## Summary
Verified against production: `claude -p` headless mode doesn't fire SessionEnd hooks (proven via `--output-format stream-json --include-hook-events`: zero `SessionEnd` events), so any session JSONLs from `-p` invocations stay orphaned locally and never reach the server. Fix: add `agnes push --quiet` as a third SessionStart entry — symmetric self-heal alongside the existing `agnes pull` entry. Existing workspaces pick this up on their next `agnes init` via the marker-based migration already in `cli/lib/hooks.py`.
Separately: a colleague's fresh install showed `agnes diagnose` warning "uploads are not being processed", which led them to suspect their `agnes push` was broken. The warning is actually about the LLM-based `verification-detector` backlog (uploads themselves were arriving fine — confirmed by 23+3 JSONLs landed on the server while the warning was firing). Reword the warning to "verification-detector backlog" + add `last_processed` to the diagnose dict so operators don't have to grep logs to confirm.
## Test plan
- [x] `pytest tests/test_lib_hooks.py` — updated count + added `agnes push in SessionStart` assertion.
- [x] `pytest tests/test_setup_hooks_template.py` — updated.
- [x] `pytest tests/test_clean_install_integration.py` — updated.
- [x] `pytest tests/test_health_session_pipeline.py` — updated warning text + asserted `last_processed` field.
<!-- devin-review-badge-begin -->
---
<a href="https://app.devin.ai/review/keboola/agnes-the-ai-analyst/pull/220" target="_blank">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://static.devin.ai/assets/gh-open-in-devin-review-dark.svg?v=1">
<img src="https://static.devin.ai/assets/gh-open-in-devin-review-light.svg?v=1" alt="Open in Devin Review">
</picture>
</a>
<!-- devin-review-badge-end -->
Caught by my own broader test scope after Devin fixes — three test files
asserted on user-visible strings that were renamed by the bootstrap PR
but the assertions weren't updated:
- tests/test_api_query_guardrail.py:110 — asserted `da fetch in suggestion`
on /api/query 400 response. Renamed to `agnes snapshot create`.
- tests/test_query_materialized_error_message.py:56 — asserted `da sync`
in materialized-not-yet error detail. Renamed to `agnes pull`.
- tests/test_cli_error_render.py:71 — fixture data + assertion both
carried `da fetch`. Updated to `agnes snapshot create`.
Plus an actual content miss: docs/setup/claude_settings.json (a template
shipped to operators) still installed `da sync` / `da sync --upload-only`
hooks. The companion test file (tests/test_setup_hooks_template.py) was
asserting that legacy state. Updated both:
- Template hooks: `agnes pull --quiet` / `agnes push --quiet`
- Test assertions + function name match the new commands
The analyst flow becomes a closed loop with the server-curated table catalog:
- `da analyst setup` writes `<workspace>/.claude/settings.json` with two hooks:
SessionStart → `da sync --quiet || true` — pulls fresh RBAC-filtered parquets at session start
SessionEnd → `da sync --upload-only --quiet || true` — uploads session jsonl + CLAUDE.local.md
- `|| true` keeps Claude Code unblocked when the server is down.
- Workspace-level (not user-home) so the hooks fire only when Claude Code opens this analyst workspace.
- `da sync --quiet` rewrites the CLI output for hook consumption — 0 stdout on success, single-line error on failure.
- Existing settings.json is patched (deep-merged), not overwritten; malformed JSON is reported, not silently overwritten.
Tests cover: workspace bootstrap, hook insertion, malformed-json safety, quiet-mode output shape.
Session testing revealed 3 issues with remote queries:
1. CLAUDE.md template recommended `cat <<HEREDOC | ssh ...` but
claude_settings.json had `cat` in deny list, causing 2-3 failed
attempts per query. Replaced with file-based approach: Write tool
creates JSON file, then `ssh ... < file` avoids the cat deny.
2. ssh/scp commands were not in the allow list, requiring manual
approval for every remote query. Added both to allow list.
3. DuckDB fetch_arrow_table() emitted DeprecationWarning on every
parquet export. Replaced with .arrow().read_all().
Also added instruction for proactive hybrid analysis when remote
tables are available (agent was only using local data until asked).
Open-source AI data analyst platform extracted from internal repo.
Includes data sync engine, Keboola adapter, Flask web portal,
server deployment scripts, and configuration templates.
