docs: update changelog for memory fixes · openclaw/openclaw@c2ea0ce
steipete
·
2026-04-26
·
via Recent Commits to openclaw:main
| Original file line number | Diff line number | Diff line change |
|---|
@@ -111,6 +111,12 @@ Docs: https://docs.openclaw.ai
|
111 | 111 | - Providers/Ollama: use Ollama's current `/api/web_search` endpoint and honor |
112 | 112 | `https://ollama.com` model-provider base URLs for Ollama Web Search. Fixes |
113 | 113 | #71741. Thanks @madhvidua. |
| 114 | +- Memory/Ollama: serialize Ollama memory embedding batches and add an inline |
| 115 | + batch timeout override, with longer defaults for local/self-hosted embedding |
| 116 | + providers. Thanks @steipete. |
| 117 | +- Sessions/usage: exclude compaction checkpoint transcript snapshots from usage |
| 118 | + totals and session discovery, while keeping old checkpoint files removable. |
| 119 | + Thanks @steipete. |
114 | 120 | - CLI/agents: keep `openclaw agents list --json` on the config-only path by |
115 | 121 | default, avoiding bundled plugin loading unless callers request |
116 | 122 | `--bindings`. Fixes #71739. Thanks @kaloster. |
|
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。
