fix: remove default wiki llm timeout ceiling

Agent-Logs-Url: https://github.com/abhigyanpatwari/GitNexus/sessions/af129945-1e0e-4d94-8676-877470c4574c

README.md

@@ -725,7 +725,7 @@ gitnexus wiki --force
 
 
 # Increase the timeout or retries for large codebase or slow LLM providers
-gitnexus wiki --timeout <seconds> # Per-attempt LLM request timeout in seconds (default: 60) 
+gitnexus wiki --timeout <seconds> # Per-attempt LLM request timeout in seconds (default: disabled)
 gitnexus wiki --retries <n>      # Max LLM retry attempts per request (default: 3)
 
 ```

gitnexus-claude-plugin/skills/gitnexus-cli/SKILL.md

@@ -62,7 +62,7 @@ Generates repository documentation from the knowledge graph using an LLM. Requir
 | `--api-key <key>` | LLM API key |
 | `--concurrency <n>` | Parallel LLM calls (default: 3) |
 | `--gist` | Publish wiki as a public GitHub Gist |
-| `--timeout <seconds>` | Per-attempt LLM request timeout in seconds (default: 60) |
+| `--timeout <seconds>` | Per-attempt LLM request timeout in seconds (default: disabled) |
 | `--retries <n>` | Max LLM retry attempts per request (default: 3) |
 
 ### list — Show all indexed repos

gitnexus/src/cli/index.ts

@@ -161,7 +161,7 @@ program
   )
   .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('--timeout <seconds>', 'Per-attempt LLM request timeout in seconds (default: disabled)')
   .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)')

gitnexus/src/core/wiki/llm-client.ts

@@ -23,7 +23,7 @@ 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). */
+  /** Per-attempt fetch timeout in ms. Omit to disable request timeouts. */
   requestTimeoutMs?: number;
   /** Max fetch attempts before giving up (default: 3). */
   maxAttempts?: number;
@@ -237,12 +237,13 @@ export async function callLLM(
           ...authHeaders,
         },
         body: JSON.stringify(body),
-        // Per-attempt timeout. Without this each retry can hang
-        // indefinitely on a frozen TCP connection — the per-call
-        // signal is the only timeout `resilientFetch` honors;
-        // `capDelayMs` only bounds the *backoff* between attempts.
-        // Default 60s; raise via --timeout for slow models or large pages.
-        signal: AbortSignal.timeout(config.requestTimeoutMs ?? 60_000),
+        // Per-attempt timeout is opt-in for wiki generation. Large local
+        // model runs can legitimately take well over a minute, so the
+        // default runtime path must not impose a hidden 60s ceiling.
+        signal:
+          config.requestTimeoutMs !== undefined
+            ? AbortSignal.timeout(config.requestTimeoutMs)
+            : undefined,
       },
       {
         breakerKey: `wiki-llm-${new URL(url).host}`,

gitnexus/test/unit/wiki-llm-client.test.ts

@@ -237,6 +237,63 @@ describe('callLLM — reasoning model params', () => {
   });
 });
 
+describe('callLLM — timeout handling', () => {
+  afterEach(() => {
+    vi.restoreAllMocks();
+    vi.unstubAllGlobals();
+  });
+
+  it('does not apply a default timeout when requestTimeoutMs is omitted', async () => {
+    const fetchSpy = vi.fn().mockResolvedValue(
+      new Response(JSON.stringify({ choices: [{ message: { content: 'answer' } }], usage: {} }), {
+        status: 200,
+        headers: { 'Content-Type': 'application/json' },
+      }),
+    );
+    vi.stubGlobal('fetch', fetchSpy);
+    const timeoutSpy = vi.spyOn(AbortSignal, 'timeout');
+
+    const { callLLM } = await import('../../src/core/wiki/llm-client.js');
+    await callLLM('test', {
+      apiKey: 'sk-test',
+      baseUrl: 'https://api.openai.com/v1',
+      model: 'gpt-4o',
+      maxTokens: 500,
+      temperature: 0,
+    });
+
+    expect(timeoutSpy).not.toHaveBeenCalled();
+    const [, init] = fetchSpy.mock.calls[0] as [string, RequestInit];
+    expect(init.signal).toBeUndefined();
+  });
+
+  it('applies an explicit timeout when requestTimeoutMs is provided', async () => {
+    const fetchSpy = vi.fn().mockResolvedValue(
+      new Response(JSON.stringify({ choices: [{ message: { content: 'answer' } }], usage: {} }), {
+        status: 200,
+        headers: { 'Content-Type': 'application/json' },
+      }),
+    );
+    vi.stubGlobal('fetch', fetchSpy);
+    const timeoutSignal = new AbortController().signal;
+    const timeoutSpy = vi.spyOn(AbortSignal, 'timeout').mockReturnValue(timeoutSignal);
+
+    const { callLLM } = await import('../../src/core/wiki/llm-client.js');
+    await callLLM('test', {
+      apiKey: 'sk-test',
+      baseUrl: 'https://api.openai.com/v1',
+      model: 'gpt-4o',
+      maxTokens: 500,
+      temperature: 0,
+      requestTimeoutMs: 120_000,
+    });
+
+    expect(timeoutSpy).toHaveBeenCalledWith(120_000);
+    const [, init] = fetchSpy.mock.calls[0] as [string, RequestInit];
+    expect(init.signal).toBe(timeoutSignal);
+  });
+});
+
 describe('callLLM — Azure content_filter error', () => {
   afterEach(() => vi.unstubAllGlobals());