riffer 0.46.0 → 0.47.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ac304f75fface8720f1e2565ea2064b643abb2f1c29f5a9dfe5281820e9d3986
-  data.tar.gz: de5695cffa30697e0356de921227caffdab12ff806e143166369c36e3ae010d6
+  metadata.gz: 63cc9b38354166dc44a162e7fb8cc168cf14e950d8cbbba582fb9710721c25a5
+  data.tar.gz: 8a386abc38526d731d7253efbab2c8e2ab345da712762d605f469c5708ec5cca
 SHA512:
-  metadata.gz: dfe9da5a5cb0a8a1147846766acc79b518a9f7025d1d95fbfddce3604e2315afafc04762b339879eee2db875aba5cc296056045f213f47a17cb9f730e17f3e07
-  data.tar.gz: b548a4b44b001b79ee295969af5a868f50d0e847a183dc9433e5b23d4b1e7c9effed3ea64a76a8f5022db959a65394d8f8ff28bba9a6d46484841322483ebe02
+  metadata.gz: 9a36b54ef99b21ea74a8e215c3ba5abb70c2bf949e40bf15056209f9cc4875c62505406568fc5a258508d17735a5d92c360510a5092a4f158733feebd6f64fb4
+  data.tar.gz: 69209c501af21331079d0e5374b4b41119619ddd81afa6debeb8e93da3955bb144370cb3c1b506411043de9544f070855c66ef62819d5affadc3d671410b906f

data/.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "0.46.0"
+  ".": "0.47.0"
 }

data/CHANGELOG.md

@@ -5,6 +5,21 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.47.0](https://github.com/janeapp/riffer/compare/riffer/v0.46.1...riffer/v0.47.0) (2026-09-11)
+
+
+### Features
+
+* **bedrock:** moving cachePoint so the conversation tail is cached ([#431](https://github.com/janeapp/riffer/issues/431)) ([4fa44b8](https://github.com/janeapp/riffer/commit/4fa44b817c00642303ac30002c33dd77c6d502ab))
+
+## [0.46.1](https://github.com/janeapp/riffer/compare/riffer/v0.46.0...riffer/v0.46.1) (2026-09-11)
+
+
+### Bug Fixes
+
+* accept JSON integers for Float params ([#429](https://github.com/janeapp/riffer/issues/429)) ([928c33b](https://github.com/janeapp/riffer/commit/928c33b1125bf013f66c8b736191bc70eb313ccd))
+* **agent:** type stream's enumerator as returning Response ([#428](https://github.com/janeapp/riffer/issues/428)) ([4d2b2d2](https://github.com/janeapp/riffer/commit/4d2b2d2aa08d1d95b97226e84180284349fff441))
+
 ## [0.46.0](https://github.com/janeapp/riffer/compare/riffer/v0.45.0...riffer/v0.46.0) (2026-09-08)
 
 

data/docs/AGENT_LIFECYCLE.md

@@ -59,6 +59,14 @@ response = MyAgent.generate('What is in this image?', files: [
 
 Streams a response as an Enumerator. Same prompt/files semantics as `generate`.
 
+Consuming the enumerator with a block returns the same `Riffer::Agent::Response` that `generate` would, so you can stream events to the user and still inspect the final outcome:
+
+```ruby
+response = MyAgent.stream('Tell me a story').each { |event| handle(event) }
+response.outcome.reason  # => :completed
+response.content
+```
+
 ```ruby
 # New conversation (class method — recommended for simple calls)
 MyAgent.stream('Tell me a story').each do |event|

data/docs/TOOLS.md

@@ -115,6 +115,8 @@ Options:
 
 `Riffer::Params::Boolean` is the preferred way to declare boolean parameters. `TrueClass` and `FalseClass` continue to work for backwards compatibility.
 
+A `Float` param accepts a whole number too, since JSON Schema's `number` covers integers — a model returning `120` for a `Float` is valid, and the validated value is coerced to `120.0`. `Integer` stays strict: `1.0` is rejected, matching JSON Schema's `integer`.
+
 ### Nested Parameters
 
 Tool params support the same nested DSL as structured output — nested objects (`Hash` with block), typed arrays (`Array, of:`), and arrays of objects (`Array` with block). See the [structured output section in Agents](AGENTS.md#nested-objects) for full syntax.

data/docs/providers/AMAZON_BEDROCK.md

@@ -94,7 +94,10 @@ model_options additional_model_request_fields: {
 
 ### cache_control
 
-Enable prompt caching for models that support it (Claude, Nova). Riffer appends a single Converse `cachePoint` to the stable prefix — after the system array, or after the tools when there is no system prompt — so system instructions and tool definitions are reused across the calls in an agent loop and across conversation turns. The volatile message tail is never cached.
+Enable prompt caching for models that support it (Claude, Nova). Riffer mirrors Anthropic's automatic caching with two Converse `cachePoint` blocks:
+
+- A **static** checkpoint at the end of the stable prefix — after the system array, or after the tools when there is no system prompt — so system instructions and tool definitions are reused across every call.
+- A **moving** checkpoint after the last content block of the final message (a user turn or a batch of tool results). Bedrock looks back roughly 20 content blocks from a checkpoint for the longest cached prefix, so the second and later calls in a tool loop, and later turns in a conversation, read the accumulated conversation from cache instead of re-billing it at the full input rate.
 
 ```ruby
 # 5-minute TTL (default)
@@ -104,7 +107,7 @@ model_options cache_control: {type: "ephemeral"}
 model_options cache_control: {type: "ephemeral", ttl: "1h"}
 ```
 
-Caching is opt-in: omit `cache_control` and no cachePoint is sent. The breakpoint is only honored once the prefix clears the model's minimum token count; on models that don't support `cachePoint`, the Converse request errors. Verify hits via `response.token_usage.cache_read_tokens`.
+Both checkpoints share the same `ttl`. Caching is opt-in: omit `cache_control` and no cachePoint is sent. A checkpoint is only honored once the content before it clears the model's minimum token count (see the per-model limits in the [AWS prompt caching guide](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html)) and is silently ignored below it, so short conversations may see no cache reads at first. On models that don't support `cachePoint`, the Converse request errors. Verify hits via `response.token_usage.cache_read_tokens`, which should grow with each step of an agent loop as the conversation accumulates.
 
 ## Example
 

data/lib/riffer/agent/run.rb

@@ -20,7 +20,7 @@ module Riffer::Agent::Run
   # for prompt/files semantics.
   #
   #--
-  #: (agent: Riffer::Agent, ?prompt: String?, ?files: Array[Hash[Symbol, untyped] | Riffer::Messages::FilePart]?, ?tags: Hash[(String | Symbol), untyped]) -> Enumerator[Riffer::StreamEvents::Base, void]
+  #: (agent: Riffer::Agent, ?prompt: String?, ?files: Array[Hash[Symbol, untyped] | Riffer::Messages::FilePart]?, ?tags: Hash[(String | Symbol), untyped]) -> Enumerator[Riffer::StreamEvents::Base, Riffer::Agent::Response]
   def stream(agent:, prompt: nil, files: nil, tags: {})
     append_user_message(agent, prompt, files: files)
     # The enumerator body runs in its own fiber, where the fiber-local OTEL

data/lib/riffer/agent.rb

@@ -155,7 +155,7 @@ class Riffer::Agent
 
   # Streams a response using a new agent instance.
   #--
-  #: (?String?, ?files: Array[Hash[Symbol, untyped] | Riffer::Messages::FilePart]?, ?context: Hash[Symbol, untyped]?, ?tags: Hash[(String | Symbol), untyped]) -> Enumerator[Riffer::StreamEvents::Base, void]
+  #: (?String?, ?files: Array[Hash[Symbol, untyped] | Riffer::Messages::FilePart]?, ?context: Hash[Symbol, untyped]?, ?tags: Hash[(String | Symbol), untyped]) -> Enumerator[Riffer::StreamEvents::Base, Riffer::Agent::Response]
   def self.stream(prompt = nil, files: nil, context: nil, tags: {})
     new(context: context).stream(prompt, files: files, tags: tags)
   end
@@ -304,13 +304,14 @@ class Riffer::Agent
     Riffer::Agent::Run.generate(agent: self, prompt: prompt, files: files, tags: tags)
   end
 
-  # Streams a response from the agent, returning an +Enumerator+ of
-  # +Riffer::StreamEvents+. See +#generate+ for prompt/files/tags semantics.
+  # Streams a response from the agent as an +Enumerator+ of
+  # +Riffer::StreamEvents+ whose block-form +each+ returns the final
+  # Riffer::Agent::Response. See +#generate+ for prompt/files/tags semantics.
   #
   # Raises Riffer::ArgumentError if structured output is configured.
   #
   #--
-  #: (?String?, ?files: Array[Hash[Symbol, untyped] | Riffer::Messages::FilePart]?, ?tags: Hash[(String | Symbol), untyped]) -> Enumerator[Riffer::StreamEvents::Base, void]
+  #: (?String?, ?files: Array[Hash[Symbol, untyped] | Riffer::Messages::FilePart]?, ?tags: Hash[(String | Symbol), untyped]) -> Enumerator[Riffer::StreamEvents::Base, Riffer::Agent::Response]
   def stream(prompt = nil, files: nil, tags: {})
     if @structured_output
       raise Riffer::ArgumentError,

data/lib/riffer/params/param.rb

@@ -121,6 +121,8 @@ class Riffer::Params::Param
 
     if [Riffer::Params::Boolean, TrueClass, FalseClass].include?(type)
       [true, false].include?(value)
+    elsif type == Float
+      value.is_a?(Numeric)
     else
       value.is_a?(type)
     end

data/lib/riffer/params.rb

@@ -79,6 +79,11 @@ class Riffer::Params
 
   # Validates arguments against parameter definitions.
   #
+  # A Float param accepts an Integer (JSON Schema <tt>"number"</tt> covers
+  # integers) and its value is coerced with +to_f+, so callers always get a
+  # Float. The same holds for the items of an <tt>of: Float</tt> array. No other
+  # type is coerced.
+  #
   # Raises Riffer::ValidationError if validation fails.
   #
   #--
@@ -112,7 +117,7 @@ class Riffer::Params
 
       value = validate_nested(param, value, errors)
 
-      validated[param.name] = value
+      validated[param.name] = coerce_value(param.type, value)
     end
 
     raise Riffer::ValidationError, errors.join("; ") if errors.any?
@@ -178,7 +183,6 @@ class Riffer::Params
       validate_nested_array_of_objects(param, value, errors)
     elsif param.type == Array && param.item_type
       validate_typed_array(param, value, errors)
-      value
     else
       value
     end
@@ -218,20 +222,40 @@ class Riffer::Params
     end
   end
 
+  # Returns the array with its valid items coerced by +coerce_value+.
   #--
-  #: (Riffer::Params::Param, Array[untyped], Array[String]) -> void
+  #: (Riffer::Params::Param, Array[untyped], Array[String]) -> Array[untyped]
   def validate_typed_array(param, value, errors)
     item_type = param.item_type
-    return unless item_type
+    return value unless item_type
 
     type_name = Riffer::Params::Param::TYPE_MAPPINGS[item_type]
     valid_item = if [Riffer::Params::Boolean, TrueClass, FalseClass].include?(item_type)
                    ->(item) { [true, false].include?(item) }
+                 elsif item_type == Float
+                   ->(item) { item.is_a?(Numeric) }
                  else
                    ->(item) { item.is_a?(item_type) }
                  end
-    value.each_with_index do |item, i|
-      errors << "#{param.name}[#{i}] must be a #{type_name}" unless valid_item.call(item)
+    value.map.with_index do |item, i|
+      unless valid_item.call(item)
+        errors << "#{param.name}[#{i}] must be a #{type_name}"
+        next item
+      end
+
+      coerce_value(item_type, item)
     end
   end
+
+  # Coerces an already-validated value to the Ruby type its param declares.
+  # Only Float coerces today, because JSON Schema "number" accepts integers and
+  # callers should not get a type that depends on whether the model wrote a
+  # decimal point. Add a branch here rather than inline at a call site.
+  #--
+  #: (Module, untyped) -> untyped
+  def coerce_value(type, value)
+    return value.to_f if type == Float
+
+    value
+  end
 end

data/lib/riffer/providers/amazon_bedrock.rb

@@ -129,21 +129,25 @@ class Riffer::Providers::AmazonBedrock < Riffer::Providers::Base
     params
   end
 
-  # Converse chains +tools -> system -> messages+, so a single +cachePoint+ at
-  # the end of the system array (or the tools array, when there is no system
-  # prompt) also caches the preceding sections.
+  # Converse treats +tools -> system -> messages+ as one prefix and looks back
+  # from a +cachePoint+ for the longest cached run, so the point on the final
+  # message reuses the previous step's cache wherever that point sat. Mixed
+  # ttls must be ordered 1h before 5m, so both points share one.
   #--
   #: (Hash[Symbol, untyped], untyped) -> void
   def apply_cache_point(params, cache_control)
     cache_point = { cache_point: build_cache_point(cache_control) }
     system = params[:system]
     tools = params.dig(:tool_config, :tools)
+    last_message = params[:messages].last
 
     if system && !system.empty?
       system << cache_point
     elsif tools && !tools.empty?
       tools << cache_point
     end
+
+    last_message[:content] << cache_point if last_message
   end
 
   #--

data/lib/riffer/version.rb

@@ -2,5 +2,5 @@
 # rbs_inline: enabled
 
 module Riffer
-  VERSION = "0.46.0" #: String
+  VERSION = "0.47.0" #: String
 end

data/sig/generated/riffer/agent/run.rbs

@@ -14,8 +14,8 @@ module Riffer::Agent::Run
   # for prompt/files semantics.
   #
   # --
-  # : (agent: Riffer::Agent, ?prompt: String?, ?files: Array[Hash[Symbol, untyped] | Riffer::Messages::FilePart]?, ?tags: Hash[(String | Symbol), untyped]) -> Enumerator[Riffer::StreamEvents::Base, void]
-  def stream: (agent: Riffer::Agent, ?prompt: String?, ?files: Array[Hash[Symbol, untyped] | Riffer::Messages::FilePart]?, ?tags: Hash[String | Symbol, untyped]) -> Enumerator[Riffer::StreamEvents::Base, void]
+  # : (agent: Riffer::Agent, ?prompt: String?, ?files: Array[Hash[Symbol, untyped] | Riffer::Messages::FilePart]?, ?tags: Hash[(String | Symbol), untyped]) -> Enumerator[Riffer::StreamEvents::Base, Riffer::Agent::Response]
+  def stream: (agent: Riffer::Agent, ?prompt: String?, ?files: Array[Hash[Symbol, untyped] | Riffer::Messages::FilePart]?, ?tags: Hash[String | Symbol, untyped]) -> Enumerator[Riffer::StreamEvents::Base, Riffer::Agent::Response]
 
   private
 

data/sig/generated/riffer/agent.rbs

@@ -113,8 +113,8 @@ class Riffer::Agent
 
   # Streams a response using a new agent instance.
   # --
-  # : (?String?, ?files: Array[Hash[Symbol, untyped] | Riffer::Messages::FilePart]?, ?context: Hash[Symbol, untyped]?, ?tags: Hash[(String | Symbol), untyped]) -> Enumerator[Riffer::StreamEvents::Base, void]
-  def self.stream: (?String?, ?files: Array[Hash[Symbol, untyped] | Riffer::Messages::FilePart]?, ?context: Hash[Symbol, untyped]?, ?tags: Hash[String | Symbol, untyped]) -> Enumerator[Riffer::StreamEvents::Base, void]
+  # : (?String?, ?files: Array[Hash[Symbol, untyped] | Riffer::Messages::FilePart]?, ?context: Hash[Symbol, untyped]?, ?tags: Hash[(String | Symbol), untyped]) -> Enumerator[Riffer::StreamEvents::Base, Riffer::Agent::Response]
+  def self.stream: (?String?, ?files: Array[Hash[Symbol, untyped] | Riffer::Messages::FilePart]?, ?context: Hash[Symbol, untyped]?, ?tags: Hash[String | Symbol, untyped]) -> Enumerator[Riffer::StreamEvents::Base, Riffer::Agent::Response]
 
   # Reconstructs a runnable agent from a wire hash produced by +#to_h+.
   # --
@@ -208,14 +208,15 @@ class Riffer::Agent
   # : (?String?, ?files: Array[Hash[Symbol, untyped] | Riffer::Messages::FilePart]?, ?tags: Hash[(String | Symbol), untyped]) -> Riffer::Agent::Response
   def generate: (?String?, ?files: Array[Hash[Symbol, untyped] | Riffer::Messages::FilePart]?, ?tags: Hash[String | Symbol, untyped]) -> Riffer::Agent::Response
 
-  # Streams a response from the agent, returning an +Enumerator+ of
-  # +Riffer::StreamEvents+. See +#generate+ for prompt/files/tags semantics.
+  # Streams a response from the agent as an +Enumerator+ of
+  # +Riffer::StreamEvents+ whose block-form +each+ returns the final
+  # Riffer::Agent::Response. See +#generate+ for prompt/files/tags semantics.
   #
   # Raises Riffer::ArgumentError if structured output is configured.
   #
   # --
-  # : (?String?, ?files: Array[Hash[Symbol, untyped] | Riffer::Messages::FilePart]?, ?tags: Hash[(String | Symbol), untyped]) -> Enumerator[Riffer::StreamEvents::Base, void]
-  def stream: (?String?, ?files: Array[Hash[Symbol, untyped] | Riffer::Messages::FilePart]?, ?tags: Hash[String | Symbol, untyped]) -> Enumerator[Riffer::StreamEvents::Base, void]
+  # : (?String?, ?files: Array[Hash[Symbol, untyped] | Riffer::Messages::FilePart]?, ?tags: Hash[(String | Symbol), untyped]) -> Enumerator[Riffer::StreamEvents::Base, Riffer::Agent::Response]
+  def stream: (?String?, ?files: Array[Hash[Symbol, untyped] | Riffer::Messages::FilePart]?, ?tags: Hash[String | Symbol, untyped]) -> Enumerator[Riffer::StreamEvents::Base, Riffer::Agent::Response]
 
   # Interrupts the agent loop from an +on_message+ callback. Equivalent to
   # <tt>throw :riffer_interrupt, reason</tt>.

data/sig/generated/riffer/params.rbs

@@ -40,6 +40,11 @@ class Riffer::Params
 
   # Validates arguments against parameter definitions.
   #
+  # A Float param accepts an Integer (JSON Schema <tt>"number"</tt> covers
+  # integers) and its value is coerced with +to_f+, so callers always get a
+  # Float. The same holds for the items of an <tt>of: Float</tt> array. No other
+  # type is coerced.
+  #
   # Raises Riffer::ValidationError if validation fails.
   #
   # --
@@ -71,7 +76,16 @@ class Riffer::Params
   # : (Riffer::Params::Param, Array[untyped], Array[String]) -> Array[untyped]
   def validate_nested_array_of_objects: (Riffer::Params::Param, Array[untyped], Array[String]) -> Array[untyped]
 
+  # Returns the array with its valid items coerced by +coerce_value+.
+  # --
+  # : (Riffer::Params::Param, Array[untyped], Array[String]) -> Array[untyped]
+  def validate_typed_array: (Riffer::Params::Param, Array[untyped], Array[String]) -> Array[untyped]
+
+  # Coerces an already-validated value to the Ruby type its param declares.
+  # Only Float coerces today, because JSON Schema "number" accepts integers and
+  # callers should not get a type that depends on whether the model wrote a
+  # decimal point. Add a branch here rather than inline at a call site.
   # --
-  # : (Riffer::Params::Param, Array[untyped], Array[String]) -> void
-  def validate_typed_array: (Riffer::Params::Param, Array[untyped], Array[String]) -> void
+  # : (Module, untyped) -> untyped
+  def coerce_value: (Module, untyped) -> untyped
 end

data/sig/generated/riffer/providers/amazon_bedrock.rbs

@@ -45,9 +45,10 @@ class Riffer::Providers::AmazonBedrock < Riffer::Providers::Base
   # : (Array[Riffer::Messages::Base], String?, Hash[Symbol, untyped]) -> Hash[Symbol, untyped]
   def build_request_params: (Array[Riffer::Messages::Base], String?, Hash[Symbol, untyped]) -> Hash[Symbol, untyped]
 
-  # Converse chains +tools -> system -> messages+, so a single +cachePoint+ at
-  # the end of the system array (or the tools array, when there is no system
-  # prompt) also caches the preceding sections.
+  # Converse treats +tools -> system -> messages+ as one prefix and looks back
+  # from a +cachePoint+ for the longest cached run, so the point on the final
+  # message reuses the previous step's cache wherever that point sat. Mixed
+  # ttls must be ordered 1h before 5m, so both points share one.
   # --
   # : (Hash[Symbol, untyped], untyped) -> void
   def apply_cache_point: (Hash[Symbol, untyped], untyped) -> void

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: riffer
 version: !ruby/object:Gem::Version
-  version: 0.46.0
+  version: 0.47.0
 platform: ruby
 authors:
 - Jake Bottrall