Update

adapters.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e617950c97411f75adb16e5d479be1da9fb75da0e8aedf126c6830be4087f581
+oid sha256:51e3e0a56ec1f40e519d92dff7bb79050bb60ab3dccce6ac2c19519e065b326a
 size 67323724

manifest.json

@@ -1,20 +1,20 @@
 {
-  "id": "nano-planner-evidence-v1",
+  "id": "nano-planner-modality-v1",
   "base_repo": "thoddnn/Qwen3.5-2B-4bit",
   "base_revision": "da5c842efe38a8404c33e02bc9c59b2d81c99c34",
-  "schema": "nano-planner-scope-v3",
+  "schema": "nano-planner-modality-v1",
   "files": {
     "adapter_config.json": {
       "sha256": "4116ad764b4a283dd3c418c5b3e3e3862b86e96dfcb6f69c27136890cd910766",
       "bytes": 10880
     },
     "adapters.safetensors": {
-      "sha256": "e617950c97411f75adb16e5d479be1da9fb75da0e8aedf126c6830be4087f581",
+      "sha256": "51e3e0a56ec1f40e519d92dff7bb79050bb60ab3dccce6ac2c19519e065b326a",
       "bytes": 67323724
     },
     "prompt.txt": {
-      "sha256": "9f2effec154a317a46977b743dfa29627d490935167f56f8cea1325f974b6295",
-      "bytes": 6469
+      "sha256": "7ee7c24f967a0fed9ca965971be031e7c50e7411ce525eb53514668e8ef3fea0",
+      "bytes": 7845
     }
   }
 }

prompt.txt

@@ -1,5 +1,5 @@
 Plan a local-file search. Return only JSON:
-{"language":"en","file_types":[],"searches":[{"query":"retrieval terms","mode":"keyword"}],"facts":[{"question":"Complete question?","scope":"any_unit","type":"boolean"}],"match_mode":"first"}.
+{"language":"en","file_types":[],"searches":[{"query":"retrieval terms","mode":"keyword"}],"facts":[{"question":"Complete question?","scope":"any_unit","type":"boolean","modality":"hybrid"}],"match_mode":"first"}.
 Use the user's language for searches and questions; preserve names and quoted text. Keys and enum values stay English. Preserve ALL requirements without inventing any.
 file_types: only explicitly requested formats. Categories: image,pdf,video,audio,document,word,spreadsheet,presentation,email,code,ebook. Or an explicitly named extension without the dot: 3fr,aac,ai,aiff,arw,avi,avif,bash,bat,bear,bmp,c,cfg,cmd,conf,cpp,cr2,cr3,craft,crw,css,csv,dcr,dng,doc,docx,eml,emlx,epub,fig,flac,gif,go,h,heic,heif,hpp,html,indd,ini,ipynb,java,jpeg,jpg,js,json,jsx,key,kt,less,log,m4a,m4v,mbox,md,mef,mkv,mov,mp3,mp4,mrw,mts,mxf,nef,notes,notion,nrw,odp,ods,odt,ogg,olk15msgsource,orf,pages,pdf,pef,php,png,ppt,pptx,ps1,psd,ptx,py,r,raf,rb,rst,rtf,rw2,sass,scala,scss,sh,sketch,sql,sr2,srw,swift,tif,tiff,toml,ts,tsx,txt,wav,webarchive,webp,wmv,xls,xlsx,xml,yaml. Otherwise []. Use audio for audio files, email for emails of any supported format; do not narrow a category to one extension unless requested. Formats are metadata filters, never verification facts. Do not assume invoices are PDFs.
 For an explicitly requested recording with neither medium specified, allow both audio and video categories; filters are alternatives, not simultaneous requirements.
@@ -16,3 +16,8 @@ Preserve the evidence source: spoken words are not text visible on a sign. Keep
 Phrase any_unit verification questions about the evidence unit supplied to the verifier, never about whether the parent container contains that evidence. Scope performs the parent-file existence aggregation. Ask “Does this page…?”, “Does this image…?”, “Does this slide…?”, “Does this row…?”, “Does this passage…?”, or “Does this spoken segment…?” as appropriate.
 For an original PDF, visual evidence is always a rendered PDF page; Fenn does not index an embedded PDF image as a separate result. Ask about this page. InDesign and other formats converted to PDF also use rendered pages. PowerPoint and Keynote use slides. Figma and Sketch may expose an embedded bitmap as a separate image, and note applications may expose an attached image, so ask about this image for those extracted-image matches. A standalone image remains file scope.
 The wording of the user’s container request does not belong in the local question. “Find a Figma file containing an image with X” becomes an image-local fact about X; “Find a PDF containing an illustration of X” becomes a page-local fact. Keep multiple conditions in one question when they must hold in the same unit. File type remains only in file_types.
+Every fact has a modality describing the evidence the verifier must inspect:
+- text: native machine-readable text, structured rows/cells, email fields, source code, or a speech transcript is authoritative. Use text for explicitly text-native formats such as TXT and Markdown, structured spreadsheets/CSV, email, code, and spoken-only requirements.
+- vision: pixels are authoritative. Use vision for visible objects, scenes, actions, layout, colors, diagrams, charts, handwriting, signatures, stamps, highlighting, and text visibly printed inside an image, video frame, rendered page, or rendered slide. An identity card or passport requested as a physical visual object, including a name visibly printed on it, is vision.
+- hybrid: native text may exist, but the requested document content can also be present only in a scan or embedded image. Use hybrid for textual or numeric facts in invoices, receipts, contracts, reports, tickets, certificates, Word files, PDFs, and unspecified general documents. This includes document identity, parties, dates, amounts, clauses, and exact phrases. Also use hybrid when a single fact genuinely needs both text or speech and visual evidence.
+Choose modality independently for every fact. Search mode does not determine modality. Filename and file-metadata facts use text. A query may mix modalities across its facts.