tegwick f818acfc62 IB-WP-0018-T03+T04: shadow sampling + report/CLI surfacing; close IB-WP-0018
T03 — wrap_with_shadow_sampling() helper in routing.py: builds a
llm-connect ShadowingAdapter around any candidate LLMAdapter with a
caller-supplied baseline, grader, and QualityLedger. async_shadow=True
by default so production load is not doubled; on_shadow_error escape
hatch keeps caller logs informed when a baseline outage swallows the
shadow path. The returned adapter is still an LLMAdapter so it slots
into a RoutingPolicy rule without further code change.

T04 — generation report enrichment plus a small CLI helper:

- _collect_adapter_choices walks artifact provenance, groups by
  (stage_id, adapter_id), and surfaces calls + prompt/completion tokens
  per (stage, adapter) pair in a new ## Per-stage adapter choices
  section. Runs that did not go through the bridge have no
  provider_metadata.adapter_id and emit an empty list, so fixture-only
  reports stay terse.
- summarise_quality_ledger() rolls a llm-connect QualityLedger up by
  (task_type, adapter_id) with mean quality, mean cost, observations,
  and cumulative tokens.
- infospace-bench routing ledger <path> CLI prints the rollup as JSON.

Five new tests cover shadow happy-path, shadow failure isolation,
ledger rollup, the routing CLI, and the report's adapter-choice
aggregation. Closes IB-WP-0018: T01-T05 are all done and the workplan
status flips from blocked to done now that LLM-WP-0004's primitives
have shipped.

144 tests pass, 1 skipped (the OpenRouter live smoke, gated as before).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-18 11:52:05 +02:00
2026-05-03 19:25:29 +02:00
2026-05-03 19:25:29 +02:00
2026-05-03 16:52:54 +00:00
2026-05-15 16:01:35 +02:00

infospace-bench

Workspace and service for creating, developing, evaluating, and inspecting structured knowledge spaces.

This repo is the application-layer successor for the infospace work that began inside markitect-main. It focuses on concrete infospaces and their lifecycle, while lower-level markdown tooling and runtime orchestration remain in sibling projects.

Start with:

  • INTENT.md
  • wiki/ProductRequirementsDocument.md
  • wiki/FunctionalRequirementsSpecification.md
  • SCOPE.md
  • docs/infospace-layout.md
  • docs/evaluation-and-inspection.md
  • docs/reference-pilot-decision.md
  • docs/markitect-main-scope-assessment.md
  • docs/markitect-tool-adapter.md
  • docs/entity-relation-model.md
  • docs/evaluation-history-and-metrics.md
  • docs/workflow-generation-pipeline.md
  • docs/kontextual-engine-boundary.md
  • docs/orthogonal-successor-roadmap.md
  • docs/legacy-infospace-feature-inventory.md
  • docs/successor-boundary-interface-map.md
  • docs/replacement-acceptance-matrix.md
  • docs/legacy-command-parity.md
  • docs/legacy-infospace-migration-guide.md
  • docs/replacement-readiness-decision.md
  • docs/wealth-vsm-generation-pipeline.md
  • docs/generic-source-generator.md
  • docs/agentic-memory-profile-pilot.md
  • docs/lefevre-epub3-validation.md
  • infospaces/bootstrap-pilot/
  • infospaces/wealth-vsm-legacy-slice/
  • infospaces/wealth-vsm-generation-pilot/
  • infospaces/agentic-memory-profile-pilot/
  • workplans/

Current development command:

python3 -m pytest
Description
Infospace project/workbench layer to create, develop, evaluate, and inspect concrete infospaces such as books, departments, projects, domains, or research corpora.
Readme MIT-0 1.4 MiB
Languages
Python 99.9%
Makefile 0.1%