bitfab 0.12.4 → 0.14.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: df5d0efa5533cd59dcfb77a2414e7a55963c51f6798e9ada18adaa1c41d1ead5
-  data.tar.gz: ca45c66023664f8c1ba7a3cdd4d89bba71b093150d93fce7cdf69810c56babb3
+  metadata.gz: d6264d16b3fdf093418d97c43141db5a83e890d0b5e8993f255498c01548c31b
+  data.tar.gz: 158be7664defce737b4b6e3a1db39f6bf13fee37aee9f9948fb63f7b2dd2a254
 SHA512:
-  metadata.gz: 3ca91c9fac20958f69b45e99e197116834ff0740ae3a7d8231e15fe1bc4f35fb4e874d3fce84fb4597d0a8253742d88d084538cfa7fa9806d85b935320eb8591
-  data.tar.gz: db85971ed1a07a084ab2e8c8a8b631e4cac0c148e33d116e9aaa856a41230f0d6de8b4efd819e7b372c1ccbe3d75287f6014e9ed5b690472c4fd0f832d77d369
+  metadata.gz: cb6a19c8fcfd500c58e0bbf7a1332fb27b6701282cc859bf2590477bae8fd4aaf871e37e15fc9eb0f70cbe7c121b5550f1d7ce536d771992282e0484eb545d1e
+  data.tar.gz: b6ab4f9aa78b82b8a14d993e1357ae9db9fd09447a16ea8e5ff301998504548f7d54339923f238e4065661fcc61e8ae3db2171a8b4c00f30b1695d20f87d7546

data/lib/bitfab/client.rb

@@ -39,8 +39,10 @@ module Bitfab
     # @param receiver [Object, Class] an instance for instance methods, or a Class for class methods
     # @param method_name [Symbol] the method to replay
     # @param trace_function_key [String] the trace function key for this method
-    # @param limit [Integer] maximum number of traces to replay (default: 5)
-    # @param trace_ids [Array<String>, nil] optional list of trace IDs to filter
+    # @param limit [Integer, nil] maximum number of traces to replay (default: 5).
+    #   Mutually exclusive with trace_ids: an explicit ID list already
+    #   determines how many traces replay, so passing both raises.
+    # @param trace_ids [Array<String>, nil] optional list of trace IDs to replay (max 100)
     # @param max_concurrency [Integer, nil] max threads for parallel replay (default: 10)
     # @param code_change_description [String, nil] optional rationale for the
     #   code change being tested in this replay (stored on the experiment)
@@ -52,7 +54,7 @@ module Bitfab
     #   "all", or "marked". "all" mocks every child span; "marked" only mocks
     #   spans declared with mock_on_replay: true.
     # @return [Hash] with :items, :test_run_id, :test_run_url
-    def replay(receiver, method_name, trace_function_key:, limit: 5, trace_ids: nil, max_concurrency: 10,
+    def replay(receiver, method_name, trace_function_key:, limit: nil, trace_ids: nil, max_concurrency: 10,
       code_change_description: nil, code_change_files: nil, experiment_group_id: nil, mock: "none")
       Replay.run(
         self, receiver, method_name,

data/lib/bitfab/http_client.rb

@@ -108,9 +108,11 @@ module Bitfab
     def start_replay(trace_function_key, limit, trace_ids: nil, code_change_description: nil,
       code_change_files: nil, experiment_group_id: nil)
       payload = {
-        "traceFunctionKey" => trace_function_key,
-        "limit" => limit
+        "traceFunctionKey" => trace_function_key
       }
+      # limit is only meaningful without trace_ids (an explicit ID list
+      # already determines the count), so it's omitted when nil.
+      payload["limit"] = limit unless limit.nil?
       payload["traceIds"] = trace_ids if trace_ids
       payload["codeChangeDescription"] = code_change_description unless code_change_description.nil?
       payload["codeChangeFiles"] = normalize_code_change_files(code_change_files) unless code_change_files.nil?

data/lib/bitfab/replay.rb

@@ -56,8 +56,10 @@ module Bitfab
     # @param receiver [Object, Class] an instance for instance methods, or a Class for class methods
     # @param method_name [Symbol] the method to replay
     # @param trace_function_key [String] the trace function key for this method
-    # @param limit [Integer] maximum number of traces to replay (default: 5)
-    # @param trace_ids [Array<String>, nil] optional list of trace IDs to filter
+    # @param limit [Integer, nil] maximum number of traces to replay (default: 5).
+    #   Mutually exclusive with trace_ids: an explicit ID list already
+    #   determines how many traces replay, so passing both raises.
+    # @param trace_ids [Array<String>, nil] optional list of trace IDs to replay (max 100)
     # @param max_concurrency [Integer, nil] max threads for parallel replay (default: 10)
     # @param code_change_description [String, nil] optional rationale for the
     #   code change being tested in this replay (stored on the experiment)
@@ -69,17 +71,31 @@ module Bitfab
     #   "all", or "marked". "all" mocks every child span; "marked" only mocks
     #   spans declared with mock_on_replay: true.
     # @return [Hash] with :items, :test_run_id, :test_run_url
-    def run(client, receiver, method_name, trace_function_key:, limit: 5, trace_ids: nil, max_concurrency: 10,
+    def run(client, receiver, method_name, trace_function_key:, limit: nil, trace_ids: nil, max_concurrency: 10,
       code_change_description: nil, code_change_files: nil, experiment_group_id: nil, mock: "none")
       unless MOCK_STRATEGIES.include?(mock.to_s)
         raise ArgumentError, "Invalid mock strategy '#{mock}'. Must be one of: #{MOCK_STRATEGIES.join(", ")}"
       end
+      if trace_ids
+        raise ArgumentError, "trace_ids must contain at least one trace ID." if trace_ids.empty?
+        if trace_ids.length > 100
+          raise ArgumentError, "trace_ids supports at most 100 trace IDs per replay (got #{trace_ids.length})."
+        end
+      end
+      if limit && trace_ids
+        raise ArgumentError,
+          "Pass either limit or trace_ids, not both: an explicit trace ID list already determines how many traces replay."
+      end
 
       http_client = client.instance_variable_get(:@http_client)
 
+      # limit is meaningless with explicit trace_ids (the ID list determines
+      # the count), so it's omitted from the request entirely.
+      effective_limit = trace_ids ? nil : (limit || 5)
+
       replay_data = http_client.start_replay(
         trace_function_key,
-        limit,
+        effective_limit,
         trace_ids:,
         code_change_description:,
         code_change_files:,
@@ -147,10 +163,16 @@ module Bitfab
     end
 
     # Fetch span data and execute a single replay item.
+    #
+    # Any error while fetching the span, building the mock tree, or
+    # deserializing inputs is captured on the returned item's :error rather
+    # than propagated, so one bad trace never aborts the whole replay run
+    # (mirrors the TypeScript and Python SDKs' per-item rescue).
     def process_single_item(http_client, server_item, receiver, method_name, test_run_id, mock_strategy)
+      metrics = extract_server_item_metrics(server_item)
+
       span = http_client.get_external_span(server_item["externalSpanId"])
       item_data = extract_span_data(span)
-      metrics = extract_server_item_metrics(server_item)
 
       mock_tree = nil
       if mock_strategy == "all" || mock_strategy == "marked"
@@ -169,6 +191,18 @@ module Bitfab
         mock_strategy:,
         mock_tree:
       )
+    rescue => e
+      warn "Bitfab: replay item for span #{server_item["externalSpanId"]} failed before execution: #{e.message}"
+      {
+        input: [],
+        result: nil,
+        original_output: nil,
+        error: e.message,
+        duration_ms: metrics&.dig(:duration_ms),
+        tokens: metrics&.dig(:tokens),
+        model: metrics&.dig(:model),
+        trace_id: nil
+      }
     end
 
     # Walk the children of a root span tree node depth-first and build a

data/lib/bitfab/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Bitfab
-  VERSION = "0.12.4"
+  VERSION = "0.14.0"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: bitfab
 version: !ruby/object:Gem::Version
-  version: 0.12.4
+  version: 0.14.0
 platform: ruby
 authors:
 - Harvest Team