llm_meta_client 1.2.0 → 1.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 5529e0613f2103802abfbf448ef5d030f63a7788e8fde7440d732fa94ced7378
-  data.tar.gz: 38223a0a3ff727e9a649fc38db922e5f89aaaa858118464ef9d410a727fff5f1
+  metadata.gz: 2fcc6377f3293f8ecd13b81cd79ea63891c18f55dfa05ee225a151f7e1fa5b84
+  data.tar.gz: 35c4cba209aed5989b43606715205a7e2b85c669fa7dd71d65a33f4dd47a293a
 SHA512:
-  metadata.gz: 2d86c22b05ff9991ff7087a370de97fc90adaf766f2a13745511d2ce7beb129828e169cbeb601b9d2996836f62fb79ca398a66a2e1fbd09a20cf78c148d5fb8a
-  data.tar.gz: 55cc853db63cca50ace6693e4b4a124ee2923371fd6709b2ef1d92e3fdcb4bc62ad433533c2e832dfff132d6ab91bf608847d583d0fdc1104beb38c54597db8d
+  metadata.gz: c959d77e7d3b8c9f5070bf2f63a74e83ba1082391694788e094c09629e76883dcf0142336af7742dd08fa46c0d36ec20ad31ad85b558ea4199cb8b7e3c4345fc
+  data.tar.gz: 651d88ddb211fd11234daf2ecee22e368d8886d27e43b94c1786d4d3980cedfb078a562ee0cd0ad06a48140c7fb07cae779326237e604b21a819d4ceb663d815

data/CHANGELOG.md

@@ -5,6 +5,23 @@ 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).
 
+## [1.3.0] - 2026-05-10
+
+### Added
+
+- Tool-call streaming end-to-end. `ServerQuery#stream` now accepts `tool_ids:` and yields a `tool_calls` event when the LLM decides to invoke MCP tools. Turn 1 (tool selection) runs synchronously; turn 2 (the follow-up after tool execution) is streamed.
+- Scaffold renders a separate "🛠 Tool calls" bubble during streaming via the new `_tool_call_message.html.erb` partial. The Stimulus controller inserts it before the streaming bubble when `event: tool_calls` arrives, and removes it once the assistant message is saved (the saved bubble's combined markdown contains the tool-call section).
+- `Chat#stream_assistant_response` accepts `tool_ids:` and threads them through. Persistence is unchanged — the saved `Message.response` includes a markdown "Tool calls" section appended to the response text, matching the existing synchronous shape.
+- When `tool_ids` is non-empty, the system prompt is augmented with an instruction to explain tool errors rather than fail silently. Models that ignore the instruction are caught by a server-side fallback (see below).
+
+### Changed
+
+- Streaming error messages now parse `error` + `message` from the response body so users see context (e.g. "Rate limit exceeded — check your provider plan…") instead of a bare HTTP code. Mid-stream `event: error` payloads with codes like `rate_limit` get the same friendlier treatment.
+
+### Notes
+
+- Requires `llm_meta_server` with the matching tool-streaming additions: `LlmRbFacade.stream!` accepting `tools:` + `on_tool_calls:` and an `Api::ChatStreamsController` that emits the `tool_calls` SSE event. Server-side fixes that ship alongside this release: an Anthropic-tool-only-response rehydrator (Claude tool-only completions weren't surfacing through `Session#functions`), and a sink injection that emits MCP `isError: true` payloads as text deltas before turn 2 (Gemini sometimes returns nothing after a tool error and would otherwise leave the bubble blank).
+
 ## [1.2.0] - 2026-05-10
 
 ### Added

data/lib/generators/llm_meta_client/scaffold/scaffold_generator.rb

@@ -31,6 +31,7 @@ module LlmMetaClient
         template "app/views/chats/update.turbo_stream.erb"
         template "app/views/chats/_message.html.erb"
         template "app/views/chats/_streaming_message.html.erb"
+        template "app/views/chats/_tool_call_message.html.erb"
         template "app/views/chats/_chat_sidebar.html.erb"
         template "app/views/chats/_messages_list.html.erb"
         template "app/views/shared/_family_field.html.erb"

data/lib/generators/llm_meta_client/scaffold/templates/app/controllers/chat_streams_controller.rb

@@ -17,9 +17,18 @@ class ChatStreamsController < ApplicationController
 
     jwt_token = current_user.id_token if user_signed_in?
     generation_settings = parse_generation_settings(params[:generation_settings_json])
+    tool_ids = Array(params[:tool_ids]).reject(&:blank?)
 
-    assembled = chat.stream_assistant_response(prompt_execution, jwt_token, generation_settings: generation_settings) do |event|
-      forward(event)
+    assembled = chat.stream_assistant_response(prompt_execution, jwt_token, tool_ids: tool_ids, generation_settings: generation_settings) do |event|
+      if event[:event] == "tool_calls"
+        tool_calls = event[:data]["tool_calls"] || []
+        forward(event: "tool_calls", data: {
+          tool_calls: tool_calls,
+          html: view_context.render(partial: "chats/tool_call_message", locals: { tool_calls: tool_calls })
+        })
+      else
+        forward(event)
+      end
     end
 
     if assembled.present?

data/lib/generators/llm_meta_client/scaffold/templates/app/controllers/chats_controller.rb

@@ -97,6 +97,7 @@ class ChatsController < ApplicationController
       # The streaming bubble is rendered by create.turbo_stream.erb and opens
       # the EventSource on connect; persistence + title gen happen at stream close.
       @generation_settings_json = params[:generation_settings_json]
+      @tool_ids = Array(params[:tool_ids]).reject(&:blank?)
     end
 
     # Return turbo stream to render both messages
@@ -189,6 +190,7 @@ class ChatsController < ApplicationController
       # The assistant response is streamed by ChatStreamsController (SSE).
       # See create action for details.
       @generation_settings_json = params[:generation_settings_json]
+      @tool_ids = Array(params[:tool_ids]).reject(&:blank?)
     end
 
     # Return turbo stream to render both messages

data/lib/generators/llm_meta_client/scaffold/templates/app/javascript/controllers/message_stream_controller.js

@@ -14,6 +14,7 @@ export default class extends Controller {
     this.source.addEventListener("done", () => this.#onDone())
     this.source.addEventListener("title", (e) => this.#onTitle(e))
     this.source.addEventListener("saved", (e) => this.#onSaved(e))
+    this.source.addEventListener("tool_calls", (e) => this.#onToolCalls(e))
     this.source.addEventListener("error", (e) => this.#onError(e))
   }
 
@@ -43,9 +44,31 @@ export default class extends Controller {
       const data = JSON.parse(event.data)
       this.element.dataset.savedExecutionId = data.execution_id
       if (data.html) this.#swapInRenderedMessage(data.html)
+      // The saved bubble's content already includes any tool calls section in
+      // markdown; remove the transient tool-call bubbles so reload and live look
+      // the same.
+      this.#removeTransientToolCallBubbles()
     } catch {}
   }
 
+  #onToolCalls(event) {
+    try {
+      const data = JSON.parse(event.data)
+      if (!data.html) return
+      const wrapper = document.createElement("template")
+      wrapper.innerHTML = data.html.trim()
+      const bubble = wrapper.content.firstElementChild
+      if (!bubble) return
+      bubble.classList.add("tool-call-streaming")
+      this.element.parentNode.insertBefore(bubble, this.element)
+      this.#scrollToBottom()
+    } catch {}
+  }
+
+  #removeTransientToolCallBubbles() {
+    document.querySelectorAll(".tool-call-streaming").forEach((el) => el.remove())
+  }
+
   // Swap the streaming bubble's role + content with the host-rendered _message
   // partial output so any markdown / syntax highlighting / partial customizations
   // applied on reload also apply right after the stream finishes. We don't

data/lib/generators/llm_meta_client/scaffold/templates/app/models/chat.rb

@@ -69,15 +69,17 @@ class Chat < ApplicationRecord
   end
 
   # Stream the assistant response from the LLM. Yields each parsed SSE event.
-  # Returns the assembled content. Caller is responsible for persistence.
-  def stream_assistant_response(prompt_execution, jwt_token, generation_settings: {}, &block)
-    summarized_context, prompt = build_streaming_context(prompt_execution, jwt_token)
+  # Returns the assembled content (with markdown "Tool calls" section appended
+  # if tools fired). Caller is responsible for persistence.
+  def stream_assistant_response(prompt_execution, jwt_token, tool_ids: [], generation_settings: {}, &block)
+    summarized_context, prompt = build_streaming_context(prompt_execution, jwt_token, with_tools: tool_ids.any?)
     LlmMetaClient::ServerQuery.new.stream(
       jwt_token,
       prompt_execution.llm_uuid,
       prompt_execution.model,
       summarized_context,
       prompt,
+      tool_ids: tool_ids,
       generation_settings: generation_settings,
       &block
     )
@@ -144,7 +146,7 @@ class Chat < ApplicationRecord
 
   # Send messages to LLM and get response
   def send_to_llm(prompt_execution, jwt_token, tool_ids: [], generation_settings: {})
-    summarized_context, prompt = build_streaming_context(prompt_execution, jwt_token)
+    summarized_context, prompt = build_streaming_context(prompt_execution, jwt_token, with_tools: tool_ids.any?)
     LlmMetaClient::ServerQuery.new.call(
       jwt_token,
       prompt_execution.llm_uuid,
@@ -158,7 +160,7 @@ class Chat < ApplicationRecord
 
   # Build the (summarized_context, prompt) tuple for an LLM call.
   # Shared by both the synchronous and streaming paths.
-  def build_streaming_context(prompt_execution, jwt_token)
+  def build_streaming_context(prompt_execution, jwt_token, with_tools: false)
     llm_options = LlmMetaClient::ServerResource.available_llm_options(jwt_token)
     raise LlmMetaClient::Exceptions::OllamaUnavailableError, "No LLM available" if llm_options.empty?
 
@@ -177,6 +179,9 @@ class Chat < ApplicationRecord
         )
       end
     summarized_context += "Additional prompt: Responses from the assistant must consist solely of the response body."
+    if with_tools
+      summarized_context += " If a tool call returns an error, do not give up silently — explain the error and what likely caused it (e.g. an invalid argument value)."
+    end
 
     [ summarized_context, prompt ]
   end

data/lib/generators/llm_meta_client/scaffold/templates/app/views/chats/_streaming_message.html.erb

@@ -1,4 +1,9 @@
-<%% stream_url = chat_stream_path(chat_id: chat.uuid, execution_id: prompt_execution.execution_id, generation_settings_json: @generation_settings_json.presence) %>
+<%% stream_url = chat_stream_path(
+  chat_id: chat.uuid,
+  execution_id: prompt_execution.execution_id,
+  generation_settings_json: @generation_settings_json.presence,
+  tool_ids: (@tool_ids.presence || nil)
+) %>
 <div class="message assistant streaming"
      data-controller="message-stream"
      data-message-stream-url-value="<%%= stream_url %>">

data/lib/generators/llm_meta_client/scaffold/templates/app/views/chats/_tool_call_message.html.erb

@@ -0,0 +1,22 @@
+<div class="message assistant tool-call">
+  <div class="message-role">🛠 Tool calls</div>
+  <div class="message-content">
+    <ul>
+      <%% tool_calls.each do |tc| %>
+        <%% name = tc["name"] || tc[:name] || "(unknown)" %>
+        <%% args = tc["arguments"] || tc[:arguments] %>
+        <%% args_str = case args
+          when Hash, Array then args.to_json
+          when nil, "" then nil
+          else args.to_s
+        end %>
+        <li>
+          <code><%%= name %></code>
+          <%% if args_str %>
+            — <code><%%= args_str %></code>
+          <%% end %>
+        </li>
+      <%% end %>
+    </ul>
+  </div>
+</div>

data/lib/llm_meta_client/server_query.rb

@@ -5,23 +5,31 @@ require "json"
 module LlmMetaClient
   class ServerQuery
     # Stream LLM responses incrementally. Yields each content delta event
-    # ({ event: "message", data: { "delta" => "..." } }) to the caller's block.
-    # Upstream "done" markers are absorbed (end-of-stream is signaled by the
-    # block returning); upstream "error" events raise ServerError.
-    # Returns the assembled content string. Tool calls are not supported here.
-    def stream(id_token, api_key_uuid, model_id, context, user_content, generation_settings: {})
+    # ({ event: "message", data: { "delta" => "..." } }) and any tool_calls
+    # event ({ event: "tool_calls", data: { "tool_calls" => [...] } }) to the
+    # caller's block. Upstream "done" markers are absorbed (end-of-stream is
+    # signaled by the block returning); upstream "error" events raise ServerError.
+    # Returns the final assistant content. If tool calls fired, the returned
+    # string mirrors the synchronous #call format (response + markdown
+    # "Tool calls" section appended) so persistence stays consistent.
+    def stream(id_token, api_key_uuid, model_id, context, user_content, tool_ids: [], generation_settings: {})
       context_and_user_content = "Context:#{context}, User Prompt: #{user_content}"
       debug_log "Streaming request to LLM: \n===>\n#{context_and_user_content}\n===>"
 
       body = { prompt: context_and_user_content }
+      body[:tool_ids] = tool_ids if tool_ids.present?
       body[:generation_settings] = generation_settings if generation_settings.present?
 
       assembled = +""
+      collected_tool_calls = []
       request_stream(api_key_uuid, id_token, model_id, body) do |event|
         case event[:event]
         when "message"
           assembled << event[:data]["delta"].to_s
           yield event if block_given?
+        when "tool_calls"
+          collected_tool_calls = event[:data]["tool_calls"] || []
+          yield event if block_given?
         when "done"
           # End-of-stream marker from upstream; no-op here.
         when "error"
@@ -31,7 +39,7 @@ module LlmMetaClient
         end
       end
 
-      assembled
+      collected_tool_calls.any? ? combine_with_tool_calls(assembled, collected_tool_calls) : assembled
     end
 
     def call(id_token, api_key_uuid, model_id, context, user_content, tool_ids: [], generation_settings: {})

data/lib/llm_meta_client/version.rb

@@ -1,3 +1,3 @@
 module LlmMetaClient
-  VERSION = "1.2.0"
+  VERSION = "1.3.0"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: llm_meta_client
 version: !ruby/object:Gem::Version
-  version: 1.2.0
+  version: 1.3.0
 platform: ruby
 authors:
 - dhq_boiler
@@ -125,6 +125,7 @@ files:
 - lib/generators/llm_meta_client/scaffold/templates/app/views/chats/_message.html.erb
 - lib/generators/llm_meta_client/scaffold/templates/app/views/chats/_messages_list.html.erb
 - lib/generators/llm_meta_client/scaffold/templates/app/views/chats/_streaming_message.html.erb
+- lib/generators/llm_meta_client/scaffold/templates/app/views/chats/_tool_call_message.html.erb
 - lib/generators/llm_meta_client/scaffold/templates/app/views/chats/create.turbo_stream.erb
 - lib/generators/llm_meta_client/scaffold/templates/app/views/chats/edit.html.erb
 - lib/generators/llm_meta_client/scaffold/templates/app/views/chats/new.html.erb