04e6fb64bb
Phase 0 — measurement gate: - tests/test_contracts.py: BOARDS↔NORMALIZERS alignment, funnel-shape guards, overlap() None contract, and the frontend↔backend EXACT-STRING vocab check (scout.ts options must resolve in coerce.py, else silent keyword-fold). - tests/run_regression.py + fixtures/regression_set.json (+ _seed_regression.py): a frozen 120-pair set (tech + non-tech) Opus-judged for recruiter-fit targets. Two metrics: score MAE and SIFT TOP-K MEMBERSHIP RECALL (do the best jobs reach Opus?). Baseline: MAE 24.7, recall 0.68 — i.e. ~32% of the genuinely-best jobs are cut before the curator ever sees them (worse for non-tech). Phase 1 — coverage (India non-tech): - Enable Indeed (misceres) + enrich indeed_to_scoutjob with details.description + location_mode (jobType is employment type, not skills → required_skills now []). - Add WorkIndia (shahidirfan) — India blue/grey-collar non-tech: build_workindia_input + workindia_to_scoutjob (real skills + description; per-job apply URL from job_id since source_url is generic and would dedup-collapse the deck). - Drop Wellfound from the stack (US-startup-heavy + 400s); kept registered-but-off. - BOARDS_ENABLED = naukri,foundit,linkedin,indeed,workindia. Pool ~90 → ~140 jobs/search. Regression scores unchanged (engine scoring untouched). 31 tests pass.
101 lines
4.9 KiB
Python
101 lines
4.9 KiB
Python
"""On-demand multi-board sweep: ScoutPrefs → all boards (parallel) → merge + dedup → ScoutJob[].
|
|
|
|
This is the retrieve layer (final shape). Slice-1a has NO engine — ranking is a placeholder
|
|
spread; the §3 cascade slots in here later without changing the output contract.
|
|
Degrade-don't-break: a board that errors/needs setup is skipped; the others still return.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import logging
|
|
|
|
from app.config import get_settings
|
|
from app.engine.apify_client import run_actor
|
|
from app.engine.board_adapters import adapters as A
|
|
from app.engine.board_adapters import coerce as C
|
|
from app.engine import normalize as N
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
def _ats_companies() -> list[dict]:
|
|
return [{"company": c.strip()} for c in get_settings().ATS_COMPANIES.split(",") if c.strip()]
|
|
|
|
|
|
# Boards whose actor takes a real page/offset → they get a per-board cursor that advances each run.
|
|
# Everyone else (Naukri/Foundit feeds — no page param) relies purely on the per-user seen-net; we do
|
|
# NOT track a meaningless cursor for them.
|
|
PAGINATING_BOARDS = {"linkedin", "indeed"}
|
|
|
|
# board key → (actor_id, build_input, normalizer). "Balanced" India stack = naukri+foundit+linkedin,
|
|
# all city-filtered at the board. The rest stay registered (code ready) but off unless enabled.
|
|
BOARDS = {
|
|
"naukri": ("blackfalcondata~naukri-jobs-feed",
|
|
# no page/offset param → per-user seen-net handles dedup (NOT actor-side incremental).
|
|
lambda p: A.build_naukri_feed_input(p, max_jobs=get_settings().NAUKRI_MAX_JOBS),
|
|
N.naukri_feed_to_scoutjob),
|
|
"foundit": ("shahidirfan~Foundit-Jobs-Scraper",
|
|
lambda p: A.build_foundit_input(p, results_wanted=get_settings().FOUNDIT_MAX_JOBS),
|
|
N.foundit_to_scoutjob),
|
|
"linkedin": ("harvestapi~linkedin-job-search",
|
|
# cursor stores the LAST page fetched (0 = none yet) → next page = last + 1.
|
|
lambda p: A.build_linkedin_input(p, recall=True, max_items=get_settings().LINKEDIN_MAX_JOBS,
|
|
page=int((p.get("_cursors") or {}).get("linkedin", 0)) + 1),
|
|
N.linkedin_to_scoutjob),
|
|
# ── registered fallbacks / other lanes (off unless added to BOARDS_ENABLED) ──
|
|
"ats": ("bovi~greenhouse-lever-ashby-job-scraper",
|
|
lambda p: A.build_ats_input(p, recall=True, companies=_ats_companies(),
|
|
max_per_company=get_settings().ATS_MAX_PER_COMPANY),
|
|
N.ats_to_scoutjob),
|
|
"naukri_v1": ("muhammetakkurtt~naukri-job-scraper",
|
|
lambda p: A.build_naukri_input(p, recall=True, max_jobs=get_settings().NAUKRI_MAX_JOBS),
|
|
N.naukri_to_scoutjob),
|
|
"indeed": ("misceres~indeed-scraper",
|
|
lambda p: A.build_indeed_input(p, max_items=get_settings().INDEED_MAX_JOBS),
|
|
N.indeed_to_scoutjob),
|
|
"wellfound": ("blackfalcondata~wellfound-scraper", # registered, OFF — US-startup-heavy, not the India fit
|
|
lambda p: A.build_wellfound_input(p, max_results=get_settings().WELLFOUND_MAX_JOBS),
|
|
N.wellfound_to_scoutjob),
|
|
"workindia": ("shahidirfan~workindia-jobs-scraper",
|
|
# India blue/grey-collar non-tech; no page param → per-user seen-net dedups.
|
|
lambda p: A.build_workindia_input(p, results_wanted=get_settings().WORKINDIA_MAX_JOBS),
|
|
N.workindia_to_scoutjob),
|
|
}
|
|
|
|
|
|
async def _fetch_board(key: str, prefs: dict, cache_mode: str | None = None):
|
|
actor, build, norm = BOARDS[key]
|
|
items = await run_actor(actor, build(prefs), cache_mode=cache_mode)
|
|
jobs = [sj for it in items if (sj := norm(it))]
|
|
return key, jobs
|
|
|
|
|
|
async def run_sweep(prefs: dict, *, fresh: bool = False) -> dict:
|
|
# fresh=True forces a live fetch + cache overwrite (dev "fresh search" toggle);
|
|
# otherwise honor the configured cache mode (dev replays cached results for $0).
|
|
cache_mode = "refresh" if fresh else None
|
|
enabled = [b.strip() for b in get_settings().BOARDS_ENABLED.split(",") if b.strip() in BOARDS]
|
|
results = await asyncio.gather(*(_fetch_board(k, prefs, cache_mode) for k in enabled), return_exceptions=True)
|
|
|
|
merged: list[dict] = []
|
|
seen: set[str] = set()
|
|
sources: dict[str, int] = {}
|
|
for r in results:
|
|
if isinstance(r, Exception):
|
|
logger.warning("board fetch failed: %s", r)
|
|
continue
|
|
key, jobs = r
|
|
sources[key] = len(jobs)
|
|
for j in jobs:
|
|
dk = (j.get("apply_url") or "").strip() or f"{j['organization']}|{j['title']}|{j.get('location_city')}".lower()
|
|
if dk in seen:
|
|
continue
|
|
seen.add(dk)
|
|
merged.append(j)
|
|
|
|
# No ranking here — the engine (app/engine/rank.py) scores + selects after the sweep.
|
|
return {"opportunities": merged, "sources": sources}
|
|
|
|
|
|
def has_mvq(prefs: dict) -> bool:
|
|
return C.has_mvq(prefs)
|