release: prepare v0.3.0-probe notes

This commit is contained in:
2026-03-13 08:10:33 +10:00
parent c4438d8129
commit 9eb3347a5c
2 changed files with 47 additions and 9 deletions
+28
View File
@@ -0,0 +1,28 @@
# Changelog
## v0.3.0-probe — 2026-03-13
### Summary
This release marks the transition from a skill-only continuity package to a
**dual-form package**:
- the existing `SKILL.md` remains the fallback behavior contract
- a new **lifecycle plugin probe** is included to validate the primary runtime path
### Added
- `plugin/lifecycle-prototype.ts`
- `references/phase2-hook-validation.md`
- `references/scope.md`
- `references/plugin-design.md`
### Changed
- repository direction clarified: primary long-term path is now a standard lifecycle plugin
- ContextEngine is now documented as a future option, not the v1 default
- README updated to describe the package as skill + lifecycle plugin probe
- skill docs aligned to the lifecycle-plugin plan
### Validated
- Experiment A passed on multiple resident subagents (`tech_geek`, `travel_assistant` after workspace/startup-rule cleanup)
- startup continuity injection can work without `read`
### Pending
- Experiment C (compaction-path verification) remains pending because no real compaction event was triggered in the earlier pressure test
+19 -9
View File
@@ -1,8 +1,12 @@
# memory-continuity # memory-continuity
OpenClaw skill for **short-term working continuity** — so an agent can recover **Current release:** `v0.3.0-probe`
structured in-flight work state after `/new`, reset, gateway interruption,
model fallback, or compaction. OpenClaw continuity package for **short-term working continuity** — currently shipped as:
- a **skill** (`SKILL.md`) for behavior contract / fallback recovery
- a **lifecycle plugin probe** (`plugin/lifecycle-prototype.ts`) for validating the primary runtime path
Its goal is to let an agent recover structured in-flight work state after `/new`, reset, gateway interruption, model fallback, or compaction.
## What problem does this solve? ## What problem does this solve?
@@ -24,12 +28,13 @@ That is the problem this skill solves.
## Current architecture stance ## Current architecture stance
This repository now treats the skill as: This repository should now be understood as a **continuity package**, not just a standalone skill.
- a **behavior contract**
- a **fallback implementation**
- a **human-readable protocol** for structured working-state checkpoints
The planned primary runtime path is a **standard lifecycle plugin** that can ### Included forms
- **Skill** = behavior contract / fallback implementation / human-readable protocol
- **Lifecycle plugin probe** = current runtime experiment for the primary architecture
The intended primary runtime path is a **standard lifecycle plugin** that can
improve startup, `/new`, and compaction continuity **without consuming improve startup, `/new`, and compaction continuity **without consuming
OpenClaws exclusive `contextEngine` slot**. OpenClaws exclusive `contextEngine` slot**.
@@ -184,15 +189,20 @@ Strengthen the current skill version:
- improve doctor and docs - improve doctor and docs
### Phase 2 ### Phase 2
Build a **standard lifecycle plugin** as the primary runtime path: Build and validate a **standard lifecycle plugin** as the primary runtime path:
- startup recovery behavior - startup recovery behavior
- `/new` checkpointing - `/new` checkpointing
- compaction-boundary checkpointing - compaction-boundary checkpointing
- end-of-run safety writes - end-of-run safety writes
- hook validation in real resident subagent sessions
### Future option ### Future option
Evaluate a ContextEngine variant later only if the slot tradeoff is justified. Evaluate a ContextEngine variant later only if the slot tradeoff is justified.
## Release notes
See `CHANGELOG.md` for the current packaged milestone history.
## License ## License
MIT MIT