mirror of
https://github.com/Kaelio/ktx.git
synced 2026-07-04 10:52:13 +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
|
|
@ -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,
|
||||
});
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue