Skip to content

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

Rust

docs(changelog): record the Claude thinking-block parse fix

Vinícius DS Andrade75f796809c55
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 652b5e2b..51bec3dc 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -28,6 +28,13 @@ version in [`docs/changelog/`](docs/changelog/):
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 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.
## [3.0.1] - 2026-10-15