Implement planning mode

config.coach-player.example.toml

@@ -1,37 +1,73 @@
+# G3 Configuration Example - Coach/Player Mode
+#
+# This configuration demonstrates using different providers for coach and player
+# roles in autonomous mode. The coach reviews code while the player implements.
+
 [providers]
-default_provider = "databricks"
-# Specify different providers for coach and player in autonomous mode
-coach = "databricks"    # Provider for coach (code reviewer) - can be more powerful/expensive
-player = "anthropic"    # Provider for player (code implementer) - can be faster/cheaper
+# Default provider used when no specific provider is specified
+default_provider = "anthropic.default"
 
-[providers.databricks]
-host = "https://your-workspace.cloud.databricks.com"
-# token = "your-databricks-token"  # Optional - will use OAuth if not provided
-model = "databricks-claude-sonnet-4"
-max_tokens = 4096
-temperature = 0.1
-use_oauth = true
-# cache_config = "ephemeral"  # Optional: Enable prompt caching for Claude models
-                              # Options: "ephemeral", "5minute", "1hour"
-                              # Reduces costs and latency for repeated prompts. Uses Anthropic's prompt caching with different TTLs.
-                                # The cache control will be automatically applied to:
-                                # - The system prompt at the start of each session
-                                # - Assistant responses after every 10 tool calls
-                                # - 5minute costs $3/mtok, more details below
-                                # https://docs.claude.com/en/docs/build-with-claude/prompt-caching#pricing
+# Coach uses a model optimized for code review and analysis
+coach = "anthropic.coach"
 
-[providers.anthropic]
+# Player uses a model optimized for code generation
+player = "anthropic.player"
+
+# Optional: Use a specialized model for planning mode
+# planner = "anthropic.planner"
+
+# Default Anthropic configuration
+[providers.anthropic.default]
 api_key = "your-anthropic-api-key"
 model = "claude-sonnet-4-5"
-max_tokens = 4096
-temperature = 0.3  # Slightly higher temperature for more creative implementations
-# cache_config = "ephemeral"  # Optional: Enable prompt caching
-                              # Options: "ephemeral", "5minute", "1hour"
-                              # Reduces costs and latency for repeated prompts. Uses Anthropic's prompt caching with different TTLs.
-# enable_1m_context = true    # optional, more expensive
+max_tokens = 64000
+temperature = 0.2
+
+# Coach configuration - focused on careful analysis
+[providers.anthropic.coach]
+api_key = "your-anthropic-api-key"
+model = "claude-sonnet-4-5"
+max_tokens = 32000
+temperature = 0.1  # Lower temperature for more consistent reviews
+
+# Player configuration - focused on code generation
+[providers.anthropic.player]
+api_key = "your-anthropic-api-key"
+model = "claude-sonnet-4-5"
+max_tokens = 64000
+temperature = 0.3  # Slightly higher for more creative implementations
+
+# Optional: Planner configuration with extended thinking
+# [providers.anthropic.planner]
+# api_key = "your-anthropic-api-key"
+# model = "claude-opus-4-5"
+# max_tokens = 64000
+# thinking_budget_tokens = 16000  # Enable extended thinking for planning
+
+# Example: Using Databricks for one of the roles
+# [providers.databricks.default]
+# host = "https://your-workspace.cloud.databricks.com"
+# model = "databricks-claude-sonnet-4"
+# max_tokens = 4096
+# temperature = 0.1
+# use_oauth = true
 
 [agent]
 fallback_default_max_tokens = 8192
 enable_streaming = true
 timeout_seconds = 60
-allow_multiple_tool_calls = true  # Enable multiple tool calls, will usually only work with Anthropic
+max_retry_attempts = 3
+autonomous_max_retry_attempts = 6
+allow_multiple_tool_calls = true
+
+[computer_control]
+enabled = false
+require_confirmation = true
+max_actions_per_second = 5
+
+[webdriver]
+enabled = false
+safari_port = 4444
+
+[macax]
+enabled = false