picoclaw/pkg/agent
Guoguo 028605cfd0
feat: execute LLM tool calls in parallel for faster response (#1070)
When the LLM returns multiple tool calls, they are now executed
concurrently using goroutines + sync.WaitGroup instead of sequentially.
Results are collected in an indexed slice and processed in original order
to preserve message ordering. MessageTool.sentInRound is changed to
atomic.Bool for thread safety.

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-04 17:17:28 +08:00
..
context.go Merge pull request #1020 from shikihane/feat/agent-vision-pipeline-v2 2026-03-03 18:35:23 +08:00
context_cache_test.go fix(agent): invalidate system prompt cache for global/builtin skills (#845) 2026-03-03 18:25:00 +08:00
context_test.go fix: handle multi-tool-call orphan detection in sanitizeHistoryForProvider 2026-02-24 21:35:15 +08:00
instance.go feat: make summarization message threshold and token percent configurable (#854) (#1029) 2026-03-04 11:23:01 +08:00
instance_test.go enable dupl check 2026-03-01 18:17:32 +11:00
loop.go feat: execute LLM tool calls in parallel for faster response (#1070) 2026-03-04 17:17:28 +08:00
loop_media.go fix: resolve linter issues (gci import grouping, gofumpt, govet shadow) 2026-03-03 17:04:54 +08:00
loop_test.go fix: resolve linter issues (gci import grouping, gofumpt, govet shadow) 2026-03-03 17:04:54 +08:00
memory.go refactor(modernize): apply safe modernize fixes 2026-02-27 16:35:07 +08:00
mock_provider_test.go feat(fmt): Fix formatting 2026-02-19 22:05:15 +02:00
registry.go feat(fmt): Run formatters 2026-02-18 21:48:23 +02:00
registry_test.go feat(fmt): Run formatters 2026-02-18 21:48:23 +02:00