ceos/opencode
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

refactor(ai): unify prompt cache configuration

Browse source
This commit is contained in:
Aiden Cline 2026-07-31 17:52:32 -05:00
commit a214ac39de
19 changed files with 64 additions and 59 deletions
Download patch file Download diff file Expand all files Collapse all files

9
packages/ai/example/tutorial.ts
View file

@ -33,9 +33,10 @@ const model = OpenAI.configure({
//
// - `generation`: common controls such as max tokens, temperature, topP/topK,
// penalties, seed, and stop sequences.
// - `cache`: provider-neutral prompt caching behavior and cache affinity.
// - `providerOptions`: namespaced provider-native behavior. For example,
// OpenAI cache keys and store behavior, Anthropic thinking, Gemini thinking
// config, or OpenRouter routing/reasoning.
// OpenAI store behavior, Anthropic thinking, Gemini thinking config, or
// OpenRouter routing/reasoning.
// - `http`: last-resort serializable overlays for final request body, headers,
// and query params. Prefer typed `providerOptions` when a field is stable.
//
@ -45,9 +46,7 @@ const request = LLM.request({
system: "You are concise and practical.",
prompt: "Tell me a joke",
generation: { maxTokens: 80, temperature: 0.7 },
providerOptions: {
openai: { promptCacheKey: "tutorial-joke" },
},
cache: { mode: "auto", key: "tutorial-joke" },
})
// 3. `generate` sends the request and collects the event stream into one