Files
ThothII/harness/README.md
T

147 lines
5.7 KiB
Markdown

# ThothII harness — `tht`
The self-contained Pi layer of ThothII: a deterministic Python CLI (`tht`) + a Pi gate
extension (`.pi/extensions/tht-gate.js`) that runs the 8-phase NL→SQL workflow,
emitting and consuming widget-descriptor JSON. Derived from the reference implementation as a validated
starting point, **adapted** (not assumed reliable) to the ThothII contract.
## Install
```bash
cd harness
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
```
The `tht` command is now on PATH. Node ≥ 20 is needed for the gate JS tests
(`npm test`).
## Configure
### `.env` (gitignored — secrets live ONLY here)
```bash
cp .env.example .env
# fill in: THT_PROFILE, THT_DB_*, THT_DWH_API_KEY, THT_SSL_CA, ...
```
Keys are never logged; URLs are fine. Rotate any key that appeared in chat.
### `workspaces/<name>.yaml`
A schema-v4 workspace wires the external relational DWH to one internal Qdrant collection.
The embedding identity and dimensions come from the Installation Model Catalog, not this
workspace descriptor. Evidence paths remain workspace-local, while Qdrant
stores the derived semantic projection for schema, Evidence, Memory, and solved-question
records. The legacy files under `workspaces/` are retained as migration fixtures; new
operator-facing descriptors live in the workspace Git registry. `${THT_*}` tokens expand
from `.env`.
> **DB support (MVP):** the `direct` transport supports **PostgreSQL only** (psycopg2
> driver, `pg_*` catalog introspection, postgres-dialect sqlcheck/EXPLAIN). The central
> production DWH is reached via the `rest` transport. Multi-dialect `direct` support
> (sqlserver/mariadb/informix, cf. `Thoth/thoth_sqldb2`) is separate future work.
### Per-customer workspace repo (deployment shape)
ThothII is generic; **evidence content and LSH indexes are per-customer** and live in a
**separate repo**, not copied into `harness/`. The deployment is two checkouts + one `.env`:
```
ThothII/ generic harness (this repo)
└── harness/ tht CLI + .env (THT_* secrets, points at the customer repo)
tht-workspace-<customer>/ per-customer workspace repo (separate git repo)
├── <customer>.yaml workspace YAML (paths ABSOLUTE, anchored here)
├── evidence/ curated evidence markdown (frontmatter-structured, by domain)
├── artifacts/ derived artifacts (gitignored; regenerated by tht)
├── indexes/ LSH index (gitignored; regenerated by `tht preprocess dwh --steps lsh`)
└── sessions/ per-session artifacts (gitignored)
```
`THT_DOCS_ROOT` in `.env` points at the **root** of the customer repo
(`evidence.source_root` + `evidence.evidence_dir` resolve the curated folder).
All `tht` commands take the customer workspace via `-c`:
```bash
tht schema introspect -c /path/to/tht-workspace-<customer>/<customer>.yaml
tht preprocess dwh --steps lsh -c /path/to/tht-workspace-<customer>/<customer>.yaml
tht session new -c /path/to/tht-workspace-<customer>/<customer>.yaml
```
## Efficiency levers setup (one-time per workspace)
To enable the three deployed optimization levers on a **new workspace**:
```bash
# Lever 1: Foreign key suggestions from approved SQL + heuristics.
# Run once after schema introspection to populate annotations.yaml.
tht schema suggest-fks \
--from-sql /path/to/customer/sessions \
--assume cod_paz=dim_patient \
-c /path/to/customer/workspace.yaml \
--write
# (psd workspace: 228 FK suggestions already generated via this command 2026-07-08)
# Levers 2 + 3: automatic at next session (context-pack + recap from ledger).
# No setup needed — SKILL.md prescribes them automatically.
```
See `PROJECT_STATE.md` for what each lever does.
## The workflow
`workflow.yaml` is the **single source of workflow truth** (spec F2). Eight phases
(F1 chiarimento → F8 datamart). Edit it to change the workflow; `phase.py`, the gate,
and the skill all read from it — no mirrored constants to drift.
```bash
tht phase meta --json # the gate reads workflow facts from here
tht phase meta # human-readable
```
## Run
The harness runs inside Pi (`pi --mode rpc`, cwd = `harness/`):
```bash
pi --mode rpc
# in Pi: /nuova-domanda "<your question in natural language>"
```
The gate (`tht-gate.js`) presents reviewer widgets (widget-descriptor), the reviewer
decides, and `tht` persists decisions to the append-only ledger (`review_decisions.jsonl`).
See `docs/testing.md` for what each interaction level validates.
## Test
```bash
pytest # L0 (testcontainers, real Postgres) + L1 (pure logic + gate builders)
npm test # gate widget-builder golden + fuzzy tests (JS)
pytest -m l2 # L2: real GLM 5.2 + remote DWH (pre-release; needs .env + VPN + CA bundle)
```
L0 needs Docker (present on the dev machine). L2 is manual, non-deterministic, and
skips cleanly without `.env`. See `docs/testing.md` for the honest split of what each
level covers and — crucially — does **not** cover.
## Layout
```
tht/ Python package (CLI + workflow + phase + decisions + db/rest/mschema/
vectorstore/evidence/search/session + memory)
.pi/ Pi project (settings, prompts, themes, extensions/tht-gate.js + gate/)
workflow.yaml single source of workflow truth (F2)
workspaces/ workspace YAML definitions (D3)
scripts/ retained legacy SQL fixtures and workspace utilities
tests/ L0 (testcontainers), L1 (logic + builders), L2 (real model + DB)
docs/ testing guide + workflow editing
```
## Reference
- Repository architecture: `../docs/architecture/overview.md`
- Components and flows: `../docs/architecture/components.md`
- Runtime contracts: `../docs/contracts/`