Research: add configurable run timeout

Surfaces the research_run_timeout_seconds setting (added in #783) in
Settings → Research as a "Max Time" field, and lets 0 disable the
wall-clock cap entirely for long deep-research runs.

- settings.py: document that 0 disables the cap; default stays 1800s.
- research_handler.py: resolve 0 (or negative) to no timeout
  (asyncio.wait_for timeout=None); other values stay bounded to
  [60, 86400] as before.
- index.html / settings.js: "Max Time" input bound to
  research_run_timeout_seconds, validated to {0} ∪ [60, 86400], with
  copy making explicit that 0 = no limit (unbounded model/API cost).

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

src/research_handler.py

@@ -216,15 +216,25 @@ class ResearchHandler:
         """
         # Resolve the hard wall-clock timeout from settings when the caller
         # didn't pin one. Local / edge models routinely need more than the
-        # old 600s default to finish a deep-research synthesis.
+        # old 600s default to finish a deep-research synthesis. A setting of
+        # 0 disables the cap entirely (unlimited run); any other value is
+        # bounded to [60, 86400] so a misconfigured settings.json can't
+        # explode into a multi-day hang.
         if hard_timeout is None:
             from src.settings import get_setting
-            hard_timeout = _bounded_int(
+            try:
-                get_setting("research_run_timeout_seconds", 1800),
+                raw_timeout = int(get_setting("research_run_timeout_seconds", 1800))
-                default=1800,
+            except (TypeError, ValueError):
-                minimum=60,
+                raw_timeout = 1800
-                maximum=86400,
+            if raw_timeout <= 0:
-            )
+                hard_timeout = None  # 0 = no wall-clock cap (asyncio.wait_for timeout=None)
+            else:
+                hard_timeout = _bounded_int(
+                    raw_timeout,
+                    default=1800,
+                    minimum=60,
+                    maximum=86400,
+                )
 
         # Cancel any existing research for this session
         if session_id in self._active_tasks:

src/settings.py

@@ -89,7 +89,10 @@ DEFAULT_SETTINGS = {
     # Hard wall-clock cap on a single deep-research run. The previous 600s
     # (10 min) default cut off slow local / edge LLMs mid-synthesis; 1800s
     # (30 min) is comfortable for most local setups while still bounding
-    # runaway jobs. Tune via Settings or by editing data/settings.json.
+    # runaway jobs. Set to 0 to disable the cap entirely (unlimited) — only
+    # for very long deep-research runs, since a stalled job then runs an
+    # unbounded model/API bill. Other values are bounded to [60, 86400].
+    # Tune via Settings or by editing data/settings.json.
     "research_run_timeout_seconds": 1800,
     "agent_max_tool_calls": 0,
     "agent_input_token_budget": 6000,

static/index.html

@@ -1463,6 +1463,10 @@
                 <label class="settings-label">Extract Parallel</label>
                 <input id="set-researchExtractConcurrency" type="text" inputmode="numeric" placeholder="3" class="settings-select" style="width:120px;">
               </div>
+              <div class="settings-row">
+                <label class="settings-label">Max Time</label>
+                <input id="set-researchRunTimeout" type="text" inputmode="numeric" placeholder="1800 sec (0 = no limit)" class="settings-select" style="width:120px;">
+              </div>
               <div id="set-researchMsg" style="font-size:11px;color:color-mix(in srgb, var(--fg) 45%, transparent);"></div>
             </div>
           </div>

static/js/settings.js

@@ -1402,6 +1402,7 @@ async function initResearchSettings() {
   var tokensInput = el('set-researchMaxTokens');
   var extractTimeoutInput = el('set-researchExtractTimeout');
   var extractConcurrencyInput = el('set-researchExtractConcurrency');
+  var runTimeoutInput = el('set-researchRunTimeout');
   var msg = el('set-researchMsg');
   var endpoints = [];
 
@@ -1424,6 +1425,9 @@ async function initResearchSettings() {
     if (settings.research_max_tokens) tokensInput.value = settings.research_max_tokens;
     if (settings.research_extraction_timeout_seconds) extractTimeoutInput.value = settings.research_extraction_timeout_seconds;
     if (settings.research_extraction_concurrency) extractConcurrencyInput.value = settings.research_extraction_concurrency;
+    if (settings.research_run_timeout_seconds !== undefined && settings.research_run_timeout_seconds !== null) {
+      runTimeoutInput.value = settings.research_run_timeout_seconds;
+    }
   } catch (e) { console.warn('Failed to load research settings', e); }
 
   function showStatus() {
@@ -1442,6 +1446,12 @@ async function initResearchSettings() {
     if (extractConcurrencyInput.value) {
       parts.push('Parallel: ' + extractConcurrencyInput.value);
     }
+    if (runTimeoutInput.value !== '') {
+      var rtv = parseInt(runTimeoutInput.value, 10);
+      if (!isNaN(rtv)) {
+        parts.push(rtv === 0 ? 'Max time: no limit' : 'Max time: ' + rtv + 's');
+      }
+    }
     if (parts.length) {
       msg.textContent = parts.join(' · ');
       msg.style.color = 'var(--fg)';
@@ -1463,6 +1473,13 @@ async function initResearchSettings() {
     if (et && et >= 15 && et <= 3600) payload.research_extraction_timeout_seconds = et;
     var ec = parseInt(extractConcurrencyInput.value, 10);
     if (ec && ec >= 1 && ec <= 12) payload.research_extraction_concurrency = ec;
+    if (runTimeoutInput.value !== '') {
+      var rt = parseInt(runTimeoutInput.value, 10);
+      // 0 = no limit (disables the hard timeout); otherwise 60s..86400s (24h)
+      if (!isNaN(rt) && (rt === 0 || (rt >= 60 && rt <= 86400))) {
+        payload.research_run_timeout_seconds = rt;
+      }
+    }
     try {
       await fetch('/api/auth/settings', { method: 'POST', credentials: 'same-origin',
         headers: { 'Content-Type': 'application/json' },
@@ -1481,6 +1498,7 @@ async function initResearchSettings() {
   tokensInput.addEventListener('change', saveResearch);
   extractTimeoutInput.addEventListener('change', saveResearch);
   extractConcurrencyInput.addEventListener('change', saveResearch);
+  runTimeoutInput.addEventListener('change', saveResearch);
 
   _registerAiEndpointRefresh(function(nextEndpoints) {
     endpoints = nextEndpoints;