 Matthew Meszaros
|
7f1bae8cac
|
feat: default the OpenAI writing, agent and warmup content batch models to gpt-6-luna instead of gpt-4o-mini, gpt-4o and gpt-5-mini, and document the new preset default in the deployment guide
|
2026-09-25 20:18:26 -07:00 |
|
|
Matthew Meszaros
|
29e3bb3a64
|
feat: drop the legacy OPENAI_*/ANTHROPIC_API_KEY/AI_LOCAL_MODEL env fallbacks (no prod deployments exist): AI_PROVIDER/AI_API_KEY/AI_MODEL/AI_BASE_URL/AI_FREE are the only AI vars, empty provider means openai, the anthropic preset and writing client key off AI_API_KEY, and the warmup Batch generator runs only when the selected provider is OpenAI
|
2026-07-16 06:39:06 +02:00 |
|
|
Matthew Meszaros
|
9d76685fb2
|
feat: add generation.Resolve mapping an AI_PROVIDER preset (openai/openrouter/groq/ollama/anthropic/custom) plus AI_API_KEY/AI_MODEL/AI_BASE_URL/AI_FREE into a provider config, erroring on a base-less custom provider instead of leaking the key to OpenAI
|
2026-07-16 06:14:19 +02:00 |
|