DSPy 3.2.1 refresh
- Retargeted install and maintainer validation guidance from exact DSPy
3.2.0to current3.2.1, while keeping committed example artifacts labeled by the DSPy version that produced them. - Added
scripts/check_dspy_surface.pyto validate the live DSPy API surface taught by the skills (GEPA,BetterTogether,Evaluate,LM,SIMBA,Embedder,configure_cache, and current primitives). - Updated GEPA guidance for current upstream best practices: train-heavy GEPA splits, GPT-5-class reflection model shape, literal-dict metric mismatch, supported
component_selectorstrings, and when to trydspy.SIMBA. - Tightened the evaluation-harness reference around DSPy 3.2.1 semantics: GEPA-compatible five-argument metric signatures and aggregation-safe metric return shapes.
- Added production cache guidance for
dspy.configure_cache(restrict_pickle=True), project-localDSPY_CACHEDIR, and provider-side prompt caching.
Validation
uv run --with pytest python -m pytest tests/ -v-> 114 passedenv -u UV_EXCLUDE_NEWER uv run --with dspy==3.2.1 python scripts/check_dspy_surface.py-> passedfor f in skills/*/example_*.py; do env -u UV_EXCLUDE_NEWER uv run --with dspy==3.2.1 python "$f" --dry-run; done-> passedgit diff --check HEAD-> passed
Review
PR: #8
The release branch passed a read-only adversarial subagent review. Initial blockers were fixed and the targeted rereview returned: No blocking findings. Approved for release.