Align all DEFAULT_SKELETON_RATIO / _DEFAULT_SKELETON_RATIO constants
to the spec-required value of 0.15 (docs/specification.md line 35294).
Previously three modules used divergent defaults:
- skeleton_compressor.py: 0.3 (2x the spec value)
- depth_breadth_projection.py: 0.2 (33% above spec)
- project_context.py: 0.2 (33% above spec)
This caused child plans to receive 2-3x more skeleton context than
intended, and produced inconsistent behaviour depending on whether
skeleton compression was invoked via the CLI or the service layer.
Changes:
- Set DEFAULT_SKELETON_RATIO = 0.15 in skeleton_compressor.py
- Set DEFAULT_SKELETON_RATIO = 0.15 in depth_breadth_projection.py
- Set _DEFAULT_SKELETON_RATIO = 0.15 in project_context.py
- Update Behave feature tests to assert the 0.15 default value
- Add new scenario to project_context_cov3.feature asserting
_DEFAULT_SKELETON_RATIO == 0.15 in _default_acms_config()
ISSUES CLOSED: #2909
Core domain types (FragmentProvenance, ContextFragment, ContextBudget,
ContextPayload) now extend their CRP counterparts via Pydantic v2
inheritance, ensuring isinstance compatibility across the model
hierarchy.
Key changes:
- CRP base types made frozen=True (no consumer mutates them)
- CRP AssembledContext fields changed from list to tuple (frozen consistency)
- Core types extend CRP bases: FragmentProvenance(CRPFragmentProvenance),
ContextFragment(CRPContextFragment), ContextBudget(CRPContextBudget),
ContextPayload(CRPAssembledContext)
- Removed duplicate ContextFragment dataclass from skeleton_compressor
- Updated project_context.py to pass tuples to frozen AssembledContext
- Added Behave tests (10 scenarios), Robot integration tests (3 cases),
and ASV benchmarks for the unified hierarchy
- Updated Known Limitations table in docs/reference/acms.md
ISSUES CLOSED: #569
Implemented SkeletonCompressorService for ACMS context inheritance, producing
compressed context representations for propagation from parent plans to child
plans. Key design decisions and implementation details:
- SkeletonMetadata (frozen Pydantic model): records ratio, original_tokens,
compressed_tokens, and source_decision_ids for full auditability of each
compression pass. Persisted on Plan.skeleton_metadata.
- SkeletonCompressorService: stateless service accepting a list of
ContextFragment objects and a skeleton_ratio in [0.0, 1.0]. Fragments are
sorted by relevance descending with a stable secondary sort on fragment_id
to guarantee deterministic output. Token budget is original_tokens*(1-ratio);
fragments are greedily selected until budget is exhausted.
- Ratio semantics: 0.0 = no compression (pass-through), 1.0 = maximum
compression (single top fragment only), None = default 0.3.
- Integration: Plan model gains optional skeleton_metadata field exposed in
as_cli_dict() under the 'skeleton' key. Service registered in DI container
as skeleton_compressor_service (Singleton, stateless).
- Tests: 22 BDD scenarios (features/skeleton_compressor.feature) covering
ratio validation, stable ordering, metadata correctness, edge cases, and
plan model integration. 6 Robot Framework smoke tests. ASV benchmark suites
at 10/100/1000 fragment scales.
- Documentation: docs/reference/skeleton_compressor.md with ratio table,
algorithm description, metadata schema, and multi-decision plan example.
ISSUES CLOSED: #194
freemo