pikuri-vectordb 0.0.5 → 0.0.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2560026784f6f00e160c090718c8896835b129fb6d81e4efa1570917aa2414d5
-  data.tar.gz: 22e7054b58ae018b1b4afcde583c70ad979aa4e859348892d3a0640e0541c288
+  metadata.gz: '0391399acefa74d05159cc96400db1c870bb2d0afbd7e924bf508932b9a4f6cc'
+  data.tar.gz: 81c65ff94ec867c0b1094846cda8edb4dad9d8e2e0a23180abaaca979d26b64f
 SHA512:
-  metadata.gz: 9c957518955fa72da1d998f041422a32b78301e488c3a5e93eb13cda4a779a81ae83b3e9ddd3041c5972973b9684c039760f77fd6c7f82f2e94a177e361d66b8
-  data.tar.gz: 420446ae9178260b0cc9e0f4fa2950c9330a74c298e83aad9b1d76e73809f67a99b9cd460a177353f63560871b2bf412fd5d3d3e7f9d22360a458946e538aabb
+  metadata.gz: 6e069b736507fdca7277fdbf75ca2a9e831597095ecf0e5dfe89e781b24faf6961baa0bf567ace1cefdfdb7588314c56732e5ef45632792af117e0e57f0ac9ae
+  data.tar.gz: ed2665499e224117cdb41f5d53fab6737f132b4a38d445853f4e79db7654602458f3615c62c58f2904d58f52764dcc1055b463de1ca57bc63510799069b2a4f4

data/README.md

@@ -106,8 +106,10 @@ piece — each swappable via the Extension's keyword arguments:
   correctness.
 
 Text extraction reuses `Pikuri::FileType.read_as_text` from
-pikuri-core — plain text / Markdown / PDF. HTML extraction is a
-deferred follow-up.
+pikuri-core — plain text / Markdown out of the box; for a PDF
+corpus, register the [pikuri-pdf](../pikuri-pdf) extractor in your
+host script (`Pikuri::Extractors::PDF.register` — `pikuri-corpus`
+does exactly that). HTML extraction is a deferred follow-up.
 
 ## Demo: `pikuri-corpus`
 

data/lib/pikuri/vector_db/tools/read.rb

@@ -46,7 +46,7 @@ module Pikuri
       # line-windowed by {Pikuri::FileType.read_as_text_paged} — the same
       # windower (and the same {DEFAULT_LIMIT}-line / 50 KB caps) that
       # backs {Pikuri::Workspace::Read}, returning a
-      # {Pikuri::FileType::Page} this tool formats. Unlike +Workspace::Read+
+      # {Pikuri::Extractor::Page} this tool formats. Unlike +Workspace::Read+
       # there is no +cat -n+ line-number prefix: nothing downstream edits
       # these documents (the citation unit is the +source+ path, not a
       # line), and dropping the prefix saves tokens on exactly the
@@ -55,23 +55,24 @@ module Pikuri
       # == Errors the LLM can react to
       #
       # Extraction goes through {Pikuri::FileType.read_as_text_paged},
-      # which routes the same way the {Indexer}'s
-      # {Pikuri::FileType.read_as_text} does — so what you read matches
-      # what was indexed (modulo edits to the file since), plus
-      # +"--- Page N ---"+ markers on PDFs. Images / binaries / a vanished
-      # file / a malformed PDF all come back as +"Error: ..."+ observations
-      # rather than raising, per CLAUDE.md "Errors are loud" (these are
-      # failures the agent reacts to, not pikuri bugs).
+      # which routes through the same {Pikuri::Extractor} registry the
+      # {Indexer}'s {Pikuri::FileType.read_as_text} does — so what you
+      # read matches what was indexed exactly (modulo edits to the file
+      # since), +"--- Page N ---"+ PDF markers included. Images /
+      # binaries / a vanished file / a malformed PDF all come back as
+      # +"Error: ..."+ observations rather than raising, per CLAUDE.md
+      # "Errors are loud" (these are failures the agent reacts to, not
+      # pikuri bugs).
       class Read < Pikuri::Tool
         # @return [Integer] default value of the +limit+ parameter
         #   (number of lines returned per call). Aliases the shared
-        #   {Pikuri::FileType::PAGE_DEFAULT_LIMIT}.
-        DEFAULT_LIMIT = Pikuri::FileType::PAGE_DEFAULT_LIMIT
+        #   {Pikuri::Extractor::PAGE_DEFAULT_LIMIT}.
+        DEFAULT_LIMIT = Pikuri::Extractor::PAGE_DEFAULT_LIMIT
 
         # @return [String] human-readable form of the shared byte cap
-        #   ({Pikuri::FileType::PAGE_MAX_BYTES}) for the continuation
+        #   ({Pikuri::Extractor::PAGE_MAX_BYTES}) for the continuation
         #   marker.
-        MAX_BYTES_LABEL = "#{Pikuri::FileType::PAGE_MAX_BYTES / 1024} KB"
+        MAX_BYTES_LABEL = "#{Pikuri::Extractor::PAGE_MAX_BYTES / 1024} KB"
 
         # @return [String] static description shown to the LLM,
         #   opencode-shape (summary + +Usage:+ bullets).
@@ -166,13 +167,13 @@ module Pikuri
         end
         private_class_method :contained?
 
-        # Format a {Pikuri::FileType::Page} as the observation: the lines
+        # Format a {Pikuri::Extractor::Page} as the observation: the lines
         # joined plain (no +cat -n+ prefix), followed by a trailer keyed
         # on the citation +source+ that tells the model whether to page
         # on. PDF pages already carry their +"--- Page N ---"+ markers
         # from the extractor.
         #
-        # @param page [Pikuri::FileType::Page]
+        # @param page [Pikuri::Extractor::Page]
         # @param source [String] the citation, used in the empty /
         #   end-of-document messages.
         # @return [String]

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: pikuri-vectordb
 version: !ruby/object:Gem::Version
-  version: 0.0.5
+  version: 0.0.6
 platform: ruby
 authors:
 - Martin Vysny
@@ -16,28 +16,28 @@ dependencies:
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 0.0.5
+        version: 0.0.6
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 0.0.5
+        version: 0.0.6
 - !ruby/object:Gem::Dependency
   name: pikuri-subagents
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 0.0.5
+        version: 0.0.6
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 0.0.5
+        version: 0.0.6
 - !ruby/object:Gem::Dependency
   name: listen
   requirement: !ruby/object:Gem::Requirement