feat: reasoning token budget + session name in header

- reasoning_budget_tokens: optional int field on local_openai models;
  when set, injects {"reasoning": {"budget_tokens": N}} via extra_body
  into every OpenRouter API call (both tool-loop and confirmation-gate
  rounds). Field exposed in the model edit form in Settings.

- session name moved from standalone full-row div between #messages
  and #input-area into the persona-switcher block in the header, as a
  third dim line under "Cortex · Local". Collapses when empty via
  :empty CSS. No JS changes required.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

cortex/model_registry.py

@@ -664,7 +664,8 @@ def save_model(username: str, model_id: str | None, host_id: str,
                label: str, model_name: str, context_k: int = 0,
                tags: list[str] | None = None,
                max_rounds: int | None = None,
-               tools: bool = True) -> str:
+               tools: bool = True,
+               reasoning_budget_tokens: int | None = None) -> str:
     """Create or update a local_openai model entry. Returns the model ID."""
     data = _load(username)
     tags = tags or []
@@ -679,6 +680,7 @@ def save_model(username: str, model_id: str | None, host_id: str,
                 m["max_rounds"]             = max_rounds
                 m["tools"]                  = tools
                 m["tags"]                   = tags
+                m["reasoning_budget_tokens"] = reasoning_budget_tokens
                 _save(username, data)
                 return model_id
         model_id = None
@@ -695,6 +697,7 @@ def save_model(username: str, model_id: str | None, host_id: str,
         "max_rounds":             max_rounds,
         "tools":                  tools,
         "tags":                   tags,
+        "reasoning_budget_tokens": reasoning_budget_tokens,
     })
     _save(username, data)
     return model_id

cortex/openai_orchestrator.py

@@ -287,6 +287,9 @@ async def _run_from_messages(
         if active_tools:
             call_kwargs["tools"] = active_tools
             call_kwargs["tool_choice"] = "auto"
+        reasoning_budget = (model_cfg or {}).get("reasoning_budget_tokens")
+        if reasoning_budget:
+            call_kwargs["extra_body"] = {"reasoning": {"budget_tokens": reasoning_budget}}
         response = await _chat_with_retry(client, **call_kwargs)
 
         choice = response.choices[0]
@@ -346,6 +349,8 @@ async def _run_from_messages(
                 conf_call: dict = {"model": model_name, "messages": messages, "tool_choice": "none"}
                 if active_tools:
                     conf_call["tools"] = active_tools
+                if reasoning_budget:
+                    conf_call["extra_body"] = {"reasoning": {"budget_tokens": reasoning_budget}}
                 conf_resp = await _chat_with_retry(client, **conf_call)
                 final_response = conf_resp.choices[0].message.content or (
                     "This action requires your explicit confirmation before it can proceed."

cortex/routers/local_llm.py

@@ -210,6 +210,7 @@ def _render(username: str, success: str = "", error: str = "") -> str:
         cur_max_rounds      = m.get("max_rounds") or 0
         cur_tools           = m.get("tools", True)
         cur_tags            = ", ".join(m.get("tags") or [])
+        cur_reasoning_budget = m.get("reasoning_budget_tokens") or 0
 
         model_rows += f'''
         <div class="model-row" id="model-{m["id"]}">
@@ -256,6 +257,11 @@ def _render(username: str, success: str = "", error: str = "") -> str:
                 <input type="number" name="max_rounds" value="{cur_max_rounds}" min="0"
                        title="Per-model tool loop cap. 0 = use the global default (orchestrator_max_rounds).">
               </div>
+              <div class="field" style="flex:0 0 auto">
+                <label title="OpenRouter reasoning budget in tokens. 0 = no reasoning override (model default). Injects reasoning.budget_tokens into the API call.">Reasoning tokens</label>
+                <input type="number" name="reasoning_budget_tokens" value="{cur_reasoning_budget}" min="0"
+                       title="OpenRouter reasoning budget in tokens. 0 = disabled. E.g. 2048 for light thinking, 8192 for deep reasoning.">
+              </div>
               <div class="field" style="flex:0 0 auto">
                 <label title="Whether this model supports tool calling. If not supported, requests skip the tool loop entirely.">Tool calling</label>
                 <select name="tools"
@@ -466,6 +472,7 @@ async def add_model(
     max_rounds:               int = Form(0),
     tools:                    int = Form(1),
     tags:                     str = Form(""),
+    reasoning_budget_tokens:  int = Form(0),
     # local-only fields
     host_id:                  str = Form(""),
     model_name:               str = Form(""),
@@ -481,6 +488,7 @@ async def add_model(
     tag_list   = [t.strip() for t in tags.split(",") if t.strip()]
     max_rounds_ = max_rounds or None
     tools_bool  = tools != 0
+    reasoning_budget_ = reasoning_budget_tokens or None
 
     if provider == "local":
         if not model_name.strip():
@@ -488,7 +496,8 @@ async def add_model(
         if not host_id.strip():
             return HTMLResponse(_render(username, error="Select a host."))
         reg.save_model(username, None, host_id, label, model_name, context_k, tag_list,
-                       max_rounds=max_rounds_, tools=tools_bool)
+                       max_rounds=max_rounds_, tools=tools_bool,
+                       reasoning_budget_tokens=reasoning_budget_)
         display = label or model_name
 
     elif provider in ("google", "anthropic"):
@@ -522,6 +531,7 @@ async def edit_model(
     max_rounds:              int = Form(0),
     tools:                   int = Form(1),
     tags:                    str = Form(""),
+    reasoning_budget_tokens: int = Form(0),
     host_id:                 str = Form(""),
     account_id:              str = Form(""),
     credential_id:           str = Form("cli"),
@@ -534,11 +544,13 @@ async def edit_model(
     tag_list          = [t.strip() for t in tags.split(",") if t.strip()]
     max_rounds_       = max_rounds or None
     tools_bool        = tools != 0
+    reasoning_budget_ = reasoning_budget_tokens or None
     if mtype == "local_openai":
         if not host_id.strip():
             return HTMLResponse(_render(username, error="Select a host for this model."))
         reg.save_model(username, model_id, host_id, label, model_name, context_k, tag_list,
-                       max_rounds=max_rounds_, tools=tools_bool)
+                       max_rounds=max_rounds_, tools=tools_bool,
+                       reasoning_budget_tokens=reasoning_budget_)
     elif mtype == "gemini_api":
         reg.save_cloud_model(username, model_id, "google", model_name, label,
                              account_id=account_id or None, context_k=context_k, tags=tag_list,

cortex/static/index.html

@@ -41,6 +41,7 @@
         <div class="persona-switcher" id="persona-switcher">
             <div class="name" id="persona-name">Inara</div>
             <div class="subtitle">Cortex · Local</div>
+            <div id="session-id"></div>
             <div class="persona-dropdown" id="persona-dropdown"></div>
         </div>
 
@@ -164,7 +165,6 @@
     </div>
 
     <div id="messages"></div>
-    <div id="session-id"></div>
 
     <div id="input-area">
         <!-- Mode select — compact dropdown, opens upward, MRU sorted -->

cortex/static/style.css

@@ -897,11 +897,14 @@
         #stop:hover { background: #5c1a1a; }
 
         #session-id {
-            font-size: 0.7rem;
+            font-size: 0.68rem;
             color: var(--border);
-            padding: 0 20px 6px;
-            background: var(--surface);
+            white-space: nowrap;
+            overflow: hidden;
+            text-overflow: ellipsis;
+            max-width: 220px;
         }
+        #session-id:empty { display: none; }
 
         /* ── Message wrappers (edit/delete controls) ──────────────── */
         .msg-wrapper {