mirror of
https://github.com/discourse/discourse.git
synced 2026-08-09 21:45:25 +08:00
f86bdd738aApply token-budgeted agent execution and context compaction to all AI agent runs instead of gating it behind execution_mode. Remove the legacy fixed-limit agent settings, keep compression_threshold defaulted to 80, and trim prompt history from the latest compression checkpoint. Why: Preserving a stable compressed context across turns keeps important conversation state available while allowing newer messages to append to a consistent prefix. That improves cache reuse and avoids repeatedly throwing away useful context just to stay under model limits. Compaction shape: before: turn 1 [full -> compact] | turn 2 [full -> compact] after: [compact checkpoint] -> turn 1 -> turn 2 -> ... --------- Co-authored-by: Rafael Silva <xfalcox@gmail.com> |
||
|---|---|---|
| .. | ||
| tools | ||
| workflows/sql_action | ||
| admin_dashboard_report_provider.rb | ||
| ai_query_enqueuer.rb | ||
| ai_query_generator.rb | ||
| ai_query_params.rb | ||
| data_explorer.rb | ||
| engine.rb | ||
| parameter.rb | ||
| queries.rb | ||
| query_creator.rb | ||
| query_group_bookmarkable.rb | ||
| query_result_cache.rb | ||
| query_result_downloader.rb | ||
| query_runner.rb | ||
| report_generator.rb | ||
| result_format_converter.rb | ||
| result_to_markdown.rb | ||
| statistics.rb | ||
| validation_error.rb | ||
