Dreaming's deep-phase promotion path appends to ~/.openclaw/workspace-<agent>/MEMORY.md
without a durable size budget. After weeks of use, the file grows past the bootstrap
injection cap (~12KB/file), at which point bootstrap silently truncates promoted memory
and (per the issue body) session writes can hit lock timeouts that wedge the gateway.
Adds a bounded compaction step in applyShortTermPromotions: before each write, drop the
OLDEST auto-promoted sections (date-ordered) until existing + new section fits within
memoryFileMaxChars (default 10,000 chars, safely below the 12KB bootstrap cap).
User-authored content is preserved unconditionally; only dreaming-owned sections are
eligible for compaction.
Verified:
- pnpm install --frozen-lockfile
- pnpm test extensions/memory-core/src/memory-budget.test.ts extensions/memory-core/src/short-term-promotion.test.ts
- pnpm exec oxfmt --check --threads=1 extensions/memory-core/src/memory-budget.ts extensions/memory-core/src/memory-budget.test.ts extensions/memory-core/src/short-term-promotion.ts extensions/memory-core/src/short-term-promotion.test.ts CHANGELOG.md
- pnpm check:changed
- pnpm tsgo:core
- pnpm tsgo:extensions
- pnpm tsgo:test:src
- git diff --check
- live driver: real applyShortTermPromotions across 5 sweeps with oversized seeded MEMORY.md — file stayed bounded, oldest sections compacted, user content preserved
Closes#73691
QQBot's gateway captured `ctx.cfg` once at startup and reused that
reference for every inbound, so peer-specific bindings added via the
CLI were ignored until the gateway restarted (the routing resolver
caches evaluated bindings keyed by the cfg object reference).
Add a small `ActiveCfgProvider` that reads `getRuntimeConfig()` from
the plugin SDK on every event and falls back to the startup snapshot
when the runtime registry is not populated, mirroring Telegram's
per-event lookup pattern. Wire it into `handleMessage` so both the
inbound pipeline and outbound dispatch run against the live config.
Fixes#69546.
