gitnexus 1.6.5-rc.26 → 1.6.5-rc.27

package/dist/cli/index.js

@@ -103,6 +103,8 @@ program
     .option('--reasoning-model', 'Mark deployment as reasoning model (o1/o3/o4-mini) — strips temperature, uses max_completion_tokens')
     .option('--no-reasoning-model', 'Disable reasoning model mode (overrides saved config)')
     .option('--concurrency <n>', 'Parallel LLM calls (default: 3)', '3')
+    .option('--timeout <seconds>', 'Per-attempt LLM request timeout in seconds (default: 60)')
+    .option('--retries <n>', 'Max LLM retry attempts per request (default: 3)')
     .option('--gist', 'Publish wiki as a public GitHub Gist after generation')
     .option('-v, --verbose', 'Enable verbose output (show LLM commands and responses)')
     .option('--review', 'Stop after grouping to review module structure before generating pages')

package/dist/cli/wiki.d.ts

@@ -17,5 +17,7 @@ export interface WikiCommandOptions {
     provider?: LLMProvider;
     verbose?: boolean;
     review?: boolean;
+    timeout?: string;
+    retries?: string;
 }
 export declare const wikiCommand: (inputPath?: string, options?: WikiCommandOptions) => Promise<void>;

package/dist/cli/wiki.js

@@ -304,6 +304,17 @@ export const wikiCommand = async (inputPath, options) => {
             }
         }
     }
+    // ── Apply per-run overrides not saved to config ────────────────────
+    if (options?.timeout) {
+        const secs = parseInt(options.timeout, 10);
+        if (!isNaN(secs) && secs > 0)
+            llmConfig.requestTimeoutMs = secs * 1000;
+    }
+    if (options?.retries) {
+        const n = parseInt(options.retries, 10);
+        if (!isNaN(n) && n > 0)
+            llmConfig.maxAttempts = n;
+    }
     // ── Setup progress bar with elapsed timer ──────────────────────────
     const bar = new cliProgress.SingleBar({
         format: '  {bar} {percentage}% | {phase}',

package/dist/core/wiki/llm-client.d.ts

@@ -19,6 +19,10 @@ export interface LLMConfig {
     apiVersion?: string;
     /** When true, strips sampling params and uses max_completion_tokens instead of max_tokens */
     isReasoningModel?: boolean;
+    /** Per-attempt fetch timeout in ms (default: 60_000). */
+    requestTimeoutMs?: number;
+    /** Max fetch attempts before giving up (default: 3). */
+    maxAttempts?: number;
 }
 export interface LLMResponse {
     content: string;

package/dist/core/wiki/llm-client.js

@@ -170,11 +170,11 @@ export async function callLLM(prompt, config, systemPrompt, options) {
             // indefinitely on a frozen TCP connection — the per-call
             // signal is the only timeout `resilientFetch` honors;
             // `capDelayMs` only bounds the *backoff* between attempts.
-            // 60s matches typical LLM completion budgets.
-            signal: AbortSignal.timeout(60_000),
+            // Default 60s; raise via --timeout for slow models or large pages.
+            signal: AbortSignal.timeout(config.requestTimeoutMs ?? 60_000),
         }, {
             breakerKey: `wiki-llm-${new URL(url).host}`,
-            retry: { maxAttempts: 3, baseDelayMs: 2_000, capDelayMs: 30_000 },
+            retry: { maxAttempts: config.maxAttempts ?? 3, baseDelayMs: 2_000, capDelayMs: 30_000 },
         });
     }
     catch (err) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gitnexus",
-  "version": "1.6.5-rc.26",
+  "version": "1.6.5-rc.27",
   "description": "Graph-powered code intelligence for AI agents. Index any codebase, query via MCP or CLI.",
   "author": "Abhigyan Patwari",
   "license": "PolyForm-Noncommercial-1.0.0",