Files
stack/notebooks/api_explorer.py
kert e8f6385bc5
All checks were successful
CI / lint (push) Successful in 29s
CI / notebooks-smoke (push) Successful in 1m24s
Deploy / notebooks (push) Has been skipped
Deploy / zotero (push) Has been skipped
Deploy / docs (push) Has been skipped
Deploy / api (push) Has been skipped
Deploy / mc (push) Has been skipped
Infra CI / notebooks (push) Successful in 48s
Infra CI / zotero (push) Successful in 12s
Infra CI / docs (push) Successful in 12s
Infra CI / api (push) Successful in 17s
Infra CI / mc (push) Successful in 21s
Deploy / report (push) Successful in 14s
CI / test (push) Successful in 16m35s
fix(notebooks): api_explorer target URL + zotero_tutorial polars schema inference
- api_explorer pointed at http://localhost:8080 — a host-side dev
  server that never exists inside the notebooks container (nb issue
  #546 alongside the api service wedge). Now defaults to the compose
  service http://api:8000, overridable via STACK_API_URL.
- zotero_tutorial's CASE/GROUP_CONCAT queries can yield columns that
  are all-NULL within polars' default inference window with strings
  appearing later ('could not append value', nb issue #561 — surfaced
  once the immutable=1 fix got reads past the lock). Pin
  infer_schema_length=None on all read_database calls.

Verified headless in the prod container: both notebooks now export
with zero cell errors.
2026-07-10 14:17:16 -04:00

356 lines
7.6 KiB
Python

import marimo
__generated_with = "0.20.4"
app = marimo.App(width="medium")
@app.cell(hide_code=True)
def _():
import marimo as mo
mo.md("""
# API Explorer
Interactive test harness for the Stack REST API. Exercises every endpoint
group: **health**, **pipelines**, **lineage**, **bib**, **schema**, and **auth**.
Defaults to the compose-internal `api` service; set `STACK_API_URL` to
point elsewhere (e.g. `http://localhost:8080` with a local
`uv run stack api serve --port 8080`).
""")
return (mo,)
@app.cell
def _():
import os
import httpx
BASE = os.environ.get("STACK_API_URL", "http://api:8000")
client = httpx.Client(base_url=BASE, timeout=30)
return (client,)
@app.cell(hide_code=True)
def _(mo):
mo.md("""
## Health Check
""")
return
@app.cell
def _(client, mo):
_r = client.get("/health")
health = _r.json()
_rows = []
for _svc in health["services"]:
_icon = "\u2705" if _svc["status"] == "ok" else "\u26a0\ufe0f"
_rows.append(
f"| {_icon} | {_svc['name']} | {_svc['status']} | {_svc.get('detail', '')} |"
)
mo.md(f"""
**Status:** {health["status"]} | **Version:** {health["version"]}
| | Service | Status | Detail |
|---|---------|--------|--------|
{chr(10).join(_rows)}
""")
return (health,)
@app.cell(hide_code=True)
def _(mo):
mo.md("""
## Pipelines
""")
return
@app.cell
def _(client, mo):
_r = client.get("/pipelines")
pipelines = _r.json()
_rows = []
for _p in pipelines:
_rows.append(f"| {_p['name']} | {_p['steps']} |")
mo.md(f"""
**{len(pipelines)} pipelines registered**
| Pipeline | Steps |
|----------|-------|
{chr(10).join(_rows)}
""")
return (pipelines,)
@app.cell
def _(client, mo, pipelines):
_name = pipelines[0]["name"] if pipelines else "readmissions"
_r = client.get(f"/pipelines/{_name}")
detail = _r.json()
_inputs_list = "\n".join(f"- `{i}`" for i in detail.get("inputs", []))
_outputs_list = "\n".join(f"- `{o}`" for o in detail.get("outputs", []))
mo.md(f"""
### Pipeline Detail: `{detail["name"]}`
**Steps:** {detail["steps"]} | **Inputs:** {len(detail.get("inputs", []))} | **Outputs:** {len(detail.get("outputs", []))}
**Inputs:**
{_inputs_list}
**Outputs:**
{_outputs_list}
""")
return
@app.cell
def _(client, mo):
_r = client.get("/pipelines/nonexistent_xyz")
pipeline_404 = _r.status_code == 404
mo.md(
f"**GET /pipelines/nonexistent_xyz** \u2192 `{_r.status_code}` {'PASS' if pipeline_404 else 'FAIL'}"
)
return (pipeline_404,)
@app.cell(hide_code=True)
def _(mo):
mo.md("""
## Lineage
""")
return
@app.cell
def _(client, mo):
_r = client.get("/lineage")
lineage = _r.json()
table_count = len(lineage["tables"])
edge_count = sum(len(v) for v in lineage["edges"].values())
col_sources = sum(len(v) for v in lineage["column_sources"].values())
mo.md(f"""
**Full lineage graph:** {table_count} tables, {edge_count} edges, {col_sources} column-level sources
""")
return (lineage,)
@app.cell
def _(client, lineage, mo):
_test_table = None
for _t, _deps in lineage["edges"].items():
if _deps and "." in _t:
_test_table = _t
break
_content = ""
if _test_table:
_r = client.get(f"/lineage/{_test_table}")
_tl = _r.json()
_content = f"""
### Table Lineage: `{_tl["table"]}`
**Inputs:** {", ".join(f"`{i}`" for i in _tl["inputs"])}
"""
else:
_content = "No table with dependencies found"
_ = mo.md(_content)
return
@app.cell
def _(client, mo):
_r = client.get("/lineage/export/mermaid")
mermaid_data = _r.json()
_lines = mermaid_data["content"].split("\n")
mo.md(f"""
### Mermaid Export
**Format:** {mermaid_data["format"]} | **Lines:** {len(_lines)}
```mermaid
{chr(10).join(_lines[:15])}
...
```
""")
return
@app.cell
def _(client, mo):
_r = client.get("/lineage/export/dot")
dot_data = _r.json()
_lines = dot_data["content"].split("\n")
mo.md(f"""
### DOT Export
**Format:** {dot_data["format"]} | **Lines:** {len(_lines)}
```dot
{chr(10).join(_lines[:10])}
...
```
""")
return
@app.cell(hide_code=True)
def _(mo):
mo.md("""
## Bibliography
""")
return
@app.cell
def _(client, mo):
_r1 = client.get("/bib/items?limit=10")
bib_items = _r1.json()
_r2 = client.get("/bib/tags")
bib_tags = _r2.json()
_item_rows = []
for _item in bib_items[:10]:
_item_rows.append(
f"| {_item['key']} | {_item['title'][:50]} | {_item['item_type']} |"
)
_tag_rows = []
for _tag in bib_tags[:10]:
_tag_rows.append(f"| {_tag['namespace']} | {_tag['count']} |")
mo.md(f"""
**{len(bib_items)} items returned** | **{len(bib_tags)} tag namespaces**
### Items (first 10)
| Key | Title | Type |
|-----|-------|------|
{chr(10).join(_item_rows)}
### Tag Namespaces
| Namespace | Count |
|-----------|-------|
{chr(10).join(_tag_rows)}
""")
return
@app.cell(hide_code=True)
def _(mo):
mo.md("""
## Schema
""")
return
@app.cell
def _(client, mo):
_r = client.get("/schema/nonexistent_table")
missing_ok = _r.status_code == 404
mo.md(
f"**GET /schema/nonexistent_table** \u2192 `{_r.status_code}` {'PASS' if missing_ok else 'FAIL'}"
)
return (missing_ok,)
@app.cell(hide_code=True)
def _(mo):
mo.md("""
## Auth
""")
return
@app.cell
def _(client, mo):
_r1 = client.post("/pipelines/run/readmissions")
auth_required = _r1.status_code in (401, 403)
_r2 = client.post("/auth/token", json={"secret": "wrong"})
wrong_secret = _r2.status_code == 401
mo.md(f"""
| Test | Status | Result |
|------|--------|--------|
| Run requires auth | `{_r1.status_code}` | {"PASS" if auth_required else "FAIL"} |
| Wrong secret rejected | `{_r2.status_code}` | {"PASS" if wrong_secret else "FAIL"} |
""")
return auth_required, wrong_secret
@app.cell(hide_code=True)
def _(mo):
mo.md("""
## Summary
""")
return
@app.cell
def _(
auth_required,
client,
health,
lineage,
missing_ok,
mo,
pipeline_404,
pipelines,
wrong_secret,
):
tests = {
"GET /health": health["status"] in ("ok", "degraded"),
"GET /pipelines": len(pipelines) > 0,
"GET /pipelines/{name}": client.get(
f"/pipelines/{pipelines[0]['name']}"
).status_code
== 200,
"GET /pipelines/404": pipeline_404,
"GET /lineage": len(lineage["tables"]) > 0,
"GET /lineage/export/mermaid": client.get("/lineage/export/mermaid").status_code
== 200,
"GET /lineage/export/dot": client.get("/lineage/export/dot").status_code == 200,
"GET /bib/items": client.get("/bib/items").status_code == 200,
"GET /bib/tags": client.get("/bib/tags").status_code == 200,
"GET /schema/404": missing_ok,
"POST /pipelines/run (no auth)": auth_required,
"POST /auth/token (wrong)": wrong_secret,
}
passed = sum(1 for v in tests.values() if v)
total = len(tests)
_rows = []
for _name, _ok in tests.items():
_icon = "\u2705" if _ok else "\u274c"
_rows.append(f"| {_icon} | {_name} | {'PASS' if _ok else 'FAIL'} |")
mo.md(f"""
### Results: {passed}/{total} passed
| | Endpoint | Result |
|---|----------|--------|
{chr(10).join(_rows)}
""")
return
if __name__ == "__main__":
app.run()