mirror of
https://github.com/discourse/discourse-ai.git
synced 2025-07-08 23:32:45 +00:00
d72ad84f8f
The structured output JSON comes embedded inside the API response, which is also a JSON. Since we have to parse the response to process it, any control characters inside the structured output are unescaped into regular characters, leading to invalid JSON and breaking during parsing. This change adds a retry mechanism that escapes
the string again if parsing fails, preventing the parser from breaking on malformed input and working around this issue.
For example:
```
original = '{ "a": "{\\"key\\":\\"value with \\n newline\\"}" }'
JSON.parse(original) => { "a" => "{\"key\":\"value with \n newline\"}" }
# At this point, the inner JSON string contains an actual newline.
```
72 lines
2.1 KiB
Ruby
72 lines
2.1 KiB
Ruby
# frozen_string_literal: true
|
|
|
|
module DiscourseAi
|
|
module Completions
|
|
class JsonStreamingTracker
|
|
attr_reader :current_key, :current_value, :stream_consumer
|
|
|
|
def initialize(stream_consumer)
|
|
@stream_consumer = stream_consumer
|
|
@current_key = nil
|
|
@current_value = nil
|
|
@parser = DiscourseAi::Completions::JsonStreamingParser.new
|
|
|
|
@parser.key do |k|
|
|
@current_key = k
|
|
@current_value = nil
|
|
end
|
|
|
|
@parser.value do |v|
|
|
if @current_key
|
|
stream_consumer.notify_progress(@current_key, v)
|
|
@current_key = nil
|
|
end
|
|
end
|
|
end
|
|
|
|
def broken?
|
|
@broken
|
|
end
|
|
|
|
def <<(raw_json)
|
|
# llm could send broken json
|
|
# in that case just deal with it later
|
|
# don't stream
|
|
return if @broken
|
|
|
|
begin
|
|
@parser << raw_json
|
|
rescue DiscourseAi::Completions::ParserError
|
|
# Note: We're parsing JSON content that was itself embedded as a string inside another JSON object.
|
|
# During the outer JSON.parse, any escaped control characters (like "\\n") are unescaped to real characters ("\n"),
|
|
# which corrupts the inner JSON structure when passed to the parser here.
|
|
# To handle this, we retry parsing with the string JSON-escaped again (`.dump[1..-2]`) if the first attempt fails.
|
|
try_escape_and_parse(raw_json)
|
|
return if @broken
|
|
end
|
|
|
|
if @parser.state == :start_string && @current_key
|
|
# this is is worth notifying
|
|
stream_consumer.notify_progress(@current_key, @parser.buf)
|
|
end
|
|
|
|
@current_key = nil if @parser.state == :end_value
|
|
end
|
|
|
|
private
|
|
|
|
def try_escape_and_parse(raw_json)
|
|
if raw_json.blank? || !raw_json.is_a?(String)
|
|
@broken = true
|
|
return
|
|
end
|
|
# Escape the string as JSON and remove surrounding quotes
|
|
escaped_json = raw_json.dump[1..-2]
|
|
@parser << escaped_json
|
|
rescue DiscourseAi::Completions::ParserError
|
|
@broken = true
|
|
end
|
|
end
|
|
end
|
|
end
|