mirror of
https://github.com/openclaw/openclaw.git
synced 2026-05-06 09:30:43 +00:00
docs(heartbeat): clarify runtime model preservation
This commit is contained in:
@@ -38,7 +38,7 @@ Docs: https://docs.openclaw.ai
|
||||
- Control UI/chat: show inline feedback when local slash-command dispatch is unavailable or fails unexpectedly instead of clearing the composer silently. Fixes #52105. Thanks @MooreQiao.
|
||||
- Memory/markdown: replace CRLF managed blocks in place and collapse duplicate marker blocks without rewriting unmanaged markdown, so Dreaming and Memory Wiki files self-heal from repeated generated sections. Fixes #75491; supersedes #75495, #75810, and #76008. Thanks @asaenokkostya-coder, @ottodeng, @everettjf, and @lrg913427-dot.
|
||||
- Agents/tools: return critical tool-loop circuit-breaker stops as blocked tool results instead of thrown tool failures, so models see the guardrail and stop retrying the same call. Thanks @rayraiser.
|
||||
- Agents/sessions: preserve pre-existing runtime model and context window after heartbeat turns so a per-run heartbeat model override does not bleed into shared-session status. Fixes #75452. Thanks @zhang-guiping.
|
||||
- Agents/sessions: preserve pre-existing runtime model and context window after heartbeat turns so a per-run heartbeat model override does not bleed into shared-session status. Fixes #75452. Thanks @zhangguiping-xydt.
|
||||
- Model commands: clarify direct and inline `/model` acknowledgements for non-default selections as session-scoped. Thanks @addu2612.
|
||||
- Doctor/gateway: stop warning that non-existent, unconfigured user-bin directories are required in the Gateway service PATH. Fixes #76017. Thanks @xiphis.
|
||||
- TUI/chat: skip full provider model normalization during context-window warmup while preserving provider-owned context metadata, avoiding cold-start stalls with large model registries. Thanks @547895019.
|
||||
|
||||
@@ -479,9 +479,9 @@ Heartbeats run full agent turns. Shorter intervals burn more tokens. To reduce c
|
||||
|
||||
## Context overflow after heartbeat
|
||||
|
||||
If a heartbeat uses a smaller local model, for example an Ollama model with a 32k window, and the next main-session turn reports context overflow, check whether the previous heartbeat left the session on the heartbeat model. OpenClaw's reset message calls this out when the last runtime model matches configured `heartbeat.model`.
|
||||
If a heartbeat previously left an existing session on a smaller local model, for example an Ollama model with a 32k window, and the next main-session turn reports context overflow, reset the session runtime model back to the configured primary model. OpenClaw's reset message calls this out when the last runtime model matches configured `heartbeat.model`.
|
||||
|
||||
Use `isolatedSession: true` to run heartbeats in a fresh session, combine it with `lightContext: true` for the smallest prompt, or choose a heartbeat model with a context window large enough for the shared session.
|
||||
Current heartbeats preserve the shared session's existing runtime model after the run completes. You can still use `isolatedSession: true` to run heartbeats in a fresh session, combine it with `lightContext: true` for the smallest prompt, or choose a heartbeat model with a context window large enough for the shared session.
|
||||
|
||||
## Related
|
||||
|
||||
|
||||
Reference in New Issue
Block a user