patient_llm 0.7.0 → 0.8.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 74014452123a066e2e43338aea8a78473d4d1e76740ae9ef4067093c3af96c5c
-  data.tar.gz: 1ae189616ab9daee96f8b8782da08871eb572024d4292c45c456d53de6706524
+  metadata.gz: 55806cbf3beeef58969661d79224bf6ff527ac3e73d92e8426ef854c0635dca0
+  data.tar.gz: bdae58940e5c112a237d5e64455ed956d42577ad0d2241bb7ea0a4576df01f02
 SHA512:
-  metadata.gz: cb5627c92970f28ce39f1e3d7da045eeb5641270a1f0b9d22413c71e68c57bd987e2d3d56cdcca2b3e80ad3c0571ecdd22729d04d39a8bcba8442b90f546055b
-  data.tar.gz: 56fb911160aa80525325c94d15a74a833610428bc67d7702c16737b8ec6c1671afa6a3d59fcb2c92b2a58a0daa0405be28981017cfca99106d5873233c53f93e
+  metadata.gz: ca5d9f04997f0bf171a4de6f5edb599b2b33991c36ce4835cde1574e251b5e6d926887de53d5a31ff7d3e76b294bb9e56e41e467ebb671b3dc36d7031d128b7c
+  data.tar.gz: 533df1b81438b348387a5824df29b3a74a9102292f2cd82de910b0c7fe85d7864cd3364292e5bd5cdca93f10181026987926c681b349668efac6feab5fea9bd3

data/CHANGELOG.md

@@ -4,6 +4,16 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## 0.8.0
+
+### Added
+
+- Requests can name the PatientHttp processor that executes them. Pass `processor:` to `PatientLLM.ask` (or through agent `ask` options), or set a default for all LLM requests with `config.processor` (a Symbol, String, or callable). When neither is set, requests use the default processor. The processor is preserved across automatic tool-loop iterations. Requires patient_http 1.5.0.
+
+### Changed
+
+- patient_http minimum version is now 1.5.0.
+
 ## 0.7.0
 
 ### Changed

data/README.md

@@ -163,6 +163,16 @@ end
 
 Validation of a callable's result (serializer names, authentication headers) happens at lookup time instead of registration time.
 
+### Naming the request processor
+
+Job-system integrations for patient_http can run multiple named processors with different configurations — for example, one tuned for long-running LLM requests and another for quick webhook deliveries. Set `processor` to route every LLM request to a named processor; it can also be a callable, resolved on every request. When unset, requests use the default processor. A per-request `processor:` option on `ask` overrides the configured value.
+
+```ruby
+PatientLLM.configure do |config|
+  config.processor = :llm
+end
+```
+
 ### Request signing (preprocessors)
 
 Some providers require request signing rather than a static authentication header — for example, AWS Bedrock with SigV4, where a signature is computed over the final outgoing request. For these, register a [request preprocessor](https://github.com/bdurand/patient_http#request-preprocessors) on the PatientHttp configuration and reference it by name from the provider. Like secrets, only the preprocessor name is serialized into the job queue; the signing logic and credentials stay on the processor side.
@@ -455,7 +465,8 @@ PatientLLM.ask(session,
   params: {max_completion_tokens: 1000},   # Additional request parameters
   preprocessors: :aws_sigv4,               # Replace the provider's request preprocessors
   timeout: 600,                            # Request timeout in seconds
-  max_tool_iterations: 3                   # Tool loop cap for this request
+  max_tool_iterations: 3,                  # Tool loop cap for this request
+  processor: :llm                          # Named PatientHttp processor for this request
 )
 ```
 

data/VERSION

@@ -1 +1 @@
-0.7.0
+0.8.0

data/lib/patient_llm/agent.rb

@@ -276,7 +276,7 @@ module PatientLLM
       #   agent. Defaults to sending the hooks to the agent itself.
       # @param options [Hash] per-request overrides forwarded to {PatientLLM.ask}
       #   (url:, serializer:, path:, headers:, params:, preprocessors:, timeout:,
-      #   max_tool_iterations:), plus session options (model:, temperature:,
+      #   max_tool_iterations:, processor:), plus session options (model:, temperature:,
       #   extra:, etc. — any PromptBuilder::Session::INITIALIZE_OPTIONS key)
       #   applied to the newly built session; session options raise
       #   ArgumentError when a session: is supplied.

data/lib/patient_llm/configuration.rb

@@ -28,9 +28,18 @@ module PatientLLM
 
     attr_reader :session_offload_options
 
+    # Name of the PatientHttp processor that executes LLM requests, used when a
+    # request does not pass its own processor: option. The value can be a
+    # Symbol, a String, or a callable resolved on every request. When nil, the
+    # default processor is used.
+    #
+    # @return [Symbol, String, #call, nil]
+    attr_accessor :processor
+
     def initialize
       @providers = {}
       @session_offload_options = nil
+      @processor = nil
     end
 
     # Register a provider.

data/lib/patient_llm.rb

@@ -156,8 +156,11 @@ module PatientLLM
     # @param max_tool_iterations [Integer, nil] Maximum automatic tool-execution rounds
     #   for this request. Overrides the provider's setting; defaults to
     #   {Callback::MAX_TOOL_ITERATIONS}.
+    # @param processor [String, Symbol, nil] Name of the PatientHttp processor that
+    #   should execute this request. Overrides the configuration's processor;
+    #   defaults to nil, which uses the default processor.
     # @return [Object] Handler-specific identifier for the enqueued request
-    def ask(session, provider:, callback:, callback_args: {}, url: nil, serializer: nil, path: nil, headers: nil, params: nil, preprocessors: nil, timeout: nil, max_tool_iterations: nil)
+    def ask(session, provider:, callback:, callback_args: {}, url: nil, serializer: nil, path: nil, headers: nil, params: nil, preprocessors: nil, timeout: nil, max_tool_iterations: nil, processor: nil)
       request_options = build_request_options(
         url: url,
         serializer: serializer,
@@ -166,7 +169,8 @@ module PatientLLM
         params: params,
         preprocessors: preprocessors,
         timeout: timeout,
-        max_tool_iterations: max_tool_iterations
+        max_tool_iterations: max_tool_iterations,
+        processor: processor
       )
 
       dispatch(session, provider: provider, callback: callback, callback_args: callback_args, request_options: request_options)
@@ -195,8 +199,10 @@ module PatientLLM
     # @param timeout [Numeric, nil] Accepted for parity with {.ask}; does not affect the preview.
     # @param max_tool_iterations [Integer, nil] Accepted for parity with {.ask}; does not
     #   affect the preview.
+    # @param processor [String, Symbol, nil] Accepted for parity with {.ask}; does not
+    #   affect the preview.
     # @return [RequestPreview] The url, headers, and JSON payload the request would send
-    def preview_request(session, provider:, url: nil, serializer: nil, path: nil, headers: nil, params: nil, preprocessors: nil, timeout: nil, max_tool_iterations: nil)
+    def preview_request(session, provider:, url: nil, serializer: nil, path: nil, headers: nil, params: nil, preprocessors: nil, timeout: nil, max_tool_iterations: nil, processor: nil)
       request_options = build_request_options(
         url: url,
         serializer: serializer,
@@ -205,7 +211,8 @@ module PatientLLM
         params: params,
         preprocessors: preprocessors,
         timeout: timeout,
-        max_tool_iterations: max_tool_iterations
+        max_tool_iterations: max_tool_iterations,
+        processor: processor
       )
 
       resolved = resolve_request(session, self.provider(provider) || {}, request_options)
@@ -250,7 +257,8 @@ module PatientLLM
           json: resolved.payload,
           headers: resolved.headers,
           preprocessors: resolved.preprocessors,
-          timeout: resolved.timeout
+          timeout: resolved.timeout,
+          processor: resolved.processor
         )
         PatientHttp.execute_inline(
           request: request,
@@ -265,6 +273,7 @@ module PatientLLM
           headers: resolved.headers,
           preprocessors: resolved.preprocessors,
           timeout: resolved.timeout,
+          processor: resolved.processor,
           raise_error_responses: true,
           callback: PatientLLM::Callback,
           callback_args: dispatch_callback_args
@@ -276,14 +285,14 @@ module PatientLLM
 
     # Fully resolved request produced by merging per-request options over the
     # provider configuration.
-    ResolvedRequest = Data.define(:url, :serializer, :headers, :payload, :preprocessors, :timeout, :max_tool_iterations)
+    ResolvedRequest = Data.define(:url, :serializer, :headers, :payload, :preprocessors, :timeout, :max_tool_iterations, :processor)
     private_constant :ResolvedRequest
 
     # Normalize per-request overrides into a request options hash. The request
     # options travel through the job queue in the callback args, which only
     # permit JSON-native values; convert Symbols (e.g. serializer names,
     # preprocessor names, header/param values) to Strings up front.
-    def build_request_options(url:, serializer:, path:, headers:, params:, preprocessors:, timeout:, max_tool_iterations:)
+    def build_request_options(url:, serializer:, path:, headers:, params:, preprocessors:, timeout:, max_tool_iterations:, processor:)
       request_options = {}
       request_options["url"] = url if url
       request_options["serializer"] = serializer.to_s if serializer
@@ -293,6 +302,7 @@ module PatientLLM
       request_options["preprocessors"] = preprocessors if preprocessors
       request_options["timeout"] = timeout if timeout
       request_options["max_tool_iterations"] = max_tool_iterations if max_tool_iterations
+      request_options["processor"] = processor.to_s if processor
 
       PromptBuilder.jsonify(request_options)
     end
@@ -335,10 +345,19 @@ module PatientLLM
         payload: payload,
         preprocessors: request_options["preprocessors"] || provider_config[:preprocessors],
         timeout: request_options["timeout"] || provider_config[:timeout],
-        max_tool_iterations: (request_options["max_tool_iterations"] || provider_config[:max_tool_iterations] || Callback::MAX_TOOL_ITERATIONS).to_i
+        max_tool_iterations: (request_options["max_tool_iterations"] || provider_config[:max_tool_iterations] || Callback::MAX_TOOL_ITERATIONS).to_i,
+        processor: request_options["processor"] || configured_processor
       )
     end
 
+    # The processor name from the configuration, calling a callable value and
+    # normalizing the result to a String. Nil when no processor is configured.
+    def configured_processor
+      value = @configuration&.processor
+      value = value.call if value.respond_to?(:call)
+      value&.to_s
+    end
+
     # Replace secret reference header values with placeholders so a preview
     # never resolves or exposes secret values.
     def redact_secret_headers(headers)

data/patient_llm.gemspec

@@ -37,6 +37,6 @@ Gem::Specification.new do |spec|
 
   spec.required_ruby_version = ">= 3.2"
 
-  spec.add_dependency "patient_http", "~> 1.3"
+  spec.add_dependency "patient_http", ">= 1.5.0"
   spec.add_dependency "prompt_builder", "~> 0.4"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: patient_llm
 version: !ruby/object:Gem::Version
-  version: 0.7.0
+  version: 0.8.0
 platform: ruby
 authors:
 - Brian Durand
@@ -13,16 +13,16 @@ dependencies:
   name: patient_http
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.3'
+        version: 1.5.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.3'
+        version: 1.5.0
 - !ruby/object:Gem::Dependency
   name: prompt_builder
   requirement: !ruby/object:Gem::Requirement