omnius 1.0.628 → 1.0.629

package/docs/DISCOVERY.json

@@ -10657,7 +10657,7 @@
       "id": "api.v1-ocr-advanced",
       "kind": "api",
       "title": "/v1/ocr/advanced",
-      "summary": "Advanced OCR — multi-PSM tesseract pipeline with optional vision refinement — body {imagePath, visionModel?, prompt?}",
+      "summary": "Alias of POST /v1/tools/ocr_image_advanced/call — managed multi-variant Tesseract OCR",
       "aliases": [
         "/v1/ocr/advanced"
       ],
@@ -10665,6 +10665,7 @@
         "rest",
         "openapi",
         "POST",
+        "Tools",
         "Vision",
         "v1",
         "ocr",
@@ -10703,23 +10704,94 @@
         "POST"
       ],
       "tags": [
+        "Tools",
         "Vision"
       ],
       "operations": {
         "post": {
-          "summary": "Advanced OCR — multi-PSM tesseract pipeline with optional vision refinement — body {imagePath, visionModel?, prompt?}",
+          "summary": "Alias of POST /v1/tools/ocr_image_advanced/call — managed multi-variant Tesseract OCR",
           "tags": [
+            "Tools",
             "Vision"
           ],
+          "description": "Uses the identical advanced OCR tool exposed to agents: auto-provisions Tesseract, requested traineddata, and the managed Python pipeline. Body is the canonical direct-tool envelope; result.data contains the parsed OCR pipeline result.",
+          "requestBody": {
+            "required": true,
+            "content": {
+              "application/json": {
+                "schema": {
+                  "type": "object",
+                  "required": [
+                    "args"
+                  ],
+                  "properties": {
+                    "args": {
+                      "type": "object",
+                      "required": [
+                        "image"
+                      ],
+                      "properties": {
+                        "image": {
+                          "type": "string"
+                        },
+                        "language": {
+                          "type": "string",
+                          "example": "eng+fra"
+                        },
+                        "regions": {
+                          "type": "boolean"
+                        },
+                        "region": {
+                          "type": "string",
+                          "example": "0,0,1200,180"
+                        },
+                        "psm": {
+                          "type": "integer",
+                          "enum": [
+                            4,
+                            6,
+                            11
+                          ]
+                        },
+                        "output_dir": {
+                          "type": "string"
+                        },
+                        "batch": {
+                          "type": "boolean"
+                        },
+                        "debug": {
+                          "type": "boolean"
+                        }
+                      }
+                    },
+                    "timeout_ms": {
+                      "type": "integer",
+                      "description": "Defaults to 300000ms; maximum 600000ms."
+                    },
+                    "max_output_chars": {
+                      "type": "integer"
+                    },
+                    "profile": {
+                      "type": "string"
+                    },
+                    "working_dir": {
+                      "type": "string",
+                      "description": "Admin scope only."
+                    }
+                  }
+                }
+              }
+            }
+          },
           "responses": {
             "200": {
-              "description": "OCR text + context block"
+              "description": "Direct-tool result envelope; consume result.data for structured OCR output."
             },
             "400": {
-              "description": "Missing imagePath"
+              "description": "Invalid direct-tool request or OCR arguments"
             },
-            "501": {
-              "description": "OCR tool unavailable"
+            "403": {
+              "description": "Tool scope/profile/working-directory denied"
             }
           }
         }
@@ -28854,7 +28926,7 @@
       "id": "guide.rest-endpoints-voice-vision",
       "kind": "guide",
       "title": "Voice, Audio, Vision, And Voicechat",
-      "summary": "POST /v1/voice/tts returns audio bytes. format can be wav or pcm. X-Sample-Rate reports the sample rate.",
+      "summary": "POST /v1/ocr/advanced is a compatibility alias for the exact agent-facing ocrimageadvanced tool. Use the same direct-tool envelope; the response retains display text in result.output and returns the parsed pipeline payload in result.data.",
       "keywords": [
         "rest",
         "endpoints",

package/docs/DISCOVERY.md

@@ -170,7 +170,7 @@ Daemon equivalents are `GET /v1/discovery/bootstrap`, `GET /v1/discovery?q=<inte
 | `api.v1-memory-write` | /v1/memory/write | Write a memory entry (PT-04) |
 | `api.v1-models` | /v1/models | List aggregated models |
 | `api.v1-nexus-status` | /v1/nexus/status | Nexus peer state |
-| `api.v1-ocr-advanced` | /v1/ocr/advanced | Advanced OCR — multi-PSM tesseract pipeline with optional vision refinement — body {imagePath, visionModel?, prompt?} |
+| `api.v1-ocr-advanced` | /v1/ocr/advanced | Alias of POST /v1/tools/ocr_image_advanced/call — managed multi-variant Tesseract OCR |
 | `api.v1-ollama-pool-cleanup` | /v1/ollama/pool/cleanup | Clean up stale Ollama pool processes |
 | `api.v1-ollama-pool-processes` | /v1/ollama/pool/processes | Scan local Ollama pool processes |
 | `api.v1-profiles` | /v1/profiles | List tool profiles; Create tool profile |
@@ -461,7 +461,7 @@ Daemon equivalents are `GET /v1/discovery/bootstrap`, `GET /v1/discovery?q=<inte
 | `guide.rest-endpoints-run` | Runs, Jobs, Todos, And Scheduled Work | Submits a long-running task to the daemon and returns an accepted job record. Runs are tracked under .omnius/jobs/. |
 | `guide.rest-endpoints-skills` | Skills And Commands | The REST docs bundle is available as: |
 | `guide.rest-endpoints-tools` | Tools, MCP, Hooks, Agents, And Code Graph | 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 taskcomplete. If a tool appears in /v1/tools with directcallable: true, the same name is callable at /v1/tools/{name}/call. |
-| `guide.rest-endpoints-voice-vision` | Voice, Audio, Vision, And Voicechat | POST /v1/voice/tts returns audio bytes. format can be wav or pcm. X-Sample-Rate reports the sample rate. |
+| `guide.rest-endpoints-voice-vision` | Voice, Audio, Vision, And Voicechat | POST /v1/ocr/advanced is a compatibility alias for the exact agent-facing ocrimageadvanced tool. Use the same direct-tool envelope; the response retains display text in result.output and returns the parsed pipeline payload in result.data. |
 | `guide.rest-errors-pagination-etags` | Errors, Pagination, ETags, And Request IDs | The OpenAPI contract documents RFC 7807 Problem Details for common errors: |
 | `guide.rest-examples-curl` | Curl Examples | curl -s "$BASE/openapi.json" \| jq '.info.title, .info.version' |
 | `guide.rest-examples-openai-sdk` | OpenAI SDK Examples | Omnius exposes an OpenAI-compatible chat-completions endpoint at /v1/chat/completions. |

package/docs/reference/rest-api.md

@@ -309,7 +309,7 @@ the store, `OMNIUS_DISABLE_CONTEXT_WINDOW_DUMPS=1` to disable it, and
 | `POST` | `/v1/vision/describe` | Vision describe placeholder |
 | `POST` | `/v1/vision/embed` | Create a vision embedding from media |
 | `POST` | `/v1/audio/embed` | Create an audio embedding from audio input |
-| `POST` | `/v1/ocr/advanced` | Advanced OCR — multi-PSM tesseract pipeline with optional vision refinement |
+| `POST` | `/v1/ocr/advanced` | Agent-equivalent managed advanced OCR (alias of `/v1/tools/ocr_image_advanced/call`) |
 
 `POST /v1/voice/tts` and `/v1/audio/speech` automatically warm the daemon.
 An explicit model must render exactly or the request fails; Omnius does not

package/docs/rest/INDEX.md

@@ -113,7 +113,7 @@ Scopes:
 | Nexus | `/v1/nexus/status`, `/v1/sponsors` |
 | Ollama pool | `/v1/ollama/pool/processes`, `/v1/ollama/pool/cleanup` |
 | Voice and audio | `/v1/voice/state`, `/v1/voice/models`, `/v1/voice/tts`, `/v1/audio/speech`, `/v1/asr/engines`, `/v1/asr/selection`, `/v1/asr/activate`, `/v1/asr/transcriptions`, `/v1/asr/test`, `/v1/audio/transcriptions`, `/v1/voicechat/ws`, `/v1/media/av/analyze` |
-| Vision/audio embeddings | `/v1/vision/describe`, `/v1/vision/embed`, `/v1/audio/embed`, `/v1/ocr/advanced` |
+| Vision/audio/OCR | `/v1/vision/describe`, `/v1/vision/embed`, `/v1/audio/embed`, `/v1/ocr/advanced` (agent-equivalent advanced OCR) |
 | Projects | `/v1/projects`, `/v1/projects/current`, `/v1/projects/switch`, `/v1/projects/register`, `/v1/projects/rename`, `/v1/projects/scan`, `/v1/projects/preferences` |
 | Code graph | `/v1/codegraph/snapshot`, `/v1/codegraph/events` |
 | Scheduled jobs | `/v1/scheduled`, `/v1/scheduled/all`, `/v1/scheduled/status`, `/v1/scheduled/kill`, `/v1/scheduled/fixup`, `/v1/scheduled/reconcile` |

package/docs/rest/endpoints/voice-vision.md

@@ -32,9 +32,28 @@
 | `POST` | `/v1/voice/speak` | Synthesize and broadcast to voicechat clients |
 | `WS` | `/v1/voicechat/ws` | Full-duplex voicechat WebSocket |
 | `POST` | `/v1/vision/describe` | Vision describe placeholder/deferred endpoint |
-| `POST` | `/v1/ocr/advanced` | Advanced OCR — multi-PSM tesseract pipeline with optional vision refinement |
+| `POST` | `/v1/ocr/advanced` | Agent-equivalent managed advanced OCR (alias of `/v1/tools/ocr_image_advanced/call`) |
 | `POST` | `/v1/media/av/analyze` | Grounded AV/audio comprehension of a media file into entities/events |
 
+## Advanced OCR
+
+`POST /v1/ocr/advanced` is a compatibility alias for the exact
+agent-facing `ocr_image_advanced` tool. Use the same direct-tool envelope;
+the response retains display text in `result.output` and returns the parsed
+pipeline payload in `result.data`.
+
+```bash
+curl -sS -X POST http://127.0.0.1:11435/v1/ocr/advanced \
+  -H 'content-type: application/json' \
+  -d '{"args":{"image":"/data/invoice.png","language":"eng","psm":6},"timeout_ms":300000}'
+```
+
+On first use, Omnius verifies and provisions Tesseract, requested traineddata,
+and the advanced Python OCR pipeline. Jetson uses Ubuntu/JetPack system Python
+packages in an isolated system-site venv; it never installs generic CUDA,
+Torch, or OpenCV replacements. The caller needs `run` scope because optional
+`output_dir`, batch, and debug modes write OCR artifacts.
+
 ## TTS
 
 `POST /v1/voice/tts` returns audio bytes. `format` can be `wav` or `pcm`. `X-Sample-Rate` reports the sample rate.

package/npm-shrinkwrap.json

@@ -1,12 +1,12 @@
 {
   "name": "omnius",
-  "version": "1.0.628",
+  "version": "1.0.629",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "omnius",
-      "version": "1.0.628",
+      "version": "1.0.629",
       "bundleDependencies": [
         "image-to-ascii"
       ],
@@ -5519,9 +5519,9 @@
       }
     },
     "node_modules/node-addon-api": {
-      "version": "8.9.1",
-      "resolved": "https://registry.npmjs.org/node-addon-api/-/node-addon-api-8.9.1.tgz",
-      "integrity": "sha512-4eUQWVPCUUUiBjLnHS3cXWeC6ryoPUc0U3rP7IuzapoGbzMqd/r6KKO0clr0b+snQhsrueFEhCZDdK+LK7hxKg==",
+      "version": "8.9.2",
+      "resolved": "https://registry.npmjs.org/node-addon-api/-/node-addon-api-8.9.2.tgz",
+      "integrity": "sha512-VijLXbi3UACN69I0JVXJsX4tjACjNoQDgv2gTF6sx2wWEi8tkSg2eX8p5gSIFi8z2+DL3oHmY6OyKce38SDolg==",
       "license": "MIT",
       "optional": true,
       "engines": {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "omnius",
-  "version": "1.0.628",
+  "version": "1.0.629",
   "description": "AI coding agent powered by open-source models (Ollama/vLLM) — interactive TUI with agentic tool-calling loop",
   "type": "module",
   "main": "./dist/library.js",