omnius 1.0.614 → 1.0.616

package/dist/index.js

@@ -808836,6 +808836,7 @@ function getOpenApiSpec() {
         }
       },
       "/v1/vision/describe": { post: { summary: "Vision describe (deferred to PT-07)", tags: ["Vision"], responses: { 501: { description: "Not yet daemon-resident" } } } },
+      "/v1/ocr/advanced": { post: { summary: "Advanced OCR — multi-PSM tesseract pipeline with optional vision refinement — body {imagePath, visionModel?, prompt?}", tags: ["Vision"], responses: { 200: { description: "OCR text + context block" }, 400: { description: "Missing imagePath" }, 501: { description: "OCR tool unavailable" } } } },
       "/v1/vision/embed": { post: { summary: "Create a vision embedding for uploaded or referenced media", tags: ["Vision"], responses: { 200: { description: "Vision embedding result" }, 400: { description: "Invalid media input" } } } },
       "/v1/audio/embed": { post: { summary: "Create an audio embedding for uploaded or referenced audio", tags: ["Voice"], responses: { 200: { description: "Audio embedding result" }, 400: { description: "Invalid audio input" } } } },
       "/v1/chat/attachments": { post: { summary: "Upload an attachment for a stateful chat", tags: ["Chat"], responses: { 200: { description: "Stored attachment metadata" }, 400: { description: "Invalid attachment" } } } },
@@ -812231,7 +812232,9 @@ function handleHelp(req3, res) {
       voice_and_vision: {
         "POST /v1/voice/tts": "Text-to-speech synthesis",
         "POST /v1/voice/asr": "Automatic speech recognition",
-        "POST /v1/vision/describe": "Describe an image (vision pipeline)"
+        "POST /v1/vision/describe": "Describe an image (vision pipeline)",
+        "POST /v1/ocr/advanced": "Advanced OCR (multi-PSM tesseract + optional vision)",
+        "POST /v1/media/av/analyze": "Grounded AV/audio comprehension of a media file"
       }
     },
     mcp_integration: {

package/docs/DISCOVERY.json

@@ -9897,6 +9897,82 @@
         "packages/cli/src/api/openapi.ts"
       ]
     },
+    {
+      "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?}",
+      "aliases": [
+        "/v1/ocr/advanced"
+      ],
+      "keywords": [
+        "rest",
+        "openapi",
+        "POST",
+        "Vision",
+        "v1",
+        "ocr",
+        "advanced"
+      ],
+      "maturity": "stable",
+      "layer": "interface",
+      "audiences": [
+        "integrator",
+        "service-agent",
+        "coding-agent"
+      ],
+      "interfaces": [
+        {
+          "type": "rest",
+          "target": "POST /v1/ocr/advanced"
+        },
+        {
+          "type": "openapi",
+          "target": "/openapi.json"
+        }
+      ],
+      "references": [
+        {
+          "type": "source",
+          "target": "packages/cli/src/api/openapi.ts",
+          "relation": "openapi-source"
+        },
+        {
+          "type": "documentation",
+          "target": "docs/reference/rest-api.md",
+          "relation": "endpoint-inventory"
+        }
+      ],
+      "methods": [
+        "POST"
+      ],
+      "tags": [
+        "Vision"
+      ],
+      "operations": {
+        "post": {
+          "summary": "Advanced OCR — multi-PSM tesseract pipeline with optional vision refinement — body {imagePath, visionModel?, prompt?}",
+          "tags": [
+            "Vision"
+          ],
+          "responses": {
+            "200": {
+              "description": "OCR text + context block"
+            },
+            "400": {
+              "description": "Missing imagePath"
+            },
+            "501": {
+              "description": "OCR tool unavailable"
+            }
+          }
+        }
+      },
+      "source_of_truth": [
+        "GET /openapi.json",
+        "packages/cli/src/api/openapi.ts"
+      ]
+    },
     {
       "id": "api.v1-ollama-pool-cleanup",
       "kind": "api",

package/docs/DISCOVERY.md

@@ -162,6 +162,7 @@ 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-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 |

package/docs/reference/rest-api.md

@@ -306,6 +306,7 @@ 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/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

@@ -112,8 +112,8 @@ Scopes:
 | Sessions and context | `/v1/sessions`, `/v1/sessions/{id}`, `/v1/context`, `/v1/context/window-dumps`, `/v1/context/window-dumps/{id}`, `/v1/context/save`, `/v1/context/restore`, `/v1/context/compact` |
 | 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` |
-| Vision/audio embeddings | `/v1/vision/describe`, `/v1/vision/embed`, `/v1/audio/embed` |
+| 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` |
 | 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

@@ -29,6 +29,8 @@
 | `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/media/av/analyze` | Grounded AV/audio comprehension of a media file into entities/events |
 
 ## TTS
 

package/npm-shrinkwrap.json

@@ -1,12 +1,12 @@
 {
   "name": "omnius",
-  "version": "1.0.614",
+  "version": "1.0.616",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "omnius",
-      "version": "1.0.614",
+      "version": "1.0.616",
       "bundleDependencies": [
         "image-to-ascii"
       ],

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "omnius",
-  "version": "1.0.614",
+  "version": "1.0.616",
   "description": "AI coding agent powered by open-source models (Ollama/vLLM) — interactive TUI with agentic tool-calling loop",
   "type": "module",
   "main": "./dist/library.js",