Skip to content

Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors

Rust

Merge origin/main into fix/anthropic-disabled-thinking

AkitaOnRails7660e95cb534
diff --cc CHANGELOG.md
index 1ed689af,2a8014cd..3a70a2c5
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@@ -28,11 -38,13 +38,18 @@@ version in [`docs/changelog/`](docs/cha
The PreCompact and PostCompaction checkpoint page uses the same bounded
reads. The writer's lifecycle-only re-check and the reader now build their
query from one shared predicate. (#1323)
+- Fixed `AI_MEMORY_LLM_REASONING_EFFORT=none` failing every Anthropic request
+ to Claude Opus 5.5 and Sonnet 5.5 with a 400. Both reject
+ `thinking: {"type": "disabled"}`. Opus 5.5 now gets no `thinking` field, as
+ Fable and Mythos already did, and Sonnet 5.5 gets
+ `thinking: {"type": "between_tools"}`, its way to turn thinking off. (#1326)
+ - Fixed the Anthropic provider rejecting any response that carried a
+ `thinking` or `redacted_thinking` block as an unknown variant. Claude
+ Opus 5, Sonnet 5, Haiku 5.5 and the later Opus, Sonnet, Fable and Mythos
+ models think when a request leaves `thinking` out, and Claude models from
+ 4.6 on are sent adaptive thinking once `AI_MEMORY_LLM_REASONING_EFFORT` is
+ set, so `memory_explore` and `ai-memory llm-test` failed as soon as the
+ model thought. The provider now skips the blocks it does not read. (#1325)
## [3.0.1] - 2026-10-15