marchwarden/tests
Jeff Smith 14cfd53514 feat(arxiv): ingest pipeline (M5.1.1)
Closes #38. First sub-milestone of M5.1 (Researcher #2: arxiv-rag).

New package researchers/arxiv/ with three modules:

- store.py — ArxivStore wraps a persistent chromadb collection at
  ~/.marchwarden/arxiv-rag/chroma/ plus a papers.json manifest. Chunk
  ids are deterministic and embedding-model-scoped (per ArxivRagProposal
  decision 4) so re-ingesting with a different embedder doesn't collide
  with prior chunks.
- ingest.py — three-phase pipeline: download_pdf (arxiv API), extract_sections
  (pymupdf with heuristic heading detection + whole-paper fallback), and
  embed_and_store (sentence-transformers, configurable via
  MARCHWARDEN_ARXIV_EMBED_MODEL). Top-level ingest() chains them and
  upserts the manifest entry. Re-ingest is idempotent — chunks for the
  same paper are dropped before re-adding.
- CLI subgroup `marchwarden arxiv add|list|info|remove`. Lazy-imports
  the heavy chromadb / torch deps so non-arxiv commands stay fast.

The heavy ML deps (pymupdf, chromadb, sentence-transformers, arxiv) are
gated behind an optional `[arxiv]` extra so the base install stays slim
for users who only want the web researcher.

Tests: 14 added (141 total passing). Real pymupdf against synthetic PDFs
generated at test time covers extract_sections; chromadb and the
embedder are stubbed via dependency injection so the tests stay fast,
deterministic, and network-free. End-to-end ingest() is exercised with
a mocked arxiv.Search that produces synthetic PDFs.

Out of scope for #38 (covered by later sub-milestones):
- Retrieval / search API (#39)
- ArxivResearcher agent loop (#40)
- MCP server (#41)
- ask --researcher arxiv flag (#42)
- Cost ledger embedding_calls field (#43)

Notes:
- pip install pulled in CUDA torch wheel (~2GB nvidia libs); harmless on
  CPU-only WSL but a future optimization would pin the CPU torch index.
- Live smoke against a real arxiv id deferred so we don't block the M3.3
  collection runner currently using the venv.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-08 20:03:42 -06:00
..
__init__.py M0.3: Implement contract v1 Pydantic models with tests 2026-04-08 14:00:45 -06:00
test_agent.py fix(observability): persist full ResearchResult and per-item trace events 2026-04-08 19:27:33 -06:00
test_arxiv_ingest.py feat(arxiv): ingest pipeline (M5.1.1) 2026-04-08 20:03:42 -06:00
test_cli.py fix(observability): persist full ResearchResult and per-item trace events 2026-04-08 19:27:33 -06:00
test_costs.py M2.5.2: Cost ledger with price table (#25) 2026-04-08 15:52:25 -06:00
test_models.py depth flag now drives constraint defaults (#30) 2026-04-08 16:27:38 -06:00
test_obs.py M2.5.1: Structured application logger via structlog (#24) 2026-04-08 15:46:51 -06:00
test_server.py M1.4: MCP server wrapping web researcher 2026-04-08 14:41:13 -06:00
test_tools.py M1.1: Search and fetch tools with tests 2026-04-08 14:17:18 -06:00
test_trace.py fix(observability): persist full ResearchResult and per-item trace events 2026-04-08 19:27:33 -06:00