omnius 1.0.729 → 1.0.730

package/dist/index.js

@@ -1,4 +1,4 @@
 [diffend] Oversized file quarantined before diffing.
 name: package/dist/index.js
-size: 38125885 bytes
-sha256: 389fd56947773740b14ff60a2d67211d846b6d332df43bcbefb49c354341b54a
+size: 38141493 bytes
+sha256: 129ae1a628f2ee04d633a2a2829eb8b968652fd68b8d93fadf28e3fc72eb1284

package/docs/DISCOVERY.json

@@ -5680,7 +5680,7 @@
       "id": "api.v1-chat",
       "kind": "api",
       "title": "/v1/chat",
-      "summary": "Stateful chat session with full agent tool access (OpenAI-compatible response shape)",
+      "summary": "Stateful direct chat with explicit autonomous-agent opt-in",
       "aliases": [
         "/v1/chat"
       ],
@@ -5729,8 +5729,8 @@
       ],
       "operations": {
         "post": {
-          "summary": "Stateful chat session with full agent tool access (OpenAI-compatible response shape)",
-          "description": "Drop-in replacement for OpenAI /v1/chat/completions and Ollama /api/chat. By default the request runs the FULL Omnius agent stack (tools, multi-agent, memory, skills) under the hood and returns an OpenAI chat.completion shape on success. Set tools=false to bypass the agent and forward straight to the configured backend (fast path).",
+          "summary": "Stateful direct chat with explicit autonomous-agent opt-in",
+          "description": "Drop-in replacement for OpenAI /v1/chat/completions and Ollama /api/chat. Requests use direct backend inference by default. Set tools=true or use_tools=true to explicitly run the full Omnius autonomous-agent stack. Explicit agent runs have a daemon-enforced whole-run deadline and duplicate-work suppression.",
           "tags": [
             "Chat"
           ],
@@ -5781,8 +5781,27 @@
                     },
                     "tools": {
                       "type": "boolean",
-                      "default": true,
-                      "description": "true (default) = full agent. false = direct backend chat. realtime=true also uses direct backend chat."
+                      "default": false,
+                      "description": "Set true to explicitly launch the full autonomous agent. Omitted or false uses direct backend chat."
+                    },
+                    "use_tools": {
+                      "type": "boolean",
+                      "default": false,
+                      "description": "Omnius-native alias for tools=true; the built-in web UI uses this explicit opt-in."
+                    },
+                    "timeout_s": {
+                      "type": "number",
+                      "minimum": 0,
+                      "maximum": 3600,
+                      "default": 180,
+                      "description": "Per-backend-request liveness timeout passed to the agent CLI."
+                    },
+                    "agent_timeout_s": {
+                      "type": "number",
+                      "minimum": 0.05,
+                      "maximum": 3600,
+                      "default": 180,
+                      "description": "Daemon-enforced whole-agent wall-clock deadline. Distinct from timeout_s."
                     }
                   }
                 }

package/docs/DISCOVERY.md

@@ -115,7 +115,7 @@ Daemon equivalents are `GET /v1/discovery/bootstrap`, `GET /v1/discovery?q=<inte
 | `api.v1-audio-speech` | /v1/audio/speech | OpenAI-compatible alias of /v1/voice/tts (input/voice/response_format names) |
 | `api.v1-audio-transcriptions` | /v1/audio/transcriptions | OpenAI-compatible alias of /v1/asr/transcriptions |
 | `api.v1-audit` | /v1/audit | Query audit log |
-| `api.v1-chat` | /v1/chat | Stateful chat session with full agent tool access (OpenAI-compatible response shape) |
+| `api.v1-chat` | /v1/chat | Stateful direct chat with explicit autonomous-agent opt-in |
 | `api.v1-chat-attachments` | /v1/chat/attachments | Upload an attachment for a stateful chat |
 | `api.v1-chat-check-in` | /v1/chat/check-in | Send a steering check-in to the active chat session — returns model inference + queued steering_packet |
 | `api.v1-chat-completions` | /v1/chat/completions | OpenAI-compatible chat completion (with optional server-side agent loop) |

package/docs/rest/endpoints/chat.md

@@ -71,7 +71,7 @@ Realtime example:
 
 ## `/v1/chat`
 
-This is the Omnius stateful chat endpoint. By default it runs the full Omnius agent stack with tools, memory, skills, and multi-agent context. Set `tools: false` to use the fast direct backend path. `realtime: true` also uses the direct backend path.
+This is the Omnius stateful chat endpoint. It uses direct backend inference by default. Set `tools: true` or `use_tools: true` to explicitly launch the full Omnius agent stack with tools, memory, skills, and multi-agent context. `realtime: true` always uses the direct backend path. Explicit agent runs default to a 180-second daemon-owned wall-clock deadline and reject equivalent concurrent work even when callers omit `session_id`.
 
 Body fields:
 
@@ -81,7 +81,10 @@ Body fields:
 | `model` | string | Optional model override |
 | `session_id` | string | Reuse or name a session |
 | `stream` | boolean | Stream when supported |
-| `tools` | boolean | Full agent stack by default |
+| `tools` | boolean | Set true to explicitly launch the full agent stack |
+| `use_tools` | boolean | Omnius-native alias for `tools: true` |
+| `timeout_s` | number | Per-backend-request liveness timeout |
+| `agent_timeout_s` | number | Whole-agent daemon deadline, default 180 seconds and maximum 3600 |
 | `realtime` | boolean | Short ASR/TTS conversation mode |
 | `realtime_options` | object | Realtime settings |
 

package/npm-shrinkwrap.json

@@ -1,12 +1,12 @@
 {
   "name": "omnius",
-  "version": "1.0.729",
+  "version": "1.0.730",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "omnius",
-      "version": "1.0.729",
+      "version": "1.0.730",
       "bundleDependencies": [
         "image-to-ascii"
       ],

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "omnius",
-  "version": "1.0.729",
+  "version": "1.0.730",
   "description": "AI coding agent powered by open-source models (Ollama/vLLM) — interactive TUI with agentic tool-calling loop",
   "type": "module",
   "main": "./dist/library.js",