omnius 1.0.196 → 1.0.198

package/docs/reference/configuration.md

@@ -7,8 +7,12 @@ Configuration is layered from environment, global user settings, project setting
 | Variable | Purpose |
 | --- | --- |
 | `OMNIUS_HOST` | Bind host and port, for example `0.0.0.0:11435` |
-| `OMNIUS_API_KEY` | Single admin bearer token |
-| `OMNIUS_API_KEYS` | Multi-key auth: `key:scope:owner:rpm:tpd:max_jobs` |
+| `OMNIUS_REST_API_KEY` | Single admin bearer token for the Omnius REST API |
+| `OMNIUS_REST_API_KEYS` | Multi-key REST auth: `key:scope:owner:rpm:tpd:max_jobs` |
+| `OMNIUS_PROVIDER_API_KEY` | Upstream model-provider bearer token |
+| `OMNIUS_MODEL_API_KEY` | Alternate upstream model-provider bearer token |
+| `OMNIUS_API_KEY` | Legacy fallback for provider auth and legacy REST auth |
+| `OMNIUS_API_KEYS` | Legacy multi-key REST auth |
 | `OMNIUS_ACCESS` | Network access policy for the daemon |
 | `OMNIUS_DAEMON` | Start in daemon mode when set to `1` |
 | `OMNIUS_FORCE_NO_THINK` | Force `think: false` for Qwen-style backends |

package/docs/reference/rest-api.md

@@ -76,6 +76,7 @@ pnpm docs:check
 | `PATCH` | `/v1/config` | Update daemon config |
 | `GET` | `/v1/config/model` | Current model |
 | `PUT` | `/v1/config/model` | Switch model |
+| `POST` | `/v1/config/model/check` | Probe model readiness with non-empty text |
 | `GET` | `/v1/config/endpoint` | Current endpoint |
 | `PUT` | `/v1/config/endpoint` | Switch endpoint |
 | `POST` | `/v1/config/endpoint/test` | Probe endpoint |

package/docs/rest/INDEX.md

@@ -64,8 +64,8 @@ OMNIUS_HOST=0.0.0.0:11435 omnius serve
 Local anonymous requests default to read behavior unless the runtime is configured for insecure loopback admin. Remote/shared deployments should use bearer keys.
 
 ```bash
-OMNIUS_API_KEY="admin-secret" omnius serve
-OMNIUS_API_KEYS="read-key:read:grafana,run-key:run:ci:60:100000:3,admin-key:admin:ops" omnius serve
+OMNIUS_REST_API_KEY="admin-secret" omnius serve
+OMNIUS_REST_API_KEYS="read-key:read:grafana,run-key:run:ci:60:100000:3,admin-key:admin:ops" omnius serve
 ```
 
 Scopes:

package/docs/rest/QUICKREF.md

@@ -40,6 +40,7 @@ curl -s http://127.0.0.1:11435/version
 
 ```bash
 curl -s http://127.0.0.1:11435/v1/models
+curl -s -X POST http://127.0.0.1:11435/v1/config/model/check
 ```
 
 ## Chat
@@ -104,6 +105,15 @@ curl -s -X POST http://127.0.0.1:11435/v1/tools/memory_search/call \
   -d '{"args":{"query":"rest api docs"}}'
 ```
 
+Deterministic bookkeeping without an agent run:
+
+```bash
+curl -s -X POST http://127.0.0.1:11435/v1/tools/todo_write/call \
+  -H 'content-type: application/json' \
+  -H 'x-omnius-session-id: regi-turn-123' \
+  -d '{"profile":"cygnus-regi-tracking","args":{"todos":[{"content":"Create NC report","status":"in_progress"}]}}'
+```
+
 ## Voice TTS
 
 ```bash

package/docs/rest/auth-and-scopes.md

@@ -7,13 +7,13 @@ Omnius can run without auth for local development, but shared deployments should
 Single admin key:
 
 ```bash
-OMNIUS_API_KEY="admin-secret" omnius serve
+OMNIUS_REST_API_KEY="admin-secret" omnius serve
 ```
 
 Multiple scoped keys:
 
 ```bash
-OMNIUS_API_KEYS="read-key:read:grafana,run-key:run:ci:60:100000:3,admin-key:admin:ops" omnius serve
+OMNIUS_REST_API_KEYS="read-key:read:grafana,run-key:run:ci:60:100000:3,admin-key:admin:ops" omnius serve
 ```
 
 Format:
@@ -22,6 +22,10 @@ Format:
 key:scope:owner:rpm:tpd:max_jobs
 ```
 
+Compatibility: `OMNIUS_API_KEY` and `OMNIUS_API_KEYS` are still accepted as legacy REST auth variables, but new deployments should use the `OMNIUS_REST_*` namespace.
+
+Provider keys are separate from REST keys. Prefer `OMNIUS_PROVIDER_API_KEY`, `OMNIUS_MODEL_API_KEY`, or provider-native variables such as `VLLM_API_KEY` for upstream model auth. `OMNIUS_API_KEY` remains a legacy fallback for provider auth and legacy REST auth, so avoid it in new remote deployments. Scoped REST keys (`OMNIUS_REST_*` and `OMNIUS_API_KEYS`) are stripped before spawning agent subprocesses and are not forwarded as model-provider credentials.
+
 Fields:
 
 - `key`: bearer token.
@@ -84,6 +88,8 @@ Mint body:
 
 Tool calls are additionally gated by each tool's security metadata. Scope alone is not the only control.
 
+Runtime keys may bind a tool profile. A run-scope key with profile `cygnus-regi-tracking` can update todos and notes but cannot expose or execute filesystem/search/shell tools.
+
 ## Request Header
 
 ```text
@@ -95,7 +101,7 @@ Authorization: Bearer <key>
 For local development, bind to loopback. For remote access, set explicit auth and access policy:
 
 ```bash
-OMNIUS_HOST=0.0.0.0:11435 OMNIUS_API_KEYS="run-key:run:remote" omnius serve
+OMNIUS_HOST=0.0.0.0:11435 OMNIUS_REST_API_KEYS="run-key:run:remote" omnius serve
 ```
 
 Do not expose an unauthenticated daemon on a public interface.

package/docs/rest/endpoints/config.md

@@ -8,6 +8,7 @@
 | `PATCH` | `/v1/config` | Update settings |
 | `GET` | `/v1/config/model` | Show active model |
 | `PUT` | `/v1/config/model` | Switch model |
+| `POST` | `/v1/config/model/check` | Probe model readiness with non-empty text |
 | `GET` | `/v1/config/endpoint` | Show active backend endpoint |
 | `PUT` | `/v1/config/endpoint` | Switch endpoint with TUI-compatible normalization |
 | `POST` | `/v1/config/endpoint/test` | Probe endpoint from daemon process |
@@ -38,7 +39,9 @@ Endpoint history mirrors the `/endpoint` TUI flow. It records recently used endp
 
 ## Model Switching
 
-`PUT /v1/config/model` updates the active model for subsequent requests. Clients can still pass per-request `model` fields to chat endpoints.
+`PUT /v1/config/model` updates the active model for subsequent requests and the daemon process, so `GET /v1/config/model` is read-after-write consistent. Clients can still pass per-request `model` fields to chat endpoints.
+
+`POST /v1/config/model/check` performs a real chat probe and returns `ok`, `backend_normalized_model_id`, `provider_model_id`, endpoint metadata, and whether non-empty visible text was produced. Use it to distinguish model catalog visibility from compute readiness.
 
 ## Runtime Keys
 

package/docs/rest/endpoints/run.md

@@ -35,6 +35,22 @@ Common body fields:
 | `profile` | Tool profile |
 | `timeout_s` | Wall-clock timeout |
 
+Profiles are enforced twice:
+
+- before model exposure, so disallowed tools are absent from tool schemas and prompts
+- at execution time, so emitted disallowed tool calls are denied
+
+The active profile name, source, search order, and allowed tool list are included in the accepted run metadata and persisted run record. `GET /v1/runs/{id}` is the canonical status source and includes output tail metadata when available. `/v1/runs/{id}/output` remains a raw log/delta endpoint.
+
+For bookkeeping integrations, prefer direct calls instead of `/v1/run`:
+
+```bash
+curl -s -X POST "$OMNIUS/v1/tools/todo_write/call" \
+  -H 'content-type: application/json' \
+  -H 'x-omnius-session-id: regi-turn-123' \
+  -d '{"profile":"cygnus-regi-tracking","args":{"todos":[{"content":"Create NC report","status":"in_progress"}]}}'
+```
+
 ## Abort
 
 `DELETE /v1/runs/{id}` aborts the job. The daemon signals the process group, escalates if needed, updates the job record, and decrements per-key active job counters.

package/docs/rest/endpoints/tools.md

@@ -17,12 +17,15 @@
 
 ## Tool Metadata
 
+`GET /v1/tools` and `POST /v1/tools/{name}/call` use the same direct-call registry, built from the `@omnius/execution` tool manifest plus virtual lifecycle tools such as `task_complete`. If a tool appears in `/v1/tools` with `direct_callable: true`, the same name is callable at `/v1/tools/{name}/call`.
+
 `GET /v1/tools` returns each tool's:
 
 - name
 - class
 - description
 - JSON-schema parameters
+- `direct_callable`
 - security categories
 - risk
 - required scope
@@ -36,16 +39,21 @@ Filters include:
 ?scope=read|run|admin
 ?risk=low|medium|high|critical
 ?limit=200&offset=0
+?profile=cygnus-regi-tracking
 ```
 
+Profiles can also be selected with `X-Tool-Profile`. Named profiles resolve in this order: built-in preset, `{working_dir}/.omnius/profiles/{name}.json`, then `~/.omnius/profiles/{name}.json`. Missing profiles fail closed.
+
 ## Tool Calls
 
 `POST /v1/tools/{name}/call` body:
 
 ```json
 {
+  "session_id": "regi-turn-123",
   "args": {},
-  "working_dir": "/path/to/repo"
+  "working_dir": "/path/to/repo",
+  "profile": "cygnus-regi-tracking"
 }
 ```
 
@@ -53,6 +61,17 @@ Filters include:
 
 Tool calls are gated by auth scope, tool policy, off-device policy, and profile restrictions.
 
+Bookkeeping tools are direct-callable and do not require a model run:
+
+```bash
+curl -s -X POST "$OMNIUS/v1/tools/todo_write/call" \
+  -H 'content-type: application/json' \
+  -H 'x-omnius-session-id: regi-turn-123' \
+  -d '{"profile":"cygnus-regi-tracking","args":{"todos":[{"content":"Create NC report","status":"in_progress"}]}}'
+```
+
+Use `todo_write`, `todo_read`, `working_notes`, and `task_complete` this way for deterministic tracking. `task_complete` on this endpoint is only a bookkeeping boundary; `/v1/runs/{id}` remains the canonical run terminal state.
+
 ## MCP
 
 MCP endpoints list connected Model Context Protocol servers and invoke tools through the daemon with the same auth and audit envelope.

package/docs/rest/examples/openai-sdk.md

@@ -9,7 +9,7 @@ import OpenAI from "openai";
 
 const client = new OpenAI({
   baseURL: "http://127.0.0.1:11435/v1",
-  apiKey: process.env.OMNIUS_API_KEY ?? "local-dev",
+  apiKey: process.env.OMNIUS_REST_API_KEY ?? "local-dev",
 });
 
 const response = await client.chat.completions.create({

package/npm-shrinkwrap.json

@@ -1,12 +1,12 @@
 {
   "name": "omnius",
-  "version": "1.0.196",
+  "version": "1.0.198",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "omnius",
-      "version": "1.0.196",
+      "version": "1.0.198",
       "bundleDependencies": [
         "image-to-ascii"
       ],

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "omnius",
-  "version": "1.0.196",
+  "version": "1.0.198",
   "description": "AI coding agent powered by open-source models (Ollama/vLLM) — interactive TUI with agentic tool-calling loop",
   "type": "module",
   "main": "./dist/index.js",
@@ -142,5 +142,5 @@
     "transcribe-cli": "^2.0.1",
     "viem": "2.47.4"
   },
-  "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\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- A local model or configured 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\n## What Omnius Does\n\n- Runs autonomous coding tasks, edits files, executes tools, tests changes, and iterates on failures.\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\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/realtime             toggle short ASR/TTS-oriented conversation mode\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| Terminal workflows | [TUI workflows](docs/guides/tui-workflows.md), [Slash commands](docs/reference/slash-commands.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| Realtime voice chat | [Realtime guide](docs/guides/realtime.md) |\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| Architecture | [Architecture overview](docs/architecture/overview.md) |\n| Agent-explorable docs | [Agent memory docs index](docs/agent-memory/INDEX.md) |\n\n## Recent Highlights\n\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- 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:\n\n```bash\nomnius serve\n```\n\nUseful entrypoints:\n\n```text\nGET  /docs\nGET  /openapi.json\nPOST /v1/chat\nPOST /v1/chat/completions\nPOST /v1/run\nGET  /v1/events\nGET  /v1/skills\nPOST /v1/tools/{name}/call\nWS   /v1/voicechat/ws\n```\n\nFor shared deployments, use bearer keys:\n\n```bash\nOMNIUS_API_KEYS=\"read-key:read:grafana,run-key:run:ci:60:100000:3,admin-key:admin:ops\" omnius serve\n```\n\nSee [docs/reference/rest-api.md](docs/reference/rest-api.md) for the maintained endpoint inventory. The canonical machine contract is generated from [packages/cli/src/api/openapi.ts](packages/cli/src/api/openapi.ts).\n\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 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\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- A local model or configured 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\n## What Omnius Does\n\n- Runs autonomous coding tasks, edits files, executes tools, tests changes, and iterates on failures.\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\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/realtime             toggle short ASR/TTS-oriented conversation mode\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| Terminal workflows | [TUI workflows](docs/guides/tui-workflows.md), [Slash commands](docs/reference/slash-commands.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| Realtime voice chat | [Realtime guide](docs/guides/realtime.md) |\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| Architecture | [Architecture overview](docs/architecture/overview.md) |\n| Agent-explorable docs | [Agent memory docs index](docs/agent-memory/INDEX.md) |\n\n## Recent Highlights\n\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- 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:\n\n```bash\nomnius serve\n```\n\nUseful entrypoints:\n\n```text\nGET  /docs\nGET  /openapi.json\nPOST /v1/chat\nPOST /v1/chat/completions\nPOST /v1/run\nGET  /v1/events\nGET  /v1/skills\nPOST /v1/tools/{name}/call\nWS   /v1/voicechat/ws\n```\n\nFor shared deployments, use bearer keys:\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```\n\nSee [docs/reference/rest-api.md](docs/reference/rest-api.md) for the maintained endpoint inventory. The canonical machine contract is generated from [packages/cli/src/api/openapi.ts](packages/cli/src/api/openapi.ts).\n\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"
 }