infospace-bench/tests
tegwick debd2b8e69 IB-WP-0020-T04: example routing config + live routing smoke
examples/routing/trading-literature.yaml is the checked-in starting
config for a Lefevre-style run. It applies the IB-WP-0018 task-type
taxonomy: cheap candidates for summary + evaluation, smart candidates
for entity + relation extraction, and a separate baseline rule wiring
claude_code for a follow-on T05 ShadowingAdapter step. Workspace-
relative ledger_path keeps adaptive observations with the workspace.

tests/test_routing_config.py gains a regression test that asserts the
shipped example parses cleanly, every stage in stage_to_task_type maps
to a declared task type, and the baseline candidate uses the
claude_code provider — so the example will not bit-rot silently.

tests/test_openrouter_live.py gains test_provider_routing_one_chapter_live_smoke
gated on the same INFOSPACE_BENCH_ENABLE_LIVE_OPENROUTER + OPENROUTER_API_KEY
opt-in as the existing static smoke. It builds a one-candidate routing
config, runs a single chapter through --provider routing, and asserts
the per-stage adapter-choices report section names the routed model
and the routed artifacts carry adapter_id provenance.

docs/generic-source-generator.md gains a "Live runs with --provider
routing" subsection that walks through the one-command routed run,
explains the --quality-floor override, and points at the parallel
live smoke test.

174 tests pass, 2 skipped (both live smokes, correctly gated).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-18 22:19:54 +02:00
..
fixtures/lefevre IB-WP-0016-T05: deterministic Lefevre acceptance fixture 2026-05-17 22:31:17 +02:00
test_agentic_memory_profile.py Agentic memory profile 2026-05-15 16:01:35 +02:00
test_archive.py archive: include contracts/, schemas/; report skipped top-level dirs 2026-05-17 12:21:19 +02:00
test_budget_registry.py IB-WP-0020-T03: routing CLI flags 2026-05-18 22:08:51 +02:00
test_cli.py IB-WP-0014: archive-list, restore, retention annotation, docs (T03-T05) 2026-05-17 11:46:23 +02:00
test_engine_boundary.py engine and lifecycle 2026-05-14 16:26:42 +02:00
test_epub3_intake.py IB-WP-0016-T02: chapter-aware chunking and stable IDs 2026-05-17 15:52:47 +02:00
test_evaluation.py Initial implementation 2026-05-14 11:32:25 +02:00
test_evaluation_history.py eval history and metrics 2026-05-14 15:35:04 +02:00
test_generic_generator.py generic source-to-infospace generator 2026-05-14 19:33:22 +02:00
test_inspection.py Initial implementation 2026-05-14 11:32:25 +02:00
test_lefevre_fixture.py IB-WP-0016-T07: review report and output policy; close IB-WP-0016 2026-05-18 01:22:41 +02:00
test_legacy_pilot.py Kontextual Engine Integration Boundary 2026-05-14 16:43:29 +02:00
test_lifecycle.py Initial implementation 2026-05-14 11:32:25 +02:00
test_markdown_adapter.py markitect-tool integration 2026-05-14 14:53:16 +02:00
test_openrouter_live.py IB-WP-0020-T04: example routing config + live routing smoke 2026-05-18 22:19:54 +02:00
test_plan_scale.py IB-WP-0016-T03: scale-aware planning 2026-05-17 18:18:09 +02:00
test_reference_pilot.py Initial implementation 2026-05-14 11:32:25 +02:00
test_replacement_readiness.py command parity and migration guide 2026-05-14 17:16:39 +02:00
test_routing_adapter.py IB-WP-0018-T03+T04: shadow sampling + report/CLI surfacing; close IB-WP-0018 2026-05-18 11:52:05 +02:00
test_routing_cli.py IB-WP-0020-T03: routing CLI flags 2026-05-18 22:08:51 +02:00
test_routing_config.py IB-WP-0020-T04: example routing config + live routing smoke 2026-05-18 22:19:54 +02:00
test_semantics.py entity relationship model 2026-05-14 15:06:17 +02:00
test_trading_literature_profile.py IB-WP-0016-T04: trading-literature profile 2026-05-17 18:59:45 +02:00
test_wealth_vsm_generation.py infospace pipeline for wealth of nations example 2026-05-14 18:04:38 +02:00
test_workflow.py acceptance matrix and workflow generation 2026-05-14 16:01:32 +02:00