markitect-main/markitect/prompts
tegwick 144a88c0c2 feat(prompts): add batch LLM evaluation orchestrator (S1.6)
BatchEvaluator runs evaluation prompts across item batches with
incremental evaluation (skip unchanged via content digest), per-item
error isolation, progress callbacks, and aggregate token usage tracking.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-19 01:40:13 +01:00
..
dependencies feat(prompts): implement Phase 5 - Dependency Tracking (FR-6) 2026-02-09 13:18:18 +01:00
execution feat(prompts): add batch LLM evaluation orchestrator (S1.6) 2026-02-19 01:40:13 +01:00
incremental feat(prompts): implement Phase 6 - Incremental Execution (FR-7, FR-8) 2026-02-09 13:18:27 +01:00
quality feat(prompts): implement Phase 7 - Quality & Validation (FR-9, FR-10) 2026-02-09 13:31:37 +01:00
queries feat(prompts): implement Phase 8 - Observability & Traceability (FR-11) 2026-02-09 20:32:18 +01:00
repositories fix(prompts): fix three infrastructure bugs in prompt dependency resolution 2026-02-11 20:53:02 +01:00
resolver fix(prompts): fix three infrastructure bugs in prompt dependency resolution 2026-02-11 20:53:02 +01:00
services feat(prompts): implement Phase 2 - Templates & Macros (FR-2) 2026-02-08 22:34:22 +01:00
templates fix(prompts): fix three infrastructure bugs in prompt dependency resolution 2026-02-11 20:53:02 +01:00
traceability feat(prompts): implement Phase 8 - Observability & Traceability (FR-11) 2026-02-09 20:32:18 +01:00
visualization feat(prompts): implement Phase 8 - Observability & Traceability (FR-11) 2026-02-09 20:32:18 +01:00
__init__.py feat(prompts): implement Phase 1 - Foundation (FR-1) 2026-02-08 22:30:26 +01:00
cli.py feat(prompts): implement Phase 8 - Observability & Traceability (FR-11) 2026-02-09 20:32:18 +01:00
models.py fix(prompts): fix three infrastructure bugs in prompt dependency resolution 2026-02-11 20:53:02 +01:00