value as Record<string, unknown>) : undefined;
|
||||
}
|
||||
|
||||
function isTurnCompleted(event: unknown): boolean {
|
||||
return eventRecord(event)?.type === 'turn.completed';
|
||||
}
|
||||
|
||||
/**
|
||||
* Drains the Codex stream once, emitting a step as each agent action completes
|
||||
* so callers see live progress and the step budget is enforced mid-run. Every
|
||||
* completed agent-action item counts (see {@link isCompletedAgentStep}), so
|
||||
* built-in `command_execution` steps decrement the budget the same as
|
||||
* `mcp_tool_call`s. A turn that produced no actions still counts as one step,
|
||||
* matching the metrics summary and the AI SDK backend.
|
||||
*/
|
||||
async function collectEvents(
|
||||
events: AsyncIterable<unknown>,
|
||||
options: CollectCodexEventsOptions = {},
|
||||
): Promise<CollectCodexEventsResult> {
|
||||
const collected: unknown[] = [];
|
||||
let completedSteps = 0;
|
||||
let sawActionStep = false;
|
||||
let budgetExceeded = false;
|
||||
let streamError: Error | undefined;
|
||||
|
||||
// The SDK yields every stdout event, then throws on a non-zero codex exec
|
||||
// exit. Catch that throw so the events already collected (which carry the
|
||||
// real `turn.failed`/`error` reason) survive for the summary; the masked
|
||||
// exit message is kept only as a fallback when no error event was emitted.
|
||||
try {
|
||||
for await (const event of events) {
|
||||
collected.push(event);
|
||||
|
||||
const isActionStep = isCompletedAgentStep(event);
|
||||
if (isActionStep) {
|
||||
sawActionStep = true;
|
||||
} else if (sawActionStep || !isTurnCompleted(event)) {
|
||||
// Only fall back to counting a bare turn as a step when the turn produced
|
||||
// no agent actions; a completed turn is terminal, so it never aborts.
|
||||
continue;
|
||||
}
|
||||
|
||||
completedSteps += 1;
|
||||
await options.onStep?.(completedSteps);
|
||||
if (isActionStep && options.stepBudget !== undefined && completedSteps >= options.stepBudget) {
|
||||
budgetExceeded = true;
|
||||
options.abortController?.abort();
|
||||
break;
|
||||
}
|
||||
}
|
||||
} catch (error) {
|
||||
streamError = error instanceof Error ? error : new Error(String(error));
|
||||
}
|
||||
|
||||
return { events: collected, budgetExceeded, ...(streamError ? { streamError } : {}) };
|
||||
}
|
||||
|
||||
function metrics(summary: CodexExecEventSummary, startedAt: number): { totalMs: number; usage: LlmTokenUsage } {
|
||||
return { totalMs: Date.now() - startedAt, usage: summary.usage };
|
||||
}
|
||||
|
||||
function summaryError(summary: CodexExecEventSummary, streamError?: Error): Error | undefined {
|
||||
// A `turn.failed`/`error` event carries the real reason; prefer it over the
|
||||
// SDK's generic non-zero-exit throw. Fall back to the stream error only when
|
||||
// no event explained the failure (e.g. spawn failure or auth before a turn).
|
||||
if (summary.error) {
|
||||
return summary.error;
|
||||
}
|
||||
if (summary.toolFailures.length > 0) {
|
||||
return new Error(`Codex runtime tool call failed: ${summary.toolFailures.join('; ')}`);
|
||||
}
|
||||
return streamError;
|
||||
}
|
||||
|
||||
function assertSuccessfulText(summary: CodexExecEventSummary, streamError?: Error): string {
|
||||
const error = summaryError(summary, streamError);
|
||||
if (error) {
|
||||
throw error;
|
||||
}
|
||||
if (!summary.finalText.trim()) {
|
||||
throw new Error('Codex completed without an agent message');
|
||||
}
|
||||
return summary.finalText;
|
||||
}
|
||||
|
||||
function parseStructuredOutput<TOutput, TSchema extends z.ZodType<TOutput>>(schema: TSchema, text: string): TOutput {
|
||||
try {
|
||||
return schema.parse(JSON.parse(text));
|
||||
} catch (error) {
|
||||
const message = error instanceof Error ? error.message : String(error);
|
||||
throw new Error(`Codex structured output failed validation: ${message}`);
|
||||
}
|
||||
}
|
||||
|
||||
async function mcpForTools(input: {
|
||||
projectDir: string;
|
||||
toolSet?: KtxRuntimeToolSet;
|
||||
startMcpServer: CodexKtxLlmRuntimeDeps['startMcpServer'];
|
||||
}): Promise<CodexRuntimeMcpServerHandle | undefined> {
|
||||
if (!input.toolSet || Object.keys(input.toolSet).length === 0) {
|
||||
return undefined;
|
||||
}
|
||||
return (input.startMcpServer ?? startCodexRuntimeMcpServer)({
|
||||
projectDir: input.projectDir,
|
||||
toolSet: input.toolSet,
|
||||
});
|
||||
}
|
||||
|
||||
function runtimeToolNames(toolSet: KtxRuntimeToolSet | undefined): string[] {
|
||||
return Object.values(toolSet ?? {}).map((descriptor) => descriptor.name);
|
||||
}
|
||||
|
||||
export class CodexKtxLlmRuntime implements KtxLlmRuntimePort {
|
||||
private readonly runner: CodexSdkRunner;
|
||||
private readonly logger: KtxLogger;
|
||||
|
||||
constructor(private readonly deps: CodexKtxLlmRuntimeDeps) {
|
||||
this.runner = deps.runner ?? new CodexSdkCliRunner();
|
||||
this.logger = deps.logger ?? noopLogger;
|
||||
}
|
||||
|
||||
async generateText(input: KtxGenerateTextInput): Promise<string> {
|
||||
const startedAt = Date.now();
|
||||
const model = modelForRole(this.deps.modelSlots, input.role);
|
||||
const mcp = await mcpForTools({
|
||||
projectDir: this.deps.projectDir,
|
||||
toolSet: input.tools,
|
||||
startMcpServer: this.deps.startMcpServer,
|
||||
});
|
||||
try {
|
||||
const config = buildCodexRuntimeConfig({
|
||||
model,
|
||||
...(mcp
|
||||
? {
|
||||
mcp: {
|
||||
url: mcp.url,
|
||||
bearerTokenEnvVar: mcp.bearerTokenEnvVar,
|
||||
bearerToken: mcp.bearerToken,
|
||||
toolNames: runtimeToolNames(input.tools),
|
||||
},
|
||||
}
|
||||
: {}),
|
||||
});
|
||||
const collected = await collectEvents(
|
||||
await this.runner.runStreamed({
|
||||
projectDir: this.deps.projectDir,
|
||||
model,
|
||||
prompt: promptWithSystem(input.system, input.prompt),
|
||||
configOverrides: config.configOverrides,
|
||||
env: config.env,
|
||||
}),
|
||||
);
|
||||
const summary = summarizeCodexExecEvents(collected.events, { startedAt });
|
||||
input.onMetrics?.(metrics(summary, startedAt));
|
||||
return assertSuccessfulText(summary, collected.streamError);
|
||||
} finally {
|
||||
await mcp?.close();
|
||||
}
|
||||
}
|
||||
|
||||
async generateObject<TOutput, TSchema extends z.ZodType<TOutput>>(
|
||||
input: KtxGenerateObjectInput<TOutput, TSchema>,
|
||||
): Promise<TOutput> {
|
||||
const startedAt = Date.now();
|
||||
const model = modelForRole(this.deps.modelSlots, input.role);
|
||||
const mcp = await mcpForTools({
|
||||
projectDir: this.deps.projectDir,
|
||||
toolSet: input.tools,
|
||||
startMcpServer: this.deps.startMcpServer,
|
||||
});
|
||||
try {
|
||||
const config = buildCodexRuntimeConfig({
|
||||
model,
|
||||
...(mcp
|
||||
? {
|
||||
mcp: {
|
||||
url: mcp.url,
|
||||
bearerTokenEnvVar: mcp.bearerTokenEnvVar,
|
||||
bearerToken: mcp.bearerToken,
|
||||
toolNames: runtimeToolNames(input.tools),
|
||||
},
|
||||
}
|
||||
: {}),
|
||||
});
|
||||
const collected = await collectEvents(
|
||||
await this.runner.runStreamed({
|
||||
projectDir: this.deps.projectDir,
|
||||
model,
|
||||
prompt: promptWithSystem(input.system, input.prompt),
|
||||
configOverrides: config.configOverrides,
|
||||
env: config.env,
|
||||
outputSchema: z.toJSONSchema(input.schema, { target: 'draft-7' }) as Record<string, unknown>,
|
||||
}),
|
||||
);
|
||||
const summary = summarizeCodexExecEvents(collected.events, { startedAt });
|
||||
input.onMetrics?.(metrics(summary, startedAt));
|
||||
return parseStructuredOutput(input.schema, assertSuccessfulText(summary, collected.streamError));
|
||||
} finally {
|
||||
await mcp?.close();
|
||||
}
|
||||
}
|
||||
|
||||
async runAgentLoop(params: RunLoopParams): Promise<RunLoopResult> {
|
||||
const startedAt = Date.now();
|
||||
const model = modelForRole(this.deps.modelSlots, params.modelRole);
|
||||
let mcp: CodexRuntimeMcpServerHandle | undefined;
|
||||
try {
|
||||
mcp = await mcpForTools({
|
||||
projectDir: this.deps.projectDir,
|
||||
toolSet: params.toolSet,
|
||||
startMcpServer: this.deps.startMcpServer,
|
||||
});
|
||||
const config = buildCodexRuntimeConfig({
|
||||
model,
|
||||
...(mcp
|
||||
? {
|
||||
mcp: {
|
||||
url: mcp.url,
|
||||
bearerTokenEnvVar: mcp.bearerTokenEnvVar,
|
||||
bearerToken: mcp.bearerToken,
|
||||
toolNames: runtimeToolNames(params.toolSet),
|
||||
},
|
||||
}
|
||||
: {}),
|
||||
});
|
||||
const abortController = new AbortController();
|
||||
const onStep = async (stepIndex: number): Promise<void> => {
|
||||
try {
|
||||
await params.onStepFinish?.({ stepIndex, stepBudget: params.stepBudget });
|
||||
} catch (error) {
|
||||
this.logger.warn(
|
||||
`[codex-runner] onStepFinish callback threw; ignoring: ${error instanceof Error ? error.message : String(error)}`,
|
||||
);
|
||||
}
|
||||
};
|
||||
const collected = await collectEvents(
|
||||
await this.runner.runStreamed({
|
||||
projectDir: this.deps.projectDir,
|
||||
model,
|
||||
prompt: promptWithSystem(params.systemPrompt, params.userPrompt),
|
||||
configOverrides: config.configOverrides,
|
||||
env: config.env,
|
||||
signal: abortController.signal,
|
||||
}),
|
||||
{ stepBudget: params.stepBudget, abortController, onStep },
|
||||
);
|
||||
const summary = summarizeCodexExecEvents(collected.events, { startedAt });
|
||||
const error = summaryError(summary, collected.streamError);
|
||||
const stopReason = collected.budgetExceeded ? 'budget' : error ? 'error' : summary.stopReason;
|
||||
return {
|
||||
stopReason,
|
||||
...(stopReason === 'error' && error ? { error } : {}),
|
||||
metrics: {
|
||||
totalMs: Date.now() - startedAt,
|
||||
usage: summary.usage,
|
||||
stepCount: summary.stepCount,
|
||||
stepBoundariesMs: summary.stepBoundariesMs,
|
||||
},
|
||||
};
|
||||
} catch (error) {
|
||||
const err = error instanceof Error ? error : new Error(String(error));
|
||||
return {
|
||||
stopReason: 'error',
|
||||
error: err,
|
||||
metrics: { totalMs: Date.now() - startedAt, usage: {}, stepCount: 0, stepBoundariesMs: [] },
|
||||
};
|
||||
} finally {
|
||||
await mcp?.close();
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// A rejected model is not an auth failure: Codex authenticated, connected, and
|
||||
// the API refused the model id. These markers come from the API error envelope
|
||||
// (e.g. "model is not supported", "invalid_request_error").
|
||||
const MODEL_UNAVAILABLE_MARKERS =
|
||||
/\bnot supported\b|\bnot available\b|\bdoes not exist\b|invalid_request_error|\bunknown model\b|\bunsupported model\b/i;
|
||||
|
||||
function describeCodexProbeFailure(model: string, message: string): { message: string; fix: string } {
|
||||
if (MODEL_UNAVAILABLE_MARKERS.test(message)) {
|
||||
const fix = `Run \`codex\` to see the models your account supports, then set llm.models.default in ktx.yaml (or rerun \`ktx setup\`).`;
|
||||
return {
|
||||
message: `Codex is authenticated, but the configured model "${model}" is not available for this Codex account. ${fix} Details: ${message}`,
|
||||
fix,
|
||||
};
|
||||
}
|
||||
const fix = `Authenticate Codex locally with the Codex CLI, verify the Codex CLI is installed, then rerun setup or \`ktx status\`.`;
|
||||
return {
|
||||
message: `Codex authentication is not usable. ${fix} Details: ${message}`,
|
||||
fix,
|
||||
};
|
||||
}
|
||||
|
||||
export async function runCodexAuthProbe(input: {
|
||||
projectDir: string;
|
||||
model: string;
|
||||
runner?: CodexSdkRunner;
|
||||
}): Promise<{ ok: true } | { ok: false; message: string; fix: string }> {
|
||||
let model: string;
|
||||
try {
|
||||
model = resolveCodexModel(input.model);
|
||||
} catch (error) {
|
||||
return {
|
||||
ok: false,
|
||||
message: error instanceof Error ? error.message : String(error),
|
||||
fix: 'Set llm.models.default in ktx.yaml to a supported codex model (codex, default, or a gpt-* / codex-* id), or rerun `ktx setup`.',
|
||||
};
|
||||
}
|
||||
|
||||
const runtime = new CodexKtxLlmRuntime({
|
||||
projectDir: input.projectDir,
|
||||
modelSlots: { default: model },
|
||||
...(input.runner ? { runner: input.runner } : {}),
|
||||
});
|
||||
try {
|
||||
await runtime.generateText({ role: 'default', prompt: 'Reply with exactly: ok' });
|
||||
return { ok: true };
|
||||
} catch (error) {
|
||||
const message = error instanceof Error ? error.message : String(error);
|
||||
return { ok: false, ...describeCodexProbeFailure(model, message) };
|
||||
}
|
||||
}
|
||||
96
packages/cli/src/context/llm/codex-sdk-runner.ts
Normal file
96
packages/cli/src/context/llm/codex-sdk-runner.ts
Normal file
|
|
@ -0,0 +1,96 @@
|
|||
import { Codex, type CodexOptions, type ThreadOptions, type TurnOptions } from '@openai/codex-sdk';
|
||||
|
||||
export interface CodexSdkRunnerInput {
|
||||
projectDir: string;
|
||||
model: string;
|
||||
prompt: string;
|
||||
configOverrides?: Record<string, unknown>;
|
||||
env?: Record<string, string>;
|
||||
outputSchema?: Record<string, unknown>;
|
||||
signal?: AbortSignal;
|
||||
}
|
||||
|
||||
export interface CodexSdkRunner {
|
||||
runStreamed(input: CodexSdkRunnerInput): Promise<AsyncIterable<unknown>>;
|
||||
}
|
||||
|
||||
type CodexThread = {
|
||||
runStreamed(input: string, turnOptions?: TurnOptions): Promise<{ events: AsyncIterable<unknown> }>;
|
||||
};
|
||||
|
||||
type CodexClient = {
|
||||
startThread(options: ThreadOptions): CodexThread;
|
||||
};
|
||||
|
||||
type CodexConstructor = new (options?: CodexOptions) => CodexClient;
|
||||
|
||||
export interface CodexSdkCliRunnerOptions {
|
||||
envBase?: NodeJS.ProcessEnv;
|
||||
codexPathOverride?: string;
|
||||
}
|
||||
|
||||
const CODEX_ENV_ALLOWLIST = new Set([
|
||||
'HOME',
|
||||
'USERPROFILE',
|
||||
'APPDATA',
|
||||
'LOCALAPPDATA',
|
||||
'XDG_CONFIG_HOME',
|
||||
'CODEX_HOME',
|
||||
'CODEX_API_KEY',
|
||||
'OPENAI_API_KEY',
|
||||
'PATH',
|
||||
'Path',
|
||||
'SYSTEMROOT',
|
||||
'COMSPEC',
|
||||
'TMPDIR',
|
||||
'TMP',
|
||||
'TEMP',
|
||||
'SSL_CERT_FILE',
|
||||
'SSL_CERT_DIR',
|
||||
'NODE_EXTRA_CA_CERTS',
|
||||
'HTTPS_PROXY',
|
||||
'HTTP_PROXY',
|
||||
'ALL_PROXY',
|
||||
'NO_PROXY',
|
||||
]);
|
||||
|
||||
function buildCodexSdkEnv(baseEnv: NodeJS.ProcessEnv, overrides: Record<string, string> | undefined): Record<string, string> {
|
||||
const env: Record<string, string> = {};
|
||||
for (const key of CODEX_ENV_ALLOWLIST) {
|
||||
const value = baseEnv[key];
|
||||
if (typeof value === 'string') {
|
||||
env[key] = value;
|
||||
}
|
||||
}
|
||||
return { ...env, ...(overrides ?? {}) };
|
||||
}
|
||||
|
||||
export class CodexSdkCliRunner implements CodexSdkRunner {
|
||||
constructor(private readonly options: CodexSdkCliRunnerOptions = {}) {}
|
||||
|
||||
async runStreamed(input: CodexSdkRunnerInput): Promise<AsyncIterable<unknown>> {
|
||||
const CodexClass = Codex as CodexConstructor;
|
||||
const codex = new CodexClass({
|
||||
...(input.configOverrides ? { config: input.configOverrides as CodexOptions['config'] } : {}),
|
||||
env: buildCodexSdkEnv(this.options.envBase ?? process.env, input.env),
|
||||
...(this.options.codexPathOverride ? { codexPathOverride: this.options.codexPathOverride } : {}),
|
||||
});
|
||||
const thread = codex.startThread({
|
||||
workingDirectory: input.projectDir,
|
||||
skipGitRepoCheck: true,
|
||||
model: input.model,
|
||||
sandboxMode: 'read-only',
|
||||
webSearchMode: 'disabled',
|
||||
approvalPolicy: 'never',
|
||||
});
|
||||
const turnOptions: TurnOptions = {
|
||||
...(input.outputSchema ? { outputSchema: input.outputSchema } : {}),
|
||||
...(input.signal ? { signal: input.signal } : {}),
|
||||
};
|
||||
const streamed = await thread.runStreamed(
|
||||
input.prompt,
|
||||
Object.keys(turnOptions).length > 0 ? turnOptions : undefined,
|
||||
);
|
||||
return streamed.events;
|
||||
}
|
||||
}
|
||||
|
|
@ -5,6 +5,7 @@ import { resolveKtxConfigReference } from '../core/config-reference.js';
|
|||
import type { KtxProjectEmbeddingConfig, KtxProjectLlmConfig } from '../project/config.js';
|
||||
import { AiSdkKtxLlmRuntime } from './ai-sdk-runtime.js';
|
||||
import { ClaudeCodeKtxLlmRuntime } from './claude-code-runtime.js';
|
||||
import { CodexKtxLlmRuntime } from './codex-runtime.js';
|
||||
import type { KtxLlmRuntimePort } from './runtime-port.js';
|
||||
|
||||
interface LocalConfigDeps {
|
||||
|
|
@ -13,6 +14,7 @@ interface LocalConfigDeps {
|
|||
createKtxLlmProvider?: typeof createKtxLlmProvider;
|
||||
createKtxEmbeddingProvider?: typeof createKtxEmbeddingProvider;
|
||||
createClaudeCodeRuntime?: (deps: ConstructorParameters<typeof ClaudeCodeKtxLlmRuntime>[0]) => KtxLlmRuntimePort;
|
||||
createCodexRuntime?: (deps: ConstructorParameters<typeof CodexKtxLlmRuntime>[0]) => KtxLlmRuntimePort;
|
||||
createAiSdkRuntime?: (deps: { llmProvider: KtxLlmProvider }) => KtxLlmRuntimePort;
|
||||
}
|
||||
|
||||
|
|
@ -104,7 +106,7 @@ export function createLocalKtxLlmProviderFromConfig(
|
|||
deps: LocalConfigDeps = {},
|
||||
): KtxLlmProvider | null {
|
||||
const resolved = resolveLocalKtxLlmConfig(config, deps.env ?? process.env);
|
||||
if (!resolved || resolved.backend === 'claude-code') {
|
||||
if (!resolved || resolved.backend === 'claude-code' || resolved.backend === 'codex') {
|
||||
return null;
|
||||
}
|
||||
return (deps.createKtxLlmProvider ?? createKtxLlmProvider)(resolved);
|
||||
|
|
@ -129,6 +131,16 @@ export function createLocalKtxLlmRuntimeFromConfig(
|
|||
env: deps.env,
|
||||
});
|
||||
}
|
||||
if (resolved.backend === 'codex') {
|
||||
const projectDir = deps.projectDir;
|
||||
if (!projectDir) {
|
||||
throw new Error('projectDir is required when creating the codex LLM runtime');
|
||||
}
|
||||
return (deps.createCodexRuntime ?? ((runtimeDeps) => new CodexKtxLlmRuntime(runtimeDeps)))({
|
||||
projectDir,
|
||||
modelSlots: resolved.modelSlots,
|
||||
});
|
||||
}
|
||||
const llmProvider = (deps.createKtxLlmProvider ?? createKtxLlmProvider)(resolved);
|
||||
return (deps.createAiSdkRuntime ?? ((runtimeDeps) => new AiSdkKtxLlmRuntime(runtimeDeps)))({ llmProvider });
|
||||
}
|
||||
|
|
|
|||
|
|
@ -3,7 +3,7 @@ import YAML from 'yaml';
|
|||
import * as z from 'zod';
|
||||
import { connectionConfigSchema } from './driver-schemas.js';
|
||||
|
||||
const KTX_LLM_BACKENDS = ['none', 'anthropic', 'vertex', 'gateway', 'claude-code'] as const;
|
||||
const KTX_LLM_BACKENDS = ['none', 'anthropic', 'vertex', 'gateway', 'claude-code', 'codex'] as const;
|
||||
const KTX_EMBEDDING_BACKENDS = ['none', 'openai', 'sentence-transformers'] as const;
|
||||
const KTX_PROMPT_CACHE_TTLS = ['5m', '1h'] as const;
|
||||
const KTX_ENRICHMENT_MODES = ['none', 'deterministic', 'llm'] as const;
|
||||
|
|
@ -38,7 +38,7 @@ const llmProviderSchema = z
|
|||
.enum(KTX_LLM_BACKENDS)
|
||||
.default('none')
|
||||
.describe(
|
||||
'LLM provider backend. "none" disables LLM features; "anthropic" / "vertex" / "gateway" require the matching nested credentials block; "claude-code" uses the local Claude Code session.',
|
||||
'LLM provider backend. "none" disables LLM features; "anthropic" / "vertex" / "gateway" require the matching nested credentials block; "claude-code" uses the local Claude Code session; "codex" uses the local Codex session.',
|
||||
),
|
||||
vertex: vertexProviderSchema.optional().describe('Vertex AI credentials, used when backend is "vertex".'),
|
||||
anthropic: apiCredentialsSchema.optional().describe('Anthropic API credentials, used when backend is "anthropic".'),
|
||||
|
|
|
|||
|
|
@ -3,7 +3,7 @@ import type { LanguageModel, TelemetrySettings, ToolCallRepairFunction, ToolSet
|
|||
export const KTX_MODEL_ROLES = ['default', 'triage', 'candidateExtraction', 'curator', 'reconcile', 'repair'] as const;
|
||||
|
||||
export type KtxModelRole = (typeof KTX_MODEL_ROLES)[number];
|
||||
type KtxLlmBackend = 'anthropic' | 'vertex' | 'gateway' | 'claude-code';
|
||||
type KtxLlmBackend = 'anthropic' | 'vertex' | 'gateway' | 'claude-code' | 'codex';
|
||||
export type KtxPromptCacheTtl = '5m' | '1h';
|
||||
|
||||
type KtxJsonValue =
|
||||
|
|
|
|||
|
|
@ -3,6 +3,9 @@ import { writeFile } from 'node:fs/promises';
|
|||
import { promisify } from 'node:util';
|
||||
import { resolveLocalKtxLlmConfig } from './context/llm/local-config.js';
|
||||
import { runClaudeCodeAuthProbe } from './context/llm/claude-code-runtime.js';
|
||||
import { formatCodexIsolationWarning } from './context/llm/codex-isolation.js';
|
||||
import { runCodexAuthProbe } from './context/llm/codex-runtime.js';
|
||||
import { DEFAULT_CODEX_MODEL } from './context/llm/codex-models.js';
|
||||
import { resolveKtxConfigReference } from './context/core/config-reference.js';
|
||||
import { type KtxProjectConfig, type KtxProjectLlmConfig, serializeKtxProjectConfig } from './context/project/config.js';
|
||||
import { loadKtxProject } from './context/project/project.js';
|
||||
|
|
@ -56,7 +59,7 @@ export interface AnthropicModelChoice {
|
|||
recommended: boolean;
|
||||
}
|
||||
|
||||
export type KtxSetupLlmBackend = 'anthropic' | 'vertex' | 'claude-code';
|
||||
export type KtxSetupLlmBackend = 'anthropic' | 'vertex' | 'claude-code' | 'codex';
|
||||
|
||||
/** @internal */
|
||||
export interface KtxSetupModelPromptAdapter {
|
||||
|
|
@ -82,6 +85,7 @@ export interface KtxSetupModelDeps {
|
|||
model: string;
|
||||
env?: NodeJS.ProcessEnv;
|
||||
}) => Promise<{ ok: true } | { ok: false; message: string }>;
|
||||
codexAuthProbe?: (input: { projectDir: string; model: string }) => Promise<{ ok: true } | { ok: false; message: string }>;
|
||||
readGcloudProject?: () => Promise<string | undefined>;
|
||||
listGcloudProjects?: () => Promise<GcloudProjectChoice[]>;
|
||||
spinner?: () => KtxCliSpinner;
|
||||
|
|
@ -110,6 +114,20 @@ const CLAUDE_CODE_MODELS: AnthropicModelChoice[] = [
|
|||
{ id: 'haiku', label: 'Claude Haiku', recommended: false },
|
||||
];
|
||||
|
||||
// Curated Codex models from OpenAI's current lineup that work under both
|
||||
// ChatGPT-account (subscription) and API-key auth. Intentionally omitted:
|
||||
// the `*-codex` ids (e.g. gpt-5.3-codex, gpt-5.2-codex) are API-key-only and
|
||||
// fail on ChatGPT-account auth, and gpt-5.3-codex-spark is a ChatGPT-Pro-only
|
||||
// research preview. Codex resolves real availability per account at runtime
|
||||
// (its binary remote-fetches the model list), so this is a convenience
|
||||
// shortlist only — the manual-entry option accepts any id your account's
|
||||
// `codex` picker exposes, and the auth probe reports an unsupported choice.
|
||||
const CODEX_MODELS: AnthropicModelChoice[] = [
|
||||
{ id: 'gpt-5.5', label: 'GPT-5.5', recommended: true },
|
||||
{ id: 'gpt-5.4', label: 'GPT-5.4', recommended: false },
|
||||
{ id: 'gpt-5.4-mini', label: 'GPT-5.4 mini', recommended: false },
|
||||
];
|
||||
|
||||
const HIDDEN_ANTHROPIC_MODEL_PATTERNS = [
|
||||
/^claude-sonnet-4$/i,
|
||||
/^claude-opus-4$/i,
|
||||
|
|
@ -272,7 +290,12 @@ export function isKtxSetupLlmConfigReady(config: KtxProjectLlmConfig): boolean {
|
|||
return typeof resolved.vertex?.location === 'string' && resolved.vertex.location.trim().length > 0;
|
||||
}
|
||||
|
||||
return resolved.backend === 'anthropic' || resolved.backend === 'gateway' || resolved.backend === 'claude-code';
|
||||
return (
|
||||
resolved.backend === 'anthropic' ||
|
||||
resolved.backend === 'gateway' ||
|
||||
resolved.backend === 'claude-code' ||
|
||||
resolved.backend === 'codex'
|
||||
);
|
||||
}
|
||||
|
||||
function hasUsableConfiguredLlm(config: KtxProjectConfig): boolean {
|
||||
|
|
@ -284,7 +307,8 @@ function buildProjectLlmConfig(
|
|||
provider:
|
||||
| { backend: 'anthropic'; credentialRef: string }
|
||||
| { backend: 'vertex'; vertex: { project?: string; location: string } }
|
||||
| { backend: 'claude-code' },
|
||||
| { backend: 'claude-code' }
|
||||
| { backend: 'codex' },
|
||||
model: string,
|
||||
): KtxProjectLlmConfig {
|
||||
if (provider.backend === 'claude-code') {
|
||||
|
|
@ -295,6 +319,14 @@ function buildProjectLlmConfig(
|
|||
};
|
||||
}
|
||||
|
||||
if (provider.backend === 'codex') {
|
||||
return {
|
||||
provider: { backend: 'codex' },
|
||||
models: { ...existing.models, default: model },
|
||||
promptCaching: existing.promptCaching,
|
||||
};
|
||||
}
|
||||
|
||||
if (provider.backend === 'vertex') {
|
||||
return {
|
||||
provider: {
|
||||
|
|
@ -515,6 +547,7 @@ async function chooseBackend(
|
|||
message: 'Which LLM provider should KTX use?',
|
||||
options: [
|
||||
{ value: 'claude-code', label: 'Claude subscription (Pro/Max)' },
|
||||
{ value: 'codex', label: 'Codex subscription' },
|
||||
{ value: 'anthropic', label: 'Anthropic API key' },
|
||||
{ value: 'vertex', label: 'Google Vertex AI for Anthropic Claude' },
|
||||
{ value: 'back', label: 'Back' },
|
||||
|
|
@ -525,7 +558,7 @@ async function chooseBackend(
|
|||
}
|
||||
return {
|
||||
status: 'ready',
|
||||
backend: choice === 'vertex' || choice === 'claude-code' ? choice : 'anthropic',
|
||||
backend: choice === 'vertex' || choice === 'claude-code' || choice === 'codex' ? choice : 'anthropic',
|
||||
prompted: true,
|
||||
};
|
||||
}
|
||||
|
|
@ -884,12 +917,51 @@ async function chooseClaudeCodeModel(args: KtxSetupModelArgs, deps: KtxSetupMode
|
|||
return { status: 'ready', model: choice };
|
||||
}
|
||||
|
||||
async function chooseCodexModel(args: KtxSetupModelArgs, deps: KtxSetupModelDeps): Promise<ChooseModelResult> {
|
||||
const providedModel = requestedModel(args);
|
||||
if (providedModel) {
|
||||
return { status: 'ready', model: providedModel };
|
||||
}
|
||||
if (args.inputMode === 'disabled') {
|
||||
return { status: 'ready', model: DEFAULT_CODEX_MODEL };
|
||||
}
|
||||
|
||||
const prompts = deps.prompts ?? createPromptAdapter();
|
||||
const choice = await prompts.select({
|
||||
message: `Which Codex model should KTX use?\n\n${ANTHROPIC_MODEL_PROMPT_CONTEXT}`,
|
||||
options: [
|
||||
...CODEX_MODELS.map((model) => ({
|
||||
value: model.id,
|
||||
label: model.label,
|
||||
...(model.recommended ? { hint: 'recommended' } : {}),
|
||||
})),
|
||||
{ value: 'manual', label: 'Enter a Codex model ID manually' },
|
||||
{ value: 'back', label: 'Back' },
|
||||
],
|
||||
});
|
||||
if (choice === 'back') {
|
||||
return { status: 'back' };
|
||||
}
|
||||
if (choice === 'manual') {
|
||||
const manual = await prompts.text({
|
||||
message: withTextInputNavigation('Codex model ID'),
|
||||
placeholder: CODEX_MODELS.find((model) => model.recommended)?.id ?? CODEX_MODELS[0]?.id,
|
||||
});
|
||||
if (manual === undefined) {
|
||||
return { status: 'back' };
|
||||
}
|
||||
return manual.trim() ? { status: 'ready', model: manual.trim() } : { status: 'missing-input' };
|
||||
}
|
||||
return { status: 'ready', model: choice };
|
||||
}
|
||||
|
||||
async function persistLlmConfig(
|
||||
projectDir: string,
|
||||
provider:
|
||||
| { backend: 'anthropic'; credentialRef: string }
|
||||
| { backend: 'vertex'; vertex: { project?: string; location: string } }
|
||||
| { backend: 'claude-code' },
|
||||
| { backend: 'claude-code' }
|
||||
| { backend: 'codex' },
|
||||
model: string,
|
||||
): Promise<void> {
|
||||
const project = await loadKtxProject({ projectDir });
|
||||
|
|
@ -1031,6 +1103,32 @@ export async function runKtxSetupAnthropicModelStep(
|
|||
return { status: 'ready', projectDir: args.projectDir };
|
||||
}
|
||||
|
||||
if (backendChoice.backend === 'codex') {
|
||||
const model = await chooseCodexModel(backendArgs, deps);
|
||||
if (model.status === 'back' && backendChoice.prompted) {
|
||||
attemptArgs = buildInteractiveRetryArgs(args);
|
||||
continue;
|
||||
}
|
||||
if (model.status === 'invalid-credential') {
|
||||
return { status: 'failed', projectDir: args.projectDir };
|
||||
}
|
||||
if (model.status !== 'ready') {
|
||||
return { status: model.status, projectDir: args.projectDir };
|
||||
}
|
||||
const probe = deps.codexAuthProbe ?? runCodexAuthProbe;
|
||||
const health = await probe({ projectDir: args.projectDir, model: model.model });
|
||||
if (!health.ok) {
|
||||
io.stderr.write(`${health.message}\n`);
|
||||
return { status: 'failed', projectDir: args.projectDir };
|
||||
}
|
||||
// Prefix the clack gutter so the warning sits inside the setup frame
|
||||
// instead of breaking out of it; kept on stderr for scripted runs.
|
||||
io.stderr.write(`│ ${formatCodexIsolationWarning()}\n`);
|
||||
await persistLlmConfig(args.projectDir, { backend: 'codex' }, model.model);
|
||||
io.stdout.write(`│ LLM ready: yes (codex, ${model.model})\n`);
|
||||
return { status: 'ready', projectDir: args.projectDir };
|
||||
}
|
||||
|
||||
const credential = await chooseCredentialRef(backendArgs, io, deps);
|
||||
if (credential.status === 'back' && backendChoice.prompted) {
|
||||
attemptArgs = buildInteractiveRetryArgs(args);
|
||||
|
|
|
|||
|
|
@ -1,6 +1,11 @@
|
|||
import { stat as statAsync, readdir as readdirAsync } from 'node:fs/promises';
|
||||
import { basename, join } from 'node:path';
|
||||
import { runClaudeCodeAuthProbe } from './context/llm/claude-code-runtime.js';
|
||||
import {
|
||||
CODEX_ISOLATION_WARNING,
|
||||
CODEX_ISOLATION_WARNING_FIX,
|
||||
} from './context/llm/codex-isolation.js';
|
||||
import { runCodexAuthProbe } from './context/llm/codex-runtime.js';
|
||||
import type { KtxConfigIssue, KtxProjectConfig, KtxProjectConnectionConfig, KtxProjectEmbeddingConfig, KtxProjectLlmConfig } from './context/project/config.js';
|
||||
import type { KtxLocalProject } from './context/project/project.js';
|
||||
import { ktxLocalStateDbPath } from './context/project/local-state-db.js';
|
||||
|
|
@ -94,6 +99,11 @@ type ClaudeCodeAuthProbe = (input: {
|
|||
env?: NodeJS.ProcessEnv;
|
||||
}) => Promise<{ ok: true } | { ok: false; message: string }>;
|
||||
|
||||
type CodexAuthProbe = (input: {
|
||||
projectDir: string;
|
||||
model: string;
|
||||
}) => Promise<{ ok: true } | { ok: false; message: string; fix: string }>;
|
||||
|
||||
const PROJECT_READY_COMMANDS = KTX_NEXT_STEP_DIRECT_COMMANDS.map((step) => step.command);
|
||||
|
||||
interface LocalStatsIngestPerConnection {
|
||||
|
|
@ -194,6 +204,7 @@ async function buildLlmStatus(
|
|||
projectDir: string;
|
||||
env: NodeJS.ProcessEnv;
|
||||
claudeCodeAuthProbe?: ClaudeCodeAuthProbe;
|
||||
codexAuthProbe?: CodexAuthProbe;
|
||||
fast?: boolean;
|
||||
useSpinner?: boolean;
|
||||
},
|
||||
|
|
@ -210,6 +221,18 @@ async function buildLlmStatus(
|
|||
fix: 'Run: ktx setup (choose an LLM provider)',
|
||||
};
|
||||
}
|
||||
// The runtime (resolveModelSlots) hard-requires llm.models.default for every
|
||||
// non-none backend; without it ingest/scan/memory throw. Report that here so
|
||||
// status never marks a project ready that the runtime would refuse to run.
|
||||
if (!model || model.trim().length === 0) {
|
||||
return {
|
||||
backend,
|
||||
model,
|
||||
status: 'fail',
|
||||
detail: `llm.models.default is required for backend "${backend}"`,
|
||||
fix: 'Set llm.models.default in ktx.yaml, then rerun `ktx status` (or rerun `ktx setup`).',
|
||||
};
|
||||
}
|
||||
if (backend === 'anthropic') {
|
||||
const ref = config.provider.anthropic?.api_key;
|
||||
const resolved = resolveRef(ref, env);
|
||||
|
|
@ -251,7 +274,7 @@ async function buildLlmStatus(
|
|||
};
|
||||
}
|
||||
if (backend === 'claude-code') {
|
||||
const modelName = model ?? 'sonnet';
|
||||
const modelName = model;
|
||||
if (options.fast === true) {
|
||||
return {
|
||||
backend,
|
||||
|
|
@ -280,6 +303,36 @@ async function buildLlmStatus(
|
|||
fix: 'Authenticate Claude Code locally with the Claude Code CLI, then rerun `ktx status`.',
|
||||
};
|
||||
}
|
||||
if (backend === 'codex') {
|
||||
const modelName = model;
|
||||
if (options.fast === true) {
|
||||
return {
|
||||
backend,
|
||||
model: modelName,
|
||||
status: 'skipped',
|
||||
detail: 'auth probe skipped (--fast)',
|
||||
};
|
||||
}
|
||||
const probe = options.codexAuthProbe ?? runCodexAuthProbe;
|
||||
const auth = await withSpinner(options.useSpinner === true, 'Probing Codex authentication', () =>
|
||||
probe({ projectDir: options.projectDir, model: modelName }),
|
||||
);
|
||||
if (auth.ok) {
|
||||
return {
|
||||
backend,
|
||||
model: modelName,
|
||||
status: 'ok',
|
||||
detail: 'local Codex session authenticated',
|
||||
};
|
||||
}
|
||||
return {
|
||||
backend,
|
||||
model: modelName,
|
||||
status: 'fail',
|
||||
detail: auth.message,
|
||||
fix: auth.fix,
|
||||
};
|
||||
}
|
||||
return { backend, model, status: 'warn', detail: 'unknown LLM backend' };
|
||||
}
|
||||
|
||||
|
|
@ -572,6 +625,13 @@ function buildWarnings(
|
|||
});
|
||||
}
|
||||
|
||||
if (llm.backend === 'codex') {
|
||||
warnings.push({
|
||||
message: CODEX_ISOLATION_WARNING,
|
||||
fix: CODEX_ISOLATION_WARNING_FIX,
|
||||
});
|
||||
}
|
||||
|
||||
return warnings;
|
||||
}
|
||||
|
||||
|
|
@ -634,6 +694,7 @@ export interface BuildProjectStatusOptions {
|
|||
env?: NodeJS.ProcessEnv;
|
||||
queryHistoryReadinessProbe?: HistoricSqlReadinessProbe;
|
||||
claudeCodeAuthProbe?: ClaudeCodeAuthProbe;
|
||||
codexAuthProbe?: CodexAuthProbe;
|
||||
configIssues?: KtxConfigIssue[];
|
||||
fast?: boolean;
|
||||
useSpinner?: boolean;
|
||||
|
|
@ -882,6 +943,7 @@ export async function buildProjectStatus(project: KtxLocalProject, options: Buil
|
|||
projectDir: project.projectDir,
|
||||
env,
|
||||
claudeCodeAuthProbe: options.claudeCodeAuthProbe,
|
||||
codexAuthProbe: options.codexAuthProbe,
|
||||
fast: options.fast,
|
||||
useSpinner: options.useSpinner,
|
||||
});
|
||||
|
|
|
|||
|
|
@ -77,9 +77,10 @@ describe('createLocalBundleIngestRuntime', () => {
|
|||
}),
|
||||
).toThrow(
|
||||
[
|
||||
'ktx ingest requires llm.provider.backend: anthropic, vertex, gateway, or claude-code, or an injected agentRunner.',
|
||||
'Configure a local Claude Code session or API-backed LLM, then rerun ingest:',
|
||||
'ktx ingest requires llm.provider.backend: anthropic, vertex, gateway, claude-code, or codex, or an injected agentRunner.',
|
||||
'Configure a local Claude Code/Codex session or API-backed LLM, then rerun ingest:',
|
||||
` ktx setup --project-dir ${project.projectDir} --llm-backend claude-code --no-input`,
|
||||
` ktx setup --project-dir ${project.projectDir} --llm-backend codex --llm-model gpt-5.5 --no-input`,
|
||||
` ktx setup --project-dir ${project.projectDir} --llm-backend anthropic --anthropic-api-key-env ANTHROPIC_API_KEY --llm-model claude-sonnet-4-6 --no-input`,
|
||||
].join('\n'),
|
||||
);
|
||||
|
|
|
|||
188
packages/cli/test/context/llm/codex-exec-events.test.ts
Normal file
188
packages/cli/test/context/llm/codex-exec-events.test.ts
Normal file
|
|
@ -0,0 +1,188 @@
|
|||
import { describe, expect, it } from 'vitest';
|
||||
import {
|
||||
parseCodexExecEventLine,
|
||||
summarizeCodexExecEvents,
|
||||
} from '../../../src/context/llm/codex-exec-events.js';
|
||||
|
||||
describe('Codex exec event parsing', () => {
|
||||
it('uses the completed turn as one step when no MCP tools run', () => {
|
||||
const summary = summarizeCodexExecEvents(
|
||||
[
|
||||
{ type: 'thread.started', thread_id: 'thr_1' },
|
||||
{ type: 'turn.started' },
|
||||
{ type: 'item.completed', item: { id: 'item_1', type: 'agent_message', text: 'hello from codex' } },
|
||||
{
|
||||
type: 'turn.completed',
|
||||
usage: {
|
||||
input_tokens: 12,
|
||||
cached_input_tokens: 4,
|
||||
output_tokens: 5,
|
||||
reasoning_output_tokens: 2,
|
||||
},
|
||||
},
|
||||
],
|
||||
{ startedAt: 100, now: () => 125 },
|
||||
);
|
||||
|
||||
expect(summary).toEqual({
|
||||
finalText: 'hello from codex',
|
||||
stopReason: 'natural',
|
||||
usage: { inputTokens: 12, outputTokens: 5, totalTokens: 17 },
|
||||
stepCount: 1,
|
||||
stepBoundariesMs: [25],
|
||||
toolCallCount: 0,
|
||||
toolFailures: [],
|
||||
});
|
||||
});
|
||||
|
||||
it('uses completed MCP tool calls as loop steps', () => {
|
||||
const offsets = [115, 140, 175];
|
||||
const summary = summarizeCodexExecEvents(
|
||||
[
|
||||
{ type: 'turn.started' },
|
||||
{
|
||||
type: 'item.started',
|
||||
item: { id: 'call_1', type: 'mcp_tool_call', server: 'ktx', tool: 'search', arguments: {}, status: 'in_progress' },
|
||||
},
|
||||
{
|
||||
type: 'item.completed',
|
||||
item: { id: 'call_1', type: 'mcp_tool_call', server: 'ktx', tool: 'search', arguments: {}, status: 'completed' },
|
||||
},
|
||||
{
|
||||
type: 'item.started',
|
||||
item: { id: 'call_2', type: 'mcp_tool_call', server: 'ktx', tool: 'lookup', arguments: {}, status: 'in_progress' },
|
||||
},
|
||||
{
|
||||
type: 'item.completed',
|
||||
item: {
|
||||
id: 'call_2',
|
||||
type: 'mcp_tool_call',
|
||||
server: 'ktx',
|
||||
tool: 'lookup',
|
||||
arguments: {},
|
||||
status: 'failed',
|
||||
error: { message: 'denied' },
|
||||
},
|
||||
},
|
||||
{ type: 'item.completed', item: { id: 'item_1', type: 'agent_message', text: 'done' } },
|
||||
{ type: 'turn.completed', usage: { input_tokens: 1, output_tokens: 1, cached_input_tokens: 0, reasoning_output_tokens: 0 } },
|
||||
],
|
||||
{ startedAt: 100, now: () => offsets.shift() ?? 175 },
|
||||
);
|
||||
|
||||
expect(summary).toEqual({
|
||||
finalText: 'done',
|
||||
stopReason: 'natural',
|
||||
usage: { inputTokens: 1, outputTokens: 1, totalTokens: 2 },
|
||||
stepCount: 2,
|
||||
stepBoundariesMs: [15, 40],
|
||||
toolCallCount: 2,
|
||||
toolFailures: ['lookup: denied'],
|
||||
});
|
||||
});
|
||||
|
||||
it('does not treat a completed MCP tool call as failed when Codex sends error: null', () => {
|
||||
// Captured verbatim from a real @openai/codex-sdk run: successful tool calls
|
||||
// carry `error: null` and `result` alongside `status: "completed"`.
|
||||
const summary = summarizeCodexExecEvents([
|
||||
{ type: 'turn.started' },
|
||||
{
|
||||
type: 'item.started',
|
||||
item: {
|
||||
id: 'item_1',
|
||||
type: 'mcp_tool_call',
|
||||
server: 'ktx',
|
||||
tool: 'echo_value',
|
||||
arguments: { value: 'ktx_codex_tool_ok' },
|
||||
result: null,
|
||||
error: null,
|
||||
status: 'in_progress',
|
||||
},
|
||||
},
|
||||
{
|
||||
type: 'item.completed',
|
||||
item: {
|
||||
id: 'item_1',
|
||||
type: 'mcp_tool_call',
|
||||
server: 'ktx',
|
||||
tool: 'echo_value',
|
||||
arguments: { value: 'ktx_codex_tool_ok' },
|
||||
result: { content: [{ type: 'text', text: 'echo:ktx_codex_tool_ok' }], structured_content: null },
|
||||
error: null,
|
||||
status: 'completed',
|
||||
},
|
||||
},
|
||||
{ type: 'item.completed', item: { id: 'm1', type: 'agent_message', text: 'done' } },
|
||||
{ type: 'turn.completed', usage: { input_tokens: 1, output_tokens: 1 } },
|
||||
]);
|
||||
|
||||
expect(summary.toolFailures).toEqual([]);
|
||||
expect(summary.toolCallCount).toBe(1);
|
||||
});
|
||||
|
||||
it('counts built-in command executions as loop steps without failing the loop', () => {
|
||||
const offsets = [110, 130];
|
||||
const summary = summarizeCodexExecEvents(
|
||||
[
|
||||
{ type: 'turn.started' },
|
||||
{ type: 'item.completed', item: { id: 'c1', type: 'command_execution', command: 'ls', status: 'completed', exit_code: 0 } },
|
||||
{ type: 'item.completed', item: { id: 'c2', type: 'command_execution', command: 'cat missing', status: 'failed', exit_code: 1 } },
|
||||
{ type: 'item.completed', item: { id: 'm1', type: 'agent_message', text: 'done' } },
|
||||
{ type: 'turn.completed', usage: { input_tokens: 2, output_tokens: 1 } },
|
||||
],
|
||||
{ startedAt: 100, now: () => offsets.shift() ?? 130 },
|
||||
);
|
||||
|
||||
expect(summary.stepCount).toBe(2);
|
||||
expect(summary.stepBoundariesMs).toEqual([10, 30]);
|
||||
// A non-zero command exit is normal agent exploration, not a runtime tool failure.
|
||||
expect(summary.toolFailures).toEqual([]);
|
||||
expect(summary.toolCallCount).toBe(0);
|
||||
});
|
||||
|
||||
it('maps turn failures into error stop reason', () => {
|
||||
const summary = summarizeCodexExecEvents([
|
||||
{ type: 'turn.started' },
|
||||
{ type: 'turn.failed', error: { message: 'Codex could not connect to required MCP server' } },
|
||||
]);
|
||||
|
||||
expect(summary.stopReason).toBe('error');
|
||||
expect(summary.error?.message).toContain('Codex could not connect to required MCP server');
|
||||
});
|
||||
|
||||
it('unwraps the Codex API error envelope into its human-readable message', () => {
|
||||
// Codex serializes API errors as a JSON envelope inside the event message.
|
||||
const apiError = JSON.stringify({
|
||||
type: 'error',
|
||||
status: 400,
|
||||
error: {
|
||||
type: 'invalid_request_error',
|
||||
message: "The 'gpt-5.3-codex' model is not supported when using Codex with a ChatGPT account.",
|
||||
},
|
||||
});
|
||||
const summary = summarizeCodexExecEvents([
|
||||
{ type: 'thread.started', thread_id: 'thr_1' },
|
||||
{ type: 'turn.started' },
|
||||
{ type: 'error', message: apiError },
|
||||
{ type: 'turn.failed', error: { message: apiError } },
|
||||
]);
|
||||
|
||||
expect(summary.stopReason).toBe('error');
|
||||
expect(summary.error?.message).toBe(
|
||||
"The 'gpt-5.3-codex' model is not supported when using Codex with a ChatGPT account.",
|
||||
);
|
||||
});
|
||||
|
||||
it('maps max-turns terminal reasons into budget stop reason when Codex emits one', () => {
|
||||
const summary = summarizeCodexExecEvents([
|
||||
{ type: 'turn.started' },
|
||||
{ type: 'turn.completed', reason: 'max_turns', usage: { input_tokens: 1, output_tokens: 1 } },
|
||||
]);
|
||||
|
||||
expect(summary.stopReason).toBe('budget');
|
||||
});
|
||||
|
||||
it('throws a clear error for malformed JSONL lines', () => {
|
||||
expect(() => parseCodexExecEventLine('{not-json')).toThrow('Codex JSONL event stream was malformed');
|
||||
});
|
||||
});
|
||||
19
packages/cli/test/context/llm/codex-isolation.test.ts
Normal file
19
packages/cli/test/context/llm/codex-isolation.test.ts
Normal file
|
|
@ -0,0 +1,19 @@
|
|||
import { describe, expect, it } from 'vitest';
|
||||
import {
|
||||
CODEX_ISOLATION_WARNING,
|
||||
CODEX_ISOLATION_WARNING_FIX,
|
||||
formatCodexIsolationWarning,
|
||||
} from '../../../src/context/llm/codex-isolation.js';
|
||||
|
||||
describe('Codex isolation warning', () => {
|
||||
it('documents the enforced and unenforced Codex isolation boundaries', () => {
|
||||
expect(CODEX_ISOLATION_WARNING).toContain('runtime MCP server to the current ktx tool set');
|
||||
expect(CODEX_ISOLATION_WARNING).toContain('disables Codex web search');
|
||||
expect(CODEX_ISOLATION_WARNING).toContain('may still load user Codex config');
|
||||
expect(CODEX_ISOLATION_WARNING).toContain('built-in command execution');
|
||||
expect(CODEX_ISOLATION_WARNING_FIX).toContain('claude-code');
|
||||
expect(formatCodexIsolationWarning()).toBe(
|
||||
`${CODEX_ISOLATION_WARNING} ${CODEX_ISOLATION_WARNING_FIX}`,
|
||||
);
|
||||
});
|
||||
});
|
||||
|
|
@ -0,0 +1,73 @@
|
|||
import { describe, expect, it, vi } from 'vitest';
|
||||
import { z } from 'zod';
|
||||
import {
|
||||
createCodexRuntimeMcpServer,
|
||||
startCodexRuntimeMcpServer,
|
||||
} from '../../../src/context/llm/codex-mcp-runtime-server.js';
|
||||
|
||||
describe('Codex runtime MCP server', () => {
|
||||
it('registers runtime tools with markdown output', async () => {
|
||||
const registered = new Map<
|
||||
string,
|
||||
{
|
||||
config: { description?: string; inputSchema: unknown };
|
||||
handler: (input: Record<string, unknown>) => Promise<unknown>;
|
||||
}
|
||||
>();
|
||||
const server = createCodexRuntimeMcpServer({
|
||||
server: {
|
||||
registerTool(name, config, handler) {
|
||||
registered.set(name, { config, handler });
|
||||
},
|
||||
},
|
||||
toolSet: {
|
||||
wiki_search: {
|
||||
name: 'wiki_search',
|
||||
description: 'Search the wiki',
|
||||
inputSchema: z.object({ query: z.string() }),
|
||||
execute: vi.fn(async () => ({ markdown: 'result markdown', structured: { matches: 1 } })),
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
expect(server).toBeDefined();
|
||||
expect([...registered.keys()]).toEqual(['wiki_search']);
|
||||
expect(registered.get('wiki_search')?.config).toMatchObject({
|
||||
description: 'Search the wiki',
|
||||
});
|
||||
await expect(registered.get('wiki_search')?.handler({ query: 'revenue' })).resolves.toEqual({
|
||||
content: [{ type: 'text', text: 'result markdown' }],
|
||||
structuredContent: { matches: 1 },
|
||||
});
|
||||
});
|
||||
|
||||
it('starts loopback HTTP MCP with a bearer token and reports the runtime URL', async () => {
|
||||
const close = vi.fn(async () => undefined);
|
||||
const runServer = vi.fn(async () => ({
|
||||
server: { address: () => ({ port: 4321 }) },
|
||||
close,
|
||||
}));
|
||||
|
||||
const handle = await startCodexRuntimeMcpServer({
|
||||
projectDir: '/tmp/ktx-project',
|
||||
toolSet: {},
|
||||
runServer: runServer as never,
|
||||
});
|
||||
|
||||
expect(handle.url).toBe('http://127.0.0.1:4321/mcp');
|
||||
expect(handle.bearerTokenEnvVar).toBe('KTX_CODEX_RUNTIME_MCP_TOKEN');
|
||||
expect(handle.bearerToken).toMatch(/^[a-f0-9]{64}$/);
|
||||
expect(runServer).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
projectDir: '/tmp/ktx-project',
|
||||
host: '127.0.0.1',
|
||||
port: 0,
|
||||
token: handle.bearerToken,
|
||||
allowedHosts: ['127.0.0.1', 'localhost'],
|
||||
allowedOrigins: [],
|
||||
}),
|
||||
);
|
||||
await handle.close();
|
||||
expect(close).toHaveBeenCalled();
|
||||
});
|
||||
});
|
||||
17
packages/cli/test/context/llm/codex-models.test.ts
Normal file
17
packages/cli/test/context/llm/codex-models.test.ts
Normal file
|
|
@ -0,0 +1,17 @@
|
|||
import { describe, expect, it } from 'vitest';
|
||||
import { resolveCodexModel } from '../../../src/context/llm/codex-models.js';
|
||||
|
||||
describe('resolveCodexModel', () => {
|
||||
it.each([
|
||||
['codex', 'gpt-5.5'],
|
||||
['default', 'gpt-5.5'],
|
||||
['gpt-5.3-codex-spark', 'gpt-5.3-codex-spark'],
|
||||
['gpt-5.4', 'gpt-5.4'],
|
||||
])('maps %s to %s', (input, expected) => {
|
||||
expect(resolveCodexModel(input)).toBe(expected);
|
||||
});
|
||||
|
||||
it.each(['', ' ', 'sonnet', 'claude-sonnet-4-6'])('rejects %s', (input) => {
|
||||
expect(() => resolveCodexModel(input)).toThrow('Unsupported Codex model');
|
||||
});
|
||||
});
|
||||
43
packages/cli/test/context/llm/codex-runtime-config.test.ts
Normal file
43
packages/cli/test/context/llm/codex-runtime-config.test.ts
Normal file
|
|
@ -0,0 +1,43 @@
|
|||
import { describe, expect, it } from 'vitest';
|
||||
import { buildCodexRuntimeConfig } from '../../../src/context/llm/codex-runtime-config.js';
|
||||
|
||||
describe('buildCodexRuntimeConfig', () => {
|
||||
it('builds generic config without SDK thread-option fields', () => {
|
||||
expect(buildCodexRuntimeConfig({ model: 'gpt-5.3-codex' })).toEqual({
|
||||
configOverrides: {
|
||||
history: { persistence: 'none' },
|
||||
},
|
||||
env: {},
|
||||
});
|
||||
});
|
||||
|
||||
it('adds only the temporary ktx MCP server and exact enabled tools', () => {
|
||||
expect(
|
||||
buildCodexRuntimeConfig({
|
||||
model: 'gpt-5.3-codex',
|
||||
mcp: {
|
||||
url: 'http://127.0.0.1:4567/mcp',
|
||||
bearerTokenEnvVar: 'KTX_CODEX_RUNTIME_MCP_TOKEN',
|
||||
bearerToken: 'secret-token',
|
||||
toolNames: ['sl_read_source', 'wiki_search'],
|
||||
},
|
||||
}),
|
||||
).toEqual({
|
||||
configOverrides: {
|
||||
history: { persistence: 'none' },
|
||||
mcp_servers: {
|
||||
ktx: {
|
||||
url: 'http://127.0.0.1:4567/mcp',
|
||||
bearer_token_env_var: 'KTX_CODEX_RUNTIME_MCP_TOKEN',
|
||||
enabled_tools: ['sl_read_source', 'wiki_search'],
|
||||
default_tools_approval_mode: 'approve',
|
||||
required: true,
|
||||
},
|
||||
},
|
||||
},
|
||||
env: {
|
||||
KTX_CODEX_RUNTIME_MCP_TOKEN: 'secret-token',
|
||||
},
|
||||
});
|
||||
});
|
||||
});
|
||||
460
packages/cli/test/context/llm/codex-runtime.test.ts
Normal file
460
packages/cli/test/context/llm/codex-runtime.test.ts
Normal file
|
|
@ -0,0 +1,460 @@
|
|||
import { describe, expect, it, vi } from 'vitest';
|
||||
import { z } from 'zod';
|
||||
import {
|
||||
CodexKtxLlmRuntime,
|
||||
runCodexAuthProbe,
|
||||
} from '../../../src/context/llm/codex-runtime.js';
|
||||
|
||||
async function* events(items: unknown[]) {
|
||||
for (const item of items) {
|
||||
yield item;
|
||||
}
|
||||
}
|
||||
|
||||
function runner(items: unknown[]) {
|
||||
return {
|
||||
runStreamed: vi.fn(async () => events(items)),
|
||||
};
|
||||
}
|
||||
|
||||
/** Yields the given events, then throws — mirroring the SDK throwing on a non-zero codex exec exit. */
|
||||
function throwingRunner(items: unknown[], error: Error) {
|
||||
return {
|
||||
runStreamed: vi.fn(async () =>
|
||||
(async function* () {
|
||||
for (const item of items) {
|
||||
yield item;
|
||||
}
|
||||
throw error;
|
||||
})(),
|
||||
),
|
||||
};
|
||||
}
|
||||
|
||||
const MODEL_UNSUPPORTED_API_ERROR = JSON.stringify({
|
||||
type: 'error',
|
||||
status: 400,
|
||||
error: {
|
||||
type: 'invalid_request_error',
|
||||
message: "The 'gpt-5.3-codex' model is not supported when using Codex with a ChatGPT account.",
|
||||
},
|
||||
});
|
||||
|
||||
function budgetRunner() {
|
||||
let observedSignal: AbortSignal | undefined;
|
||||
return {
|
||||
observedSignal: () => observedSignal,
|
||||
runStreamed: vi.fn(async (input: { signal?: AbortSignal }) => {
|
||||
observedSignal = input.signal;
|
||||
return events([
|
||||
{ type: 'turn.started' },
|
||||
{ type: 'item.started', item: { type: 'mcp_tool_call', server: 'ktx', tool: 'first', status: 'in_progress' } },
|
||||
{ type: 'item.completed', item: { type: 'mcp_tool_call', server: 'ktx', tool: 'first', status: 'completed' } },
|
||||
{ type: 'item.started', item: { type: 'mcp_tool_call', server: 'ktx', tool: 'second', status: 'in_progress' } },
|
||||
{ type: 'item.completed', item: { type: 'mcp_tool_call', server: 'ktx', tool: 'second', status: 'completed' } },
|
||||
{ type: 'turn.completed', usage: { input_tokens: 1, output_tokens: 1 } },
|
||||
]);
|
||||
}),
|
||||
};
|
||||
}
|
||||
|
||||
describe('CodexKtxLlmRuntime', () => {
|
||||
it('generates text with the role-selected model and metrics', async () => {
|
||||
const onMetrics = vi.fn();
|
||||
const fakeRunner = runner([
|
||||
{ type: 'turn.started' },
|
||||
{ type: 'item.completed', item: { type: 'agent_message', text: 'hello' } },
|
||||
{ type: 'turn.completed', usage: { input_tokens: 3, output_tokens: 4, total_tokens: 7 } },
|
||||
]);
|
||||
const runtime = new CodexKtxLlmRuntime({
|
||||
projectDir: '/tmp/project',
|
||||
modelSlots: { default: 'codex', triage: 'gpt-5.4' },
|
||||
runner: fakeRunner,
|
||||
});
|
||||
|
||||
await expect(runtime.generateText({ role: 'triage', system: 'system', prompt: 'prompt', onMetrics })).resolves.toBe('hello');
|
||||
expect(fakeRunner.runStreamed).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
projectDir: '/tmp/project',
|
||||
model: 'gpt-5.4',
|
||||
prompt: 'system\n\nprompt',
|
||||
}),
|
||||
);
|
||||
expect(onMetrics).toHaveBeenCalledWith(expect.objectContaining({ usage: { inputTokens: 3, outputTokens: 4, totalTokens: 7 } }));
|
||||
});
|
||||
|
||||
it('generates and validates structured output', async () => {
|
||||
const fakeRunner = runner([
|
||||
{ type: 'turn.started' },
|
||||
{ type: 'item.completed', item: { type: 'agent_message', text: '{"answer":"yes"}' } },
|
||||
{ type: 'turn.completed' },
|
||||
]);
|
||||
const runtime = new CodexKtxLlmRuntime({
|
||||
projectDir: '/tmp/project',
|
||||
modelSlots: { default: 'codex' },
|
||||
runner: fakeRunner,
|
||||
});
|
||||
|
||||
await expect(
|
||||
runtime.generateObject({
|
||||
role: 'default',
|
||||
prompt: 'json',
|
||||
schema: z.object({ answer: z.string() }),
|
||||
}),
|
||||
).resolves.toEqual({ answer: 'yes' });
|
||||
expect(fakeRunner.runStreamed).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
outputSchema: expect.objectContaining({ type: 'object' }),
|
||||
}),
|
||||
);
|
||||
});
|
||||
|
||||
it('returns a structured-output error when Codex final text is invalid JSON', async () => {
|
||||
const fakeRunner = runner([
|
||||
{ type: 'turn.started' },
|
||||
{ type: 'item.completed', item: { type: 'agent_message', text: 'not json' } },
|
||||
{ type: 'turn.completed' },
|
||||
]);
|
||||
const runtime = new CodexKtxLlmRuntime({
|
||||
projectDir: '/tmp/project',
|
||||
modelSlots: { default: 'codex' },
|
||||
runner: fakeRunner,
|
||||
});
|
||||
|
||||
await expect(
|
||||
runtime.generateObject({
|
||||
role: 'default',
|
||||
prompt: 'json',
|
||||
schema: z.object({ answer: z.string() }),
|
||||
}),
|
||||
).rejects.toThrow('Codex structured output failed validation');
|
||||
});
|
||||
|
||||
it('starts and closes a temporary MCP server for tool-backed agent loops', async () => {
|
||||
const close = vi.fn(async () => undefined);
|
||||
const startMcpServer = vi.fn(async () => ({
|
||||
url: 'http://127.0.0.1:4321/mcp',
|
||||
bearerTokenEnvVar: 'KTX_CODEX_RUNTIME_MCP_TOKEN' as const,
|
||||
bearerToken: 'token',
|
||||
close,
|
||||
}));
|
||||
const fakeRunner = runner([
|
||||
{ type: 'turn.started' },
|
||||
{ type: 'item.started', item: { type: 'mcp_tool_call', name: 'wiki_search' } },
|
||||
{ type: 'item.completed', item: { type: 'agent_message', text: 'done' } },
|
||||
{ type: 'turn.completed', usage: { input_tokens: 1, output_tokens: 1, total_tokens: 2 } },
|
||||
]);
|
||||
const runtime = new CodexKtxLlmRuntime({
|
||||
projectDir: '/tmp/project',
|
||||
modelSlots: { default: 'codex' },
|
||||
runner: fakeRunner,
|
||||
startMcpServer,
|
||||
});
|
||||
const onStepFinish = vi.fn();
|
||||
|
||||
const result = await runtime.runAgentLoop({
|
||||
modelRole: 'default',
|
||||
systemPrompt: 'system',
|
||||
userPrompt: 'user',
|
||||
stepBudget: 5,
|
||||
telemetryTags: {},
|
||||
onStepFinish,
|
||||
toolSet: {
|
||||
aliased_wiki_tool: {
|
||||
name: 'wiki_search',
|
||||
description: 'Search wiki',
|
||||
inputSchema: z.object({ query: z.string() }),
|
||||
execute: vi.fn(),
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
expect(result.stopReason).toBe('natural');
|
||||
expect(result.metrics).toMatchObject({ stepCount: 1, usage: { inputTokens: 1, outputTokens: 1, totalTokens: 2 } });
|
||||
expect(onStepFinish).toHaveBeenCalledWith({ stepIndex: 1, stepBudget: 5 });
|
||||
expect(startMcpServer).toHaveBeenCalledWith({ projectDir: '/tmp/project', toolSet: expect.any(Object) });
|
||||
expect(fakeRunner.runStreamed).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
env: { KTX_CODEX_RUNTIME_MCP_TOKEN: 'token' },
|
||||
configOverrides: expect.objectContaining({
|
||||
mcp_servers: expect.objectContaining({
|
||||
ktx: expect.objectContaining({
|
||||
url: 'http://127.0.0.1:4321/mcp',
|
||||
enabled_tools: ['wiki_search'],
|
||||
required: true,
|
||||
}),
|
||||
}),
|
||||
}),
|
||||
}),
|
||||
);
|
||||
expect(close).toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it('returns error stop reason on turn failure', async () => {
|
||||
const runtime = new CodexKtxLlmRuntime({
|
||||
projectDir: '/tmp/project',
|
||||
modelSlots: { default: 'codex' },
|
||||
runner: runner([{ type: 'turn.failed', error: { message: 'boom' } }]),
|
||||
});
|
||||
|
||||
const result = await runtime.runAgentLoop({
|
||||
modelRole: 'default',
|
||||
systemPrompt: 'system',
|
||||
userPrompt: 'user',
|
||||
stepBudget: 5,
|
||||
telemetryTags: {},
|
||||
toolSet: {},
|
||||
});
|
||||
|
||||
expect(result.stopReason).toBe('error');
|
||||
expect(result.error?.message).toBe('boom');
|
||||
});
|
||||
|
||||
it('surfaces failed MCP tool calls as agent-loop errors', async () => {
|
||||
const runtime = new CodexKtxLlmRuntime({
|
||||
projectDir: '/tmp/project',
|
||||
modelSlots: { default: 'codex' },
|
||||
runner: runner([
|
||||
{ type: 'turn.started' },
|
||||
{ type: 'item.started', item: { type: 'mcp_tool_call', server: 'ktx', tool: 'search', status: 'in_progress' } },
|
||||
{
|
||||
type: 'item.completed',
|
||||
item: {
|
||||
type: 'mcp_tool_call',
|
||||
server: 'ktx',
|
||||
tool: 'search',
|
||||
status: 'failed',
|
||||
error: { message: 'denied' },
|
||||
},
|
||||
},
|
||||
{ type: 'turn.completed', usage: { input_tokens: 1, output_tokens: 1 } },
|
||||
]),
|
||||
});
|
||||
|
||||
const result = await runtime.runAgentLoop({
|
||||
modelRole: 'default',
|
||||
systemPrompt: 'system',
|
||||
userPrompt: 'user',
|
||||
stepBudget: 5,
|
||||
telemetryTags: {},
|
||||
toolSet: {},
|
||||
});
|
||||
|
||||
expect(result.stopReason).toBe('error');
|
||||
expect(result.error?.message).toBe('Codex runtime tool call failed: search: denied');
|
||||
expect(result.metrics).toMatchObject({
|
||||
stepCount: 1,
|
||||
usage: { inputTokens: 1, outputTokens: 1, totalTokens: 2 },
|
||||
});
|
||||
});
|
||||
|
||||
it('returns budget and aborts the Codex stream when local MCP step budget is reached', async () => {
|
||||
const fakeRunner = budgetRunner();
|
||||
const runtime = new CodexKtxLlmRuntime({
|
||||
projectDir: '/tmp/project',
|
||||
modelSlots: { default: 'codex' },
|
||||
runner: fakeRunner,
|
||||
});
|
||||
const onStepFinish = vi.fn();
|
||||
|
||||
const result = await runtime.runAgentLoop({
|
||||
modelRole: 'default',
|
||||
systemPrompt: 'system',
|
||||
userPrompt: 'user',
|
||||
stepBudget: 1,
|
||||
telemetryTags: {},
|
||||
onStepFinish,
|
||||
toolSet: {
|
||||
first: {
|
||||
name: 'first',
|
||||
description: 'First tool',
|
||||
inputSchema: z.object({}),
|
||||
execute: vi.fn(),
|
||||
},
|
||||
},
|
||||
});
|
||||
|
||||
expect(result.stopReason).toBe('budget');
|
||||
expect(result.error).toBeUndefined();
|
||||
expect(result.metrics).toMatchObject({ stepCount: 1 });
|
||||
expect(onStepFinish).toHaveBeenCalledTimes(1);
|
||||
expect(onStepFinish).toHaveBeenCalledWith({ stepIndex: 1, stepBudget: 1 });
|
||||
expect(fakeRunner.observedSignal()?.aborted).toBe(true);
|
||||
});
|
||||
|
||||
it('counts built-in command_execution steps against the budget and aborts the stream', async () => {
|
||||
let observedSignal: AbortSignal | undefined;
|
||||
const fakeRunner = {
|
||||
observedSignal: () => observedSignal,
|
||||
runStreamed: vi.fn(async (input: { signal?: AbortSignal }) => {
|
||||
observedSignal = input.signal;
|
||||
return events([
|
||||
{ type: 'turn.started' },
|
||||
{ type: 'item.started', item: { type: 'command_execution', command: 'ls', status: 'in_progress' } },
|
||||
{ type: 'item.completed', item: { type: 'command_execution', command: 'ls', status: 'completed', exit_code: 0 } },
|
||||
{ type: 'item.started', item: { type: 'command_execution', command: 'cat a', status: 'in_progress' } },
|
||||
{ type: 'item.completed', item: { type: 'command_execution', command: 'cat a', status: 'completed', exit_code: 0 } },
|
||||
{ type: 'item.completed', item: { type: 'command_execution', command: 'cat b', status: 'completed', exit_code: 0 } },
|
||||
{ type: 'turn.completed', usage: { input_tokens: 1, output_tokens: 1 } },
|
||||
]);
|
||||
}),
|
||||
};
|
||||
const runtime = new CodexKtxLlmRuntime({
|
||||
projectDir: '/tmp/project',
|
||||
modelSlots: { default: 'codex' },
|
||||
runner: fakeRunner,
|
||||
});
|
||||
const onStepFinish = vi.fn();
|
||||
|
||||
const result = await runtime.runAgentLoop({
|
||||
modelRole: 'default',
|
||||
systemPrompt: 'system',
|
||||
userPrompt: 'user',
|
||||
stepBudget: 2,
|
||||
telemetryTags: {},
|
||||
onStepFinish,
|
||||
toolSet: {},
|
||||
});
|
||||
|
||||
expect(result.stopReason).toBe('budget');
|
||||
expect(result.error).toBeUndefined();
|
||||
expect(result.metrics).toMatchObject({ stepCount: 2 });
|
||||
expect(onStepFinish).toHaveBeenCalledTimes(2);
|
||||
expect(onStepFinish).toHaveBeenLastCalledWith({ stepIndex: 2, stepBudget: 2 });
|
||||
expect(fakeRunner.observedSignal()?.aborted).toBe(true);
|
||||
});
|
||||
|
||||
it('fires onStepFinish live as each step completes, before the stream drains', async () => {
|
||||
const order: string[] = [];
|
||||
async function* liveEvents() {
|
||||
yield { type: 'turn.started' };
|
||||
yield { type: 'item.completed', item: { type: 'mcp_tool_call', server: 'ktx', tool: 'a', status: 'completed' } };
|
||||
order.push('yielded-after-step-1');
|
||||
yield { type: 'item.completed', item: { type: 'mcp_tool_call', server: 'ktx', tool: 'b', status: 'completed' } };
|
||||
order.push('yielded-after-step-2');
|
||||
yield { type: 'item.completed', item: { type: 'agent_message', text: 'done' } };
|
||||
yield { type: 'turn.completed', usage: { input_tokens: 1, output_tokens: 1 } };
|
||||
}
|
||||
const fakeRunner = { runStreamed: vi.fn(async () => liveEvents()) };
|
||||
const runtime = new CodexKtxLlmRuntime({
|
||||
projectDir: '/tmp/project',
|
||||
modelSlots: { default: 'codex' },
|
||||
runner: fakeRunner,
|
||||
});
|
||||
|
||||
const result = await runtime.runAgentLoop({
|
||||
modelRole: 'default',
|
||||
systemPrompt: 'system',
|
||||
userPrompt: 'user',
|
||||
stepBudget: 10,
|
||||
telemetryTags: {},
|
||||
onStepFinish: ({ stepIndex }) => {
|
||||
order.push(`step-${stepIndex}`);
|
||||
},
|
||||
toolSet: {},
|
||||
});
|
||||
|
||||
expect(result.stopReason).toBe('natural');
|
||||
expect(result.metrics).toMatchObject({ stepCount: 2 });
|
||||
expect(order).toEqual(['step-1', 'yielded-after-step-1', 'step-2', 'yielded-after-step-2']);
|
||||
});
|
||||
|
||||
it('surfaces the real Codex error event even when the SDK stream throws afterward', async () => {
|
||||
// The SDK yields the error/turn.failed events on stdout, then throws on the
|
||||
// non-zero exit. The masked exit message must not hide the real API error.
|
||||
const fakeRunner = throwingRunner(
|
||||
[
|
||||
{ type: 'thread.started', thread_id: 't' },
|
||||
{ type: 'turn.started' },
|
||||
{ type: 'error', message: MODEL_UNSUPPORTED_API_ERROR },
|
||||
{ type: 'turn.failed', error: { message: MODEL_UNSUPPORTED_API_ERROR } },
|
||||
],
|
||||
new Error('Codex Exec exited with code 1: Reading prompt from stdin...'),
|
||||
);
|
||||
const runtime = new CodexKtxLlmRuntime({
|
||||
projectDir: '/tmp/project',
|
||||
modelSlots: { default: 'codex' },
|
||||
runner: fakeRunner,
|
||||
});
|
||||
|
||||
await expect(runtime.generateText({ role: 'default', prompt: 'hi' })).rejects.toThrow(
|
||||
'not supported when using Codex with a ChatGPT account',
|
||||
);
|
||||
});
|
||||
|
||||
it('probes Codex authentication through a minimal non-interactive turn', async () => {
|
||||
const fakeRunner = runner([
|
||||
{ type: 'turn.started' },
|
||||
{ type: 'item.completed', item: { type: 'agent_message', text: 'ok' } },
|
||||
{ type: 'turn.completed' },
|
||||
]);
|
||||
|
||||
await expect(
|
||||
runCodexAuthProbe({
|
||||
projectDir: '/tmp/project',
|
||||
model: 'codex',
|
||||
runner: fakeRunner,
|
||||
}),
|
||||
).resolves.toEqual({ ok: true });
|
||||
});
|
||||
|
||||
it('reports an unavailable model without blaming auth when Codex rejects the model', async () => {
|
||||
const fakeRunner = throwingRunner(
|
||||
[
|
||||
{ type: 'turn.started' },
|
||||
{ type: 'turn.failed', error: { message: MODEL_UNSUPPORTED_API_ERROR } },
|
||||
],
|
||||
new Error('Codex Exec exited with code 1: Reading prompt from stdin...'),
|
||||
);
|
||||
|
||||
const result = await runCodexAuthProbe({
|
||||
projectDir: '/tmp/project',
|
||||
model: 'gpt-5.3-codex',
|
||||
runner: fakeRunner,
|
||||
});
|
||||
|
||||
expect(result.ok).toBe(false);
|
||||
if (!result.ok) {
|
||||
expect(result.message).not.toContain('authentication is not usable');
|
||||
expect(result.message).toContain('not available');
|
||||
expect(result.message).toContain('gpt-5.3-codex');
|
||||
expect(result.message).toContain('not supported when using Codex with a ChatGPT account');
|
||||
// A model-access failure must steer the user at the model config, not auth.
|
||||
expect(result.fix).toContain('llm.models.default');
|
||||
expect(result.fix).not.toContain('Authenticate Codex');
|
||||
}
|
||||
});
|
||||
|
||||
it('reports an auth failure when Codex exits without an error event', async () => {
|
||||
const fakeRunner = throwingRunner(
|
||||
[],
|
||||
new Error('Codex Exec exited with code 1: Not logged in. Run `codex login`.'),
|
||||
);
|
||||
|
||||
const result = await runCodexAuthProbe({
|
||||
projectDir: '/tmp/project',
|
||||
model: 'gpt-5.5',
|
||||
runner: fakeRunner,
|
||||
});
|
||||
|
||||
expect(result.ok).toBe(false);
|
||||
if (!result.ok) {
|
||||
expect(result.message).toContain('authentication is not usable');
|
||||
expect(result.message).toContain('Not logged in');
|
||||
expect(result.fix).toContain('Authenticate Codex');
|
||||
}
|
||||
});
|
||||
|
||||
it('rejects an unsupported model id before probing, steering at llm.models.default', async () => {
|
||||
const result = await runCodexAuthProbe({
|
||||
projectDir: '/tmp/project',
|
||||
model: 'not-a-real-model',
|
||||
});
|
||||
|
||||
expect(result.ok).toBe(false);
|
||||
if (!result.ok) {
|
||||
expect(result.message).toContain('Unsupported Codex model');
|
||||
expect(result.fix).toContain('llm.models.default');
|
||||
}
|
||||
});
|
||||
});
|
||||
97
packages/cli/test/context/llm/codex-sdk-runner.test.ts
Normal file
97
packages/cli/test/context/llm/codex-sdk-runner.test.ts
Normal file
|
|
@ -0,0 +1,97 @@
|
|||
import { describe, expect, it, vi } from 'vitest';
|
||||
|
||||
const sdkMock = vi.hoisted(() => {
|
||||
const events = (async function* () {
|
||||
yield { type: 'turn.completed', usage: { input_tokens: 1, output_tokens: 2 } };
|
||||
})();
|
||||
const runStreamed = vi.fn(async () => ({ events }));
|
||||
const startThread = vi.fn(() => ({ runStreamed }));
|
||||
const Codex = vi.fn(function Codex(this: { startThread: typeof startThread }, options?: unknown) {
|
||||
Object.assign(this, { options, startThread });
|
||||
});
|
||||
return { Codex, startThread, runStreamed };
|
||||
});
|
||||
|
||||
vi.mock('@openai/codex-sdk', () => ({ Codex: sdkMock.Codex }));
|
||||
|
||||
import { CodexSdkCliRunner } from '../../../src/context/llm/codex-sdk-runner.js';
|
||||
|
||||
async function collectAsync<T>(items: AsyncIterable<T>): Promise<T[]> {
|
||||
const collected: T[] = [];
|
||||
for await (const item of items) {
|
||||
collected.push(item);
|
||||
}
|
||||
return collected;
|
||||
}
|
||||
|
||||
describe('CodexSdkCliRunner', () => {
|
||||
it('passes isolated env through the SDK and runtime controls through thread options', async () => {
|
||||
const runner = new CodexSdkCliRunner({
|
||||
envBase: {
|
||||
HOME: '/home/ktx-user',
|
||||
PATH: '/usr/local/bin:/usr/bin',
|
||||
CODEX_HOME: '/home/ktx-user/.codex',
|
||||
HTTPS_PROXY: 'http://proxy.example',
|
||||
KTX_UNRELATED_SECRET: 'must-not-copy', // pragma: allowlist secret
|
||||
},
|
||||
});
|
||||
const previousToken = process.env.KTX_CODEX_RUNTIME_MCP_TOKEN;
|
||||
process.env.KTX_CODEX_RUNTIME_MCP_TOKEN = 'outer-token';
|
||||
const outputSchema = {
|
||||
type: 'object',
|
||||
properties: { answer: { type: 'string' } },
|
||||
required: ['answer'],
|
||||
additionalProperties: false,
|
||||
};
|
||||
const controller = new AbortController();
|
||||
|
||||
try {
|
||||
const events = await runner.runStreamed({
|
||||
projectDir: '/tmp/ktx-project',
|
||||
model: 'gpt-5.3-codex',
|
||||
prompt: 'Return JSON.',
|
||||
configOverrides: {
|
||||
history: { persistence: 'none' },
|
||||
},
|
||||
env: { KTX_CODEX_RUNTIME_MCP_TOKEN: 'run-token' },
|
||||
outputSchema,
|
||||
signal: controller.signal,
|
||||
});
|
||||
|
||||
expect(sdkMock.Codex).toHaveBeenCalledWith({
|
||||
config: {
|
||||
history: { persistence: 'none' },
|
||||
},
|
||||
env: {
|
||||
HOME: '/home/ktx-user',
|
||||
PATH: '/usr/local/bin:/usr/bin',
|
||||
CODEX_HOME: '/home/ktx-user/.codex',
|
||||
HTTPS_PROXY: 'http://proxy.example',
|
||||
KTX_CODEX_RUNTIME_MCP_TOKEN: 'run-token',
|
||||
},
|
||||
});
|
||||
expect(process.env.KTX_CODEX_RUNTIME_MCP_TOKEN).toBe('outer-token');
|
||||
expect(sdkMock.startThread).toHaveBeenCalledWith({
|
||||
workingDirectory: '/tmp/ktx-project',
|
||||
skipGitRepoCheck: true,
|
||||
model: 'gpt-5.3-codex',
|
||||
sandboxMode: 'read-only',
|
||||
webSearchMode: 'disabled',
|
||||
approvalPolicy: 'never',
|
||||
});
|
||||
expect(sdkMock.runStreamed).toHaveBeenCalledWith('Return JSON.', {
|
||||
outputSchema,
|
||||
signal: controller.signal,
|
||||
});
|
||||
await expect(collectAsync(events)).resolves.toEqual([
|
||||
{ type: 'turn.completed', usage: { input_tokens: 1, output_tokens: 2 } },
|
||||
]);
|
||||
} finally {
|
||||
if (previousToken === undefined) {
|
||||
delete process.env.KTX_CODEX_RUNTIME_MCP_TOKEN;
|
||||
} else {
|
||||
process.env.KTX_CODEX_RUNTIME_MCP_TOKEN = previousToken;
|
||||
}
|
||||
}
|
||||
});
|
||||
});
|
||||
|
|
@ -22,4 +22,25 @@ describe('local KTX LLM runtime config', () => {
|
|||
}),
|
||||
).toBeNull();
|
||||
});
|
||||
|
||||
it('creates a Codex runtime for codex backend without creating an AI SDK provider', () => {
|
||||
const runtime = createLocalKtxLlmRuntimeFromConfig(
|
||||
{
|
||||
provider: { backend: 'codex' },
|
||||
models: { default: 'codex', triage: 'gpt-5.4' },
|
||||
},
|
||||
{ env: {}, projectDir: '/tmp/project', createCodexRuntime: vi.fn((deps) => ({ deps }) as never) },
|
||||
);
|
||||
|
||||
expect(runtime).toMatchObject({ deps: expect.objectContaining({ projectDir: '/tmp/project' }) });
|
||||
});
|
||||
|
||||
it('returns null from the AI SDK provider factory for codex backend', () => {
|
||||
expect(
|
||||
createLocalKtxLlmProviderFromConfig({
|
||||
provider: { backend: 'codex' },
|
||||
models: { default: 'codex' },
|
||||
}),
|
||||
).toBeNull();
|
||||
});
|
||||
});
|
||||
|
|
|
|||
|
|
@ -231,6 +231,31 @@ llm:
|
|||
});
|
||||
});
|
||||
|
||||
it('parses Codex as a first-class LLM backend', () => {
|
||||
const config = parseKtxProjectConfig(`
|
||||
llm:
|
||||
provider:
|
||||
backend: codex
|
||||
models:
|
||||
default: gpt-5.3-codex
|
||||
triage: gpt-5.3-codex
|
||||
candidateExtraction: gpt-5.3-codex
|
||||
curator: gpt-5.3-codex
|
||||
reconcile: gpt-5.3-codex
|
||||
repair: gpt-5.3-codex
|
||||
`);
|
||||
|
||||
expect(config.llm.provider.backend).toBe('codex');
|
||||
expect(config.llm.models).toEqual({
|
||||
default: 'gpt-5.3-codex',
|
||||
triage: 'gpt-5.3-codex',
|
||||
candidateExtraction: 'gpt-5.3-codex',
|
||||
curator: 'gpt-5.3-codex',
|
||||
reconcile: 'gpt-5.3-codex',
|
||||
repair: 'gpt-5.3-codex',
|
||||
});
|
||||
});
|
||||
|
||||
it('parses gateway LLM, OpenAI scan embeddings, and sentence-transformers ingest embeddings', () => {
|
||||
const config = parseKtxProjectConfig(`
|
||||
llm:
|
||||
|
|
@ -530,7 +555,7 @@ describe('generateKtxProjectConfigJsonSchema', () => {
|
|||
const llm = (schema.properties as Record<string, { properties?: Record<string, unknown> }>).llm;
|
||||
const provider = llm?.properties?.provider as { properties?: Record<string, unknown> };
|
||||
const backend = provider?.properties?.backend as { enum?: readonly string[] };
|
||||
expect(backend?.enum).toEqual(['none', 'anthropic', 'vertex', 'gateway', 'claude-code']);
|
||||
expect(backend?.enum).toEqual(['none', 'anthropic', 'vertex', 'gateway', 'claude-code', 'codex']);
|
||||
|
||||
const storage = (schema.properties as Record<string, { properties?: Record<string, unknown> }>).storage;
|
||||
const state = storage?.properties?.state as { enum?: readonly string[] };
|
||||
|
|
|
|||
|
|
@ -422,6 +422,8 @@ describe('runKtxDoctor', () => {
|
|||
'llm:',
|
||||
' provider:',
|
||||
' backend: anthropic',
|
||||
' models:',
|
||||
' default: claude-sonnet-4-5',
|
||||
'',
|
||||
].join('\n'),
|
||||
'utf-8',
|
||||
|
|
@ -543,6 +545,8 @@ describe('runKtxDoctor', () => {
|
|||
'llm:',
|
||||
' provider:',
|
||||
' backend: anthropic',
|
||||
' models:',
|
||||
' default: claude-sonnet-4-5',
|
||||
'ingest:',
|
||||
' adapters:',
|
||||
' - live-database',
|
||||
|
|
@ -652,6 +656,8 @@ describe('runKtxDoctor', () => {
|
|||
'llm:',
|
||||
' provider:',
|
||||
' backend: anthropic',
|
||||
' models:',
|
||||
' default: claude-sonnet-4-5',
|
||||
'',
|
||||
].join('\n'),
|
||||
'utf-8',
|
||||
|
|
@ -698,6 +704,8 @@ describe('runKtxDoctor', () => {
|
|||
'llm:',
|
||||
' provider:',
|
||||
' backend: anthropic',
|
||||
' models:',
|
||||
' default: claude-sonnet-4-5',
|
||||
'ingest:',
|
||||
' adapters:',
|
||||
' - live-database',
|
||||
|
|
|
|||
|
|
@ -337,10 +337,13 @@ describe('runKtxIngest', () => {
|
|||
|
||||
expect(runIo.stdout()).toBe('');
|
||||
expect(runIo.stderr()).toContain(
|
||||
'ktx ingest requires llm.provider.backend: anthropic, vertex, gateway, or claude-code, or an injected agentRunner.',
|
||||
'ktx ingest requires llm.provider.backend: anthropic, vertex, gateway, claude-code, or codex, or an injected agentRunner.',
|
||||
);
|
||||
expect(runIo.stderr()).toContain('Configure a local Claude Code session or API-backed LLM, then rerun ingest:');
|
||||
expect(runIo.stderr()).toContain('Configure a local Claude Code/Codex session or API-backed LLM, then rerun ingest:');
|
||||
expect(runIo.stderr()).toContain(`ktx setup --project-dir ${projectDir} --llm-backend claude-code --no-input`);
|
||||
expect(runIo.stderr()).toContain(
|
||||
`ktx setup --project-dir ${projectDir} --llm-backend codex --llm-model gpt-5.5 --no-input`,
|
||||
);
|
||||
expect(runIo.stderr()).toContain(
|
||||
`ktx setup --project-dir ${projectDir} --llm-backend anthropic --anthropic-api-key-env ANTHROPIC_API_KEY --llm-model claude-sonnet-4-6 --no-input`,
|
||||
);
|
||||
|
|
|
|||
|
|
@ -312,4 +312,13 @@ describe('createKtxLlmProvider', () => {
|
|||
}),
|
||||
).toThrow('claude-code is not an AI SDK LanguageModel backend');
|
||||
});
|
||||
|
||||
it('rejects codex as an AI SDK LanguageModel backend', () => {
|
||||
expect(() =>
|
||||
createKtxLlmProvider({
|
||||
backend: 'codex',
|
||||
modelSlots: { default: 'gpt-5.3-codex' },
|
||||
}),
|
||||
).toThrow('codex is not an AI SDK LanguageModel backend');
|
||||
});
|
||||
});
|
||||
|
|
|
|||
|
|
@ -66,6 +66,7 @@ function makePromptAdapter(options: {
|
|||
nextProviderChoice === 'anthropic' ||
|
||||
nextProviderChoice === 'vertex' ||
|
||||
nextProviderChoice === 'claude-code' ||
|
||||
nextProviderChoice === 'codex' ||
|
||||
nextProviderChoice === 'back'
|
||||
) {
|
||||
return selectValues.shift() ?? nextProviderChoice;
|
||||
|
|
@ -183,6 +184,7 @@ describe('setup Anthropic model step', () => {
|
|||
message: expect.stringContaining('Which LLM provider should KTX use?'),
|
||||
options: [
|
||||
{ value: 'claude-code', label: 'Claude subscription (Pro/Max)' },
|
||||
{ value: 'codex', label: 'Codex subscription' },
|
||||
{ value: 'anthropic', label: 'Anthropic API key' },
|
||||
{ value: 'vertex', label: 'Google Vertex AI for Anthropic Claude' },
|
||||
{ value: 'back', label: 'Back' },
|
||||
|
|
@ -215,6 +217,85 @@ describe('setup Anthropic model step', () => {
|
|||
expect(authProbe).toHaveBeenCalledWith(expect.objectContaining({ projectDir: tempDir, model: 'sonnet' }));
|
||||
});
|
||||
|
||||
it('configures Codex backend and validates local auth', async () => {
|
||||
const io = makeIo();
|
||||
const codexAuthProbe = vi.fn(async () => ({ ok: true as const }));
|
||||
|
||||
const result = await runKtxSetupAnthropicModelStep(
|
||||
{
|
||||
projectDir: tempDir,
|
||||
inputMode: 'disabled',
|
||||
llmBackend: 'codex',
|
||||
llmModel: 'gpt-5.5',
|
||||
skipLlm: false,
|
||||
},
|
||||
io.io,
|
||||
{ codexAuthProbe },
|
||||
);
|
||||
|
||||
expect(result.status).toBe('ready');
|
||||
const config = parseKtxProjectConfig(await readFile(join(tempDir, 'ktx.yaml'), 'utf-8'));
|
||||
expect(config.llm).toMatchObject({
|
||||
provider: { backend: 'codex' },
|
||||
models: { default: 'gpt-5.5' },
|
||||
});
|
||||
expect(codexAuthProbe).toHaveBeenCalledWith(expect.objectContaining({ projectDir: tempDir, model: 'gpt-5.5' }));
|
||||
// The warning carries the clack gutter so it renders inside the setup frame.
|
||||
expect(io.stderr()).toContain('│ Codex backend isolation is limited');
|
||||
expect(io.stderr()).toContain('may still load user Codex config');
|
||||
});
|
||||
|
||||
it('defaults the Codex model to gpt-5.5 when none is provided non-interactively', async () => {
|
||||
const io = makeIo();
|
||||
const codexAuthProbe = vi.fn(async () => ({ ok: true as const }));
|
||||
|
||||
const result = await runKtxSetupAnthropicModelStep(
|
||||
{
|
||||
projectDir: tempDir,
|
||||
inputMode: 'disabled',
|
||||
llmBackend: 'codex',
|
||||
skipLlm: false,
|
||||
},
|
||||
io.io,
|
||||
{ codexAuthProbe },
|
||||
);
|
||||
|
||||
expect(result.status).toBe('ready');
|
||||
const config = parseKtxProjectConfig(await readFile(join(tempDir, 'ktx.yaml'), 'utf-8'));
|
||||
expect(config.llm).toMatchObject({
|
||||
provider: { backend: 'codex' },
|
||||
models: { default: 'gpt-5.5' },
|
||||
});
|
||||
expect(codexAuthProbe).toHaveBeenCalledWith(expect.objectContaining({ projectDir: tempDir, model: 'gpt-5.5' }));
|
||||
});
|
||||
|
||||
it('offers the curated Codex models during interactive setup', async () => {
|
||||
const io = makeIo();
|
||||
const prompts = makePromptAdapter({ selectValues: ['codex', 'gpt-5.5'] });
|
||||
const codexAuthProbe = vi.fn(async () => ({ ok: true as const }));
|
||||
|
||||
const result = await runKtxSetupAnthropicModelStep(
|
||||
{ projectDir: tempDir, inputMode: 'auto', skipLlm: false },
|
||||
io.io,
|
||||
{ prompts, codexAuthProbe },
|
||||
);
|
||||
|
||||
expect(result.status).toBe('ready');
|
||||
expect(prompts.select).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
message: expect.stringContaining('Which Codex model should KTX use?'),
|
||||
options: [
|
||||
{ value: 'gpt-5.5', label: 'GPT-5.5', hint: 'recommended' },
|
||||
{ value: 'gpt-5.4', label: 'GPT-5.4' },
|
||||
{ value: 'gpt-5.4-mini', label: 'GPT-5.4 mini' },
|
||||
{ value: 'manual', label: 'Enter a Codex model ID manually' },
|
||||
{ value: 'back', label: 'Back' },
|
||||
],
|
||||
}),
|
||||
);
|
||||
expect(codexAuthProbe).toHaveBeenCalledWith(expect.objectContaining({ model: 'gpt-5.5' }));
|
||||
});
|
||||
|
||||
it('prompts for the Claude Code model during interactive setup', async () => {
|
||||
const io = makeIo();
|
||||
const prompts = makePromptAdapter({ selectValues: ['claude-code', 'opus'] });
|
||||
|
|
|
|||
|
|
@ -44,6 +44,17 @@ function withClaudeCodeLlm(config: KtxProjectConfig): KtxProjectConfig {
|
|||
};
|
||||
}
|
||||
|
||||
function withCodexLlm(config: KtxProjectConfig): KtxProjectConfig {
|
||||
return {
|
||||
...config,
|
||||
llm: {
|
||||
...config.llm,
|
||||
provider: { backend: 'codex' },
|
||||
models: { ...config.llm.models, default: 'gpt-5.5' },
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
function baseProjectConfig(): KtxProjectConfig {
|
||||
return withClaudeCodeLlm(buildDefaultKtxProjectConfig());
|
||||
}
|
||||
|
|
@ -391,6 +402,126 @@ describe('buildProjectStatus --fast', () => {
|
|||
});
|
||||
});
|
||||
|
||||
describe('buildProjectStatus codex', () => {
|
||||
it('reports authenticated local Codex session', async () => {
|
||||
const project = projectWithConfig(withCodexLlm(buildDefaultKtxProjectConfig()));
|
||||
const status = await buildProjectStatus(project, {
|
||||
codexAuthProbe: async () => ({ ok: true as const }),
|
||||
});
|
||||
|
||||
expect(status.llm).toMatchObject({
|
||||
backend: 'codex',
|
||||
model: 'gpt-5.5',
|
||||
status: 'ok',
|
||||
detail: 'local Codex session authenticated',
|
||||
});
|
||||
expect(status.warnings).toEqual(
|
||||
expect.arrayContaining([
|
||||
expect.objectContaining({
|
||||
message: expect.stringContaining('Codex backend isolation is limited'),
|
||||
fix: expect.stringContaining('claude-code'),
|
||||
}),
|
||||
]),
|
||||
);
|
||||
const rendered = renderProjectStatus(status, { verbose: false, useColor: false });
|
||||
expect(rendered).toContain('Codex backend isolation is limited');
|
||||
});
|
||||
|
||||
it('skips Codex auth probe with --fast', async () => {
|
||||
let probeCalls = 0;
|
||||
const project = projectWithConfig(withCodexLlm(buildDefaultKtxProjectConfig()));
|
||||
const status = await buildProjectStatus(project, {
|
||||
fast: true,
|
||||
codexAuthProbe: async () => {
|
||||
probeCalls += 1;
|
||||
return { ok: true };
|
||||
},
|
||||
});
|
||||
|
||||
expect(probeCalls).toBe(0);
|
||||
expect(status.llm.status).toBe('skipped');
|
||||
expect(status.llm.detail).toMatch(/--fast/);
|
||||
});
|
||||
|
||||
it('surfaces the probe fix for a model-access failure instead of an auth fix', async () => {
|
||||
const project = projectWithConfig(withCodexLlm(buildDefaultKtxProjectConfig()));
|
||||
const status = await buildProjectStatus(project, {
|
||||
codexAuthProbe: async () => ({
|
||||
ok: false,
|
||||
message: 'Codex is authenticated, but the configured model "gpt-5.5" is not available...',
|
||||
fix: 'Run `codex` to see the models your account supports, then set llm.models.default in ktx.yaml (or rerun `ktx setup`).',
|
||||
}),
|
||||
});
|
||||
|
||||
expect(status.llm.status).toBe('fail');
|
||||
expect(status.llm.fix).toContain('llm.models.default');
|
||||
expect(status.llm.fix).not.toContain('Authenticate Codex');
|
||||
});
|
||||
});
|
||||
|
||||
describe('buildProjectStatus llm models.default requirement', () => {
|
||||
function withBackendNoModel(
|
||||
backend: KtxProjectConfig['llm']['provider']['backend'],
|
||||
): KtxProjectConfig {
|
||||
const config = buildDefaultKtxProjectConfig();
|
||||
return {
|
||||
...config,
|
||||
llm: { ...config.llm, provider: { backend }, models: {} },
|
||||
};
|
||||
}
|
||||
|
||||
it('fails codex without llm.models.default and never probes', async () => {
|
||||
let probeCalls = 0;
|
||||
const project = projectWithConfig(withBackendNoModel('codex'));
|
||||
const status = await buildProjectStatus(project, {
|
||||
codexAuthProbe: async () => {
|
||||
probeCalls += 1;
|
||||
return { ok: true };
|
||||
},
|
||||
});
|
||||
|
||||
expect(probeCalls).toBe(0);
|
||||
expect(status.llm.status).toBe('fail');
|
||||
expect(status.llm.detail).toContain('llm.models.default');
|
||||
expect(status.verdict).toBe('blocked');
|
||||
});
|
||||
|
||||
it('fails claude-code without llm.models.default and never probes', async () => {
|
||||
let probeCalls = 0;
|
||||
const project = projectWithConfig(withBackendNoModel('claude-code'));
|
||||
const status = await buildProjectStatus(project, {
|
||||
claudeCodeAuthProbe: async () => {
|
||||
probeCalls += 1;
|
||||
return { ok: true };
|
||||
},
|
||||
});
|
||||
|
||||
expect(probeCalls).toBe(0);
|
||||
expect(status.llm.status).toBe('fail');
|
||||
expect(status.llm.detail).toContain('llm.models.default');
|
||||
expect(status.verdict).toBe('blocked');
|
||||
});
|
||||
|
||||
it('fails anthropic without llm.models.default even when the key is set', async () => {
|
||||
const config = withBackendNoModel('anthropic');
|
||||
const project = projectWithConfig({
|
||||
...config,
|
||||
llm: {
|
||||
...config.llm,
|
||||
provider: { backend: 'anthropic', anthropic: { api_key: 'env:ANTHROPIC_API_KEY' } }, // pragma: allowlist secret
|
||||
models: {},
|
||||
},
|
||||
});
|
||||
const status = await buildProjectStatus(project, {
|
||||
env: { ANTHROPIC_API_KEY: 'sk-test' }, // pragma: allowlist secret
|
||||
});
|
||||
|
||||
expect(status.llm.status).toBe('fail');
|
||||
expect(status.llm.detail).toContain('llm.models.default');
|
||||
expect(status.verdict).toBe('blocked');
|
||||
});
|
||||
});
|
||||
|
||||
describe('buildLocalStatsStatus', () => {
|
||||
let tempDir: string;
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue