data_redactor 0.15.0-aarch64-linux → 0.17.0-aarch64-linux

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 186d6a1ed6ad690e0b022c9410dd1bc9ce79ca6d57f8f953c1081321757025ed
-  data.tar.gz: 13f8fbf32f59af749fa660fadd5ce47820ad726d86acb239907a3237e2a3c478
+  metadata.gz: 206353fa82d49af6e4b9d528eb27d95047d6121e575bc824640aa3595f785f2c
+  data.tar.gz: 1b1207d478038a66887af84363242913344345fb317277ac41554131c3989810
 SHA512:
-  metadata.gz: 6377bd25095e6614a85c4333b8b1d7a9d74d3fe892485520dd4643f53bf48faab684c431dd1fc52cbecf17abdff6c4a9823f8adbfce88104aa37d5d27f0c23fb
-  data.tar.gz: 622c9bd536de4a34cf53ea4c09f36cb6b14efd82d7b5228155d308b4284c8ec05e067ebee5535520cc29857100a2eadd188a8499310c7faa62f49b0c57a2e0ee
+  metadata.gz: 9e09a76ab4c81bc1b148b9b4f06d93be6df2a260608e195d2a59d424aeec55bc99f004cdfb2a8f22f7136e7200ba4350847b7ffbf260fa5461d141de4e6686cb
+  data.tar.gz: e75715b813870bdcf5fba2aa7ad7a4b8e87e0b15294473ba481c4b260a4e3ca037d32a5b669800448e821463f2fe9c95b9a45b5b829932dd3fcbf8adf463eccc

data/CHANGELOG.md

@@ -7,6 +7,48 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.17.0] - 2026-06-21
+
+### Added
+- **Transparent `ruby_llm` integration (opt-in monkeypatch).**
+  `require "data_redactor/integrations/ruby_llm"` then
+  `DataRedactor::Integrations::RubyLLM.install!` prepends a small patch onto
+  `RubyLLM::Protocol#render`, so **every** outbound request is deep-redacted
+  before it is posted — no per-call `.redact`. One hook covers all providers
+  (Anthropic, OpenAI, Gemini, Bedrock, Responses) and scrubs the user prompt,
+  system prompt, tool definitions, and any file/command-output that an agent fed
+  back as a tool result (all inlined as strings in the payload). Forwards
+  `only:`/`except:`/`placeholder:`; idempotent; fails fast at `install!` if an
+  unsupported `ruby_llm` version is loaded or `Protocol#render` is missing.
+  **Limitation:** base64 attachments (PDFs/images/audio) and URL-referenced
+  files are not redacted — the secret bytes are encoded or remote, so patterns
+  cannot see them. This is a monkeypatch on internal API and is version-pinned;
+  the clean alternative remains per-call `DataRedactor.redact` before `chat.ask`.
+
+## [0.16.0] - 2026-06-21
+
+### Added
+- **Opt-in `#redact` refinements.** `require "data_redactor/refinements"` then
+  `using DataRedactor::Refinements` adds `#redact` to `String` (→
+  `DataRedactor.redact`) and to `Hash`/`Array` (→ `DataRedactor.redact_deep`), e.g.
+  `"email a@b.com".redact` and `chat.ask(user_input.redact)`. Refinements are
+  lexically scoped, so they never pollute the core classes globally — apps that
+  don't opt in are unaffected and there is no collision risk. Forwards
+  `only:`/`except:`/`placeholder:`; never mutates the receiver.
+  `DataRedactor.redact` remains the primary API.
+- **Length-aware placeholder modes.** `placeholder: :length` replaces each match
+  with `[REDACTED:N]` and `placeholder: :tagged_length` with `[REDACTED:TAGNAME:N]`,
+  where `N` is the **byte length** of the redacted value. Readers can gauge what
+  was there without seeing it. Both compose with `only:`/`except:` and are
+  forwarded by `redact_deep`, `redact_json`, and the integrations. Additive —
+  two new values for the existing `placeholder:` keyword; no behaviour changes.
+- **CI: ASan/UBSan memory-safety gate.** New job builds the matcher engine
+  standalone under `-fsanitize=address,undefined` and drives it over an
+  adversarial corpus + seeded fuzz loop (catches the `OP_EOL`-class OOB read).
+- **CI: throughput-trend history + PR comment.** New job records the C/pure-Ruby
+  ratio over time (history in `actions/cache`, no gh-pages), posts a sticky PR
+  comment comparing each run to the previous point, and fails on a >10% drop.
+
 ## [0.15.0] - 2026-06-17
 
 ### Changed
@@ -312,7 +354,9 @@ features as 0.7.1 plus the pipeline fix.
 - `DataRedactor.redact(text)` module function returning the input with every match replaced by `[REDACTED]`.
 - RSpec suite with one example per pattern.
 
-[Unreleased]: https://github.com/danielefrisanco/data_redactor/compare/v0.15.0...HEAD
+[Unreleased]: https://github.com/danielefrisanco/data_redactor/compare/v0.17.0...HEAD
+[0.17.0]: https://github.com/danielefrisanco/data_redactor/compare/v0.16.0...v0.17.0
+[0.16.0]: https://github.com/danielefrisanco/data_redactor/compare/v0.15.0...v0.16.0
 [0.15.0]: https://github.com/danielefrisanco/data_redactor/compare/v0.14.1...v0.15.0
 [0.14.1]: https://github.com/danielefrisanco/data_redactor/compare/v0.14.0...v0.14.1
 [0.14.0]: https://github.com/danielefrisanco/data_redactor/compare/v0.13.0...v0.14.0

data/README.md

@@ -6,6 +6,12 @@
 
 A Ruby gem with a C extension for high-performance regex-based redaction of sensitive data from strings.
 
+> 📄 The engineering behind the v19 matching engine is written up as an experience
+> report, *"The Fastest Engine Is Not the Shippable Engine: Replacing a Regex Engine
+> for Data Redaction Under Production Constraints,"* currently under review at
+> *Software: Practice and Experience* (Manuscript ID 7985366). Source and the
+> reproducibility bundle are in [`paper/`](paper/).
+
 ## What it does
 
 DataRedactor scans text for sensitive data — API keys and cloud secrets, IBANs,
@@ -103,9 +109,18 @@ DataRedactor.redact(text, placeholder: :hash)
 # "user@example.com"  → "[CONTACT_3d7a]"
 # "user@example.com"  → "[CONTACT_3d7a]"  (same every time)
 # "other@example.com" → "[CONTACT_91fc]"  (different value, different hash)
+
+# Length — embeds the byte length of the redacted value, so readers can
+# gauge what was there without seeing it.
+DataRedactor.redact(text, placeholder: :length)
+# "user@example.com"  → "[REDACTED:16]"
+
+# Tagged length — tag name plus byte length.
+DataRedactor.redact(text, placeholder: :tagged_length)
+# "user@example.com"  → "[REDACTED:CONTACT:16]"
 ```
 
-All three modes compose with `only:` and `except:`:
+All modes compose with `only:` and `except:`:
 
 ```ruby
 DataRedactor.redact(text, only: :contact, placeholder: :tagged)
@@ -165,6 +180,24 @@ safe_json = DataRedactor.redact_json('{"email":"alice@example.com","count":3}')
 DataRedactor.redact_json("not json")  # => JSON::ParserError
 ```
 
+### `#redact` refinements (opt-in)
+
+Prefer `"text".redact` over `DataRedactor.redact("text")`? Opt into the refinement. It adds `#redact` to `String` (via `redact`) and to `Hash`/`Array` (via `redact_deep`) **only in the files that `using` it** — refinements are lexically scoped, so the core classes are never monkey-patched globally and there is no collision risk for apps that don't opt in. `DataRedactor.redact` remains the primary API.
+
+```ruby
+require "data_redactor/refinements"
+using DataRedactor::Refinements
+
+"email alice@example.com".redact            # => "email [REDACTED]"
+{ token: "AKIAIOSFODNN7EXAMPLE" }.redact    # => { token: "[REDACTED]" }
+["a@b.com", 3].redact                       # => ["[REDACTED]", 3]
+
+# Handy right before sending text to an LLM:
+chat.ask(user_input.redact)
+```
+
+`#redact` forwards `only:`/`except:`/`placeholder:` and never mutates the receiver. Without `using DataRedactor::Refinements` in the current file, `#redact` is not defined.
+
 ### Custom patterns
 
 Teams often have internal IDs that the gem can't ship. Register them at boot — or at runtime from any thread (registration is thread-safe, see [Thread safety](#thread-safety)):
@@ -309,6 +342,45 @@ safe_response = DataRedactor::Integrations::OpenAI.redact_response(response)
 
 `content` may be a plain String or an array of content blocks/parts (`{ type: "text", text: "..." }`) — only the `text` of `text` blocks is redacted; image and other block types pass through untouched. For Claude, a top-level `system:` String is also redacted; for OpenAI, a `{ role: "system" }` message in the array is redacted like any other. Pass a bare `messages` array or the whole request Hash (with a `messages` key) — either works.
 
+### RubyLLM
+
+[RubyLLM](https://rubyllm.com) is a unified Ruby client for every major LLM provider — and a perfect match for `data_redactor`: anything you send to a model is exactly the kind of free text that leaks secrets and PII. Because RubyLLM takes plain strings, you can scrub them with `DataRedactor.redact` before they leave the process — no extra integration required:
+
+```ruby
+require "ruby_llm"
+require "data_redactor"
+
+chat = RubyLLM.chat(model: "claude-opus-4-8")
+chat.with_instructions(DataRedactor.redact("You are a support agent for ACME Corp."))
+
+user_input = "My card is 4111 1111 1111 1111 and my email is alice@example.com"
+chat.ask(DataRedactor.redact(user_input))
+# the model receives: "My card is [REDACTED] and my email is [REDACTED]"
+```
+
+Wrap each prompt (and any `with_instructions` system prompt) in `DataRedactor.redact` before passing it to `ask`. This is a per-call step you opt into, and it's the recommended approach.
+
+#### Transparent mode (every request, no per-call wrapping)
+
+If you'd rather redact **every** outbound request automatically — including the system prompt, tool definitions, and any file contents or shell-command output an agent feeds back as a tool result — opt into the monkeypatch:
+
+```ruby
+require "ruby_llm"
+require "data_redactor/integrations/ruby_llm"
+
+DataRedactor::Integrations::RubyLLM.install!   # once, at boot
+
+chat = RubyLLM.chat(model: "claude-opus-4-8")
+chat.ask("my card is 4111111111111111")        # sent as "my card is [REDACTED]"
+```
+
+`install!` prepends a patch onto `RubyLLM::Protocol#render` — the one point where every provider (Anthropic, OpenAI, Gemini, Bedrock, Responses) has assembled its final request — and deep-redacts the payload before it's posted. It forwards `only:`/`except:`/`placeholder:`, is idempotent, and **fails fast** at `install!` if an unsupported `ruby_llm` version is loaded or the internal API has moved (so it never silently leaks).
+
+Two caveats, by design:
+
+- **It's a monkeypatch on RubyLLM internals**, pinned to a supported version range. Prefer per-call `DataRedactor.redact` (above) unless you specifically need transparency. RubyLLM does not yet expose a public request hook ([crmne/ruby_llm#765](https://github.com/crmne/ruby_llm/issues/765) tracks the connection-middleware hook that would let us drop the patch).
+- **Base64 attachments** (PDFs, images, audio sent inline) and **URL-referenced files** are not redacted — the sensitive bytes are encoded or remote, so patterns cannot see them.
+
 ## Detected patterns (89 total)
 
 The table below is a representative sample. Use `DataRedactor.pattern_names` for the canonical, machine-readable list — it stays in sync with the C extension automatically.

data/lib/data_redactor/integrations/ruby_llm.rb

@@ -0,0 +1,120 @@
+require "data_redactor"
+
+module DataRedactor
+  module Integrations
+    # Transparent outbound redaction for the `ruby_llm` gem (crmne/ruby_llm).
+    #
+    # Calling {install!} prepends a small module onto `RubyLLM::Protocol` that
+    # deep-redacts the **rendered request payload** before it is posted to any
+    # provider. `Protocol#render` is the single point where every provider
+    # (Anthropic, OpenAI/chat_completions, Gemini, Bedrock/Converse, Responses)
+    # has assembled its final request Hash, so one hook covers them all without
+    # knowing any provider-specific shape.
+    #
+    # Because the payload is walked with {DataRedactor.redact_deep}, this scrubs
+    # **every String leaf** in the request: the user prompt, the system prompt,
+    # tool definitions, and — crucially — any file contents or shell-command
+    # output that an agent fed back in as a tool result, since those are already
+    # inlined as strings in `messages` by the time `render` runs.
+    #
+    # This is a monkeypatch (a `prepend` onto a private internal class). It is
+    # opt-in and pinned: {install!} raises unless a supported `ruby_llm` version
+    # is loaded and `RubyLLM::Protocol#render` still exists, so an upstream
+    # refactor fails loudly at install time rather than silently leaking data.
+    # Prefer this only when you need redaction to be *transparent*; otherwise
+    # redact per call with {DataRedactor.redact} before `chat.ask`.
+    #
+    # ## What is NOT redacted
+    # - **Base64 attachments** (PDFs, images, audio sent inline as base64) — the
+    #   sensitive bytes are encoded, so patterns cannot see into them.
+    # - **URL-referenced files/images** — the content lives on a remote server
+    #   and never enters the payload.
+    #
+    # @example Make every ruby_llm request redacted, app-wide
+    #   require "data_redactor/integrations/ruby_llm"
+    #   DataRedactor::Integrations::RubyLLM.install!
+    #
+    #   chat = RubyLLM.chat(model: "claude-opus-4-8")
+    #   chat.ask("my card is 4111111111111111")  # sent as "my card is [REDACTED]"
+    #
+    # @example Scope the redaction with the usual filters
+    #   DataRedactor::Integrations::RubyLLM.install!(only: [:financial, :contact])
+    module RubyLLM
+      module_function
+
+      # ruby_llm versions whose `Protocol#render` chokepoint this integration
+      # has been verified against. Bump (and re-verify) on each ruby_llm release.
+      SUPPORTED_VERSION = "~> 1.16"
+
+      # Prepend the redaction patch onto `RubyLLM::Protocol`. Idempotent: a
+      # second call with the patch already installed is a no-op (the filter
+      # options from the first successful install are kept).
+      #
+      # The `only:`/`except:`/`placeholder:` filters are captured here and
+      # applied to every subsequent request.
+      #
+      # @param only [Symbol, String, Array, nil] forwarded to {DataRedactor.redact_deep}.
+      # @param except [Symbol, String, Array, nil] forwarded to {DataRedactor.redact_deep}.
+      # @param placeholder [String, Symbol] forwarded to {DataRedactor.redact_deep}.
+      # @return [void]
+      # @raise [RuntimeError] if `ruby_llm` is not loaded, the loaded version is
+      #   outside {SUPPORTED_VERSION}, or `RubyLLM::Protocol#render` is missing
+      #   (i.e. an upstream refactor moved the chokepoint).
+      def install!(only: nil, except: nil, placeholder: DataRedactor::PLACEHOLDER_DEFAULT)
+        ensure_compatible!
+
+        @options = { only: only, except: except, placeholder: placeholder }
+        return if installed?
+
+        ::RubyLLM::Protocol.prepend(PayloadPatch)
+      end
+
+      # @return [Boolean] whether the redaction patch is currently on
+      #   `RubyLLM::Protocol`.
+      def installed?
+        defined?(::RubyLLM::Protocol) &&
+          ::RubyLLM::Protocol.ancestors.include?(PayloadPatch)
+      end
+
+      # @!visibility private
+      # @return [Hash] the filter options captured at {install!}.
+      def options
+        @options ||= { only: nil, except: nil, placeholder: DataRedactor::PLACEHOLDER_DEFAULT }
+      end
+
+      # @!visibility private
+      def ensure_compatible!
+        unless defined?(::RubyLLM::VERSION)
+          raise "data_redactor ruby_llm integration: require \"ruby_llm\" before calling install!"
+        end
+
+        unless Gem::Requirement.new(SUPPORTED_VERSION).satisfied_by?(Gem::Version.new(::RubyLLM::VERSION))
+          raise "data_redactor ruby_llm integration supports ruby_llm #{SUPPORTED_VERSION}, " \
+                "got #{::RubyLLM::VERSION}. Check for a newer data_redactor or pin ruby_llm."
+        end
+
+        unless ::RubyLLM::Protocol.method_defined?(:render) || ::RubyLLM::Protocol.private_method_defined?(:render)
+          raise "data_redactor ruby_llm integration: RubyLLM::Protocol#render not found — " \
+                "the upstream request-rendering API changed. This integration needs an update."
+        end
+      end
+
+      # Prepended onto `RubyLLM::Protocol`. `Protocol#complete` calls
+      # `payload = render(...)` and then posts that payload, so redacting the
+      # return value of `render` redacts the request without touching anything
+      # else in the send path.
+      module PayloadPatch
+        def render(*args, **kwargs)
+          payload = super
+          opts = DataRedactor::Integrations::RubyLLM.options
+          DataRedactor.redact_deep(
+            payload,
+            only: opts[:only],
+            except: opts[:except],
+            placeholder: opts[:placeholder]
+          )
+        end
+      end
+    end
+  end
+end

data/lib/data_redactor/refinements.rb

@@ -0,0 +1,69 @@
+# frozen_string_literal: true
+
+require "data_redactor"
+
+module DataRedactor
+  # Opt-in refinements that add a `#redact` method to `String`, `Hash`, and
+  # `Array` as sugar over {DataRedactor.redact} / {DataRedactor.redact_deep}.
+  #
+  # Refinements are lexically scoped: `#redact` exists only in files that
+  # `using DataRedactor::Refinements`, so loading this file never pollutes the
+  # core classes globally. Apps that don't opt in are unaffected, and there is
+  # no collision risk with other libraries' `String#redact`.
+  #
+  # `DataRedactor.redact` remains the primary API; this is convenience only.
+  #
+  # @example
+  #   require "data_redactor/refinements"
+  #   using DataRedactor::Refinements
+  #
+  #   "email alice@example.com".redact            #=> "email [REDACTED]"
+  #   { token: "AKIAIOSFODNN7EXAMPLE" }.redact    #=> { token: "[REDACTED]" }
+  #   chat.ask(user_input.redact)                 # scrub before sending to an LLM
+  module Refinements
+    refine String do
+      # Redact this String via {DataRedactor.redact}. Returns a new String; the
+      # receiver is not mutated.
+      #
+      # @param only forwarded to {DataRedactor.redact}
+      # @param except forwarded to {DataRedactor.redact}
+      # @param placeholder forwarded to {DataRedactor.redact}
+      # @return [String] the redacted copy.
+      # @example
+      #   "ssn 123-45-6789".redact #=> "ssn [REDACTED]"
+      def redact(only: nil, except: nil, placeholder: DataRedactor::PLACEHOLDER_DEFAULT)
+        DataRedactor.redact(self, only: only, except: except, placeholder: placeholder)
+      end
+    end
+
+    refine Hash do
+      # Deep-redact this Hash's String values via {DataRedactor.redact_deep}.
+      # Returns a deep copy; the receiver is not mutated and keys are untouched.
+      #
+      # @param only forwarded to {DataRedactor.redact_deep}
+      # @param except forwarded to {DataRedactor.redact_deep}
+      # @param placeholder forwarded to {DataRedactor.redact_deep}
+      # @return [Hash] a deep copy with String leaves redacted.
+      # @example
+      #   { email: "a@b.com" }.redact #=> { email: "[REDACTED]" }
+      def redact(only: nil, except: nil, placeholder: DataRedactor::PLACEHOLDER_DEFAULT)
+        DataRedactor.redact_deep(self, only: only, except: except, placeholder: placeholder)
+      end
+    end
+
+    refine Array do
+      # Deep-redact this Array's String elements via {DataRedactor.redact_deep}.
+      # Returns a deep copy; the receiver is not mutated.
+      #
+      # @param only forwarded to {DataRedactor.redact_deep}
+      # @param except forwarded to {DataRedactor.redact_deep}
+      # @param placeholder forwarded to {DataRedactor.redact_deep}
+      # @return [Array] a deep copy with String leaves redacted.
+      # @example
+      #   ["a@b.com", 3].redact #=> ["[REDACTED]", 3]
+      def redact(only: nil, except: nil, placeholder: DataRedactor::PLACEHOLDER_DEFAULT)
+        DataRedactor.redact_deep(self, only: only, except: except, placeholder: placeholder)
+      end
+    end
+  end
+end

data/lib/data_redactor/version.rb

@@ -1,4 +1,4 @@
 module DataRedactor
   # Current gem version. Follows {https://semver.org Semantic Versioning 2.0.0}.
-  VERSION = "0.15.0"
+  VERSION = "0.17.0"
 end

data/lib/data_redactor.rb

@@ -23,8 +23,10 @@ require_relative "data_redactor/name_pattern"
 #
 # @example Custom placeholder
 #   DataRedactor.redact(text, placeholder: "***")
-#   DataRedactor.redact(text, placeholder: :tagged) # => "[REDACTED:CONTACT]"
-#   DataRedactor.redact(text, placeholder: :hash)   # => "[CONTACT_a3f9]"
+#   DataRedactor.redact(text, placeholder: :tagged)        # => "[REDACTED:CONTACT]"
+#   DataRedactor.redact(text, placeholder: :hash)          # => "[CONTACT_a3f9]"
+#   DataRedactor.redact(text, placeholder: :length)        # => "[REDACTED:16]"
+#   DataRedactor.redact(text, placeholder: :tagged_length) # => "[REDACTED:CONTACT:16]"
 #
 # @example Audit / dry-run
 #   DataRedactor.scan(text)
@@ -125,12 +127,15 @@ module DataRedactor
   #   and/or pattern name(s).
   # @param except [Symbol, String, Array, nil] exclude the given tag(s)
   #   and/or pattern name(s). May be combined with +only:+.
-  # @param placeholder [String, :tagged, :hash] replacement strategy.
-  #   A String is used verbatim. +:tagged+ produces +[REDACTED:TAGNAME]+.
-  #   +:hash+ produces a deterministic +[TAGNAME_xxxx]+ token (4-hex djb2)
-  #   so the same input value always maps to the same token.
+  # @param placeholder [String, :tagged, :hash, :length, :tagged_length]
+  #   replacement strategy. A String is used verbatim. +:tagged+ produces
+  #   +[REDACTED:TAGNAME]+. +:hash+ produces a deterministic +[TAGNAME_xxxx]+
+  #   token (4-hex djb2) so the same input value always maps to the same token.
+  #   +:length+ produces +[REDACTED:N]+ and +:tagged_length+ produces
+  #   +[REDACTED:TAGNAME:N]+, where +N+ is the byte length of the redacted value.
   # @return [String] a new string with every match replaced.
-  # @raise [ArgumentError] if +placeholder:+ is not a String/:tagged/:hash.
+  # @raise [ArgumentError] if +placeholder:+ is not a String/:tagged/:hash/
+  #   :length/:tagged_length.
   # @raise [UnknownTagError] if any Symbol in +only:+/+except:+ is not in {TAGS}.
   # @raise [UnknownPatternError] if any String in +only:+/+except:+ is not in {pattern_names}.
   #
@@ -194,7 +199,7 @@ module DataRedactor
   #   Any type is accepted; non-String scalars are returned as-is.
   # @param only [Symbol, String, Array, nil] forwarded to {redact}.
   # @param except [Symbol, String, Array, nil] forwarded to {redact}.
-  # @param placeholder [String, :tagged, :hash] forwarded to {redact}.
+  # @param placeholder [String, :tagged, :hash, :length, :tagged_length] forwarded to {redact}.
   # @return [Hash, Array, String, Object] a new structure of the same shape
   #   with all String leaves redacted.
   # @raise [ArgumentError] if the structure contains a circular reference.
@@ -217,7 +222,7 @@ module DataRedactor
   # @param json_string [String] valid JSON input.
   # @param only [Symbol, String, Array, nil] forwarded to {redact}.
   # @param except [Symbol, String, Array, nil] forwarded to {redact}.
-  # @param placeholder [String, :tagged, :hash] forwarded to {redact}.
+  # @param placeholder [String, :tagged, :hash, :length, :tagged_length] forwarded to {redact}.
   # @return [String] a JSON string with all String values redacted.
   # @raise [JSON::ParserError] if +json_string+ is not valid JSON.
   #
@@ -425,17 +430,20 @@ module DataRedactor
   # Translate the user-facing +placeholder:+ value into the +(mode_int, str)+
   # pair the C layer expects.
   #
-  # @param placeholder [String, :tagged, :hash]
+  # @param placeholder [String, :tagged, :hash, :length, :tagged_length]
   # @return [Array(Integer, String)]
   # @raise [ArgumentError] if +placeholder+ is none of the accepted values.
   def resolve_placeholder(placeholder)
     case placeholder
-    when :tagged then [PH_MODE_TAGGED, ""]
-    when :hash   then [PH_MODE_HASH,   ""]
-    when String  then [PH_MODE_PLAIN,  placeholder]
+    when :tagged        then [PH_MODE_TAGGED,        ""]
+    when :hash          then [PH_MODE_HASH,          ""]
+    when :length        then [PH_MODE_LENGTH,        ""]
+    when :tagged_length then [PH_MODE_TAGGED_LENGTH, ""]
+    when String         then [PH_MODE_PLAIN,         placeholder]
     else
       raise ArgumentError,
-        "placeholder must be a String, :tagged, or :hash — got #{placeholder.inspect}"
+        "placeholder must be a String, :tagged, :hash, :length, or :tagged_length " \
+        "— got #{placeholder.inspect}"
     end
   end
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: data_redactor
 version: !ruby/object:Gem::Version
-  version: 0.15.0
+  version: 0.17.0
 platform: aarch64-linux
 authors:
 - Daniele Frisanco
@@ -120,7 +120,9 @@ files:
 - lib/data_redactor/integrations/openai.rb
 - lib/data_redactor/integrations/rack.rb
 - lib/data_redactor/integrations/rails.rb
+- lib/data_redactor/integrations/ruby_llm.rb
 - lib/data_redactor/name_pattern.rb
+- lib/data_redactor/refinements.rb
 - lib/data_redactor/version.rb
 homepage: https://github.com/danielefrisanco/data_redactor
 licenses: