goldstein/infoxtractor
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
infoxtractor/tests/unit
History
Dirk Riemann 34f8268cd5
All checks were successful
tests / test (push) Successful in 1m8s
Details
tests / test (pull_request) Successful in 1m18s
Details
fix(genai): inject JSON schema into Ollama system prompt 
format=json loose mode gives valid JSON but no shape — models default
to emitting {} when the system prompt doesn't list fields. Prepend a
schema-guidance system message with the full Pydantic schema (after
the existing null-branch sanitiser) so the model sees exactly what
shape to produce. Pydantic still validates on parse.

Unit tests updated to check the schema message is prepended without
disturbing the caller's own messages.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-18 14:02:25 +02:00
..
__init__.py feat(scaffold): project skeleton with uv + pytest + forgejo CI 2026-04-18 10:36:43 +02:00
test_alembic_smoke.py feat(store): Alembic scaffolding + initial ix_jobs migration (spec §4) 2026-04-18 11:37:21 +02:00
test_app_wiring.py feat(app): production wiring — factories, pipeline, /healthz real probes 2026-04-18 12:09:11 +02:00
test_config.py fix(deploy): switch to network_mode: host — reach postgis + ollama on loopback 2026-04-18 13:00:02 +02:00
test_contracts.py feat(contracts): ResponseIX + Provenance + Job envelope (spec §3, §9.3) 2026-04-18 10:50:22 +02:00
test_errors.py feat(errors): add IXException + IXErrorCode per spec §8 2026-04-18 10:46:01 +02:00
test_factories.py feat(app): production wiring — factories, pipeline, /healthz real probes 2026-04-18 12:09:11 +02:00
test_genai_fake.py feat(clients): OCRClient + GenAIClient protocols + fakes (spec §6.2, §6.3) 2026-04-18 11:08:24 +02:00
test_genai_step.py chore(model): switch default IX_DEFAULT_MODEL to qwen3:14b (already on host) 2026-04-18 12:20:23 +02:00
test_ingestion_fetch.py feat(ingestion): fetch_file + MIME sniff + DocumentIngestor (spec §6.1) 2026-04-18 11:12:00 +02:00
test_ingestion_mime.py feat(ingestion): fetch_file + MIME sniff + DocumentIngestor (spec §6.1) 2026-04-18 11:12:00 +02:00
test_ingestion_pages.py feat(ingestion): fetch_file + MIME sniff + DocumentIngestor (spec §6.1) 2026-04-18 11:12:00 +02:00
test_ocr_fake.py feat(clients): OCRClient + GenAIClient protocols + fakes (spec §6.2, §6.3) 2026-04-18 11:08:24 +02:00
test_ocr_step.py feat(pipeline): OCRStep — run OCR + page tags + SegmentIndex (spec §6.2) 2026-04-18 11:15:46 +02:00
test_ollama_client.py fix(genai): inject JSON schema into Ollama system prompt 2026-04-18 14:02:25 +02:00
test_pipeline.py feat(pipeline): Step ABC + Pipeline runner + Timer (spec §3, §4) 2026-04-18 11:06:46 +02:00
test_pipeline_end_to_end.py test(pipeline): end-to-end hermetic test with fakes + synthetic fixture 2026-04-18 11:24:29 +02:00
test_provenance_mapper.py feat(provenance): mapper + verifier for ReliabilityStep (spec §9.4, §6) 2026-04-18 11:01:19 +02:00
test_provenance_normalize.py feat(provenance): normalisers + short-value skip rule (spec §6) 2026-04-18 10:56:31 +02:00
test_provenance_verify.py feat(provenance): mapper + verifier for ReliabilityStep (spec §9.4, §6) 2026-04-18 11:01:19 +02:00
test_reliability_step.py feat(pipeline): ReliabilityStep — writes reliability flags (spec §6) 2026-04-18 11:20:18 +02:00
test_response_handler_step.py feat(pipeline): ResponseHandlerStep — shape-up final payload (spec §8) 2026-04-18 11:21:36 +02:00
test_scaffolding.py feat(scaffold): project skeleton with uv + pytest + forgejo CI 2026-04-18 10:36:43 +02:00
test_segment_index.py feat(segmentation): SegmentIndex + prompt-text formatter (spec §9.1) 2026-04-18 10:53:46 +02:00
test_setup_step.py feat(pipeline): SetupStep — validate + fetch + MIME + pages (spec §6.1) 2026-04-18 11:14:04 +02:00
test_surya_client.py feat(ocr): SuryaOCRClient — real OCR backend (spec §6.2) 2026-04-18 12:04:19 +02:00
test_use_case_bank_statement_header.py chore(model): switch default IX_DEFAULT_MODEL to qwen3:14b (already on host) 2026-04-18 12:20:23 +02:00
test_use_case_registry.py feat(use_cases): registry + bank_statement_header (spec §7) 2026-04-18 10:51:43 +02:00