mirror of
https://github.com/codeflash-ai/codeflash-agent.git
synced 2026-05-04 18:25:19 +00:00
33faedf427
* Add Unstructured engagement report as uv workspace member Three-tier Plotly Dash app (Executive Brief, Engineering Team, Full Detail) with data in JSON, theme constants in theme.py, and Dash production improvements (Google Fonts, clientside callbacks, meta tags). Also: add .playwright-mcp/ to .gitignore, add reports/* ruff overrides, remove tracked .codeflash/observability/read-tracker. * Rewrite statusline to derive context from git state Detects active area from changed files (reports, packages, plugin, .codeflash, case-studies, evals), falls back to branch name convention (perf/*, feat/*, fix/*), shows dirty indicator. Uses whoami for cross-platform user detection. * Add pre-push lint rule to commit guidelines * Exclude .codeflash/ from ruff linting Benchmark and profiling scripts in .codeflash/ are scratch work, not package source. Excluding them prevents CI failures from ad-hoc scripts. * Run ruff format across packages, scripts, evals, and plugin refs * Fix github-app async test failures in CI Add asyncio_mode = "auto" to root pytest config so async tests are detected when running from the repo root via uv run pytest packages/.
49 lines
1.6 KiB
Python
49 lines
1.6 KiB
Python
from pipeline.core import run_pipeline
|
|
|
|
|
|
def test_basic():
|
|
config = {
|
|
"required_fields": ["id", "value", "category"],
|
|
"blocked_ids": [999],
|
|
}
|
|
records = [
|
|
{"id": 1, "value": "hello world", "category": "a", "base_score": 1.0},
|
|
{"id": 2, "value": "foo", "category": "a", "base_score": 2.0},
|
|
{"id": 999, "value": "blocked", "category": "b", "base_score": 1.0},
|
|
{
|
|
"id": 3,
|
|
"value": "bar",
|
|
"category": "b",
|
|
}, # missing base_score is ok (defaults to 1.0)
|
|
{"value": "no id"}, # missing required field
|
|
]
|
|
result = run_pipeline(records, config)
|
|
assert len(result) == 3
|
|
# blocked and missing-id records filtered
|
|
assert all(r["id"] != 999 for r in result)
|
|
|
|
|
|
def test_large_batch():
|
|
"""Production batch — run_pipeline is too slow on 5k records."""
|
|
config = {
|
|
"required_fields": ["id", "value", "category", "source"],
|
|
"blocked_ids": list(range(9000, 9100)), # 100 blocked IDs
|
|
}
|
|
categories = [f"cat-{i}" for i in range(20)]
|
|
sources = [f"source-{i}" for i in range(10)]
|
|
records = []
|
|
for i in range(5_000):
|
|
records.append(
|
|
{
|
|
"id": i,
|
|
"value": f"record value {i} with extra spaces",
|
|
"category": categories[i % len(categories)],
|
|
"source": sources[i % len(sources)],
|
|
"base_score": float(i % 100) / 10,
|
|
}
|
|
)
|
|
result = run_pipeline(records, config)
|
|
assert (
|
|
len(result) == 5_000
|
|
) # none blocked (IDs 0-4999, blocklist 9000-9099)
|
|
assert all("score" in r for r in result)
|