zeroclaw/tests
Argenis 95bf229225
fix(config): enable compact_context by default (#3995)
* fix: change compact_context default to true

Local LLMs with limited context windows immediately run out of context
when compact_context defaults to false. The system prompt alone can
consume 25K+ tokens, exceeding even 55K context windows with history.

Setting compact_context=true by default limits system prompt injection
to 6000 chars and RAG results to 2 chunks, making the agent usable
with smaller models out of the box.

Fixes #3987

* docs: update compact_context default to true in config reference

Update all locale variants (en, zh-CN, vi) to reflect the new default.

* test: update tests to expect compact_context default of true

Update assertions in schema.rs unit tests and config_persistence.rs
component tests to match the new default value.
2026-03-19 15:13:14 -04:00
..
component fix(config): enable compact_context by default (#3995) 2026-03-19 15:13:14 -04:00
fixtures test: restructure test suite into five-level taxonomy 2026-03-11 11:03:33 -04:00
integration fix(telegram): avoid duplicate finalize_draft messages (#3259) 2026-03-16 18:24:19 -04:00
live feat(runtime): add configurable reasoning effort (#3785) 2026-03-17 09:21:53 -04:00
manual fix(docs): remove stale onboarding flags after CLI changes (#3516) 2026-03-14 17:54:14 -04:00
support fix(memory): filter autosave noise and scope recall/store by session (#3695) 2026-03-16 16:36:35 -04:00
system test: restructure test suite into five-level taxonomy 2026-03-11 11:03:33 -04:00
test_component.rs test: restructure test suite into five-level taxonomy 2026-03-11 11:03:33 -04:00
test_integration.rs test: restructure test suite into five-level taxonomy 2026-03-11 11:03:33 -04:00
test_live.rs test: restructure test suite into five-level taxonomy 2026-03-11 11:03:33 -04:00
test_system.rs test: restructure test suite into five-level taxonomy 2026-03-11 11:03:33 -04:00