Adds the managed offload mode: point codegraph_explore at the CodeGraph AI metered gateway (https://ai.getcodegraph.com) with an org token instead of a BYO provider key. Same synthesis client, pointed at codegraph-ai-proxy (a metered OpenAI-compatible gateway). - credentials.ts — org token in ~/.codegraph/credentials.json (0600); unlike a BYO provider key it's a revocable org-scoped auth token (gh/npm-login style), kept out of config.json - config.ts — managed branch in resolveOffload: default gateway URL + public model id (openai/gpt-oss-120b) + login token as bearer; managed requires a token to be enabled - reasoner.ts — fetchUsage() reads the credit balance from /v1/usage - bin/codegraph.ts — `codegraph offload login --token <t>` / `logout`; status shows the managed tier + live balance Proven GREEN end-to-end against a local wrangler-dev of the proxy: org token validated, credits prechecked, real Cerebras synthesis returned, and credits metered + charged (250,000 → 248,473). Graceful degrade on upstream failure; balance via /v1/usage. Phase 3 (codegraph login device flow) replaces the manual --token. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
150 lines
6.0 KiB
TypeScript
150 lines
6.0 KiB
TypeScript
/**
|
|
* Reasoning-offload configuration: the persistent, machine-level settings the
|
|
* `codegraph offload` CLI writes, merged with `CODEGRAPH_OFFLOAD_*` env overrides.
|
|
*
|
|
* Stored in `~/.codegraph/config.json` under the `offload` key — the same global
|
|
* home CodeGraph already uses for the daemon registry — because the reasoning
|
|
* endpoint is a per-machine choice (the model you bring), not per-project state.
|
|
* Every codegraph MCP server on the machine picks it up, so a user configures it
|
|
* once. Env vars override the file (CI / ephemeral / advanced use).
|
|
*
|
|
* For a BYO endpoint, the API key is NEVER written to disk: the CLI stores the
|
|
* NAME of an env var (`keyEnv`) and reads the key from it at call time. The
|
|
* MANAGED tier ("CodeGraph AI") instead authenticates with a revocable, org-scoped
|
|
* token from `codegraph offload login`, stored separately in `credentials.json`
|
|
* (see ./credentials) — so `config.json` itself never carries a secret either way.
|
|
*/
|
|
import * as fs from 'fs';
|
|
import * as path from 'path';
|
|
import * as os from 'os';
|
|
import { readOffloadToken } from './credentials';
|
|
|
|
/** Managed tier ("CodeGraph AI") — the metered gateway used when logged in. */
|
|
export const MANAGED_DEFAULT_URL = 'https://ai.getcodegraph.com/v1';
|
|
/** The gateway's public model id (it translates this to the upstream provider id). */
|
|
export const MANAGED_DEFAULT_MODEL = 'openai/gpt-oss-120b';
|
|
|
|
export interface OffloadConfig {
|
|
/** Managed tier: route through CodeGraph AI (metered) with the logged-in org token. */
|
|
managed?: boolean;
|
|
/** OpenAI-compatible base URL ending in `/v1` (e.g. https://api.cerebras.ai/v1). */
|
|
url?: string;
|
|
/** Model id to request (default `gpt-oss-120b` BYO, `openai/gpt-oss-120b` managed). */
|
|
model?: string;
|
|
/** Name of the env var holding the provider API key (never persisted). BYO only. */
|
|
keyEnv?: string;
|
|
/** reasoning_effort: low | medium | high (default `low`). */
|
|
effort?: string;
|
|
/** Output style: plain | report (default `plain`). */
|
|
style?: string;
|
|
}
|
|
|
|
export interface ResolvedOffload {
|
|
/** True when the offload is usable (endpoint present; for managed, a token too). */
|
|
enabled: boolean;
|
|
/** Managed tier (CodeGraph AI, metered) vs BYO endpoint. */
|
|
managed: boolean;
|
|
url?: string;
|
|
model: string;
|
|
/** Resolved API key / org token (from env, the configured `keyEnv`, or login), if any. */
|
|
apiKey?: string;
|
|
/** Where the key/token came from (for `status` display) — never the secret itself. */
|
|
keySource?: string;
|
|
effort: string;
|
|
style: string;
|
|
timeoutMs: number;
|
|
maxTokens: number;
|
|
strip: boolean;
|
|
debug: boolean;
|
|
/** Where the endpoint came from — drives `codegraph offload status`. */
|
|
origin: 'env' | 'config' | 'none';
|
|
}
|
|
|
|
function configDir(): string {
|
|
return path.join(os.homedir(), '.codegraph');
|
|
}
|
|
function configPath(): string {
|
|
return path.join(configDir(), 'config.json');
|
|
}
|
|
|
|
function readUserConfig(): Record<string, unknown> {
|
|
try {
|
|
return JSON.parse(fs.readFileSync(configPath(), 'utf8')) as Record<string, unknown>;
|
|
} catch {
|
|
return {};
|
|
}
|
|
}
|
|
|
|
function writeUserConfig(cfg: Record<string, unknown>): void {
|
|
fs.mkdirSync(configDir(), { recursive: true });
|
|
fs.writeFileSync(configPath(), JSON.stringify(cfg, null, 2) + '\n');
|
|
}
|
|
|
|
/** The persisted offload block (empty object if none). */
|
|
export function readOffloadConfig(): OffloadConfig {
|
|
const cfg = readUserConfig();
|
|
const o = cfg.offload;
|
|
return o && typeof o === 'object' ? (o as OffloadConfig) : {};
|
|
}
|
|
|
|
/** Persist (or, with `null`, clear) the offload block, leaving other config keys intact. */
|
|
export function writeOffloadConfig(offload: OffloadConfig | null): void {
|
|
const cfg = readUserConfig();
|
|
if (offload === null) delete cfg.offload;
|
|
else cfg.offload = offload;
|
|
writeUserConfig(cfg);
|
|
}
|
|
|
|
const trimmed = (v: string | undefined): string | undefined => {
|
|
const t = v?.trim();
|
|
return t ? t : undefined;
|
|
};
|
|
|
|
/** Merge the persisted config with `CODEGRAPH_OFFLOAD_*` env overrides (env wins). */
|
|
export function resolveOffload(env: NodeJS.ProcessEnv = process.env): ResolvedOffload {
|
|
const c = readOffloadConfig();
|
|
const managed = !!c.managed;
|
|
const envUrl = trimmed(env.CODEGRAPH_OFFLOAD_URL);
|
|
const envKey = trimmed(env.CODEGRAPH_OFFLOAD_KEY);
|
|
|
|
let url: string | undefined;
|
|
let apiKey: string | undefined;
|
|
let keySource: string | undefined;
|
|
let model: string;
|
|
|
|
if (managed) {
|
|
// Managed tier: default to the CodeGraph AI gateway + its public model id; the
|
|
// bearer is the org token from `codegraph offload login` (or an env override).
|
|
url = envUrl ?? trimmed(c.url) ?? MANAGED_DEFAULT_URL;
|
|
model = trimmed(env.CODEGRAPH_OFFLOAD_MODEL) ?? trimmed(c.model) ?? MANAGED_DEFAULT_MODEL;
|
|
if (envKey) { apiKey = envKey; keySource = 'CODEGRAPH_OFFLOAD_KEY'; }
|
|
else { const t = readOffloadToken(); if (t) { apiKey = t; keySource = 'codegraph login'; } }
|
|
} else {
|
|
// BYO: endpoint + (optional) provider key resolved from env or the named env var.
|
|
url = envUrl ?? trimmed(c.url);
|
|
model = trimmed(env.CODEGRAPH_OFFLOAD_MODEL) ?? trimmed(c.model) ?? 'gpt-oss-120b';
|
|
if (envKey) { apiKey = envKey; keySource = 'CODEGRAPH_OFFLOAD_KEY'; }
|
|
else if (c.keyEnv && trimmed(env[c.keyEnv])) { apiKey = trimmed(env[c.keyEnv]); keySource = c.keyEnv; }
|
|
}
|
|
|
|
const origin: ResolvedOffload['origin'] = envUrl ? 'env' : (managed || trimmed(c.url)) ? 'config' : 'none';
|
|
|
|
return {
|
|
// Managed needs both an endpoint AND a token (no token → effectively logged out);
|
|
// BYO needs only an endpoint (some endpoints require no auth).
|
|
enabled: managed ? (!!url && !!apiKey) : !!url,
|
|
managed,
|
|
url,
|
|
model,
|
|
apiKey,
|
|
keySource,
|
|
effort: trimmed(env.CODEGRAPH_OFFLOAD_EFFORT) ?? trimmed(c.effort) ?? 'low',
|
|
style: trimmed(env.CODEGRAPH_OFFLOAD_STYLE) ?? trimmed(c.style) ?? 'plain',
|
|
timeoutMs: Number(env.CODEGRAPH_OFFLOAD_TIMEOUT_MS) || 20000,
|
|
maxTokens: Number(env.CODEGRAPH_OFFLOAD_MAXTOKENS) || 12000,
|
|
strip: env.CODEGRAPH_OFFLOAD_STRIP === '1',
|
|
debug: env.CODEGRAPH_OFFLOAD_DEBUG === '1',
|
|
origin,
|
|
};
|
|
}
|