fix(agents): fix Brave llm-context empty snippets (#41387)

Merged via squash.

Prepared head SHA: 1e6f1d9d51
Co-authored-by: zheliu2 <15888718+zheliu2@users.noreply.github.com>
Co-authored-by: obviyus <22031114+obviyus@users.noreply.github.com>
Reviewed-by: @obviyus
This commit is contained in:
Zhe Liu
2026-03-09 22:39:57 -04:00
committed by GitHub
parent 1720174757
commit 25c2facc2b
4 changed files with 92 additions and 10 deletions

View File

@@ -41,6 +41,7 @@ Docs: https://docs.openclaw.ai
- Agents/fallback: treat HTTP 499 responses as transient in both raw-text and structured failover paths so Anthropic-style client-closed overload responses trigger model fallback reliably. (#41468) thanks @zeroasterisk.
- Plugins/context-engine model auth: expose `runtime.modelAuth` and plugin-sdk auth helpers so plugins can resolve provider/model API keys through the normal auth pipeline. (#41090) thanks @xinhuagu.
- CLI/memory teardown: close cached memory search/index managers in the one-shot CLI shutdown path so watcher-backed memory caches no longer keep completed CLI runs alive after output finishes. (#40389) thanks @Julbarth.
- Tools/web search: treat Brave `llm-context` grounding snippets as plain strings so `web_search` no longer returns empty snippet arrays in LLM Context mode. (#41387) thanks @zheliu2.
## 2026.3.8