​

Consolidate

1. Consolidator — runs every 6h. Walks recent journal entries per crew and produces a set of learned rules appended to .memory/topics/learned-YYYY-MM-DD.md. Emits memory.consolidated.
2. Compactor — runs daily at 03:00 UTC. Rolls up low-signal entries older than 30 days into a single system.compaction entry and deletes the originals. warn/error rows are preserved indefinitely.

​

Candidate entry types

var candidateTypes = []journal.EntryType{
    journal.EntryPeerEscalation,
    journal.EntrySummaryGenerated,
    journal.EntryKeeperDecision,
    journal.EntryMissionStatus,
    journal.EntryEvalRegression,
}

​

Rules output

# Learned Rules 2026-04-17

## Rule: prefer staged deployments for schema changes
**Source:** peer.escalation j_a1b2..., mission.status_change j_xyz...
**Confidence:** 0.8

When a migration adds a non-nullable column, roll it out in two steps
(add nullable, backfill, alter to NOT NULL) to avoid production downtime.

## Rule: ...

​

Summarizer

type SummarizerClient interface {
    Summarize(ctx context.Context, req SummarizeRequest) (SummarizeResponse, error)
}

​

Which model runs it

crewship keeper aux set curator --provider anthropic --model claude-haiku-4-5
crewship keeper aux set curator --provider ollama --model qwen2.5:7b

• Background runner skips every crew silently (the pin-snapshot path still runs).
• Manual trigger returns 202 Accepted with note: "no summarizer configured, skipping" and emits system.consolidation_triggered + system.consolidation_completed (status=skipped-no-summarizer) so the audit trail captures the no-op.

​

Compactor

• warn and error severity
• summary.generated, memory.consolidated
• Everything under approval.*, checkpoint.*, fork.*, eval.regression_detected
• Anything tagged with priority='permanent' (see Crew Journal — Priority markers)

​

Archive layer (PR #212)

SELECT id, ts, entry_type, summary
FROM (
  SELECT id, ts, entry_type, summary FROM journal_entries
  UNION ALL
  SELECT id, ts, entry_type, summary FROM journal_entries_archived
) WHERE workspace_id = ?
ORDER BY ts DESC
LIMIT 100;

​

Manual trigger

POST /api/v1/consolidate/run
Body: {"crew_id": "...", "since": "24h"}  // both optional

​

CLI

crewship consolidate run
crewship consolidate run --crew cmo2pe4dj0005ba0a129f
crewship consolidate run --since 24h
crewship consolidate run --since 7d

​

Journal entries emitted

​

Gotchas

• Ollama must be reachable when the curator slot points at it (and for the episodic indexer, which always does). Set OLLAMA_MODELS="/Volumes/SSD 990 PRO/ollama-models" and ollama serve before starting the server locally. Consolidation itself is no longer Ollama-only: a curator slot on a hosted provider works with no Ollama at all.
• The triggered journal entry is always emitted. Even the “no summarizer” skip path emits both triggered + completed so operators see the full round-trip. If you filter for memory.consolidated only, you’ll miss skipped runs.
• Per-workspace in-flight guard. A second manual trigger for the same workspace while the first is running returns 409. Track worker_id if you need to wait for completion.
• Compactor is aggressive on info/notice. If you rely on exec.command entries older than 30 days for forensics, export them out-of-band before the Compactor rolls them up.

​

Related

• Crew Journal — input stream.
• Episodic memory — the vector index built from the entry types these workers emit.
• Memory System — consumes the generated topics/learned-*.md files.
• crewship consolidate, Consolidate API.