generated from coulomb/repo-seed
tegwick
0a83e908ce
T01 — task-type taxonomy. docs/routing-task-types.md names the five generation stages as the default identity-mapped task types (summarize-source, extract-entities, extract-relations, evaluate-entity, synthesize-report) and records the recommended quality floors per stage. The taxonomy explicitly does not decide which adapter ships per task type, where the ledger lives, or what a quality score means — those stay with the caller per the LLM-WP-0004 scope guardrail. T02 — RoutingAssistedGenerationAdapter bridge in src/infospace_bench/routing.py. Wraps any llm-connect RoutingPolicy or AdaptiveRoutingPolicy as an infospace-bench AssistedGenerationAdapter: maps stage_id -> task_type (overridable), resolves an LLMAdapter, delegates execute_prompt with a configurable RunConfig, and surfaces the resolved adapter id, task type, model, usage, and finish_reason back on AssistedGenerationResult.metadata. Provider tag stays back-compatible with the strings already used in run records and the budget rollup (openrouter / claude_code / openai / gemini / mock / routing). T05 — eight tests in tests/test_routing_adapter.py cover: static-policy per-stage resolution, stage_to_task_type overrides, default-mapping completeness, fall-through for unmapped stage ids, the adaptive path selecting the cheaper qualifying adapter when a quality_floor is set, adaptive policy falling back to static when no floor is set, response metadata round-trip with provider tagging, and estimated_cost_per_1k pass-through. Adds llm-connect as a path dependency on pyproject.toml and to the pytest pythonpath. Static OpenRouter and fixture paths are unchanged; this commit only adds the option of routing. 139 tests pass, 1 skipped (the OpenRouter live smoke, gated as before). T03 (shadow-mode integration) and T04 (CLI + per-stage chosen-adapter in the generation report) follow next. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
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.mdwiki/ProductRequirementsDocument.mdwiki/FunctionalRequirementsSpecification.mdSCOPE.mddocs/infospace-layout.mddocs/evaluation-and-inspection.mddocs/reference-pilot-decision.mddocs/markitect-main-scope-assessment.mddocs/markitect-tool-adapter.mddocs/entity-relation-model.mddocs/evaluation-history-and-metrics.mddocs/workflow-generation-pipeline.mddocs/kontextual-engine-boundary.mddocs/orthogonal-successor-roadmap.mddocs/legacy-infospace-feature-inventory.mddocs/successor-boundary-interface-map.mddocs/replacement-acceptance-matrix.mddocs/legacy-command-parity.mddocs/legacy-infospace-migration-guide.mddocs/replacement-readiness-decision.mddocs/wealth-vsm-generation-pipeline.mddocs/generic-source-generator.mddocs/agentic-memory-profile-pilot.mddocs/lefevre-epub3-validation.mdinfospaces/bootstrap-pilot/infospaces/wealth-vsm-legacy-slice/infospaces/wealth-vsm-generation-pilot/infospaces/agentic-memory-profile-pilot/workplans/
Current development command:
python3 -m pytest