vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-06 14:40:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: typography hygiene + 2 in-body H1 removals across 5 pages

Browse Source
This commit is contained in:
Vincent Koc
2026-05-05 21:01:08 -07:00
parent f35fb7288a
commit 0d73f174a9
5 changed files with 24 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/concepts/agent-loop.md
View File

@@ -6,8 +6,8 @@ read_when:
title: "Agent loop"
---
An agentic loop is the full “real” run of an agent: intake → context assembly → model inference →
tool execution → streaming replies → persistence. It’s the authoritative path that turns a message
An agentic loop is the full "real" run of an agent: intake → context assembly → model inference →
tool execution → streaming replies → persistence. It's the authoritative path that turns a message
into actions and a final reply, while keeping session state consistent.
In OpenClaw, a loop is a single, serialized run per session that emits lifecycle and stream events
@@ -67,7 +67,7 @@ wired end-to-end.
## Prompt assembly + system prompt
- System prompt is built from OpenClaw’s base prompt, skills prompt, bootstrap context, and per-run overrides.
- System prompt is built from OpenClaw's base prompt, skills prompt, bootstrap context, and per-run overrides.
- Model-specific limits and compaction reserve tokens are enforced.
- See [System prompt](/concepts/system-prompt) for what the model sees.