vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-08-02 08:11:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor(config): retire redundant settings (#113174)

Browse Source 
* refactor(config): retire redundant settings

* style: apply current formatter

* chore: update plugin sdk baseline

* fix: keep Codex tool caps context-aware

* chore: remove stale imports

* test: align WhatsApp QA debounce config

* fix(config): clean up retired config checks

* fix(ci): align config cleanup checks
This commit is contained in:
Peter Steinberger
2026-07-23 17:45:02 -07:00
committed by GitHub
parent 1603781bb0
commit bb657eec93
99 changed files with 796 additions and 1445 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
docs/reference/token-use.md
View File

@@ -71,19 +71,17 @@ Runtime-heavy surfaces have their own explicit caps under
| Key | Purpose |
| ------------------------ | ------------------------------------------------------------------------ |
| `memoryGetMaxChars` | Max characters `memory_get` returns before truncation. |
| `memoryGetDefaultLines` | Default `memory_get` line window when a request omits `lines`. |
| `toolResultMaxChars` | Advanced ceiling for a single live tool result (up to `1000000` chars). |
| `postCompactionMaxChars` | Max characters retained from `AGENTS.md` during post-compaction refresh. |
These are bounded runtime excerpts and injected runtime-owned blocks,
separate from bootstrap limits, startup-context limits, and skills prompt
limits.
`toolResultMaxChars` is unset by default, so OpenClaw derives the live
tool-result cap from the effective model context window: `16000` chars below
OpenClaw derives the live tool-result cap from the effective model context
window: `16000` chars below
100K tokens, `32000` chars at 100K+ tokens, `64000` chars at 200K+ tokens.
The runtime context-share guard still caps a single tool result at 30% of the
context window even when a larger explicit ceiling is configured.
The runtime context-share guard also caps a single tool result at 30% of the
context window.
Large provider windows are not enabled automatically when they materially
change cost or latency. For example, direct OpenAI GPT-5.5 and GPT-5.6 models