* feat: generalize pending-final-delivery for subagents and main session
(cherry picked from commit 677fcbfaf87c8cd6de8b5bd02099b29b7d49e916)
* feat(agents): implement Phase 2 durable final delivery for main sessions
(cherry picked from commit b4e39f0ddf6dbd3f0d3b9226df8e714ad722f751)
* fix(agents): narrow heartbeat deferral to pending final delivery
* fix(agents): clear final delivery after dispatch
* fix(agents): gate durable delivery retry capture
---------
Co-authored-by: Mert Basar <MertBasar0@users.noreply.github.com>
Summary:
- Adds an OpenCode provider-policy public artifact that delegates Claude thinking profiles, plus regression tests and a changelog entry for preserving `xhigh` on `opencode/claude-opus-4-7`.
- Reproducibility: yes. Source inspection on current main shows the model-switch path remaps unsupported store ... vider-policy-api` artifact for the fallback resolver; the proposed test exercises that stored-`xhigh` path.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head efa152cca5.
- Required merge gates passed before the squash merge.
Prepared head SHA: efa152cca5
Review: https://github.com/openclaw/openclaw/pull/76760#issuecomment-4366483080
Co-authored-by: mkdev11 <MkDev11@users.noreply.github.com>
Summary:
- The PR changes Gateway reload planning, CLI plugin install-index writes, plugin runtime/cache cleanup, docs, changelog, and tests so plugin enable/disable hot reloads while install/update/uninstall stay restart-backed.
- Reproducibility: yes. The earlier blocker has a source-level reproduction: run an external plugin install/up ... watches config and only the managed plugin index changes; the PR now tests that path and queues a restart.
ClawSweeper fixups:
- Included follow-up commit: fix: hot reload plugin management changes
- Included follow-up commit: fix(clawsweeper): address review for automerge-openclaw-openclaw-7597…
- Ran the ClawSweeper repair loop before final review.
Validation:
- ClawSweeper review passed for head 860594f722.
- Required merge gates passed before the squash merge.
Prepared head SHA: 860594f722
Review: https://github.com/openclaw/openclaw/pull/75976#issuecomment-4363168379
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Codex review on PR #75960 flagged that prepareClaudeCliSkillsPlugin and
the claude-live-session fingerprint read skillsSnapshot.resolvedSkills
directly without a disk fallback. After the persistence-layer strip,
those consumers would see an empty Skill[] on cold session resume,
breaking the documented Claude Code skills integration.
Add a hydration helper in ensureSkillSnapshot that rebuilds
resolvedSkills from a fresh workspace scan when the loaded snapshot
lacks it, while keeping the persisted prompt/skills/skillFilter/version
fields untouched so the model's prompt-cache key stays stable across
resume. The embedded runner's existing consumer-level fallback in
src/agents/pi-embedded-runner/skills-runtime.ts is now a redundant
safety net rather than the only fallback path.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Each SessionEntry carried the fully parsed Skill[] (including each
SKILL.md body) inside skillsSnapshot.resolvedSkills, multiplied across
every active session. Strip the field at the persistence chokepoint —
normalizeSessionStore in store-load.ts — so every load and every save
naturally drops it. The runtime already falls back to a workspace skill
scan when resolvedSkills is absent (see
src/agents/pi-embedded-runner/skills-runtime.ts:14), so prompts and
session resume behavior are unchanged.
Legacy sessions.json files self-heal on first load: normalize strips
the in-memory store, the next write rewrites the file in stripped form.
Test fixture (100 sessions × 50 skills × ~3KB body) goes from ~32MB to
under 2MB on disk.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
