omnius 1.0.808 → 1.0.810

package/dist/api/py-embed.js

@@ -294932,13 +294932,17 @@ except Exception as exc:
 `;
 var LUXTTS_DAEMON_PY = String.raw`
 import json, os, sys, traceback, wave
+# OMNIUS_LUXTTS_CPU_ONLY_V1
+os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
+os.environ["HIP_VISIBLE_DEVICES"] = "-1"
+os.environ["ROCR_VISIBLE_DEVICES"] = "-1"
 import numpy as np
 import torch
 repo = os.environ.get("LUXTTS_REPO_PATH") or ""
 if repo:
     sys.path.insert(0, repo)
 from zipvoice.luxvoice import LuxTTS
-device = "cuda" if torch.cuda.is_available() else "cpu"
+device = "cpu"
 tts = LuxTTS(model_path="YatharthS/LuxTTS", device=device, threads=4)
 print(json.dumps({"type": "ready", "device": device}), flush=True)
 for line in sys.stdin:

package/dist/index.js

@@ -1,4 +1,4 @@
 [diffend] Oversized file quarantined before diffing.
 name: package/dist/index.js
-size: 41387219 bytes
-sha256: 2ab731ca98384df639ae734c17d520296d44e53de1f181b94719d3755b39acf1
+size: 41440515 bytes
+sha256: 9640eabe6501fbee41cb81f68bfc7d1df8f5adc8e7ccabcb95ea1964421ef4d0

package/dist/library.js

@@ -296557,7 +296557,6 @@ var init_audio_playback = __esm({
     init_model_store();
     init_luxtts_runtime_contract();
     init_python_cuda_runtime();
-    init_python_cuda_runtime_async();
     SUPERTONIC_INFER_PY = String.raw`
 import json, sys, traceback
 try:
@@ -296591,13 +296590,17 @@ except Exception as exc:
 `;
     LUXTTS_DAEMON_PY = String.raw`
 import json, os, sys, traceback, wave
+# OMNIUS_LUXTTS_CPU_ONLY_V1
+os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
+os.environ["HIP_VISIBLE_DEVICES"] = "-1"
+os.environ["ROCR_VISIBLE_DEVICES"] = "-1"
 import numpy as np
 import torch
 repo = os.environ.get("LUXTTS_REPO_PATH") or ""
 if repo:
     sys.path.insert(0, repo)
 from zipvoice.luxvoice import LuxTTS
-device = "cuda" if torch.cuda.is_available() else "cpu"
+device = "cpu"
 tts = LuxTTS(model_path="YatharthS/LuxTTS", device=device, threads=4)
 print(json.dumps({"type": "ready", "device": device}), flush=True)
 for line in sys.stdin:

package/dist/update-worker.js

@@ -295366,13 +295366,17 @@ except Exception as exc:
 `;
 var LUXTTS_DAEMON_PY = String.raw`
 import json, os, sys, traceback, wave
+# OMNIUS_LUXTTS_CPU_ONLY_V1
+os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
+os.environ["HIP_VISIBLE_DEVICES"] = "-1"
+os.environ["ROCR_VISIBLE_DEVICES"] = "-1"
 import numpy as np
 import torch
 repo = os.environ.get("LUXTTS_REPO_PATH") or ""
 if repo:
     sys.path.insert(0, repo)
 from zipvoice.luxvoice import LuxTTS
-device = "cuda" if torch.cuda.is_available() else "cpu"
+device = "cpu"
 tts = LuxTTS(model_path="YatharthS/LuxTTS", device=device, threads=4)
 print(json.dumps({"type": "ready", "device": device}), flush=True)
 for line in sys.stdin:

package/docs/DISCOVERY.json

@@ -5730,7 +5730,7 @@
       "operations": {
         "post": {
           "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.",
+          "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 reject duplicate concurrent work and continue until completion, failure, explicit Stop, or daemon shutdown. They have no whole-run wall-clock deadline; legacy agent_timeout_s and OMNIUS_CHAT_AGENT_TIMEOUT_S are ignored.",
           "tags": [
             "Chat"
           ],
@@ -5798,10 +5798,8 @@
                     },
                     "agent_timeout_s": {
                       "type": "number",
-                      "minimum": 0.05,
-                      "maximum": 3600,
-                      "default": 180,
-                      "description": "Daemon-enforced whole-agent wall-clock deadline. Distinct from timeout_s."
+                      "deprecated": true,
+                      "description": "Ignored compatibility field. Agent runs have no whole-run wall-clock deadline."
                     }
                   }
                 }
@@ -6096,7 +6094,7 @@
               "$ref": "#/components/parameters/MinimumOmniusVersion"
             }
           ],
-          "description": "Standard OpenAI chat-completion proxy by default. Set agent_loop=true to enter a bounded synchronous server-side loop that auto-executes selected daemon tools and re-prompts the model. Ollama targets use native /api/chat tool messages. timeout_s bounds each backend call; agent_timeout_s bounds the whole loop (default 45s, max 600s). daemon_tool_names explicitly limits the offered catalog; factual-first implicitly limits it to web_search/web_fetch when no names are supplied. Identical repeated calls fail with HTTP 508 instead of looping. SSE streaming outside agent_loop honors OpenAI tool_calls deltas.",
+          "description": "Standard OpenAI chat-completion proxy by default. Set agent_loop=true to enter a synchronous server-side loop that auto-executes selected daemon tools and re-prompts the model. Ollama targets use native /api/chat tool messages. timeout_s bounds each backend call; agent loops have no whole-run wall-clock deadline. Legacy agent_timeout_s and OMNIUS_AGENT_LOOP_TOTAL_TIMEOUT_MS are ignored. daemon_tool_names explicitly limits the offered catalog; factual-first implicitly limits it to web_search/web_fetch when no names are supplied. Identical repeated calls fail with HTTP 508 instead of looping. SSE streaming outside agent_loop honors OpenAI tool_calls deltas.",
           "requestBody": {
             "required": true,
             "content": {
@@ -6150,7 +6148,7 @@
                     },
                     "timeout_s": {
                       "type": "number",
-                      "description": "Q1 — per-request timeout in seconds (1-3600). Overrides OMNIUS_BACKEND_TIMEOUT_S."
+                      "description": "Per-backend-request liveness timeout in seconds, capped at 3600. Overrides OMNIUS_BACKEND_TIMEOUT_S."
                     },
                     "agent_loop": {
                       "type": "boolean",
@@ -6177,10 +6175,8 @@
                     },
                     "agent_timeout_s": {
                       "type": "number",
-                      "minimum": 5,
-                      "maximum": 600,
-                      "default": 45,
-                      "description": "Total server-side agent-loop deadline. Distinct from per-backend timeout_s."
+                      "deprecated": true,
+                      "description": "Ignored compatibility field. Agent loops have no whole-run wall-clock deadline."
                     },
                     "agent_max_tool_rounds": {
                       "type": "integer",
@@ -6285,7 +6281,7 @@
               }
             },
             "504": {
-              "description": "Backend round or total agent-loop deadline expired"
+              "description": "A backend request exceeded its liveness timeout"
             },
             "508": {
               "description": "The model repeated an identical daemon tool call"

package/docs/rest/endpoints/chat.md

@@ -43,11 +43,11 @@ Important body fields:
 | `tools` | array | OpenAI-shape tools array |
 | `tool_choice` | any | OpenAI-shape tool choice |
 | `parallel_tool_calls` | boolean | Forwarded to backend |
-| `timeout_s` | number | Per-request timeout |
+| `timeout_s` | number | Per-backend-request liveness timeout |
 | `agent_loop` | boolean | Run server-side tool loop |
 | `include_daemon_tools` | array | Permit the bounded core daemon-tool catalog by scope: `read`, `run`, `admin` |
 | `daemon_tool_names` | array | Exact daemon-tool allowlist; recommended for local models |
-| `agent_timeout_s` | number | Whole-loop deadline, default 45 seconds and maximum 600 |
+| `agent_timeout_s` | number | Deprecated compatibility field; ignored |
 | `agent_max_tool_rounds` | integer | Daemon tool rounds before forced final synthesis; default 1 |
 | `agent_prefetch_web_search` | boolean | Explicit one-generation web-search prefetch; factual-first enables it automatically |
 | `max_turns` | integer | Server-side agent loop turn cap |
@@ -71,7 +71,7 @@ Realtime example:
 
 ## `/v1/chat`
 
-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`.
+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 reject equivalent concurrent work even when callers omit `session_id` and continue until completion, failure, explicit Stop, or daemon shutdown. Agent runs have no whole-run wall-clock deadline; legacy `agent_timeout_s` and `OMNIUS_CHAT_AGENT_TIMEOUT_S` are ignored.
 
 Body fields:
 
@@ -84,7 +84,7 @@ Body fields:
 | `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 |
+| `agent_timeout_s` | number | Deprecated compatibility field; ignored |
 | `realtime` | boolean | Short ASR/TTS conversation mode |
 | `realtime_options` | object | Realtime settings |
 
@@ -144,4 +144,4 @@ For ASR/TTS systems that only need the text brain, use `/realtime` or `/v1/realt
 
 `/v1/chat/completions` can run an internal tool loop when `agent_loop: true`. This lets clients collapse multiple model/tool round trips into one daemon request. Daemon tool calls execute inline; client-owned tool calls can still be yielded in OpenAI-compatible shape.
 
-Ollama-backed loops use its native `/api/chat` tool protocol. `timeout_s` applies to each backend round, while `agent_timeout_s` bounds the complete loop and defaults to 45 seconds. For a normal loop, the planning turn is capped at 96 output tokens; one daemon-tool round is the default, after which Omnius removes daemon schemas for final synthesis. `prompt_template: "factual-first"` skips that model-planning round entirely: Omnius executes the already-mandated, authorized `web_search` using the latest user turn, inserts the protocol-correct tool evidence, and performs one grounded synthesis generation. `agent_prefetch_web_search: true` opts into the same path directly. Generic/deeper tool workflows remain available through `agent_max_tool_rounds`. Omnius returns typed HTTP 504/508 failures, caps tool evidence at 6,000 characters, and limits the implicit catalog unless `daemon_tool_names` requests exact additions.
+Ollama-backed loops use its native `/api/chat` tool protocol. `timeout_s` applies to each backend round. There is no whole-loop wall-clock deadline; legacy `agent_timeout_s` and `OMNIUS_AGENT_LOOP_TOTAL_TIMEOUT_MS` are ignored. Each daemon tool retains its own execution timeout and cancellation handling, and the loop still respects client disconnects, `max_turns`, and repeated-call guards. For a normal loop, the planning turn is capped at 96 output tokens; one daemon-tool round is the default, after which Omnius removes daemon schemas for final synthesis. `prompt_template: "factual-first"` skips that model-planning round entirely: Omnius executes the already-mandated, authorized `web_search` using the latest user turn, inserts the protocol-correct tool evidence, and performs one grounded synthesis generation. `agent_prefetch_web_search: true` opts into the same path directly. Generic/deeper tool workflows remain available through `agent_max_tool_rounds`. Backend liveness timeouts return typed HTTP 504 failures, and identical repeated tool calls return HTTP 508. Omnius caps tool evidence at 6,000 characters and limits the implicit catalog unless `daemon_tool_names` requests exact additions.

package/npm-shrinkwrap.json

@@ -1,12 +1,12 @@
 {
   "name": "omnius",
-  "version": "1.0.808",
+  "version": "1.0.810",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "omnius",
-      "version": "1.0.808",
+      "version": "1.0.810",
       "bundleDependencies": [
         "image-to-ascii"
       ],

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "omnius",
-  "version": "1.0.808",
+  "version": "1.0.810",
   "description": "AI coding agent powered by open-source models (Ollama/vLLM) — interactive TUI with agentic tool-calling loop",
   "type": "module",
   "main": "./dist/library.js",