mirror of
https://gh.wpcy.net/https://github.com/discourse/discourse.git
synced 2026-06-19 03:23:50 +08:00
b8abe100c5
Introduce an "agentic" execution mode as an alternative to the default fixed-turn/tool-limit approach. In agentic mode, personas use a configurable token budget (`max_turn_tokens`) to govern how long a tool-use session can run, with automatic context compression when the conversation exceeds a configurable threshold percentage (`compression_threshold`) of the model's context window. Key changes: - Add `execution_mode`, `max_turn_tokens`, and `compression_threshold` columns to `ai_personas` via migration - Refactor `Bot#reply` to support token-budget loop control with a thread-local token accumulator, budget exhaustion hints, and a safety valve at 100 completions - Add `maybe_compress_context` which summarizes middle conversation messages when token usage crosses the compression threshold, preserving system prompt and recent tail messages - Update `StreamReplyCustomToolsSession` to track accumulated tokens across rounds and handle budget exhaustion in the custom tools path - Discount cached tokens (Anthropic) in the token accumulator to avoid over-counting reused KV cache prefixes - Update persona editor UI with execution mode selector and conditional fields (agentic shows token budget/compression; default shows max context posts)
16 lines
469 B
Ruby
Vendored
16 lines
469 B
Ruby
Vendored
# frozen_string_literal: true
|
|
|
|
module DiscourseAi
|
|
module Completions
|
|
class ExecutionContext
|
|
attr_accessor :token_usage_tracker
|
|
attr_reader :audit_logger, :structured_audit_logger
|
|
|
|
def initialize(token_usage_tracker: nil, audit_logger: nil, structured_audit_logger: nil)
|
|
@token_usage_tracker = token_usage_tracker
|
|
@audit_logger = audit_logger
|
|
@structured_audit_logger = structured_audit_logger
|
|
end
|
|
end
|
|
end
|
|
end
|
