The compression threshold is threshold × context_length where context_length is the MAIN agent model's window, not the auxiliary/summary model's. On a 262,144-token model at the default 0.50 the threshold is 131,072 — close to a common 128K figure by coincidence of the percentage, which has led to confusion that the auxiliary model's context limit is the trigger. Add a note preempting that misreading and pointing to the separate summary-model-context constraint. |
||
|---|---|---|
| .. | ||
| _category_.json | ||
| acp-internals.md | ||
| adding-platform-adapters.md | ||
| adding-providers.md | ||
| adding-tools.md | ||
| agent-loop.md | ||
| architecture.md | ||
| browser-supervisor.md | ||
| context-compression-and-caching.md | ||
| context-engine-plugin.md | ||
| contributing.md | ||
| creating-skills.md | ||
| cron-internals.md | ||
| extending-the-cli.md | ||
| gateway-internals.md | ||
| image-gen-provider-plugin.md | ||
| memory-provider-plugin.md | ||
| model-provider-plugin.md | ||
| plugin-llm-access.md | ||
| programmatic-integration.md | ||
| prompt-assembly.md | ||
| provider-runtime.md | ||
| session-storage.md | ||
| tools-runtime.md | ||
| trajectory-format.md | ||
| video-gen-provider-plugin.md | ||
| web-search-provider-plugin.md | ||