lkn
/
ollie-core
Archived
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
This repository has been archived on 2026-08-16. You can view files and clone it, but cannot push or open issues or pull requests.
ollie-core/pkg/backend
History
Levi Neely efac665ffe core: tool schema caching and large tool result caching 
Tool schema caching:
- Mark the last tool with cache_control:ephemeral before each Anthropic
  request; Anthropic caches all preceding tools as a prefix
- Same for OpenRouter+Claude via openAITool.CacheControl extension

Large tool result caching (Anthropic only):
- In buildAnthropicMessages, scan backwards through the encoded output
  and mark the last tool_result block ≥4096 bytes with cache_control
- 4096 bytes ≈ 1024 tokens, Anthropic's minimum cache entry size
- OpenAI wire format has no block structure for tool results; skip

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 		2026-04-28 12:22:45 +02:00
..
anthropic.go core: tool schema caching and large tool result caching 2026-04-28 12:22:45 +02:00
anthropic_stream_test.go core: Anthropic prompt caching and cache-aware cost accounting 2026-04-28 12:01:14 +02:00
backend.go core: Anthropic prompt caching and cache-aware cost accounting 2026-04-28 12:01:14 +02:00
backend_test.go agent: retry on transient backend errors and mid-stream drops 2026-04-27 17:54:27 +02:00
codewhisperer.go kiro: implement social token refresh via desktop.kiro.dev 2026-04-26 18:11:21 +02:00
codewhisperer_internal.go kiro: implement social token refresh via desktop.kiro.dev 2026-04-26 18:11:21 +02:00
copilot.go backend: extract stream parsers, shared HTTP, url.URL, comprehensive tests 2026-04-21 15:32:03 +02:00
new.go backend: require OLLIE_BACKEND/OLLIE_MODEL; no silent ollama default 2026-04-26 18:25:39 +02:00
new_test.go backend: require OLLIE_BACKEND/OLLIE_MODEL; no silent ollama default 2026-04-26 18:25:39 +02:00
ollama.go backend: remove unreachable NewRequestWithContext guards (URL validated in ctor) 2026-04-21 15:47:34 +02:00
ollama_stream_test.go backend: extract parseOllamaContextLength, 100% coverage 2026-04-21 15:39:52 +02:00
openai.go core: tool schema caching and large tool result caching 2026-04-28 12:22:45 +02:00
openai_encode_test.go core: cache system prompt on OpenRouter+Claude via content block encoding 2026-04-28 12:14:46 +02:00
openai_stream_test.go backend: extract stream parsers, shared HTTP, url.URL, comprehensive tests 2026-04-21 15:32:03 +02:00
openai_test.go backend: extract stream parsers, shared HTTP, url.URL, comprehensive tests 2026-04-21 15:32:03 +02:00
testhelper_test.go backend: extract stream parsers, shared HTTP, url.URL, comprehensive tests 2026-04-21 15:32:03 +02:00