NSCT Agent 8ea6269f9a feat(stage21): implement reproducibility — research_run_hash, full provenance tracking ...

- compute_research_run_hash(): deterministic SHA256 from query+budget+created_at
- ProvenanceEntry / ProvenanceLog: step-by-step trace with inputs, outputs, metadata, errors
- ResearchRun model: research_run_hash field (64-char hex)
- ResearchRunProvenance SQLAlchemy table for DB persistence
- Orchestrator: auto-log provenance before/after each pipeline step
- 35 tests: hash determinism, entry/log methods, storage model, integration

2026-09-05 14:27:45 +00:00

..

models

fix(stage11): resolve subagent merge conflicts — audio models, vision fix, test fixes

2026-08-25 17:29:17 +00:00

stages

feat(stage21): implement reproducibility — research_run_hash, full provenance tracking

2026-09-05 14:27:45 +00:00

conftest.py

Stage 0: Repository und Architekturgrundlage

2026-08-23 11:33:45 +00:00

test_cli.py

feat(stage15): implement CLI with search, status, report, sources, claims, list, delete

2026-08-27 17:09:36 +00:00

test_context_budget_integration.py

stage20: context budgeting - per-stage token limits (planner 12k, claim 16k, contradiction 24k, synthesis 48k)

2026-08-29 08:57:18 +00:00

test_context_budget.py

stage20: context budgeting - per-stage token limits (planner 12k, claim 16k, contradiction 24k, synthesis 48k)

2026-08-29 08:57:18 +00:00

test_crawler.py

Stage 3: Crawler und Content Extraction

2026-08-23 12:53:19 +00:00

test_health.py

Stage 0: Repository und Architekturgrundlage

2026-08-23 11:33:45 +00:00

test_logging.py

feat(stage16): implement observability — structured logging, metrics, tracing

2026-08-27 19:44:46 +00:00

test_metrics.py

feat(stage16): implement observability — structured logging, metrics, tracing

2026-08-27 19:44:46 +00:00

test_planner.py

Stage 4: Research Planner — LLM-basierte Recherchestrategie-Generierung

2026-08-23 13:28:23 +00:00

test_priority_limiter.py

fix: priority_queue async context methods (async_fix for Python 3.14+). Add test_priority_limiter.py tests for async context manager

2026-09-05 13:36:49 +00:00

test_rest_research.py

feat(stage14): implement REST API for research lifecycle

2026-08-27 16:07:47 +00:00

test_search.py

STAGE 2: Search Provider Abstraction für NSCT

2026-08-23 12:16:29 +00:00

test_stage13_gap_analysis.py

feat(stage13): implement Iterative Research / Gap Analysis\n\nImplement Gap Analysis Engine (Stage 13):\n- GapAnalysisEngine: detect single-source claims, contradictions,\n missing primary sources, weak evidence\n- IterationReport: structured gap findings with severity & target\n- GapSearchQuery: derived search queries per gap finding\n- Integration into ResearchOrchestrator: runs gap analysis after\n extracting, then executes gap searches iteratively\n- 17 tests covering all analysis categories and edge cases

2026-08-26 11:19:35 +00:00