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

feat(llm): enforce request precedence (#34440)

Browse source
This commit is contained in:
Shoubhit Dash 2026-06-29 19:24:37 +05:30 • committed by GitHub
commit 08c5a2a5e8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 173 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

3
packages/llm/src/protocols/anthropic-messages.ts
View file

@ -504,6 +504,7 @@ const lowerThinking = Effect.fn("AnthropicMessages.lowerThinking")(function* (re
const fromRequest = Effect.fn("AnthropicMessages.fromRequest")(function* (request: LLMRequest) {
const toolChoice = request.toolChoice ? yield* lowerToolChoice(request.toolChoice) : undefined
const generation = request.generation
const outputLimit = request.model.defaults?.limits?.output ?? request.model.route.defaults.limits?.output ?? 4096
// Allocate the 4-breakpoint budget in invalidation order: tools → system →
// messages. Tools live highest in the cache hierarchy, so when callers
// over-mark we keep their tool hints and shed the message-tail ones first.
@ -533,7 +534,7 @@ const fromRequest = Effect.fn("AnthropicMessages.fromRequest")(function* (reques
tools,
tool_choice: toolChoice,
stream: true as const,
max_tokens: generation?.maxTokens ?? request.model.route.defaults.limits?.output ?? 4096,
max_tokens: generation?.maxTokens ?? outputLimit,
temperature: generation?.temperature,
top_p: generation?.topP,
top_k: generation?.topK,