skill_optimizer
diapason.learning.agents.skill_optimizer
¶
SkillOptimizer — per-skill DSPy/GEPA optimization wrapper (Plan 2A).
Buckets traces by skill name, runs the underlying optimizer on each skill's
bucket, and writes the result as a sidecar overlay file in
~/.diapason/learning/skills/<skill-name>/optimized.toml.
The actual DSPy/GEPA invocation is done in _run_dspy / _run_gepa,
which are isolated for easy mocking in tests. In Plan 2A these are
deliberately minimal — they call the existing optimizer modules and extract
the description + few-shot examples. Plan 2B will measure the impact via
benchmarks.
SkillOptimizationResult
dataclass
¶
Result of optimizing a single skill.
SkillOptimizer
¶
Per-skill optimization wrapper around DSPyAgentOptimizer / GEPA.
Parameters¶
min_traces_per_skill:
Minimum trace count for a skill to be eligible for optimization.
optimizer:
"dspy" or "gepa". Determines which underlying optimizer is
called inside _run_dspy / _run_gepa.
optimize(trace_store, skill_manager, *, overlay_dir=None)
¶
Run the per-skill optimization loop.
Returns a dict mapping skill name to result. Writes overlay TOML files for each skill that produced output.