بنقرة واحدة
migrate
Handle cqs schema version upgrades — check version, attempt migration, rebuild if needed.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Handle cqs schema version upgrades — check version, attempt migration, rebuild if needed.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Run a multi-category code audit on the cqs codebase. Spawns parallel agents per batch.
Trust-boundary security audit of cqs — fans out unbiddable-auditor agents across 6 categories (RT-INJ/RT-FS/RT-RES/RT-DATA/RT-RELAY/RT-EXFIL), attacker mindset, run-the-attack PoC + regression guard.
Run the retrieval recall gate with dead-gold triage and the binary A/B regression test. Required before release tags; use after any retrieval-adjacent merge.
Run after making changes, before committing — reviews the current git diff for impact and risk via cqs review.
Release a new version of cqs. Bumps version, updates changelog, runs the recall gate, publishes to crates.io, creates GitHub release.
One-command setup for cqs in a new project — skills, tears infrastructure, CLAUDE.md, init, index.
| name | migrate |
| description | Handle cqs schema version upgrades — check version, attempt migration, rebuild if needed. |
| disable-model-invocation | false |
| argument-hint |
Handle schema version mismatches when upgrading cqs.
cqs stats 2>&1
If it works normally, no migration needed. If you see a schema error, continue.
Errors tell you the versions:
from, cqs expects to. Auto-migration was attempted but no migration path exists.cqs attempts auto-migration when it opens the database. If you're seeing SchemaMismatch, it means no migration path exists for that version jump.
Check available migrations:
grep -n "migrate_v" src/store/migrations.rs
When auto-migration isn't available, the only option is a full rebuild:
# Back up the old index (just in case)
cp -r .cqs/ .cq.backup/
# Delete and rebuild
rm -rf .cqs/
cqs init
cqs index
This re-parses all source files and re-embeds them. Notes in docs/notes.toml are preserved (they live outside .cqs/).
References have their own databases at the same schema version:
cqs ref list
For each reference:
cqs ref update <name>
If that fails with schema errors, remove and re-add:
cqs ref remove <name>
cqs ref add <name> <source_path> --weight <weight>
cqs stats
Should show the current schema version and correct chunk counts.
rm -rf .cq.backup/
.cqs/ is gitignored — rebuilding only costs time, not data. But it now holds named slots (.cqs/slots/<name>/index.db) and the embeddings cache (.cqs/embeddings_cache.db) — rm -rf .cqs/ nukes ALL slots and the cache. Prefer removing just the broken slot dir if only one slot is affected.docs/notes.toml) are never lost — they're separate from the indexmetadata table: SELECT value FROM metadata WHERE key = 'schema_version'src/store/helpers/mod.rs:CURRENT_SCHEMA_VERSION)systemctl --user stop cqs-watch (restart after)