omnius 1.0.869 → 1.0.871

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

@@ -0,0 +1,78 @@
+{
+  "feature": "Genuine configured Omni comprehension client and agent tools; no production synthetic graph fallback",
+  "verifiedAt": "2026-10-17T07:01:24.955511+00:00",
+  "baseCommit": "dde62b6fe5704c4eb0376cd3b8b81c6babc5cd0b",
+  "passed": true,
+  "uniqueTests": 71,
+  "uniqueTestFiles": 9,
+  "suites": {
+    "audio-analyze.test.ts": 5,
+    "audio-classifier-runtime.test.ts": 6,
+    "av-foundation.test.ts": 4,
+    "av-ingest.test.ts": 4,
+    "av-phase3.test.ts": 6,
+    "av-phase4.test.ts": 7,
+    "av-phase5.test.ts": 7,
+    "omni-comprehension-contract.test.ts": 13,
+    "omni-comprehension.test.ts": 19
+  },
+  "rawReports": [
+    "/tmp/omnius-omni-execution-final.json",
+    "/tmp/omnius-omni-execution-final.log"
+  ],
+  "checks": {
+    "executionNoEmit": "PASS: pnpm --filter @omnius/execution exec tsc --noEmit --tsBuildInfoFile /tmp/omnius-omni-execution-typecheck.tsbuildinfo",
+    "ownedDiffCheck": "PASS"
+  },
+  "verificationScope": "Isolated HTTP adapter fixtures, real CPU-only FFmpeg/FFprobe, actual tool entry points and explicit scaffold-registry regressions. No live model or GPU inference. This receipt does not count root API/browser/transport gates.",
+  "behavior": [
+    "An exact explicitly configured logical -omni tag is required; an optional requested tag must match exactly. The server-controlled adapter URL supports configured base paths and optional Bearer auth. Neither model discovery nor alternate backend/model/CPU inference fallback occurs.",
+    "Health/contract report configured capability only. Adapter v1 model echo does not attest loaded weight identity, accelerator placement, actual media coverage, or remote cancellation.",
+    "Actual local media is probed before CPU normalization. Audio becomes PCM16 mono16k WAV; video becomes bounded MP4 with1fps/32frames requested and dimensions constrained to640. Inputs over60s audio,32s video, or128MiB fail explicitly; no implicit duration truncation. Normalized media32MiB and JSON response1MiB are capped.",
+    "Outgoing requests explicitly use stream:false,think:false,cache_prompt:false,speech_mode:never,response_modalities:[text]. Questions use chat(comprehension+language); direct descriptions use describe(comprehension only). Accepted replies must be settled assistant messages with the exact expected route and no unresolved tool calls.",
+    "Current-media provenance must match exactly. Audio-only input cannot become visual evidence; tool data and prior dialogue cannot become current observations. Transcript, non-speech audio and visual observations remain distinct typed fields. No fabricated tracks, bounding boxes or confidence scores are generated.",
+    "AVComprehendTool uses the shared real client and returns typed results/errors, supports owned cancellation, and no longer invokes synthetic entities/events. Production buildRegistry contains only live sidecar adapters; unavailable roles yield no evidence. buildMockRegistry remains explicit for scaffold tests only.",
+    "AudioAnalyzeTool comprehend uses Omni first. A successful Omni result bypasses legacy graph ingestion/persistence while retaining deterministic measured acoustic evidence. Unconfigured/unavailable Omni has an explicit limitation and truthful acoustic fallback; malformed provenance, cancelled work and invalid media are errors.",
+    "Direct native descriptions retain the full original once, including untagged observations; typed component observations remain available separately. A question/answer may additionally present distinct evidence sections.",
+    "CPU normalization and HTTP operations use owned AbortSignals and temporary files are removed on success, cancellation and rejected responses. Existing audio conditioning/diagnostics now accept the same cancellation signal."
+  ],
+  "limits": [
+    "No live model request or zero-token model-load probe was sent. The observed external runtime is not attested as the requested weights/GPU by adapter health; live tests require the mandatory designated-hardware gate.",
+    "Client cancellation and cleanup do not prove the external adapter stopped remote GPU computation. Adapter v1 has no authenticated per-operation cancellation receipt.",
+    "Video coverage is sampled; source metadata records submittedDurationSec,samplingRequested and actualCoverage:not_reported. Backend effective frame/audio coverage is not asserted.",
+    "Weights are not provisioned or downloaded by this client. Existing detector, embedding and ASR tools retain their separate capabilities; they are not falsely labelled the configured omni model."
+  ],
+  "isolation": {
+    "network": "Exact allowlisted loopback fake HTTP adapter or intercepted fixture transport only",
+    "media": "Scratch files with actual CPU codecs; source/config/media roots isolated",
+    "noActions": [
+      "No shared build/dist edits",
+      "No service/container/daemon change",
+      "No CUDA allocation",
+      "No live inference",
+      "No package install or publication",
+      "No user media/cache mutation"
+    ]
+  },
+  "deduplication": "71 tests in9 suites is the final authoritative aggregate; earlier40/64 iterations and independent13 are not added again. Explicit synthetic foundation tests verify scaffold plumbing, not inference accuracy.",
+  "ownedFiles": [
+    "packages/execution/src/av/omni-comprehension.ts",
+    "packages/execution/src/av/sidecar-adapter.ts",
+    "packages/execution/src/index.ts",
+    "packages/execution/src/tools/av-comprehend.ts",
+    "packages/execution/src/tools/audio-analyze.ts",
+    "packages/execution/src/audio-input-conditioning.ts",
+    "packages/execution/tests/av-ingest.test.ts",
+    "packages/execution/tests/omni-comprehension.test.ts"
+  ],
+  "sourceSha256": {
+    "packages/execution/src/av/omni-comprehension.ts": "79703b12a34fd88f3f6f391b53803b27b346d76a2a36dbe6f9c4969358e652e1",
+    "packages/execution/src/av/sidecar-adapter.ts": "bb5ebb83f77dab416154ba8d56572eb3a209ec10889326c028a862800c9115c5",
+    "packages/execution/src/index.ts": "2f5d134b33a3a86569c537bfbb8a0f491a0b99ab9d9ea1a56e8bffe5dd1ed45b",
+    "packages/execution/src/tools/av-comprehend.ts": "c586f9d87f02c635ecd309b3d0e2fd11301d6cd30e841750cfc74edf5dddebd8",
+    "packages/execution/src/tools/audio-analyze.ts": "45e02071191783914ddd92f5c2b3741386392efbe092e4fc756040a6807a27d3",
+    "packages/execution/src/audio-input-conditioning.ts": "a5092a0e0e1ea2fab1d9bbfb224f97c2db733df19b1404008a9448f117347bf9",
+    "packages/execution/tests/av-ingest.test.ts": "18148c0b29be7d73b7159467456a521934293ae2916a088e222cc60e8fe2831a",
+    "packages/execution/tests/omni-comprehension.test.ts": "d50de42ac477f8c42faea9b71cab41cd1288e8630a5de640649cfa31cabd8095"
+  }
+}

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/docs/work-orders/evidence/tui-response-ownership-verification-20261016.json

@@ -0,0 +1,79 @@
+{
+  "feature": "Single rich accepted terminal response and lossless reply persistence",
+  "verifiedAt": "2026-10-17T06:34:45.968783+00:00",
+  "baseCommit": "ab17b1451280ad2f1510815bd3ab78eeb645455e",
+  "passed": true,
+  "verificationScope": "Focused main/child response ownership, actual mocked-transport runner/executor, native application projection, persistence and interruption tests; not the entire CLI or a live-inference test.",
+  "uniqueTests": 97,
+  "uniqueTestFiles": 10,
+  "suites": {
+    "activity-diagnostic-visibility.test.ts": 15,
+    "agent-response.test.ts": 4,
+    "interrupted-inference-presentation.test.ts": 3,
+    "media-generation-block.test.ts": 9,
+    "native-inprocess-agent-runner.test.ts": 1,
+    "native-inprocess-agent.test.ts": 15,
+    "stream-renderer.test.ts": 22,
+    "task-handoff.test.ts": 18,
+    "tui-interaction-context.test.ts": 6,
+    "tui-structured-memory-lifecycle.test.ts": 4
+  },
+  "rawReports": [
+    "/tmp/omnius-response-owner-final.json"
+  ],
+  "deduplication": "The final 97-test aggregate is authoritative. Earlier 9/20/29/53-test iterations are not added. Root native, helper/browser and canonical-restore checks are separate receipts and not double-counted here.",
+  "checks": {
+    "cliNoEmit": "PASS: pnpm --filter omnius exec tsc --noEmit",
+    "ownedDiffCheck": "PASS"
+  },
+  "behavior": [
+    "Main final selection and last visible assistant response use the shared lossless assistant normalizer. Original indentation, Markdown lists/fences/paragraphs and terminal newlines are preserved by selection; storage-only whitespace flattening is retained only on metadata.",
+    "Removed the eight-line prefix/substring deletion workaround. Successful generation details collapse by owned retained block identity, and successive main turns do not reopen/reuse the previous generation; the final accepted response has one rich presentation.",
+    "New per-host AgentResponsePresenter owns child generation documents and exactly one accepted final. Successful child final uses the shared native task-complete column and compact receipt. Main and child task_complete summaries/control arguments do not become a second conversation body.",
+    "Child failed/unknown completion attempts retain collapsed technical arguments and outcome evidence; interrupted observed partial output remains inspectable. Only a settled completed runner result can promote its accepted reply. A completion event or tool success alone is insufficient.",
+    "Native child result callback runs after workflow result preparation, is suppressed after cancellation, and presentation exceptions cannot change executor outcome. An exact owner token prevents stale native events/results from a prior use of a view ID from affecting its replacement. Pending child calls correlate by action ID.",
+    "Saved assistantResponse is no longer flattened or capped at1200 in the save normalizer or main persistence/handoff callsites. The actual public runWithTUI fixture verifies one accepted final plus save/reload and handoff equality for a reply over1200 characters containing fenced indentation, lists, blank lines and first/last markers.",
+    "Native media ownership is consumed once before the generic main renderer and secondary ASCII/audio hooks. Child native media results also suppress duplicate generic cards, while unrelated tool previews retain their existing path.",
+    "Stream interruption now fences late old chunks until explicit new start, cancels pending timers, clears hidden reasoning, retains observed native partial output with paused status, and discards only the plain fallback tail that had not been rendered. Explicit flush/end still preserves ordinary plain output."
+  ],
+  "externalChildBoundary": [
+    "full_sub_agent buildSubProcessArgs (execution/tools/full-sub-agent.ts) passes neither --json nor --verbose. Current piped child runWithTUI has streaming disabled and the repaired main lifecycle skips raw task_complete copies and prints one final response.",
+    "Parent onViewWrite/recordAgentOutput still captures unstructured stdout/stderr process text. Arbitrary external or older child binaries remain raw captured logs; no authoritative rich-final extraction or text-heuristic deletion is claimed for that boundary. No new backend protocol or unrelated execution edits were introduced."
+  ],
+  "isolation": [
+    "Inference transports are synthetic before backend construction. Actual FileReadTool and real runner completion transactions operate only on scratch project/configuration directories.",
+    "No live model request, GPU/CUDA allocation, download, shared build/dist change, production daemon/service action, package install/publication, or unrelated dirty-file edit was performed."
+  ],
+  "limits": [
+    "One existing fire-and-forget identity observer can finish after a test scratch directory is removed, emitting IK-OBSERVE ENOENT. Assertions pass; root independently observed the same teardown diagnostic. This unrelated identity lifecycle was not expanded.",
+    "Actual OpenTUI final rendering/collapse and canonical restoration are verified in the separate widget/root suites. This receipt counts application projection and mocked-transport lifecycle behavior only."
+  ],
+  "ownedFiles": [
+    "packages/cli/src/tui/interactive.ts",
+    "packages/cli/src/tui/agent-response.ts",
+    "packages/cli/src/tui/native-inprocess-agent.ts",
+    "packages/cli/src/tui/tui-interaction-context.ts",
+    "packages/cli/src/tui/omnius-directory.ts",
+    "packages/cli/src/tui/stream-renderer.ts",
+    "packages/cli/tests/agent-response.test.ts",
+    "packages/cli/tests/tui-interaction-context.test.ts",
+    "packages/cli/tests/native-inprocess-agent.test.ts",
+    "packages/cli/tests/native-inprocess-agent-runner.test.ts",
+    "packages/cli/tests/tui-structured-memory-lifecycle.test.ts",
+    "packages/cli/tests/stream-renderer.test.ts"
+  ],
+  "sourceSha256": {
+    "packages/cli/src/tui/interactive.ts": "2be57f7dbbfac26234d471183bdc26079afab84d2661da40ce8a996ad4963de5",
+    "packages/cli/src/tui/agent-response.ts": "e3744c42c659670dde5843667ad8be6b545e6cf21c1b4c5473a3a00ba68e3977",
+    "packages/cli/src/tui/native-inprocess-agent.ts": "43e97fdb4e218891dfbcad1bef2d5402bdfbfac90d6dd54efc630bff1e3846fc",
+    "packages/cli/src/tui/tui-interaction-context.ts": "c1ce24e3299f9e47dbdaf301eef2d0dd53eb01521bf8d0e44242caa4a2db453b",
+    "packages/cli/src/tui/omnius-directory.ts": "704fa84f53ce5590424b64869976e4d3b0b74d7146758b345544cad427211394",
+    "packages/cli/src/tui/stream-renderer.ts": "b6cfa3e1a0edce0b4ae662ef50b682109d1ace5ddc2d2d72c1775ce56dc75ed4",
+    "packages/cli/tests/agent-response.test.ts": "64ed136d72627f011a22cdb37da0e3bc02790d3475d8666dd857c66934a64dee",
+    "packages/cli/tests/tui-interaction-context.test.ts": "a09ea8e92d7bcb363263f79652f09694bdd28269a70ca2d93e26c556c4f72a83",
+    "packages/cli/tests/native-inprocess-agent.test.ts": "34cc2b06c5c8c4e55b7c73697adf1820f62e4ea5f227c83eea5ad3121d1b3206",
+    "packages/cli/tests/native-inprocess-agent-runner.test.ts": "da33fda071a05bb7e76977de7f7da968e16609b44599b6f9c59b583984007293",
+    "packages/cli/tests/tui-structured-memory-lifecycle.test.ts": "1cbaac4f85cb2421d9313c0a2bee32608757e2002d5f1317ed028a013d9781f3",
+    "packages/cli/tests/stream-renderer.test.ts": "208507623ecc33687b45bc91a15cd5c6572e0018bea3f4114e8ae067e40abc9f"
+  }
+}

package/npm-shrinkwrap.json

@@ -1,12 +1,12 @@
 {
   "name": "omnius",
-  "version": "1.0.869",
+  "version": "1.0.871",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "omnius",
-      "version": "1.0.869",
+      "version": "1.0.871",
       "bundleDependencies": [
         "image-to-ascii"
       ],

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "omnius",
-  "version": "1.0.869",
+  "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 agentic coding runtime: terminal UI, autonomous coding loop, REST daemon, model router, memory layer, media tools, Telegram bridge, and peer-to-peer inference mesh in one CLI.\n\nIt is designed for open-weight and user-controlled models first, while still routing cleanly through Ollama, vLLM, OpenAI-compatible endpoints, OpenRouter, Groq, Chutes, sponsor peers, COHERE peers, and other configured providers.\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)](LICENSE)\n\n## Install\n\n```bash\nnpm install -g omnius\nomnius\n```\n\nWith no inference profile selected, Omnius starts with **Built-in free** models.\nNo API key or local model download is required. It selects the highest-ranked\ncompatible free model from the current catalog and retains a known default\nwhen catalog discovery is temporarily unavailable. Use `/model` to choose among\nthe built-in free models and models on your configured endpoint. Existing local\nand cloud profiles are preserved, including temporarily offline endpoints.\n\nAutomatic fallback tries compatible alternatives within its time and rate-limit\nbounds. External services can still be unavailable; Omnius reports exhaustion\nwithout claiming a successful answer. `/fallback manual` asks before switching\nto an alternative after the selected endpoint or model fails.\n\nUse `/setup` for optional provider configuration, `/free` inside setup to return\nto built-in free inference, or `/setup local` for local model setup. Setup asks\nfor a key only when you choose a provider that requires one. Keys stay local;\nthe setup helper sees opaque references, and only the selected provider receives\nits key for the connection check. Local model downloads remain an explicit choice.\n\nThe base install is compiler-free: a fresh machine does not need `make`, a C++\ntoolchain, or Python just to install and launch Omnius. The installer provisions\nthe AIWG companion separately without its optional native semantic-index addon,\nso an unavailable native build cannot roll back the Omnius CLI.\n\nIf npm succeeds but a new terminal reports `omnius: command not found`, inspect\nthe global prefix and add its command directory to `PATH`:\n\n```bash\nnpm prefix -g\nexport PATH=\"$(npm prefix -g)/bin:$PATH\"\nhash -r\nomnius --version\n```\n\nPersist that export in the profile used by your shell, or open a new terminal\nafter an nvm/fnm setup change. `npx omnius@latest` is an immediate fallback.\n\nRequirements:\n\n- Node.js 22 or newer\n- npm 10 or newer for published CLI use\n- pnpm 9 or newer for workspace development\n- Internet access for built-in free inference, or a configured local model or remote endpoint\n\nStart the REST daemon:\n\n```bash\nomnius serve\n```\n\nThe daemon defaults to `http://127.0.0.1:11435`. Open the interactive API docs at `http://127.0.0.1:11435/docs`.\n\nRegister the native system tray indicator (Linux, macOS, and Windows x64):\n\n```bash\nomnius tray install\nomnius tray status\n```\n\nThe per-login indicator observes the daemon over loopback, checks health and npm\nupdates every 10 seconds, and provides dashboard, logs, and explicit daemon\ncontrols. Its version row is passive when current and becomes a verified global\nupdate action only when a newer exact semver is available. See the\n[system tray guide](docs/guides/system-tray.md), including Ubuntu/GNOME setup.\n\n## Agent Discovery\n\nThe npm package ships its complete documentation and a machine-readable\ncapability catalog. An agent does not need to inspect Omnius source or guess\nwhich endpoint owns a capability:\n\n```bash\nomnius discover \"bring your own inference\"\nomnius show workflow.choose-entrypoint\nomnius show layer.orchestration\nomnius show store.project\nomnius show provider.anthropic\nomnius show provider.gemini\nomnius show tool.web-search\nomnius discover \"evidence-bound decision impasse\"\nomnius show tool.adjudicate\nomnius discover \"osint research\"\nomnius show capability.osint-research\nomnius capabilities --json\n```\n\nWith the daemon running, begin at `GET /v1/discovery/bootstrap`. The same\ndiscovery cascade is available at `GET /v1/discovery`, with exact entry expansion at\n`GET /v1/discovery/{id}`. The live API contract remains available at\n`/openapi.json`, direct tool metadata at `/v1/tools`, and skills at\n`/v1/skills`.\n\nStart with [the discovery guide](docs/DISCOVERY.md) when integrating another\nagent or service, and use the [agent system map](docs/architecture/agent-system-map.md)\nto trace layers, modules, runtimes, and state ownership. Use [bring-your-own inference](docs/guides/bring-your-own-inference.md)\nfor provider protocols and keys, and [tools and web search](docs/guides/tools-and-web-search.md)\nfor the distinction between direct tools and agent-bound tools. The\n[evidence-bound adjudication guide](docs/ADJUDICATION.md) explains how a\ntop-level full agent freezes an admissible record, isolates a genuine decision\nimpasse from accumulated working context, fans review out across fresh\nevidence-scoped constituents, validates evidence citations and quorum, and\nproduces a durable verdict receipt. Top-level runtimes execute constituents in\na dedicated `full_sub_agent` process profile that cannot load tools, project\ncontext, memory, or the ambient parent environment. The process runs outside\nthe project directory. Cancellation and deadlines terminate its child processes;\nordinary child transport failure is recorded before bounded direct fallback.\nPlanner schema drift uses a deterministic question-framing fallback, and\ndurable artifact replay verifies the case, findings, verdict, and receipt\nhashes without new inference. The\n[categorized OSINT research guide](docs/guides/osint-research.md) documents\nthe local discover → exact expansion → explicit web-tool workflow.\n\n## What Omnius Does\n\n- Runs autonomous coding tasks, edits files, executes tools, tests changes, and iterates on failures.\n- Resolves genuine decision impasses in fresh evidence-scoped contexts that reduce parent-context anchoring, with host-validated citations, quorum, preserved dissent, and durable verdict receipts.\n- Provides a dense terminal UI for model selection, endpoint routing, task control, shell output, voice, sponsors, Telegram, and system telemetry.\n- Exposes a REST daemon with OpenAI/Ollama-compatible inference, agentic task execution, memory, skills, tools, MCP, events, voice, projects, and governance endpoints.\n- Routes models through local, cloud, sponsor, and peer-to-peer endpoints without assuming local Ollama is the only source.\n- Supports realtime spoken conversation for ASR/TTS clients through `/realtime` and REST `realtime: true`.\n- Supports image, video, sound, music, TTS, ASR, voice clone references, Telegram media workflows, and sponsor-provided media generation.\n- Keeps project runtime state in `.omnius/`, which is intentionally ignored by git.\n\n## Common Workflows\n\nFor large PDF collections, Omnius retains originals in a durable scoped index\nand processes ordering, manipulation, summary and extraction in resumable steps.\nSee the [PDF collections guide](docs/guides/pdf-collections.md) for coverage,\nsource provenance, numeric checks and complete delivery of large results.\n\n```bash\nomnius \"inspect this repo and summarize the main entrypoints\"\nomnius serve\n```\n\n```text\n/help                 command help\n/model                select or inspect the active model\n/endpoint             select or configure local, cloud, sponsor, or peer endpoints\n/title                name the current session\n/realtime             toggle short ASR/TTS-oriented conversation mode\n/voice                choose TTS, voice-clone, voicechat, and ASR controls\n/voice asr            select, set up, activate, or test an exact ASR engine/model\n/indicator            reconcile the daemon, then start the native tray indicator\n/update check         force an update availability check\n/update quick         run the verified global update with live TUI progress\n/update full          run the full clean/build/install/restart verification flow\n/broker               inspect model broker, RAM/VRAM thresholds, and loaded models\n/sponsor              expose local or upstream capacity to peers\n/cohere               participate in distributed COHERE inference\n/telegram             configure or toggle the Telegram bridge\n/skills               list explorable skills and docs memories\n/pause                pause after the current turn boundary\n/stop                 interrupt the active run\n/resume               resume saved state\n```\n\n## Current Feature Areas\n\n| Area | What to read |\n| --- | --- |\n| Install and setup | [Install](docs/getting-started/install.md), [First run](docs/getting-started/first-run.md), [Model providers](docs/getting-started/model-providers.md) |\n| Agent discovery | [Discovery cascade](docs/DISCOVERY.md), [machine catalog](docs/DISCOVERY.json), [agent integration](docs/guides/agent-integration.md) |\n| Bring your own inference | [Provider protocols and keys](docs/guides/bring-your-own-inference.md) |\n| Tools and web search | [Tool discovery and invocation](docs/guides/tools-and-web-search.md) |\n| Evidence-bound adjudication | [Adjudication tool, panel workflow, verdict contract, and harness](docs/ADJUDICATION.md) |\n| Terminal workflows | [TUI workflows](docs/guides/tui-workflows.md), [Slash commands](docs/reference/slash-commands.md) |\n| Web dashboard | [All dashboard routes, workspaces, sessions, Voice, Generate, updates, and observability](docs/guides/dashboard.md) |\n| REST daemon | [REST reference](docs/reference/rest-api.md), [REST quickref](docs/rest/QUICKREF.md), [OpenAPI source](docs/rest/openapi-source.md) |\n| System tray | [Cross-platform tray and Ubuntu setup](docs/guides/system-tray.md) |\n| Realtime voice chat | [Realtime guide](docs/guides/realtime.md) |\n| TTS and selectable ASR | [Voice/vision REST guide](docs/rest/endpoints/voice-vision.md), [Dashboard Voice page](docs/guides/dashboard.md#voice-and-asr) |\n| Sponsor and COHERE mesh | [Sponsor and COHERE guide](docs/guides/sponsor-and-cohere.md) |\n| Telegram bridge | [Telegram guide](docs/guides/telegram.md) |\n| Media generation | [Media guide](docs/guides/media-generation.md) |\n| Operations | [Runtime hygiene](docs/operations/runtime-hygiene.md), [Security and remote access](docs/operations/security-and-remote-access.md) |\n| Service compatibility | [Runtime version gate](docs/operations/version-compatibility.md) |\n| Architecture | [Architecture overview](docs/architecture/overview.md) |\n| Agent-explorable docs | [Agent memory docs index](docs/agent-memory/INDEX.md) |\n\n## Web Dashboard\n\n`omnius serve` exposes a self-contained operational dashboard at\n`http://127.0.0.1:11435/`. All pages use the same compact NOCLIP-derived style\ntokens and responsive observability-card grid, while keeping workspace, model,\nsession, run, service, and update state visible instead of hiding it behind\ndecorative pages.\n\n| Route | Purpose |\n| --- | --- |\n| `/chat` (`/`) | Stateful browser and imported TUI chats, full-history hydration, live run recovery, attachments, files, plan/context, and steering check-ins |\n| `/agent` | One-shot task contracts, personas/profiles, tool/isolation controls, run records, output, and events |\n| `/voice` | Voicechat, exact TTS model/options, clone references, ASR engine/model setup and activation, real-file ASR testing, transcript, and TTS testing |\n| `/generate` | Image/video/audio/music jobs, AV analysis, model/store controls, relocation progress, and global gallery |\n| `/projects` | Scan, register, rename, activate, and remove workspaces |\n| `/dashboard` (`/jobs`) | CPU/RAM/GPU/VRAM, processes, scheduler, services, usage, and verified updates |\n| `/activity` | Live run/tool/memory/engine event observability |\n| `/discover` | Agent bootstrap, capability intent search, and exact entry expansion |\n| `/settings` (`/config`) | Models, endpoints, voice, runtime, access, keys, appearance, and services |\n\nThe clickable sidebar brand opens the registered-workspace picker. Workspace\nselection scopes preferences, files, session history, chat pins/folders/search,\nand agent defaults. Chats, TUI visual history, and one-shot agent runs are\ndistinct records: `/quit`, `/exit`, manual-save noise, empty histories, and\nduplicate TUI transcripts are rejected from the chat projection; selecting a\nvalid session loads its full history and in-flight status from the daemon.\nThe chat top bar also reports the effective API base path and authentication\nmode. Streams retain split frames, Stop terminates the daemon-owned process\nlease, and assistant-provided web/file links stay inert until the daemon\nreturns a validation receipt.\n\nThe dashboard checks for updates every 10 seconds. An update button appears only\nfor a newer exact semver and drives `POST /v1/update`, then polls the durable\ntransaction until the global npm package, resolved executable, restarted daemon,\npackage/boot hashes, and tray runtime are reconciled. See the\n[complete dashboard guide](docs/guides/dashboard.md) for state ownership,\nsecurity, page-by-page behavior, and exact REST flows.\n\n## Terminal Over SSH\n\nThe TUI paints for a local terminal, where a full-area repaint costs nothing.\nOver a network the same cadence has to share the link with your keystrokes, so\nOmnius detects a remote session (`SSH_TTY` / `SSH_CONNECTION` / `SSH_CLIENT`)\nand paces itself: decorative chrome animates slower, a wheel-scroll burst is\ncollapsed into a single repaint, unchanged footer frames are not re-sent, and\nthe mouse filter allows more time for escape sequences split across packets.\nNothing changes about how the TUI looks, and local sessions are unaffected.\n\nDetection is environment-based, so it can miss a session where those variables\ndo not reach the process — most often tmux or mosh, whose panes may inherit a\nstale environment from the server. Force the profile when that happens:\n\n```bash\nOMNIUS_TUI_PACING=remote omnius   # pace for a network link\nOMNIUS_TUI_PACING=local omnius    # force local cadence\n```\n\nIf scrolling or typing still feels heavy, `OMNIUS_TUI_PROFILE=compatible`\nadditionally drops the animated truecolor chrome, and `OMNIUS_TUI_PERF=1` logs\nany content reflow that overruns its frame budget to stderr.\n\n## Shared Media Dependencies\n\nImage, video, audio, and music generation share a **single, system-wide dependency store** instead of duplicating heavy runtimes per project or per Telegram group.\n\nEarlier builds wrote a private Python venv plus Hugging Face / Torch / pip caches under every scoped working directory (for example `…/telegram-creative/<group-id>/.omnius/image-gen/.venv`). On a busy machine the same multi-gigabyte diffusers stack and model weights were re-downloaded once per group — tens of gigabytes of pure duplication.\n\nEverything now resolves to one source of truth under `~/.omnius` (override with `OMNIUS_HOME`):\n\n| Location | Holds |\n| --- | --- |\n| `~/.omnius/runtimes/<kind>/.venv-<backend>` | One shared Python venv per kind+backend (image/video/audio) |\n| `~/.omnius/models/huggingface/{hub,transformers,diffusers}` | Shared model weights — downloaded once, reused everywhere |\n| `~/.omnius/models/{torch,cache,pip-cache}` | Shared Torch hub, XDG, and pip caches |\n| `~/.omnius/models/_meta.json` | LRU usage index for automatic disk-pressure eviction |\n| `~/.omnius/media/{images,videos,audio,music}` | Global generated-media gallery (project-independent) |\n\nProject directories keep only lightweight session artifacts; no venvs or model weights are written per project.\n\n**Migrate and dedup existing machines.** A one-time cleanup consolidates any legacy per-group caches into the unified store — unique weights are moved (never re-downloaded), duplicates and stale venvs are reclaimed:\n\n```bash\n# TUI — current project only\n/models cleanup\n# TUI — every project + nested scoped group on this machine (dry-run first)\n/models cleanup --all --dry-run\n/models cleanup --all\n```\n\n```bash\n# REST — preview, then apply\ncurl -s -X POST localhost:11435/v1/media/migrate -H 'content-type: application/json' -d '{\"dryRun\":true}'\ncurl -s -X POST localhost:11435/v1/media/migrate -H 'content-type: application/json' -d '{}'\n# Inspect store + reclaimable legacy caches\ncurl -s localhost:11435/v1/media/store\n```\n\n**Generate over REST.** The daemon (default `127.0.0.1:11435`, a port in the IANA dynamic/private range that avoids common system-service collisions) exposes the local generators so any user on the machine can list models, generate, and browse the global gallery without the CLI:\n\n```bash\ncurl -s localhost:11435/v1/media/models\ncurl -s -X POST localhost:11435/v1/media/image -H 'content-type: application/json' -d '{\"prompt\":\"a compact robot painter\"}'\ncurl -s -X POST localhost:11435/v1/media/music -H 'content-type: application/json' -d '{\"prompt\":\"warm lo-fi piano loop\"}'\ncurl -s localhost:11435/v1/media/gallery\n```\n\nThe same surface drives the **Generate** tab in the web UI (`http://127.0.0.1:11435`) — pick a kind (image/video/audio/music), choose a model loaded from the system, generate, and review every previously generated file in one global gallery.\n\n## Recent Highlights\n\n- The dashboard now has nine route-level operational surfaces with shared modular observability grids, a searchable workspace picker, and project-scoped navigation state.\n- Chat history unifies persisted browser sessions with quality-filtered TUI transcripts, rejects command/noise sessions such as `/quit`, hydrates full history on selection, and exposes summaries, follow-up suggestions, reactive live deltas, and canonical deletion.\n- `/indicator` reconciles daemon ownership and health before launching the tray; the tray polls every 10 seconds and turns its version row into a retryable verified-update action only when an update exists.\n- Dashboard, tray, and TUI update actions now share an exact-version global transaction with live phase/output and package, executable, daemon, hash, restart, and tray verification.\n- TTS exposes GLaDOS, Overwatch, `luxtts:announcer-testchamber03`, and configurable Voicebox models; ASR independently exposes Whisper, managed `transcribe-cli`, Nemotron readiness, and pinned Microsoft VibeVoice ASR with Jetson/ARM64 CUDA-aware setup.\n- LuxTTS auto-setup on Jetson ARM64 requires CPU ONNX Runtime at import time, validates CUDA Torch separately against the host runtime, preserves existing caches during repair, and never substitutes generic PyPI Torch or automatic sudo for an AGX Orin deployment.\n- `/realtime` and REST `realtime: true` provide short, natural, SOUL.md-aware conversation for ASR/TTS clients.\n- Endpoint setup and sponsor setup aggregate models from all enabled endpoints, including external OpenAI-compatible routers.\n- `/sponsor` can expose text inference and media generation for image, video, sound, and music with per-modality limits.\n- Sponsor and COHERE status surfaces now use shared telemetry concepts: concurrency, request rate, daily tokens, peer usage, model usage, and remote system metrics.\n- The TUI reports token production rate as `t/s`, supports Shift+Enter multiline input, and renders dynamic shell output inside bounded Unicode cards.\n- Telegram state is scoped by user and group, supports durable reply preferences, and feeds raw platform/tool failures back into the agent loop.\n- Telegram media ingress is byte- and duration-bounded, cache-only before routing, deduplicated by Telegram file identity, and evidence-gated after admission. Speech uses scoped transcription; music/general audio uses typed semantic or explicitly acoustic-only analysis without false listening claims.\n- Telegram public creative work now includes typed PDF/DOCX creation and hash-guarded review, fixed-operation FFmpeg audio editing, and root-confined image crop/resize/mask/composite workflows. Host-signed content capabilities bind review evidence and durable Telegram delivery to the exact artifact bytes.\n- Ollama pool cleanup now accounts for process groups and orphan runner processes that can keep VRAM pinned.\n- REST documentation is available both as human docs and as Omnius-discoverable docs skills.\n\n## REST API\n\nStart the daemon (default `http://127.0.0.1:11435`; interactive docs at `/docs`, machine spec at `/openapi.json`):\n\n```bash\nomnius serve\n```\n\nFor shared deployments, gate access with scoped bearer keys (`read` < `run` < `admin`):\n\n```bash\nOMNIUS_REST_API_KEYS=\"read-key:read:grafana,run-key:run:ci:60:100000:3,admin-key:admin:ops\" omnius serve\n# then: Authorization: Bearer <key>\n```\n\nThe complete supported endpoint inventory follows. The canonical machine\ncontract is generated from [`packages/cli/src/api/openapi.ts`](packages/cli/src/api/openapi.ts),\nvalidated against [`docs/reference/rest-api.md`](docs/reference/rest-api.md),\nand projected into the generated block below. `pnpm docs:check` now fails when\nany of those three surfaces drift. Browser HTML pages, Swagger static assets,\nand implementation-only compatibility bridges are intentionally outside this\nstable REST contract.\n\n<!-- BEGIN GENERATED REST INVENTORY -->\n### Docs And Compatibility Aliases\n\n| Method | Path | Purpose |\n| --- | --- | --- |\n| `GET` | `/docs` | Swagger UI |\n| `GET` | `/api/docs` | Swagger UI alias |\n| `GET` | `/openapi.json` | OpenAPI JSON |\n| `GET` | `/openapi.yaml` | OpenAPI YAML |\n| `GET` | `/v3/api-docs` | OpenAPI alias |\n| `GET` | `/swagger.json` | Swagger-era alias |\n| `GET` | `/api-docs` | OpenAPI alias |\n| `GET` | `/swagger-ui` | Swagger UI alias |\n| `GET` | `/redoc` | ReDoc renderer |\n| `GET` | `/` | HATEOAS API root when the client does not request HTML |\n| `GET` | `/help` | Compact daemon integration help |\n| `GET` | `/v1/routes` | Flat grep-friendly daemon route summary |\n| `GET` | `/routes` | Route-summary compatibility alias |\n| `GET` | `/asyncapi.json` | AsyncAPI 2.6 voicechat WebSocket contract |\n| `GET` | `/asyncapi` | AsyncAPI compatibility alias |\n\n### Health And Observability\n\n| Method | Path | Purpose |\n| --- | --- | --- |\n| `GET` | `/health` | Liveness probe |\n| `GET` | `/health/ready` | Backend readiness |\n| `GET` | `/health/startup` | Startup probe |\n| `GET` | `/version` | Package version and platform |\n| `GET` | `/metrics` | Prometheus metrics |\n| `GET` | `/v1/events` | Server-sent event stream |\n| `GET` | `/v1/usage` | Token usage and rate limits |\n| `GET` | `/v1/audit` | Audit log query |\n| `GET` | `/v1/cost` | Cost tracker |\n| `GET` | `/v1/system` | CPU, RAM, GPU, and system snapshot |\n\n### Discovery\n\n| Method | Path | Purpose |\n| --- | --- | --- |\n| `GET` | `/v1/discovery/bootstrap` | Compact agent bootstrap and start-here map |\n| `GET` | `/v1/discovery` | Search layers, workflows, runtimes, modules, stores, and capabilities |\n| `GET` | `/v1/discovery/{id}` | Expand one stable capability entry |\n\n### Inference And Chat\n\n| Method | Path | Purpose |\n| --- | --- | --- |\n| `GET` | `/v1/models` | Aggregated model list |\n| `POST` | `/v1/chat/completions` | OpenAI-compatible chat completion |\n| `POST` | `/v1/chat` | Stateful Omnius chat |\n| `POST` | `/api/chat` | Ollama-compatible chat alias |\n| `POST` | `/v1/generate` | Ollama-compatible one-shot generation |\n| `POST` | `/api/generate` | Ollama-compatible generate alias |\n| `POST` | `/v1/embeddings` | OpenAI-compatible embeddings |\n| `POST` | `/api/embed` | Ollama-compatible embeddings alias |\n| `GET` | `/api/tags` | Ollama-compatible model tags |\n| `POST` | `/realtime` | Text-only voice-adapter reply from a transcript |\n| `POST` | `/v1/realtime` | Auth-scoped realtime adapter alias |\n| `GET` | `/v1/chat/sessions` | Workspace-scoped persisted browser chats and importable TUI sessions |\n| `GET` | `/v1/chat/sessions/{id}` | Hydrate full session history, transcript, and in-flight state |\n| `DELETE` | `/v1/chat/sessions/{id}` | Permanently delete a canonical chat or TUI history session |\n| `POST` | `/v1/chat/sessions/{id}/summarize` | Generate + cache an inference-based session title/summary |\n| `POST` | `/v1/chat/suggest-followup` | Suggest one short next-message follow-up (ghost-text input) |\n| `GET` | `/v1/chat/sessions/{id}/status` | Reactive recall: live run status + unseen deltas (`?since=<seq>`) |\n| `POST` | `/v1/chat/sessions/{id}/pause` | Pause the exact daemon-owned chat generation at a safe admission boundary |\n| `POST` | `/v1/chat/sessions/{id}/resume` | Resume the exact paused daemon-owned chat generation |\n| `POST` | `/v1/chat/sessions/{id}/stop` | Stop the daemon-owned chat process lease; idle/terminal calls are idempotent |\n| `POST` | `/v1/chat/check-in` | Steering check-in for active chat |\n| `POST` | `/v1/chat/attachments` | Upload an attachment for a stateful chat |\n| `POST` | `/v1/links/validate` | Validate an external HTTP(S) destination under the daemon egress policy |\n\n#### Session History Contract\n\n`GET /v1/chat/sessions` is a history index, not merely a list of processes that\nare currently active. It returns canonical persisted browser chats for the\nselected workspace and, by default, quality-filtered TUI visual sessions that\ncan be imported on demand. Pass `?root=/absolute/workspace` to scope the list and\n`?include_tui=0` to omit TUI history. Exit-only inputs such as `/quit` and\n`/exit`, manual-save noise, empty transcripts, and duplicate normalized TUI\nsessions are rejected by the session-quality projection rather than presented as\nchats.\n\nSelecting a row should call `GET /v1/chat/sessions/{id}`. That response hydrates\nthe complete public message history (system prompts are intentionally omitted),\nthe original TUI transcript when applicable, token counts, timestamps, source\nand project identity, and any in-flight run with a bounded partial-output tail.\nUse the `status` endpoint with `?since=<seq>` for cheap reactive polling while a\nrun is active. `DELETE /v1/chat/sessions/{id}` is an admin operation and removes\nthe canonical record; deleting only a browser-side row does not remove daemon\nhistory.\n\nPause and resume use the exact session and active external-run identity. Both\noperations require `run` scope. An idle session returns `200`. An accepted\nrequest returns `200` with the lifecycle acknowledgement, owner generation,\ncurrent phase, resumability, and pending acknowledgement count. A lifecycle\nrejection returns `409`. A live owner that does not acknowledge within the\ncontrol deadline returns `504`. Clients must not treat a local UI pause as a\ndaemon pause.\n\n`POST /realtime` and `/v1/realtime` are text-only conversation adapters. They\naccept transcript text through `message`, `text`, `recent_turn`, `asr_text`, or\n`callerText`, optionally accept adapter-local `soul_md`, and can return plain\ntext with `Accept: text/plain` or `format: \"text\"`. ASR and TTS remain separate\noperations.\n\n### Agentic Runs\n\n| Method | Path | Purpose |\n| --- | --- | --- |\n| `POST` | `/v1/run` | Submit agentic task |\n| `GET` | `/v1/runs` | List runs |\n| `GET` | `/v1/runs/{id}` | Get run details |\n| `GET` | `/v1/runs/{id}/output` | Read captured run output and status |\n| `DELETE` | `/v1/runs/{id}` | Abort run |\n| `POST` | `/v1/todos` | Create or update todos for current session |\n| `GET` | `/v1/todos` | List sessions with todos |\n| `GET` | `/v1/todos/{session_id}` | Get session todos |\n| `DELETE` | `/v1/todos/{session_id}` | Delete session todos |\n| `POST` | `/v1/evaluate` | Evaluate a run |\n| `POST` | `/v1/index` | Trigger repository indexing |\n\n### Configuration, Keys, Profiles, Projects\n\nAn authenticated `PUT /v1/config/model` records a new operator model choice,\nincluding when the selected name has not changed. A running TUI adopts that\nchoice for its next main task or inherited Telegram turn at the same backend\nendpoint and provider. Existing runners and explicit Telegram overrides retain\ntheir configuration. Startup CLI/environment choices take precedence over old\nsaved settings; a later operator selection acts like a new local `/model`\ncommand. This behavior requires the updated TUI process.\n\n| Method | Path | Purpose |\n| --- | --- | --- |\n| `GET` | `/v1/config` | Read daemon config |\n| `PATCH` | `/v1/config` | Update daemon config |\n| `GET` | `/v1/config/model` | Current model |\n| `PUT` | `/v1/config/model` | Switch model |\n| `POST` | `/v1/config/model/check` | Probe model readiness with non-empty text |\n| `GET` | `/v1/config/endpoint` | Current endpoint |\n| `PUT` | `/v1/config/endpoint` | Switch endpoint |\n| `POST` | `/v1/config/endpoint/test` | Probe endpoint |\n| `GET` | `/v1/config/endpoint/history` | Endpoint history |\n| `DELETE` | `/v1/config/endpoint/history` | Remove endpoint history item |\n| `POST` | `/v1/share/generate` | Generate remote-access share URL |\n| `GET` | `/v1/keys` | List runtime API keys |\n| `POST` | `/v1/keys` | Mint runtime API key |\n| `DELETE` | `/v1/keys/{prefix}` | Revoke runtime API keys by prefix |\n| `GET` | `/v1/profiles` | List tool profiles |\n| `POST` | `/v1/profiles` | Create tool profile |\n| `GET` | `/v1/profiles/{name}` | Get profile |\n| `DELETE` | `/v1/profiles/{name}` | Delete profile |\n| `GET` | `/v1/projects` | List known projects |\n| `DELETE` | `/v1/projects` | Unregister a project |\n| `GET` | `/v1/projects/current` | Current project |\n| `POST` | `/v1/projects/switch` | Switch project |\n| `POST` | `/v1/projects/register` | Register project |\n| `POST` | `/v1/projects/rename` | Rename project |\n| `GET` | `/v1/projects/preferences` | Read project preferences |\n| `PUT` | `/v1/projects/preferences` | Patch project preferences |\n| `DELETE` | `/v1/projects/preferences` | Reset project preferences |\n| `GET` | `/v1/projects/scan` | Scan configured roots for discoverable workspaces |\n| `GET` | `/v1/admin/access` | Read the daemon network access mode |\n| `POST` | `/v1/admin/access` | Change and persist access mode from loopback only |\n\n### Skills, Commands, Tools, MCP\n\n| Method | Path | Purpose |\n| --- | --- | --- |\n| `GET` | `/v1/skills` | List skills |\n| `GET` | `/v1/skills/{name}` | Load skill content |\n| `GET` | `/v1/commands` | List slash commands |\n| `POST` | `/v1/commands/{cmd}` | Execute slash command |\n| `GET` | `/v1/tools` | List tools (built-in + external) |\n| `POST` | `/v1/tools/register` | Register an application-specific external tool |\n| `GET` | `/v1/tools/{name}` | Tool metadata |\n| `DELETE` | `/v1/tools/{name}` | Unregister an external tool |\n| `POST` | `/v1/tools/{name}/call` | Call tool |\n| `POST` | `/v1/tools/{name}/eval` | Evaluate an external tool against test cases |\n| `GET` | `/v1/mcps` | List MCP servers |\n| `GET` | `/v1/mcps/{name}` | MCP server details |\n| `POST` | `/v1/mcps/{name}/call` | Call MCP tool |\n| `GET` | `/v1/hooks` | Hook registry |\n| `GET` | `/v1/agents` | Agent type registry |\n| `GET` | `/v1/codegraph/snapshot` | Code graph snapshot |\n| `GET` | `/v1/codegraph/events` | Code graph SSE |\n\n#### Registering Application-Specific Tools\n\nApplications can register their own tools so Omnius agents can discover and\ninvoke them alongside built-ins. `transport.type` selects the bridge:\n\n- `http` makes Omnius POST `{name, args, session_id}` to the application's\n  `callback_url` and relay the result.\n- `mcp` proxies to a named tool on an MCP server and can auto-connect from the\n  supplied connection descriptor.\n\nRegistrations persist per workspace at `.omnius/external-tools.json`, appear in\n`GET /v1/tools`, and use the same scope and off-device security gates as built-in\ntools. Registration needs `run` scope; a non-loopback caller needs `admin`.\n\n```bash\ncurl -s -X POST localhost:11435/v1/tools/register -H 'content-type: application/json' -d '{\n  \"name\": \"lookup_order\",\n  \"description\": \"Look up an order by id\",\n  \"parameters\": {\"type\":\"object\",\"properties\":{\"id\":{\"type\":\"string\"}},\"required\":[\"id\"]},\n  \"security\": {\"requires_scope\":\"run\",\"risk\":\"low\"},\n  \"transport\": {\"type\":\"http\",\"callback_url\":\"https://app.internal/tools/lookup_order\",\"auth_header\":\"Bearer …\"}\n}'\ncurl -s localhost:11435/v1/tools/lookup_order\ncurl -s -X POST localhost:11435/v1/tools/lookup_order/call -H 'content-type: application/json' -d '{\"args\":{\"id\":\"A-1001\"}}'\ncurl -s -X POST localhost:11435/v1/tools/lookup_order/eval -H 'content-type: application/json' -d '{\"cases\":[{\"name\":\"known\",\"args\":{\"id\":\"A-1001\"},\"expect\":{\"success\":true}}]}'\ncurl -s -X DELETE localhost:11435/v1/tools/lookup_order\n```\n\nThe MCP equivalent uses a transport such as\n`{\"type\":\"mcp\",\"server\":\"acme\",\"tool\":\"search\",\"connect\":{\"url\":\"https://app.internal/mcp\",\"transport\":\"streamable-http\"}}`.\n\n### AIWG\n\n| Method | Path | Purpose |\n| --- | --- | --- |\n| `GET` | `/v1/aiwg` | AIWG root and control map |\n| `GET` | `/v1/aiwg/frameworks` | List frameworks |\n| `GET` | `/v1/aiwg/frameworks/{name}` | Framework details |\n| `GET` | `/v1/aiwg/frameworks/{name}/content` | Tier-aware content |\n| `GET` | `/v1/aiwg/skills` | List AIWG skills |\n| `GET` | `/v1/aiwg/skills/{name}` | Load AIWG skill |\n| `GET` | `/v1/aiwg/agents` | List AIWG agents |\n| `GET` | `/v1/aiwg/agents/{name}` | Load AIWG agent |\n| `GET` | `/v1/aiwg/addons` | List AIWG addons |\n| `POST` | `/v1/aiwg/use` | Tier-sized activation bundle |\n| `POST` | `/v1/aiwg/expand` | Expand matching AIWG item |\n\n### Memory, Sessions, Context\n\n| Method | Path | Purpose |\n| --- | --- | --- |\n| `GET` | `/v1/memory` | Memory backend summary |\n| `POST` | `/v1/memory/search` | Search memory |\n| `POST` | `/v1/memory/write` | Write memory |\n| `GET` | `/v1/memory/episodes` | List episodes |\n| `GET` | `/v1/memory/failures` | List failure records |\n| `POST` | `/v1/memory/ingest` | Ingest content or files into memory |\n| `GET` | `/v1/memory/entities` | List extracted memory entities |\n| `POST` | `/v1/memory/jobs/run` | Run a named memory-maintenance job |\n| `POST` | `/v1/memory/feedback` | Record relevance or quality feedback for a memory item |\n| `POST` | `/v1/memory/speaker-identities/enroll` | Admin-only, explicit-consent speaker exemplar enrollment in one exact vector space |\n| `POST` | `/v1/memory/speaker-identities/match` | Admin-only provisional speaker candidate matching without durable assignment |\n| `GET` | `/v1/sessions` | List task sessions |\n| `GET` | `/v1/sessions/{id}` | Get session history |\n| `GET` | `/v1/context` | Current context snapshot |\n| `GET` | `/v1/context/window-dumps` | List persisted outbound model context-window dumps |\n| `GET` | `/v1/context/window-dumps/{id}` | Fetch a full outbound model context-window dump |\n| `POST` | `/v1/context/save` | Save context entry |\n| `GET` | `/v1/context/restore` | Build restore prompt |\n| `POST` | `/v1/context/compact` | Request compaction |\n\nContext-window dumps are written before backend inference for main agents, sub-agents, internal runners, and adversary audits. Query\n`GET /v1/context/window-dumps?agent_type=main` for summaries with signal/noise\nmetrics, or fetch a full payload by id. Dumps include focus-supervisor state when\na next-action contract is active. Set `OMNIUS_CONTEXT_WINDOW_DUMP_DIR` to move\nthe store, `OMNIUS_DISABLE_CONTEXT_WINDOW_DUMPS=1` to disable it, and\n`OMNIUS_FOCUS_SUPERVISOR=off|auto|strict` to tune focus enforcement.\n\n### Files, Web, Nexus, Ollama Pool\n\n| Method | Path | Purpose |\n| --- | --- | --- |\n| `GET` | `/v1/files` | List workspace directory |\n| `POST` | `/v1/files/read` | Read workspace file |\n| `GET` | `/v1/files/raw` | Stream raw workspace bytes with content type and range support |\n| `HEAD` | `/v1/files/raw` | Inspect raw-file response metadata |\n| `GET` | `/v1/web/search` | Inspect web-search availability, schema, and security policy |\n| `POST` | `/v1/web/search` | Search the web directly through the Omnius tool runtime |\n| `GET` | `/v1/web/fetch` | Inspect web-fetch availability, schema, and security policy |\n| `POST` | `/v1/web/fetch` | Fetch a URL directly through the Omnius tool runtime |\n| `GET` | `/v1/web/crawl` | Inspect web-crawl availability, schema, and security policy |\n| `POST` | `/v1/web/crawl` | Crawl a website directly through the Omnius tool runtime |\n| `GET` | `/v1/nexus/status` | Nexus peer state |\n| `GET` | `/v1/sponsors` | Sponsor directory cache |\n| `GET` | `/v1/ollama/pool/processes` | Ollama process inventory |\n| `POST` | `/v1/ollama/pool/cleanup` | Cleanup stale Ollama pool processes |\n\nThe `/v1/web/*` routes are stable aliases of the shared tool registry. `GET`\nreturns the corresponding tool metadata. `POST` uses the same authentication,\nprofile, origin, timeout, output-size, audit, and network-egress policy as a\ndirect tool call. Send search requests as\n`{\"args\":{\"query\":\"...\",\"num_results\":5,\"provider\":\"duckduckgo\"}}` and\nfetch requests as `{\"args\":{\"url\":\"https://example.com\"}}`. Crawl uses the\nschema returned by its `GET` route and requires the browser dependencies that\nthe metadata reports. POST responses use the standard `ToolResult` envelope.\n\n### Voice, Audio, Vision\n\n| Method | Path | Purpose |\n| --- | --- | --- |\n| `GET` | `/v1/voice/state` | Voice runtime status |\n| `POST` | `/v1/voice/start` | Select an optional model, enable voice, and wait for readiness |\n| `POST` | `/v1/voice/stop` | Pause daemon voice input while leaving TTS warm |\n| `GET` | `/v1/voice/models` | TTS models |\n| `POST` | `/v1/voice/models/switch` | Switch and enable an exact TTS model by default |\n| `POST` | `/v1/voice/models/{modelId}/pull` | Install runtime prerequisites and pull one managed TTS model |\n| `POST` | `/v1/voice/models/{modelId}/deploy` | Pull and deploy one managed CUDA TTS model |\n| `GET` | `/v1/voice/supertonic-settings` | Voice tuning settings |\n| `POST` | `/v1/voice/supertonic-settings` | Update voice tuning settings |\n| `GET` | `/v1/asr/engines` | Canonical ASR engines/models, capabilities, readiness, and selection |\n| `GET` | `/v1/asr/status` · `/v1/asr/selection` | Selected engine/model and runtime status |\n| `GET` | `/v1/asr/downloads` | List persistent ASR weight download and deployment transitions |\n| `POST` | `/v1/asr/downloads` | Start or resume an ASR weight download |\n| `GET` | `/v1/asr/downloads/{engineId}/{modelId}` | Poll one ASR download and deployment transition |\n| `POST` | `/v1/asr/downloads/{engineId}/{modelId}` | Start or resume this model download |\n| `POST` | `/v1/asr/downloads/{engineId}/{modelId}/retry` | Retry or resume a failed or interrupted ASR weight download |\n| `PATCH` | `/v1/asr/selection` | Persist and activate an exact engine/model |\n| `POST` | `/v1/asr/activate` | Activate and persist an exact engine/model |\n| `POST` | `/v1/asr/engines/{engineId}/setup` | Install a managed runtime and pinned weights |\n| `POST` | `/v1/asr/engines/{engineId}/models/{modelId}/pull` | Pull one exact ASR model and validate its managed runtime |\n| `POST` | `/v1/asr/engines/{engineId}/models/{modelId}/deploy` | Pull, select, and activate one exact ASR model |\n| `POST` | `/v1/asr/transcriptions` · `/v1/asr/test` | Transcribe/test using the real selected backend |\n| `GET` | `/v1/voice/asr-models` | Compatibility registry alias |\n| `POST` | `/v1/voice/asr-models/switch` | Compatibility activation alias |\n| `POST` | `/v1/voice/tts` | Synthesize speech |\n| `POST` | `/v1/audio/speech` | OpenAI-compatible TTS alias |\n| `GET` | `/v1/audio/classify/health` | Jetson CUDA/TensorRT YAMNet readiness |\n| `POST` | `/v1/audio/classify/setup` | Provision and warm the pinned JetPack TensorRT YAMNet runtime |\n| `POST` | `/v1/audio/classify` | Direct-tool compatible CUDA audio classification |\n| `GET` | `/v1/audio/embed/health` | Role-typed embedding readiness (`?kind=acoustic|speaker|semantic`) |\n| `POST` | `/v1/audio/embed/setup` | Provision/warm one role-typed embedding runtime (admin; `?kind=...`) |\n| `POST` | `/v1/audio/embed` | Managed role-typed audio embedding (`?kind=...`) |\n| `GET` | `/v1/audio/diarization/live/readiness` | Non-mutating managed Sortformer worker readiness |\n| `POST` | `/v1/audio/diarization/live/setup` | Verify and warm a local Sortformer runtime (admin) |\n| `POST` | `/v1/audio/diarization/live` | Managed live/session-local speaker-turn diarization |\n| `POST` | `/v1/audio/diarization/live/cancel` | Terminate live worker work and clear its queue |\n| `GET` | `/v1/audio/diarization/reconcile/readiness` | Non-mutating managed Community-1 worker readiness |\n| `POST` | `/v1/audio/diarization/reconcile/setup` | Verify and warm a local Community-1 runtime (admin) |\n| `POST` | `/v1/audio/diarization/reconcile` | Managed offline/dream reconciliation proposals |\n| `POST` | `/v1/audio/diarization/reconcile/cancel` | Terminate reconciliation work and clear its queue |\n| `POST` | `/v1/voice/transcribe` | Transcribe audio |\n| `POST` | `/v1/voice/asr` | Legacy transcription alias |\n| `POST` | `/v1/audio/transcriptions` | OpenAI-compatible transcription alias |\n| `POST` | `/v1/voice/transcribe/stream` | Isolated final transcription over SSE (no shared mic state or fake partials) |\n| `POST` | `/v1/voice/clone-refs` | Upload voice clone reference |\n| `GET` | `/v1/voice/clone-refs` | List clone references |\n| `POST` | `/v1/voice/clone-refs/upload` | Upload clone reference |\n| `POST` | `/v1/voice/clone-refs/from-url` | Fetch clone reference |\n| `POST` | `/v1/voice/clone-refs/{filename}/activate` | Activate clone reference |\n| `POST` | `/v1/voice/clone-refs/{filename}/rename` | Rename clone reference |\n| `DELETE` | `/v1/voice/clone-refs/{filename}` | Delete clone reference |\n| `POST` | `/v1/voice/speak` | Broadcast speech to voicechat clients |\n| `GET` | `/v1/voicechat/ws` | WebSocket upgrade for full-duplex voicechat |\n| `POST` | `/v1/vision/describe` | Vision describe placeholder |\n| `GET` | `/v1/vision/embed/readiness` | Non-mutating isolated OpenCLIP readiness |\n| `POST` | `/v1/vision/embed/setup` | Explicit isolated OpenCLIP setup (admin scope) |\n| `POST` | `/v1/vision/embed` | Create a vision embedding from media |\n| `GET` | `/v1/ocr/readiness` | Non-mutating advanced-OCR dependency and backend readiness |\n| `POST` | `/v1/ocr/setup` | Create and verify the isolated OCR venv (admin scope) |\n| `POST` | `/v1/ocr/advanced` | Agent-equivalent managed advanced OCR (alias of `/v1/tools/ocr_image_advanced/call`) |\n\n`POST /v1/voice/tts` and `/v1/audio/speech` automatically warm the daemon.\nAn explicit model must render exactly or the request fails; Omnius does not\nsilently synthesize with another voice. Responses include `X-Voice-Model`,\n`X-Voice-Backend`, and `X-Sample-Rate`. Available models include GLaDOS,\nOverwatch, `luxtts:announcer-testchamber03`, and the selected Voicebox suite.\nSet `OMNIUS_VOICEBOX_MODELS=all` for every carried-in Voicebox model, leave it\nat `stable` for the default set, or provide a comma-separated subset.\n\nASR selection is independent from TTS selection. The registry currently exposes\nOpenAI Whisper, managed `transcribe-cli`, NVIDIA Nemotron (reported unavailable\nuntil its legacy bootstrap is migrated), and Microsoft VibeVoice ASR. VibeVoice\nuses the exact pinned `microsoft/VibeVoice-ASR` checkpoint, reports setup and\nactivation separately, supports completed files up to 60 minutes with speakers,\ntimestamps, and `?context=` hotwords, and is deliberately not advertised as an\nincremental PCM backend. Its managed setup inherits the host CUDA-enabled Torch\nbuild (needed on Jetson/ARM64), never installs generic PyPI Torch, and activation\nrequires one explicit capable GPU. Discrete Linux uses `nvidia-smi` process/GPU\nevidence; Jetson/L4T uses NVIDIA's documented `tegrastats` plus CUDA Torch device\nproperties because `nvidia-smi` is unavailable there. Model weights live under\nthe unified Omnius ASR cache and are not shipped in the npm package.\n\n### Generative Media\n\nAll generation is backed by the unified `~/.omnius` model store and shared venvs (single source of truth — no per-project duplication). Generated files are consolidated into the global gallery at `~/.omnius/media/{images,videos,audio,music}`.\n\n| Method | Path | Purpose |\n| --- | --- | --- |\n| `GET` | `/v1/media/models` | List available image/video/audio/music models |\n| `GET` | `/v1/media/store` | Unified store disk usage + reclaimable legacy caches |\n| `POST` | `/v1/media/migrate` | Dedup + migrate legacy per-group caches into the unified store |\n| `POST` | `/v1/media/relocate` | Relocate the whole media store (weights/venvs/gallery) to a chosen folder |\n| `GET` | `/v1/media/relocate/status` | Status + progress of the media-store relocation job |\n| `POST` | `/v1/media/av/analyze` | Analyze a media file into a grounded entity/event answer (AV comprehension) |\n| `POST` | `/v1/media/image` | Generate an image |\n| `POST` | `/v1/media/video` | Generate a video |\n| `POST` | `/v1/media/audio` | Generate a sound effect |\n| `POST` | `/v1/media/music` | Generate music |\n| `GET` | `/v1/media/gallery` | List previously generated media (global, newest first) |\n| `GET` | `/v1/media/file` | Stream one generated media file |\n\nManaged TTS `pull` installs the model's runtime prerequisites and weights. It\ndoes not start inference. Managed TTS `deploy` also verifies the selected CUDA\ndevice and starts the persistent runtime. Both operations return `200` when\nready, `404` when the model has no matching managed adapter, and `500` when\ninstallation, download, CUDA preflight, or startup fails.\n\nASR download requests use `{engineId, modelId, device?}`. A collection POST\nreturns `200` when weights are ready or `202` with `statusUrl`, `retryUrl`, and\n`pollAfterMs` while work is pending. Duplicate work coalesces. Poll the model\nURL until its download is ready and its deployment is active. A missing job\nreturns `404`. Model-specific POST and retry requests return `200` when ready or\n`202` when accepted. The model `pull` and `deploy` routes accept optional\n`{device}`. Pull validates the managed runtime and CUDA placement. Deploy also\npersists the selection after readiness and returns a pollable `202` transition\nwhen activation is pending.\n\n### Engines And Scheduled Jobs\n\n| Method | Path | Purpose |\n| --- | --- | --- |\n| `GET` | `/v1/engines` | Long-running engine status |\n| `GET` | `/v1/services` | List all active daemon-owned REST services and their routes |\n| `GET` | `/v1/services/{id}` | Get one daemon-owned REST service contract |\n| `GET` | `/v1/scheduled` | List scheduled jobs |\n| `DELETE` | `/v1/scheduled/all` | Delete all tasks, timers, cron entries, and persisted sources |\n| `GET` | `/v1/scheduled/status` | Scheduler status |\n| `POST` | `/v1/scheduled/{id}` | Enable or disable one scheduled task or user timer |\n| `DELETE` | `/v1/scheduled/{id}` | Delete one scheduled task or user timer |\n| `POST` | `/v1/scheduled/kill` | Kill scheduled job |\n| `POST` | `/v1/scheduled/fixup` | Reconcile scheduled state |\n| `GET` | `/v1/scheduled/reconcile` | Preview scheduled reconciliation |\n| `POST` | `/v1/scheduled/reconcile` | Preview or apply scheduled reconciliation |\n| `GET` | `/v1/services/systemd` | Systemd service status |\n| `POST` | `/v1/services/systemd/{unit}` | Act on one user-level systemd unit |\n| `GET` | `/v1/update` | Self-update status |\n| `POST` | `/v1/update` | Start an exact-version verified global update transaction |\n\n`GET /v1/services` is the agent-readable service inventory generated from the\nOpenAPI document. Each entry states lifecycle ownership, interactive-session\ndependency, registered routes, and a readiness or status route when one exists.\n`GET /v1/services/{id}` returns one service contract or `404` for an unknown\nservice ID. These discovery routes do not mutate services. `/listen` and\n`/hangup` control voice sessions only and do not own the REST daemon.\n\n#### Verified Global Update Transaction\n\n`POST /v1/update` is not a CLI-local package edit. It starts one durable\ntransaction that installs the requested exact npm version globally, verifies\nthe installed package and resolved `omnius` executable, restarts and verifies\nthe daemon, verifies package/hash/runtime agreement, and relaunches the tray if\nit was running. The response is `202` with operation state; poll\n`GET /v1/update` for live phase, subprocess output, verification evidence, and\nthe final success or failure. Concurrent transactions and requests with no\navailable target return `409`.\n\nThe web dashboard and native tray both use this same endpoint. Update discovery\nis shared and semver-aware, so an older cached registry result cannot downgrade\nor falsely present an update. A completed transaction means the global package,\nexecutable, daemon, and tray runtime were all reconciled—not merely that `npm`\nexited successfully.\n\n### AIMS Governance\n\n| Method | Path | Purpose |\n| --- | --- | --- |\n| `GET` | `/v1/aims` | AIMS root and endpoint index |\n| `GET` | `/v1/aims/policies` | Policy register |\n| `PUT` | `/v1/aims/policies` | Replace policy register |\n| `GET` | `/v1/aims/roles` | Roles and responsibilities |\n| `GET` | `/v1/aims/resources` | Resource inventory |\n| `GET` | `/v1/aims/impact-assessments` | Impact assessments |\n| `POST` | `/v1/aims/impact-assessments` | File impact assessment |\n| `GET` | `/v1/aims/lifecycle` | Lifecycle state |\n| `GET` | `/v1/aims/data-quality` | Data quality controls |\n| `GET` | `/v1/aims/transparency` | Model cards and transparency |\n| `GET` | `/v1/aims/usage` | AIMS usage view |\n| `GET` | `/v1/aims/suppliers` | Supplier inventory |\n| `GET` | `/v1/aims/incidents` | Incident records |\n| `POST` | `/v1/aims/incidents` | File incident |\n| `GET` | `/v1/aims/oversight` | Human oversight gates |\n| `GET` | `/v1/aims/decisions` | Consequential decision log |\n| `GET` | `/v1/aims/config-history` | Config change history |\n\n### Browser And Compatibility Surfaces\n\nThe dashboard HTML routes (`/`, `/chat`, `/agent`, `/voice`, `/generate`,\n`/projects`, `/dashboard`, `/jobs`, `/activity`, `/discover`, `/settings`, and\n`/config`) are documented in the [dashboard guide](../guides/dashboard.md). They\nare pages, not JSON API operations; `/` returns the HATEOAS JSON root when the\nclient does not request HTML.\n\nSwagger/ReDoc trailing-slash variants, `/api/docs/*` static assets, and\n`/favicon.ico` exist for browsers. They are delivery details rather than stable\nintegration endpoints. The daemon also retains browser/legacy bridges at\n`/v1/model`, `/v1/endpoint`, `/v1/theme`, `/v1/tor/*`, `/v1/remote-proxy`, and\n`/v1/command`. New clients should prefer `/v1/config/model`,\n`/v1/config/endpoint`, `/v1/config`, and `/v1/commands/{cmd}`. Compatibility\nhandlers may accept additional HTTP verbs for old dashboard bundles; only the\nmethods in the supported inventory above are contractual.\n<!-- END GENERATED REST INVENTORY -->\n## Agent-Explorable Documentation\n\nOmnius discovers project-local docs skills from `.aiwg/addons/*/skills`. The docs bundles in this repo expose high-signal entrypoints for agents:\n\n```text\n/skills omnius docs\nskill_execute name=\"omnius-docs\"\nskill_execute name=\"omnius-rest-docs\"\nskill_extract name=\"omnius-realtime-docs\" query=\"How does realtime REST mode work?\"\n```\n\nThe intended pattern is index first, targeted document second, not loading the whole manual into the active context.\n\n## Development\n\n```bash\npnpm install\npnpm -r build\npnpm docs:check\n```\n\nFocused checks used for the docs skill surface:\n\n```bash\npnpm --filter @omnius/execution exec vitest run tests/skill-discovery.test.ts\npnpm --filter omnius exec vitest run tests/realtime-mode.test.ts tests/command-registry.test.ts\n```\n\n## Publishing\n\nPublish only from `publish/`.\n\n```bash\ncd omnius\npnpm -r clean || true\nfind . -name 'tsconfig.tsbuildinfo' -not -path '*/node_modules/*' -delete\npnpm -r build\nnode scripts/build-publish.mjs\ncd publish\nmkdir -p .npm-cache\nNPM_CONFIG_CACHE=$(pwd)/.npm-cache npm pack --prefer-online --cache-min=0 --registry https://registry.npmjs.org/\nNPM_CONFIG_CACHE=$(pwd)/.npm-cache npm publish --access public --prefer-online --cache-min=0 --registry https://registry.npmjs.org/\n```\n\nBefore publishing, verify `README.md`, `package.json`, `dist/index.js`, and `dist/launcher.cjs` are in the tarball, and that `package.json` includes `readmeFilename: \"README.md\"` plus a string `readme`.\n\n## License\n\nOmnius is released under [CC-BY-NC-4.0](LICENSE) 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"
 }