alex/g3
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

adds cache_control

Browse Source
This commit is contained in:
Jochen
2025-11-18 22:38:52 +11:00
parent 39efa24c55
commit 296bf5a449
7 changed files with 466 additions and 125 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
config.coach-player.example.toml
View File

@@ -11,12 +11,23 @@ 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
[providers.anthropic]
api_key = "your-anthropic-api-key"
model = "claude-3-haiku-20240307" # Using a faster model for player
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.
[agent]
fallback_default_max_tokens = 8192