Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
Rust
Merge pull request #1109 from viniciusdsandrade/fix/mcp-feedback-reason-scrub-before-cap
Fabio Akitab9b8bf026f08
diff --cc CHANGELOG.mdindex e7531d41,1d77b242..8793f4d5--- a/CHANGELOG.md+++ b/CHANGELOG.md@@@ -323,19 -313,11 +323,22 @@@ and this project adheres to [Semantic Vbefore use or persistence. Invalid historical identities were projected asunknown (`native_session_id: ""`) in workstream search without rewritingstored history; the CLI also protected reads from older servers. (#1079)+- Ordered the default single-page and batch consolidation prompts for+ prefix-cache reuse: in the user content, the fixed batch text (header ++ field schema) and the project instructions now lead, followed by the+ current body / slot and title state, with the session id and the+ observation dump last. In the single-page prompt the current body is+ the session's own page body, so the prefix shared across sessions of+ one project is the system prompt plus the instructions block when+ present. The system prompt, budget math, clipping, and observation+ selection are unchanged — blocks were only permuted — and the input+ budget remains an approximate character estimate (no tokenizer+ ceiling, no cache hit guaranteed). (#1102)### Fixed+ - Fixed `memory_feedback` storing an unmatched secret prefix when a `reason`+ straddled the 500-character cap: the reason is now scrubbed before the cap+ is applied, matching the #980 title-hint order. (#1109)- Fixed hook `title_hint` extraction leaving a trailing CR on Windows CRLFpayloads and keeping embedded newlines on SessionStart, Notification, andPostCompaction titles. First-line splitting now uses `str::lines`. (#1111)