Diagnose common cqs issues — stale index, model download, schema mismatch, connection issues.
The English summary is being prepared. Showing the original description.
Review the instructions the agent will receive before you install.
Guided diagnosis of common cqs issues. Run through checks in order, stop at first problem found.
cqs --version
If not found: cargo install --path . (from source) or check ~/.cargo/bin/ is in PATH.
ls -la .cqs/ && cat .cqs/active_slot 2>/dev/null
ls -la .cqs/slots/$(cat .cqs/active_slot 2>/dev/null || echo default)/ 2>/dev/null
The index lives in the active slot: .cqs/slots/<name>/index.db plus HNSW sidecars (index.hnsw*; legacy pre-slot layouts kept files at .cqs/ top level). If missing: cqs init && cqs index.
Run cqs stats. Check:
If empty: cqs index to rebuild.
cqs stats 2>&1
If you see "SchemaMismatch" or "SchemaNewerThanCq":
/migrate to upgradeCurrent schema version: check src/store/helpers/mod.rs for CURRENT_SCHEMA_VERSION.
cqs doctor # checks model, index, hardware in one pass
ls -la ~/.cache/huggingface/hub/models--onnx-community--embeddinggemma-300m-ONNX/
Default model is EmbeddingGemma-300m (since v1.35.0); alternative presets via CQS_EMBEDDING_MODEL / --model live under their own models--* dirs. If missing or incomplete, cqs downloads on first use. Check network access to huggingface.co.
If corrupted: delete the directory and let cqs re-download (blake3 checksums verify integrity).
cqs ping
systemctl --user status cqs-watch
cqs ping should report a connected daemon and a sub-100ms round-trip. Common issues:
systemctl --user start cqs-watch (or cqs watch --serve ad hoc)systemctl --user restart cqs-watchCQS_NO_DAEMON=1 cqs <cmd>ANTHROPIC_API_KEY is set (see SECURITY.md)Compare cqs stats last update time vs recent file modifications.
Fix: cqs index (one-time) or cqs watch (continuous).
cqs ref list
Check that source paths still exist and chunk counts are > 0.
If source moved: cqs ref remove <name> and re-add with new path.
After running checks, summarize:
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Comment-archaeology sweep - find work items hiding in TODO/FIXME/for-now comments and plan-doc ledgers, judge them, file issues, queue trivial fixes. Good idle-loop activity.
The English summary is being prepared. Showing the original description.
Run a multi-category code audit on the cqs codebase. Spawns parallel agents per batch.
The English summary is being prepared. Showing the original description.
Run before modifying a function — impact + test-map + explain in one pass, presented as a modification checklist.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
Run after making changes, before committing — reviews the current git diff for impact and risk via cqs review.
The English summary is being prepared. Showing the original description.
Unified cqs CLI dispatcher — semantic code search, call graph navigation, impact analysis, quality tools, notes, and infrastructure. Use `/cqs <command> [args]` for any cqs operation.
The English summary is being prepared. Showing the original description.