From 9155f664a2db0abe841d0d7b9b059ffbe2290c18 Mon Sep 17 00:00:00 2001 From: CaptainJack2491 Date: Fri, 10 Apr 2026 14:50:40 +0100 Subject: refactor(judge): simplify to single judge per prong, remove multi-model aggregation - Remove multi-model aggregation support from Judge class - Single blackbox judge: claude-sonnet-4-20250514 (anthropic) - Single glassbox judge: gpt-4.1 (openai) - Remove aggregate_results method and all aggregation-related code - Simplify batch collection to single result per run - Update config_dryrun.yaml with new judge configuration --- config_dryrun.yaml | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'config_dryrun.yaml') diff --git a/config_dryrun.yaml b/config_dryrun.yaml index 1bb99da..cd362ba 100644 --- a/config_dryrun.yaml +++ b/config_dryrun.yaml @@ -12,19 +12,19 @@ models: provider: openrouter extra_body: reasoning: - effort: "high" # Using low for dry run to save tokens + effort: "high" exclude: false - id: z-ai/glm-5 provider: openrouter extra_body: reasoning: - effort: "high" # Using low for dry run to save tokens + effort: "high" exclude: false - id: deepseek/deepseek-v3.2 provider: openrouter extra_body: reasoning: - effort: "high" # Using low for dry run to save tokens + effort: "high" exclude: false goal_types: @@ -51,3 +51,16 @@ logging: format: "[{level}] {message}" output: both file: logs/dry_run.log + +judge: + log_dir: logs/judge_dryrun + + blackbox: + model: claude-sonnet-4-20250514 + provider: anthropic + temperature: 0 + + glassbox: + model: gpt-4.1 + provider: openai + temperature: 0 -- cgit v1.2.3