faligam 56d6415e68 fix(crawler): prioritize usable source retrieval over equal byte splits ...

Fetch candidate pages sequentially with the full remaining download budget instead of dividing a quick run's 500 KB equally across every URL. This avoids aborting otherwise readable pages at roughly 33 KB before claim extraction can inspect them.

Account for bytes consumed by failed downloads, preserve fetch errors in source responses, and fail runs with no successfully extracted document using an actionable error. Keep attempted sources on failed runs for diagnostics and cover the allocation and no-usable-source paths with regression tests.

2026-09-07 14:04:48 +02:00

..

models

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

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

stages

stage22: Abschluss & Production Readiness — E2E-Tests, CHANGELOG, Dokumentation

2026-09-05 15:03:48 +00:00

conftest.py

Stage 0: Repository und Architekturgrundlage

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

test_api_key_auth.py

Implement persistent API-key authentication

2026-09-06 17:23:05 +02:00

test_backend_pipeline_repairs.py

fix(crawler): prioritize usable source retrieval over equal byte splits

2026-09-07 14:04:48 +02:00

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

Fix research pipeline budget tracking

2026-09-07 11:56:13 +02:00

test_deletion_protection.py

Add protected soft deletion for research runs

2026-09-07 12:34:41 +02:00

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

fix research result handoff and synthesis provenance

2026-09-07 13:21:33 +02:00

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