Scott.Idem/Cortex-Inara
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: reasoning token budget + session name in header

Browse Source 
- 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>
This commit is contained in:
Scott Idem
2026-05-09 21:35:23 -04:00
parent 85792a7bcf
commit a66c5a7f84
5 changed files with 80 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

82
cortex/routers/local_llm.py
View File

@@ -204,12 +204,13 @@ def _render(username: str, success: str = "", error: str = "") -> str:
else:
extra_fields = '<input type="hidden" name="credential_id" value="cli">'
cur_label = m.get("label", "")
cur_model_name = m.get("model_name", "")
cur_ctx = m.get("context_k", 0) or 0
cur_max_rounds = m.get("max_rounds") or 0
cur_tools = m.get("tools", True)
cur_tags = ", ".join(m.get("tags") or [])
cur_label = m.get("label", "")
cur_model_name = m.get("model_name", "")
cur_ctx = m.get("context_k", 0) or 0
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"
@@ -459,20 +465,21 @@ async def remove_host(request: Request, host_id: str):
@router.post("/settings/local/models/add", include_in_schema=False)
async def add_model(
request: Request,
provider: str = Form("local"),
label: str = Form(""),
context_k: int = Form(0),
max_rounds: int = Form(0),
tools: int = Form(1),
tags: str = Form(""),
request: Request,
provider: str = Form("local"),
label: str = Form(""),
context_k: int = Form(0),
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(""),
host_id: str = Form(""),
model_name: str = Form(""),
# cloud-only fields
cloud_model_name: str = Form(""),
account_id: str = Form(""),
credential_id: str = Form("cli"),
cloud_model_name: str = Form(""),
account_id: str = Form(""),
credential_id: str = Form("cli"),
):
username = _get_user(request)
if not username:
@@ -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"):
@@ -513,32 +522,35 @@ async def add_model(
@router.post("/settings/local/models/{model_id}/edit", include_in_schema=False)
async def edit_model(
request: Request,
model_id: str,
mtype: str = Form(""),
label: str = Form(""),
model_name: str = Form(""),
context_k: int = Form(0),
max_rounds: int = Form(0),
tools: int = Form(1),
tags: str = Form(""),
host_id: str = Form(""),
account_id: str = Form(""),
credential_id: str = Form("cli"),
request: Request,
model_id: str,
mtype: str = Form(""),
label: str = Form(""),
model_name: str = Form(""),
context_k: int = Form(0),
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"),
):
username = _get_user(request)
if not username:
return RedirectResponse("/login", status_code=302)
if not model_name.strip():
return HTMLResponse(_render(username, error="Model name is required."))
tag_list = [t.strip() for t in tags.split(",") if t.strip()]
max_rounds_ = max_rounds or None
tools_bool = tools != 0
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,