PR #66609: fix(context-engine): fix MockContextEngine ID mismatch regression

• Repository: openclaw/openclaw
• Author: tentacloos
• State: closed | merged: False
• Link: https://github.com/openclaw/openclaw/pull/66609

Description (problem / solution / changelog)

Fixes #66591 - Critical regression where lossless-claw context engine is completely broken in release 2026.4.14

Problem

The validation added in commit 2677f7cf14 requires context engine to match the registered ID. had hardcoded but could be registered with dynamic IDs, causing validation failures that break user systems with lossless-claw enabled.

Root Cause

• New validation: throws error 'info.id must match registered id'
• returns hardcoded
• Tests register with dynamic IDs like 'cross-chunk-12345'
• Similar pattern likely exists in third-party plugins like lossless-claw

Solution

✅ Update MockContextEngine constructor to accept parameter
✅ Set info.id dynamically instead of hardcoded 'mock'
✅ Update all test usages to pass correct engineId
✅ Add regression test specifically for #66591
✅ All 37 tests pass including new regression test

Testing

• Added regression test: Verifies class-based engines work with dynamic IDs
• All existing tests pass: 37/37 ✅
• Full quality checks pass: TypeScript, lint, import cycles ✅
• Zero breaking changes: Maintains backward compatibility

Files Changed

• : Fix MockContextEngine + add regression test

Status: Ready for review - Critical fix for P0 regression

Changed files

• src/context-engine/context-engine.test.ts (modified, +20/-7)

PR #65589: feat(memory-core): dreaming circuit breaker to prevent runaway cost and data corruption

• Repository: openclaw/openclaw
• Author: bahadorkhaleghi1982
• State: open | merged: False
• Link: https://github.com/openclaw/openclaw/pull/65589

Description (problem / solution / changelog)

Summary

• Adds a DreamingBudgetEnforcer module to the memory-core plugin that prevents dreaming runaway loops from burning unbounded API costs and corrupting daily notes
• Implements three independent safety layers: per-cycle deduplication, sliding-window cost circuit breaker, and confidence-gated candidate filtering
• Includes an integration helper (filterCandidatesThroughEnforcer) showing exactly how the enforcer plugs into the existing dreaming.ts pipeline
• Covers all functionality with 51 unit tests including boundary conditions, persistence round-trips, and edge cases

Motivation

Issue #65550 documents a real production incident where the dreaming system entered an uncontrolled loop:

• 94 LLM subagent sessions spawned in 65 minutes
• $4.35 burned on API calls producing entirely garbage output
• 302 lines of dream fragments overwrote real daily notes (data corruption)
• All candidates had confidence: 0.00, recalls: 0 — zero-value entries that should never have been processed
• 76 of 94 sessions reprocessed the same stale data with no deduplication

Root causes identified:

1. No per-cycle deduplication — same candidates reprocessed in tight loops
2. No cost tracking or budget cap — no awareness of accumulated API spend
3. No candidate quality gate — zero-confidence entries passed through to expensive LLM calls

Users' only recourse is disabling dreaming entirely (dreaming.enabled: false), losing the long-term memory consolidation feature that is a core differentiator of OpenClaw.

Design

DreamingBudgetEnforcer (dreaming-budget.ts)

A stateful class instantiated at the start of each dreaming cycle with three guard methods:

Plus a composite checkCandidate() that runs all three checks in priority order (budget > quality > dedup).

Persistence: Budget state is saved to memory/.dreams/dreaming-budget.json via atomic write (temp file + rename) so it survives SIGUSR1 restarts. Uses the same file I/O patterns as short-term-promotion.ts.

Configuration: All thresholds are configurable via the plugin config schema under dreaming.budget:

{
  "dreaming": {
    "budget": {
      "maxCostUsd": 1.0,
      "windowMs": 3600000,
      "minConfidence": 0.05,
      "minRecalls": 1
    }
  }
}

Integration guide (dreaming-budget-integration.ts)

Documents the 6 exact integration points in the existing dreaming.ts pipeline with code snippets showing where each enforcer call is inserted. Also exports filterCandidatesThroughEnforcer() — a helper that filters ranked promotion candidates through all three safety layers and returns a breakdown of skip reasons.

Test plan

• 51 vitest unit tests covering:
  • Fingerprinting: consistency, normalization, uniqueness, format validation
  • Deduplication: first/second encounter, case variants, cross-instance independence
  • Quality gate: zero confidence, zero recall, NaN, negative, custom thresholds
  • Cost breaker: under/over budget, latching behavior, window reset, default cost, invalid values
  • Composite check: priority ordering (budget > quality > dedup)
  • Persistence: save/load round-trip, missing file, corrupt JSON, wrong version, restart survival
  • Integration filter: valid candidates, duplicates, low quality, budget exceeded, empty list
  • Boundary conditions: exactly-at-threshold for confidence/cost, latch persistence through window expiry, state immutability
• Verify existing dreaming.test.ts tests still pass after integration
• Manual test: enable dreaming with budget.maxCostUsd: 0.10 and verify the cycle halts at the budget with a warning log

Closes #65550

Changed files

• extensions/memory-core/src/dreaming-budget-integration.ts (added, +167/-0)
• extensions/memory-core/src/dreaming-budget.test.ts (added, +541/-0)
• extensions/memory-core/src/dreaming-budget.ts (added, +245/-0)