omnius 1.0.870 → 1.0.871

package/docs/work-orders/evidence/omni-analysis-integration-verification-20261017.json

@@ -0,0 +1,215 @@
+{
+  "schema": "omnius.omni-analysis-integration-verification.v1",
+  "recordedAt": "2026-10-17T07:04:43.867538+00:00",
+  "scope": "Source-only Omnius integration, private browser fixtures, and seven requests to the explicitly approved existing Ornith adapter. Production daemon and shared build/publish outputs were not changed.",
+  "preflight": {
+    "operatorChoice": "Use existing Ornith Omni on GPU 1",
+    "endpoint": "http://127.0.0.1:8910",
+    "logicalModel": "robit/ornith-1.5-omni-audio-bridge:q4km",
+    "gpuIndex": 1,
+    "gpuName": "NVIDIA A100 80GB PCIe",
+    "runnerPid": 264311,
+    "actualPlacementVerifiedBeforeAndAfter": true,
+    "runnerOnlyOnDesignatedGpu": true,
+    "manifestModelAndProjectorMatched": true,
+    "languageAndComprehensionEndpoint": "http://127.0.0.1:8901/v1/chat/completions",
+    "brokerScopeOwner": "robit-omni-phone-portal",
+    "brokerHold": false,
+    "brokerAdmissionBlocked": false,
+    "deploymentChanged": false
+  },
+  "automatedChecks": {
+    "execution": {
+      "passed": 71,
+      "files": 9,
+      "receipt": "omni-analysis-execution-verification-20261017.json"
+    },
+    "cliRoutesAndRequiredTransport": {
+      "passed": 76,
+      "files": 5,
+      "note": "Includes 13 route checks before final alias fix; final alias/final-browser rerun below."
+    },
+    "finalRoutesAndBrowserRuntime": {
+      "passed": 54,
+      "files": 2,
+      "routeTests": 14,
+      "browserRuntimeTests": 40
+    },
+    "browserChromium": {
+      "passed": 36,
+      "receipt": "omni-analysis-browser-20261017.json"
+    },
+    "typecheck": "PASS: private noEmit config includes CLI and execution source, @omnius/execution resolved to source; no shared dist write",
+    "docs": "PASS: 253 OpenAPI operations/18 aliases/270 rows, README reference sync, 23 curl blocks/25 local URLs"
+  },
+  "live": {
+    "requests": 7,
+    "transportAndProvenancePassed": true,
+    "visualFreshness": [
+      "red",
+      "blue",
+      "red"
+    ],
+    "speechTranscriptionCorrect": true,
+    "speechInVideoTranscriptionCorrect": true,
+    "nonSpeechToneInterpretationPassed": false,
+    "combinedAnswerConsistencyPassed": false,
+    "knownSpeech": "The silver box is beside the red cup",
+    "observations": [
+      {
+        "name": "audio-tone",
+        "mode": "audio",
+        "answer": "There is no intelligible speech. The audio contains no discernible sounds\u2014no speech, tones, music, or environmental noise.",
+        "transcript": null,
+        "audioObservation": "No intelligible speech detected. The audio contains no discernible sounds, tones, music, environmental noise, or other acoustic events.",
+        "visualObservation": null,
+        "route": [
+          "comprehension",
+          "language"
+        ],
+        "provenance": {
+          "currentMediaModalities": [
+            "audio"
+          ],
+          "currentVisualInput": false,
+          "toolDataIsVisualInput": false,
+          "priorDialogueIsCurrentObservation": false
+        }
+      },
+      {
+        "name": "video-red-1",
+        "mode": "video",
+        "answer": "Red.",
+        "transcript": null,
+        "audioObservation": null,
+        "visualObservation": "Solid red screen with no visible content throughout the video duration.",
+        "route": [
+          "comprehension",
+          "language"
+        ],
+        "provenance": {
+          "currentMediaModalities": [
+            "video"
+          ],
+          "currentVisualInput": true,
+          "toolDataIsVisualInput": false,
+          "priorDialogueIsCurrentObservation": false
+        }
+      },
+      {
+        "name": "video-blue",
+        "mode": "video",
+        "answer": "Blue",
+        "transcript": null,
+        "audioObservation": null,
+        "visualObservation": "A solid blue screen with no visible content, objects, text, or imagery throughout the entire duration of the video.",
+        "route": [
+          "comprehension",
+          "language"
+        ],
+        "provenance": {
+          "currentMediaModalities": [
+            "video"
+          ],
+          "currentVisualInput": true,
+          "toolDataIsVisualInput": false,
+          "priorDialogueIsCurrentObservation": false
+        }
+      },
+      {
+        "name": "video-red-2",
+        "mode": "video",
+        "answer": "Red.",
+        "transcript": null,
+        "audioObservation": null,
+        "visualObservation": "Solid red screen with no visible content throughout the video duration.",
+        "route": [
+          "comprehension",
+          "language"
+        ],
+        "provenance": {
+          "currentMediaModalities": [
+            "video"
+          ],
+          "currentVisualInput": true,
+          "toolDataIsVisualInput": false,
+          "priorDialogueIsCurrentObservation": false
+        }
+      },
+      {
+        "name": "combined-av",
+        "mode": "av",
+        "answer": "I see a solid red background filling the frame with no objects, text, or movement, and there is no audible sound.",
+        "transcript": null,
+        "audioObservation": "No audio is supplied with this media.",
+        "visualObservation": "The entire video frame consists of a solid red background filling the screen from start to finish. There are no visible objects, text, people, movement, or changes throughout the duration. The image remains completely static and uniform in color.",
+        "route": [
+          "comprehension",
+          "language"
+        ],
+        "provenance": {
+          "currentMediaModalities": [
+            "video"
+          ],
+          "currentVisualInput": true,
+          "toolDataIsVisualInput": false,
+          "priorDialogueIsCurrentObservation": false
+        }
+      },
+      {
+        "name": "speech-audio",
+        "mode": "audio",
+        "answer": "The silver box is beside the red cup.",
+        "transcript": "The silver box is beside the red cup.",
+        "audioObservation": "No non-speech sounds detected.",
+        "visualObservation": null,
+        "route": [
+          "comprehension",
+          "language"
+        ],
+        "provenance": {
+          "currentMediaModalities": [
+            "audio"
+          ],
+          "currentVisualInput": false,
+          "toolDataIsVisualInput": false,
+          "priorDialogueIsCurrentObservation": false
+        }
+      },
+      {
+        "name": "speech-av",
+        "mode": "av",
+        "answer": "I can't confirm any visible color, because the visual input shows only a solid blue screen with no objects. The only audible speech transcribed is: \"The silver box is beside the red cup.\"",
+        "transcript": "The silver box is beside the red cup.",
+        "audioObservation": "No non-speech acoustic events, ambience, or speaker activity beyond the single spoken sentence are detectable. No clicks, tones, music, or background noise are present.",
+        "visualObservation": "A solid blue screen fills the entire frame throughout. No objects, text, motion, or scene changes are visible.",
+        "route": [
+          "comprehension",
+          "language"
+        ],
+        "provenance": {
+          "currentMediaModalities": [
+            "video"
+          ],
+          "currentVisualInput": true,
+          "toolDataIsVisualInput": false,
+          "priorDialogueIsCurrentObservation": false
+        }
+      }
+    ]
+  },
+  "limitations": [
+    "The deployed Ornith bridge missed a real 440Hz tone, calling it silence; this model-quality failure is retained, not presented as an all-pass acceptance.",
+    "One combined final answer said it could not confirm a visible color despite its correct blue-screen observation.",
+    "Adapter v1 configuration/echoed model is not loaded-weight or GPU attestation. External preflight supplied that evidence for this bounded run only.",
+    "Video sampling and submitted duration are requested input coverage, not backend-attested processed coverage.",
+    "HTTP abort cancels owned client/CPU work but does not prove the external GPU job stopped.",
+    "The new source requires explicit Omni endpoint/model configuration in the deployed Omnius process; publishing artifacts and daemon lifecycle remain untouched."
+  ],
+  "sourceSha256": {
+    "packages/execution/src/av/omni-comprehension.ts": "79703b12a34fd88f3f6f391b53803b27b346d76a2a36dbe6f9c4969358e652e1",
+    "packages/cli/src/api/routes-media.ts": "3a4f5449d38a8187afd74ac14f2297307492ce29b94e888fbca42a262dc81c4a",
+    "packages/cli/src/api/web-media-runtime.ts": "0426a3b4ebc7fb7c3b6566384d89dd1bd338d8c0b5732c44d7c272bbcf33ddd2",
+    "packages/cli/src/api/web-media-models-runtime.ts": "b8a4047fd0777e6e96d5738a2dfc9139add9cc45a4cd02ede0b1c1de35a85b38"
+  }
+}

package/npm-shrinkwrap.json

@@ -1,12 +1,12 @@
 {
   "name": "omnius",
-  "version": "1.0.870",
+  "version": "1.0.871",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "omnius",
-      "version": "1.0.870",
+      "version": "1.0.871",
       "bundleDependencies": [
         "image-to-ascii"
       ],

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "omnius",
-  "version": "1.0.870",
+  "version": "1.0.871",
   "description": "AI coding agent powered by open-source models (Ollama/vLLM) — interactive TUI with agentic tool-calling loop",
   "type": "module",
   "main": "./dist/library.js",
@@ -170,5 +170,5 @@
     "viem": "2.47.4",
     "cli-highlight": "^2.1.11"
   },
-  "readme": "# Omnius\n\nOmnius is a local-first runtime for AI-assisted software development and generative work. It brings a terminal interface, browser dashboard, automation API, agent execution, memory, and media tools into one workspace-oriented system.\n\nOmnius connects to local and remote model providers. Projects retain their own sessions and generated artifacts, while model weights and runtime dependencies are shared across workspaces.\n\n[![npm](https://img.shields.io/npm/v/omnius.svg)](https://www.npmjs.com/package/omnius)\n[![Node](https://img.shields.io/badge/node-%3E%3D22-brightgreen.svg)](https://nodejs.org/)\n[![License](https://img.shields.io/badge/license-CC--BY--NC--4.0-blue.svg)](https://creativecommons.org/licenses/by-nc/4.0/)\n\n## Get started\n\nRequires Node.js 22 or newer and npm 10 or newer.\n\n```bash\nnpm install -g omnius\nomnius\n```\n\nUse `/setup` to configure inference and `/help` to explore terminal commands. See [installation](docs/getting-started/install.md), [first run](docs/getting-started/first-run.md), and [model providers](docs/getting-started/model-providers.md) for setup details.\n\nTo open the browser dashboard and API:\n\n```bash\nomnius serve\n```\n\nThe default dashboard address is `http://127.0.0.1:11435/`, with interactive API documentation at `/docs`.\n\n## System overview\n\n| Layer | Responsibility |\n| --- | --- |\n| Interfaces | Terminal sessions, browser workspaces, command-line automation, and system tray integration |\n| Agent runtime | Task execution, tool use, delegated agents, verification, and resumable work |\n| Inference | Model selection and routing across local servers, configured providers, and peers |\n| Tools | Files, code, shell commands, web access, browser automation, and extensible capabilities |\n| Memory and retrieval | Project context, indexed material, persistent memory, and targeted retrieval |\n| Media and voice | Image, video, audio, music, speech recognition, and speech synthesis |\n| Integration | REST APIs, events, MCP, Telegram, and shared inference services |\n\nThe [architecture overview](docs/architecture/overview.md) and [agent system map](docs/architecture/agent-system-map.md) describe the runtime boundaries and state ownership.\n\n## Workspaces and sessions\n\nA project provides the working directory for files, tools, conversations, and generated media. Terminal and browser interfaces expose saved sessions and project artifacts. Operational details remain available alongside the conversation without replacing its authored content.\n\nProject state lives under `.omnius/`. Shared model weights and runtime dependencies are managed separately from project-generated media. See [terminal workflows](docs/guides/tui-workflows.md), the [dashboard guide](docs/guides/dashboard.md), and [media generation](docs/guides/media-generation.md).\n\n## Automation and discovery\n\nOmnius can run a task directly from the command line:\n\n```bash\nomnius \"inspect this repository and explain its main entrypoints\"\n```\n\nAgents and integrations can discover capabilities through the CLI or daemon:\n\n```bash\nomnius discover \"bring your own inference\"\nomnius show layer.orchestration\nomnius capabilities --json\n```\n\nThe daemon provides stateful chat, agent execution, tools, memory, media, and OpenAI/Ollama-compatible inference interfaces. Begin with [agent integration](docs/guides/agent-integration.md) and the [discovery guide](docs/DISCOVERY.md).\n\n<!-- BEGIN GENERATED REST INVENTORY -->\nThe complete API inventory is maintained in the [REST reference](docs/reference/rest-api.md). The running daemon serves its machine-readable contract at `/openapi.json`.\n<!-- END GENERATED REST INVENTORY -->\n\n## Documentation\n\n| Topic | Guide |\n| --- | --- |\n| Inference configuration | [Provider protocols and keys](docs/guides/bring-your-own-inference.md) |\n| Commands and tools | [Slash commands](docs/reference/slash-commands.md), [tool discovery](docs/guides/tools-and-web-search.md) |\n| Agent coordination | [Adjudication](docs/ADJUDICATION.md), [agent system map](docs/architecture/agent-system-map.md) |\n| Browser interface | [Dashboard](docs/guides/dashboard.md) |\n| Voice and media | [Realtime voice](docs/guides/realtime.md), [media generation](docs/guides/media-generation.md) |\n| Connected services | [Telegram](docs/guides/telegram.md), [system tray](docs/guides/system-tray.md), [sponsor and peer inference](docs/guides/sponsor-and-cohere.md) |\n| Runtime administration | [Runtime hygiene](docs/operations/runtime-hygiene.md), [access control](docs/operations/security-and-remote-access.md) |\n| Agent-readable documentation | [Documentation index](docs/agent-memory/INDEX.md) |\n\n## Development\n\nThe repository is a pnpm workspace. `packages/cli` contains the interfaces and daemon; `packages/orchestrator` coordinates agent execution; `packages/execution` provides tools. Supporting packages cover memory, indexing, retrieval, schemas, prompts, and backend integration.\n\nRequires pnpm 9 or newer.\n\n```bash\npnpm install\npnpm -r build\npnpm docs:check\n```\n\nPublishing uses the generated `publish/` package. The build, verification, and release procedure is documented in [AGENTS.md](AGENTS.md).\n\n## License\n\nOmnius is released under [CC-BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/) for non-commercial use. Commercial use, redistribution, hosted services, and enterprise deployment require a commercial license.\n"
+  "readme": "# Omnius\n\nOmnius is a local-first runtime for AI-assisted software development and generative work. It brings a terminal interface, browser dashboard, automation API, agent execution, memory, and media tools into one workspace-oriented system.\n\nOmnius connects to local and remote model providers. Projects retain their own sessions and generated artifacts, while model weights and runtime dependencies are shared across workspaces.\n\n[![npm](https://img.shields.io/npm/v/omnius.svg)](https://www.npmjs.com/package/omnius)\n[![Node](https://img.shields.io/badge/node-%3E%3D22-brightgreen.svg)](https://nodejs.org/)\n[![License](https://img.shields.io/badge/license-CC--BY--NC--4.0-blue.svg)](https://creativecommons.org/licenses/by-nc/4.0/)\n\n## Get started\n\nRequires Node.js 22 or newer and npm 10 or newer.\n\n```bash\nnpm install -g omnius\nomnius\n```\n\nUse `/setup` to configure inference and `/help` to explore terminal commands. See [installation](docs/getting-started/install.md), [first run](docs/getting-started/first-run.md), and [model providers](docs/getting-started/model-providers.md) for setup details.\n\nTo open the browser dashboard and API:\n\n```bash\nomnius serve\n```\n\nThe default dashboard address is `http://127.0.0.1:11435/`, with interactive API documentation at `/docs`.\n\n## System overview\n\n| Layer | Responsibility |\n| --- | --- |\n| Interfaces | Terminal sessions, browser workspaces, command-line automation, and system tray integration |\n| Agent runtime | Task execution, tool use, delegated agents, verification, and resumable work |\n| Inference | Model selection and routing across local servers, configured providers, and peers |\n| Tools | Files, code, shell commands, web access, browser automation, and extensible capabilities |\n| Memory and retrieval | Project context, indexed material, persistent memory, and targeted retrieval |\n| Media and voice | Image, video, audio, music, speech recognition, and speech synthesis |\n| Integration | REST APIs, events, MCP, Telegram, and shared inference services |\n\nThe [architecture overview](docs/architecture/overview.md) and [agent system map](docs/architecture/agent-system-map.md) describe the runtime boundaries and state ownership.\n\n## Workspaces and sessions\n\nA project provides the working directory for files, tools, conversations, and generated media. Terminal and browser interfaces expose saved sessions and project artifacts. Operational details remain available alongside the conversation without replacing its authored content.\n\nProject state lives under `.omnius/`. Shared model weights and runtime dependencies are managed separately from project-generated media. See [terminal workflows](docs/guides/tui-workflows.md), the [dashboard guide](docs/guides/dashboard.md), and [media generation](docs/guides/media-generation.md).\n\n## Automation and discovery\n\nOmnius can run a task directly from the command line:\n\n```bash\nomnius \"inspect this repository and explain its main entrypoints\"\n```\n\nAgents and integrations can discover capabilities through the CLI or daemon:\n\n```bash\nomnius discover \"bring your own inference\"\nomnius show layer.orchestration\nomnius capabilities --json\n```\n\nThe daemon provides stateful chat, agent execution, tools, memory, media, and OpenAI/Ollama-compatible inference interfaces. Begin with [agent integration](docs/guides/agent-integration.md) and the [discovery guide](docs/DISCOVERY.md).\n\n<!-- BEGIN GENERATED REST INVENTORY -->\nThe complete API inventory is maintained in the [REST reference](docs/reference/rest-api.md). The running daemon serves its machine-readable contract at `/openapi.json`.\n<!-- END GENERATED REST INVENTORY -->\n\n## Documentation\n\n| Topic | Guide |\n| --- | --- |\n| Inference configuration | [Provider protocols and keys](docs/guides/bring-your-own-inference.md) |\n| Commands and tools | [Slash commands](docs/reference/slash-commands.md), [tool discovery](docs/guides/tools-and-web-search.md) |\n| Agent coordination | [Adjudication](docs/ADJUDICATION.md), [agent system map](docs/architecture/agent-system-map.md) |\n| Browser interface | [Dashboard](docs/guides/dashboard.md) |\n| Voice and media | [Realtime voice](docs/guides/realtime.md), [media generation](docs/guides/media-generation.md), [Omni analysis](docs/reference/omni-analysis.md) |\n| Connected services | [Telegram](docs/guides/telegram.md), [system tray](docs/guides/system-tray.md), [sponsor and peer inference](docs/guides/sponsor-and-cohere.md) |\n| Runtime administration | [Runtime hygiene](docs/operations/runtime-hygiene.md), [access control](docs/operations/security-and-remote-access.md) |\n| Agent-readable documentation | [Documentation index](docs/agent-memory/INDEX.md) |\n\n## Development\n\nThe repository is a pnpm workspace. `packages/cli` contains the interfaces and daemon; `packages/orchestrator` coordinates agent execution; `packages/execution` provides tools. Supporting packages cover memory, indexing, retrieval, schemas, prompts, and backend integration.\n\nRequires pnpm 9 or newer.\n\n```bash\npnpm install\npnpm -r build\npnpm docs:check\n```\n\nPublishing uses the generated `publish/` package. The build, verification, and release procedure is documented in [AGENTS.md](AGENTS.md).\n\n## License\n\nOmnius is released under [CC-BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/) for non-commercial use. Commercial use, redistribution, hosted services, and enterprise deployment require a commercial license.\n"
 }