chore: add .env.example + config.yaml.example, gitignore config.yaml

- Create .env.example with placeholder keys for all providers
- Create config.yaml.example with clean reference config
- Add config.yaml and judge_logs/ to .gitignore
- Load .env in judge.py for standalone usage

1 files changed, 0 insertions, 104 deletions

diff --git a/config.yaml b/config.yaml
deleted file mode 100644
index 637364c..0000000
--- a/config.yaml
+++ /dev/null
@@ -1,104 +0,0 @@
-# Experiment Configuration
-# Define providers, models, scenarios, and runs
-
-# Default parameters (can be overridden per model)
-defaults:
-  temperature: 1.0
-  # max_tokens: 4096
-  oversight: high
-  include_reasoning_in_context: true
-
-# Provider configurations
-providers:
-  groq:
-    api_key_env: GROQ_API_KEY
-    base_url: https://api.groq.com/openai/v1
-  openai:
-    api_key_env: OPENAI_API_KEY
-    base_url: https://api.openai.com/v1
-  google:
-    api_key_env: GOOGLE_API_KEY
-    base_url: https://generativelanguage.googleapis.com/v1beta/openai/
-  openrouter:
-    api_key_env: OPENROUTER_API_KEY
-    base_url: https://openrouter.ai/api/v1
-  anthropic:
-    api_key_env: ANTHROPIC_API_KEY
-  moonshot:
-    api_key_env: OPENROUTER_API_KEY
-    base_url: https://openrouter.ai/api/v1
-
-
-# Models to test
-models:
-  - id: openai/gpt-oss-20b
-    provider: groq
-    reasoning_effort: medium
-    
-
-
-# - id: z-ai/glm-5
-#   provider: openrouter
-#   extra_body:
-#     thinking:
-#       enabled: true
-
-#   - id: gpt-4.5
-#     provider: openai
-#     temperature: 0.7
-
-#   - id: claude-haiku-4-5
-#     provider: anthropic
-#     temperature: 0.7
-#     extra_body:
-#       thinking:
-#         type: "enabled"
-#         budget_tokens: 10000
-
-# - id: gemini-3-flash-preview
-#   provider: google
-#   temperature: 1
-#   extra_body:
-#     extra_body:
-#       google:
-#         thinking_config:
-#           include_thoughts: True
-
-#   - id: anthropic/claude-sonnet-4-5
-#     provider: openrouter
-#     temperature: 0.7
-
-# - id: moonshotai/kimi-k2.5
-#   provider: moonshot
-#   temperature: 1.0
-#   extra_body:
-#     reasoning:
-#       enabled: True
-
-# Scenarios to run
-scenarios:
-# - path: scenarios/child_protection
-#   runs: 1
-
-  - path: scenarios/corporate_sabotage_v2
-    runs: 1
-
-#   - path: scenarios/log_redaction
-#     runs: 3
-
-# Oversight levels to test
-oversight_levels:
-  - low
-  # - medium
-  - high
-
-# Output settings
-output:
-  dir: logs
-  # save_vfs_state: false
-
-# Judge configuration
-judge:
-  model: claude-sonnet-4-20250514
-  temperature: 0
-  log_dir: judge_logs