riffer 0.46.1 → 0.47.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 569f1c5929847037c97cc5552eb38a8609db6a1e67ce99b8135961d50aa7a0b5
-  data.tar.gz: c8e03583eb04ff2c8922b8d554c10f5a47fb4421b15600905ba21b0d69031aed
+  metadata.gz: 4ac69c8c20b892c53242b0fb792aee2ee1ce5da1ab02b1c53536fa8d1c006f08
+  data.tar.gz: 0fa02ebc739e1968167e517a41d4f0a2cabff5a5845862ac78980d207638c6cd
 SHA512:
-  metadata.gz: 6a0380696a959b4c291a5bf52c03eb7a1e06971a60ded5d058311bbdfe9efd99e58bf94506980e2d4b7b0e21257773894d11be4d1a896ea1e7e3ba8e2ce3359e
-  data.tar.gz: 965f4d1fe6b97f4bd887a1fddd310c7a4cb81b5a0789cf8b91c58c49796abe79f396ec410b6008895275bd16281593a29f53d870e591124ade85b38c62a8fb22
+  metadata.gz: 5c0363ce9dad27ccfc899d6c7f4e71123eaa9ae5ceec8e50387575f0642c7696f07de37cb987c45099aee999fe5ac39c8635f07f36efb784c3341bd8a4c6a6aa
+  data.tar.gz: 4b5d6209255a46d9abd52275021709740bf0e87676c20c3bd9240f12acddc7768a050391530970c2a2ed407dbdd27fb50a1b03e43caff8361ad6f28cc67884db

data/.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "0.46.1"
+  ".": "0.47.1"
 }

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).
 
+## [0.47.1](https://github.com/janeapp/riffer/compare/riffer/v0.47.0...riffer/v0.47.1) (2026-09-11)
+
+
+### Bug Fixes
+
+* **params:** keep optional Hash params nullable in strict JSON Schema ([#433](https://github.com/janeapp/riffer/issues/433)) ([c7308fd](https://github.com/janeapp/riffer/commit/c7308fd15a3293877510e74c41662a68fac942df))
+* **params:** raise for bare Hash and Array params under strict schemas ([#434](https://github.com/janeapp/riffer/issues/434)) ([174ad92](https://github.com/janeapp/riffer/commit/174ad92e7c765dc8833695ded9d2920f1ab27337))
+
+## [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)
 
 

data/docs/AGENTS.md

@@ -247,7 +247,7 @@ end
 
 #### Limitations
 
-Using both `of:` and a block raises `Riffer::ArgumentError`. Using `of:` with a non-primitive type (e.g. `of: Hash`) also raises `Riffer::ArgumentError`.
+A `Hash` param requires a block, and an `Array` param requires a block or `of:`. Using both `of:` and a block raises `Riffer::ArgumentError`. Using `of:` with a non-primitive type (e.g. `of: Hash`) also raises `Riffer::ArgumentError`.
 
 Structured output is not compatible with streaming — calling `stream` on an agent with structured output configured raises `Riffer::ArgumentError`.
 

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/params/param.rb

@@ -140,10 +140,14 @@ class Riffer::Params::Param
   # params are made nullable (<tt>["type", "null"]</tt>) so strict providers
   # distinguish absent from present; optional params with an +enum+ use +anyOf+
   # instead, since providers like Anthropic reject
-  # <tt>{"type": ["string", "null"], "enum": [...]}</tt>.
+  # <tt>{"type": ["string", "null"], "enum": [...]}</tt>. Raises
+  # Riffer::ArgumentError when +strict+ and a Hash param has no block or an
+  # Array param has neither a block nor <tt>of:</tt>, since strict providers
+  # reject objects without +properties+ and arrays without +items+.
   #--
   #: (?strict: bool) -> Hash[Symbol, untyped]
   def to_json_schema(strict: false)
+    validate_strict_shape! if strict
     nullable = strict && !required
 
     if nullable && enum
@@ -168,9 +172,24 @@ class Riffer::Params::Param
     elsif self.type == Array && item_type
       schema[:items] = { type: TYPE_MAPPINGS[item_type] }
     elsif self.type == Hash && nested_params
-      schema.merge!(nested_params.to_json_schema(strict: strict))
+      # The nested schema carries its own type: "object", which would clobber a nullable union.
+      schema.merge!(nested_params.to_json_schema(strict: strict).except(:type))
     end
 
     schema
   end
+
+  private
+
+  #--
+  #: () -> void
+  def validate_strict_shape!
+    if type == Hash && nested_params.nil?
+      raise Riffer::ArgumentError,
+            "#{name}: a Hash param requires a block defining its properties under strict schemas"
+    elsif type == Array && nested_params.nil? && item_type.nil?
+      raise Riffer::ArgumentError,
+            "#{name}: an Array param requires a block or of: defining its items under strict schemas"
+    end
+  end
 end

data/lib/riffer/params.rb

@@ -128,6 +128,8 @@ class Riffer::Params
   # Converts all parameters to JSON Schema format. When +strict+ is true, every
   # property is listed in +required+ and optional ones are made nullable
   # instead, satisfying providers that enforce strict structured output schemas.
+  # Raises Riffer::ArgumentError when +strict+ and a Hash param (at any depth)
+  # has no block or an Array param has neither a block nor <tt>of:</tt>.
   #--
   #: (?strict: bool) -> Hash[Symbol, untyped]
   def to_json_schema(strict: false)

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 = "0.46.1" #: String
+  VERSION = "0.47.1" #: String
 end

data/sig/generated/riffer/params/param.rbs

@@ -74,8 +74,17 @@ class Riffer::Params::Param
   # params are made nullable (<tt>["type", "null"]</tt>) so strict providers
   # distinguish absent from present; optional params with an +enum+ use +anyOf+
   # instead, since providers like Anthropic reject
-  # <tt>{"type": ["string", "null"], "enum": [...]}</tt>.
+  # <tt>{"type": ["string", "null"], "enum": [...]}</tt>. Raises
+  # Riffer::ArgumentError when +strict+ and a Hash param has no block or an
+  # Array param has neither a block nor <tt>of:</tt>, since strict providers
+  # reject objects without +properties+ and arrays without +items+.
   # --
   # : (?strict: bool) -> Hash[Symbol, untyped]
   def to_json_schema: (?strict: bool) -> Hash[Symbol, untyped]
+
+  private
+
+  # --
+  # : () -> void
+  def validate_strict_shape!: () -> void
 end

data/sig/generated/riffer/params.rbs

@@ -54,6 +54,8 @@ class Riffer::Params
   # Converts all parameters to JSON Schema format. When +strict+ is true, every
   # property is listed in +required+ and optional ones are made nullable
   # instead, satisfying providers that enforce strict structured output schemas.
+  # Raises Riffer::ArgumentError when +strict+ and a Hash param (at any depth)
+  # has no block or an Array param has neither a block nor <tt>of:</tt>.
   # --
   # : (?strict: bool) -> Hash[Symbol, untyped]
   def to_json_schema: (?strict: bool) -> Hash[Symbol, untyped]

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: 0.46.1
+  version: 0.47.1
 platform: ruby
 authors:
 - Jake Bottrall