Files
repo-scoping/src/repo_registry/core/service.py

3393 lines
125 KiB
Python

from __future__ import annotations
from collections.abc import Sequence
from dataclasses import asdict, replace
from typing import Any
from repo_registry.acceptance import (
blocking_quality_gate_outcomes,
evaluate_candidate_capability_quality,
)
from repo_registry.core.models import (
AbilitySummary,
AnalysisRunDiff,
AnalysisRunDiffItem,
AnalysisRunDiffSection,
AnalysisRun,
CapabilitySummary,
CandidateAbility,
CandidateCapability,
CandidateEvidence,
CandidateFeature,
CandidateGraph,
CharacteristicRebuildResult,
ContentChunk,
DependencyEdge,
DependencyGraph,
DependencyGraphViewProfile,
DependencyImpactAnalysis,
DependencyImpactItem,
ExpectationGap,
ObservedFact,
Repository,
RepositoryAbilityMap,
ReviewDecision,
ScanSummary,
SearchResult,
)
from repo_registry.candidate_graph.generator import CandidateGraphGenerator
from repo_registry.candidate_graph.normalization import normalize_candidate_drafts
from repo_registry.content_indexing.extractor import ContentExtractor
from repo_registry.core.logging import log_operation
from repo_registry.llm_extraction.extractor import LLMCandidateExtractor
from repo_registry.llm_extraction.mapper import LLMExtractionMapper
from repo_registry.repo_ingestion.git import GitIngestionService
from repo_registry.repo_ingestion.metadata import RepositoryMetadataExtractor
from repo_registry.repo_scanning.scanner import DeterministicScanner
from repo_registry.semantic import EmbeddingProvider, cosine_similarity
from repo_registry.storage.sqlite import RegistryStore
class RegistryService:
"""Application service for the manual registry MVP."""
def __init__(
self,
store: RegistryStore,
ingestion: GitIngestionService | None = None,
llm_extractor: LLMCandidateExtractor | None = None,
embedding_provider: EmbeddingProvider | None = None,
) -> None:
self.store = store
self.scanner = DeterministicScanner()
self.ingestion = ingestion or GitIngestionService()
self.metadata_extractor = RepositoryMetadataExtractor()
self.candidate_generator = CandidateGraphGenerator()
self.content_extractor = ContentExtractor()
self.llm_extractor = llm_extractor
self.llm_mapper = LLMExtractionMapper()
self.embedding_provider = embedding_provider
def register_repository(
self,
*,
url: str,
name: str | None = None,
description: str | None = None,
branch: str = "main",
access_username: str | None = None,
access_password: str | None = None,
) -> Repository:
if name is None or description is None:
checkout = self.ingestion.resolve(
url,
branch=branch,
access_username=access_username,
access_password=access_password,
)
metadata = self.metadata_extractor.extract(checkout.source_path, url)
else:
metadata = None
repository = self.store.create_repository(
name=name or (metadata.name if metadata is not None else "repository"),
url=url,
description=description
or (metadata.description if metadata is not None else None),
branch=branch,
)
log_operation(
"repository_registered",
repository_id=repository.id,
repository_name=repository.name,
branch=repository.branch,
metadata_imported=metadata is not None,
)
return repository
def list_repositories(self) -> list[Repository]:
return self.store.list_repositories()
def get_repository(self, repository_id: int) -> Repository:
return self.store.get_repository(repository_id)
def update_repository(
self,
repository_id: int,
*,
name: str | None = None,
description: str | None = None,
branch: str | None = None,
) -> Repository:
return self.store.update_repository(
repository_id,
name=name,
description=description,
branch=branch,
)
def delete_repository(self, repository_id: int) -> None:
self.store.delete_repository(repository_id)
def analyze_repository(
self,
repository_id: int,
*,
source_path: str | None = None,
use_cached_checkout: bool = False,
use_llm_assistance: bool = True,
trusted_auto_approve: bool = False,
access_username: str | None = None,
access_password: str | None = None,
) -> ScanSummary:
repository = self.store.get_repository(repository_id)
run = self.store.create_analysis_run(repository_id)
self.store.update_repository_status(repository_id, "analyzing")
log_operation(
"analysis_started",
repository_id=repository_id,
analysis_run_id=run.id,
source_override=source_path is not None,
)
try:
if source_path is None:
if use_cached_checkout:
checkout = self.ingestion.cached_checkout(repository.url)
if checkout is None:
raise RuntimeError(
"cached checkout was requested, but no checkout exists "
"for this repository"
)
else:
checkout = self.ingestion.resolve(
repository.url,
branch=repository.branch,
access_username=access_username,
access_password=access_password,
)
scan_source = checkout.source_path
else:
scan_source = source_path
scan_result = self.scanner.scan(scan_source)
except Exception as exc:
failed_run = self.store.fail_analysis_run(repository_id, run.id, str(exc))
log_operation(
"analysis_failed",
repository_id=repository_id,
analysis_run_id=run.id,
error=str(exc),
)
return ScanSummary(analysis_run=failed_run, snapshot=None, facts=[])
completed_run = self.store.complete_analysis_run(
repository_id,
run.id,
scan_result,
)
snapshot = (
self.store.get_snapshot(completed_run.snapshot_id)
if completed_run.snapshot_id is not None
else None
)
facts = self.store.list_observed_facts(repository_id, completed_run.id)
chunks = self.content_extractor.extract(scan_result.source_path, facts)
self.store.replace_content_chunks(
repository_id,
completed_run.id,
completed_run.snapshot_id,
chunks,
)
stored_chunks = self.store.list_content_chunks(repository_id, completed_run.id)
try:
candidates, candidate_source = self._generate_candidates(
repository,
facts,
stored_chunks,
use_llm_assistance=use_llm_assistance,
)
except Exception as exc:
log_operation(
"llm_extraction_failed",
repository_id=repository_id,
analysis_run_id=completed_run.id,
error=str(exc),
)
self.store.create_review_decision(
repository_id,
completed_run.id,
action="llm_extraction_failed",
notes=str(exc),
)
candidates = self.candidate_generator.generate(
repository,
facts,
stored_chunks,
)
candidate_source = "deterministic"
candidates = normalize_candidate_drafts(candidates)
self.store.replace_candidate_graph(repository_id, completed_run.id, candidates)
if "llm" in candidate_source:
log_operation(
"llm_extraction_used",
repository_id=repository_id,
analysis_run_id=completed_run.id,
candidate_count=len(candidates),
)
self.store.create_review_decision(
repository_id,
completed_run.id,
action="llm_extraction_used",
notes=(
f"Generated {len(candidates)} candidate ability draft(s) "
f"from {candidate_source} candidate generation."
),
)
if trusted_auto_approve:
self.trusted_auto_approve_candidate_graph(
repository_id,
completed_run.id,
notes=(
"Trusted auto-populate mode reviewed candidate graph "
f"after {candidate_source} candidate generation."
),
)
log_operation(
"analysis_completed",
repository_id=repository_id,
analysis_run_id=completed_run.id,
fact_count=len(facts),
content_chunk_count=len(stored_chunks),
candidate_count=len(candidates),
candidate_source=candidate_source,
)
return ScanSummary(
analysis_run=completed_run,
snapshot=snapshot,
facts=facts,
)
def _generate_candidates(
self,
repository: Repository,
facts: list[ObservedFact],
chunks: list[ContentChunk],
*,
use_llm_assistance: bool = True,
):
deterministic = self.candidate_generator.generate(repository, facts, chunks)
if use_llm_assistance and self.llm_extractor is not None:
extracted = self.llm_extractor.extract(repository, chunks)
if extracted:
llm_candidates = self.llm_mapper.map(extracted, facts, chunks)
return (
self._merge_llm_candidates(llm_candidates, deterministic),
"llm+deterministic",
)
return deterministic, "deterministic"
def _merge_llm_candidates(
self,
llm_candidates: list,
deterministic: list,
) -> list:
if not deterministic:
return [
ability
for ability in llm_candidates
if self._candidate_ability_has_trusted_sources(ability)
]
merged_deterministic = list(deterministic)
trusted_llm = []
folded_capabilities = []
for ability in llm_candidates:
if self._candidate_ability_has_trusted_sources(ability):
trusted_llm.append(ability)
else:
folded_capabilities.extend(ability.capabilities)
if folded_capabilities:
target = merged_deterministic[0]
merged_deterministic[0] = replace(
target,
capabilities=[*target.capabilities, *folded_capabilities],
)
return [*trusted_llm, *merged_deterministic]
def _candidate_ability_has_trusted_sources(self, ability) -> bool:
if not ability.source_refs:
return False
return any(
ref.kind in {"intent", "documentation", "interface", "test", "example"}
and not ref.path.lower().endswith("scope.md")
for ref in ability.source_refs
)
def list_analysis_runs(self, repository_id: int) -> list[AnalysisRun]:
return self.store.list_analysis_runs(repository_id)
def get_analysis_run(self, repository_id: int, analysis_run_id: int) -> AnalysisRun:
return self.store.get_analysis_run(repository_id, analysis_run_id)
def list_abilities(self) -> list[AbilitySummary]:
return self.store.list_abilities()
def list_capabilities(self) -> list[CapabilitySummary]:
return self.store.list_capabilities()
def list_review_decisions(
self,
repository_id: int,
analysis_run_id: int | None = None,
) -> list[ReviewDecision]:
return self.store.list_review_decisions(repository_id, analysis_run_id)
def record_expectation_gap(
self,
repository_id: int,
*,
analysis_run_id: int | None = None,
expected_type: str,
expected_name: str,
source: str,
notes: str = "",
) -> ExpectationGap:
gap = self.store.create_expectation_gap(
repository_id,
analysis_run_id,
expected_type=expected_type,
expected_name=expected_name,
source=source,
notes=notes,
)
self.store.create_review_decision(
repository_id,
analysis_run_id,
action="record_expectation_gap",
notes=f"{source} expected {expected_type}: {expected_name}",
)
return gap
def list_expectation_gaps(
self,
repository_id: int,
analysis_run_id: int | None = None,
) -> list[ExpectationGap]:
return self.store.list_expectation_gaps(repository_id, analysis_run_id)
def list_observed_facts(
self,
repository_id: int,
analysis_run_id: int | None = None,
) -> list[ObservedFact]:
return self.store.list_observed_facts(repository_id, analysis_run_id)
def list_content_chunks(
self,
repository_id: int,
analysis_run_id: int | None = None,
) -> list[ContentChunk]:
return self.store.list_content_chunks(repository_id, analysis_run_id)
def candidate_graph(self, repository_id: int, analysis_run_id: int) -> CandidateGraph:
return self.store.get_candidate_graph(repository_id, analysis_run_id)
def rebuild_characteristics_from_scratch(
self,
repository_id: int,
*,
dry_run: bool = True,
confirm: bool = False,
source_path: str | None = None,
use_cached_checkout: bool = False,
use_llm_assistance: bool = True,
access_username: str | None = None,
access_password: str | None = None,
) -> CharacteristicRebuildResult:
if not dry_run and not confirm:
raise ValueError("confirmed rebuild requires confirm=True")
repository = self.store.get_repository(repository_id)
previous_counts = self._approved_counts(repository_id)
previous_ids = self._approved_ids(repository_id)
summary = self.analyze_repository(
repository_id,
source_path=source_path,
use_cached_checkout=use_cached_checkout,
use_llm_assistance=use_llm_assistance,
trusted_auto_approve=False,
access_username=access_username,
access_password=access_password,
)
if summary.analysis_run.status != "completed":
return CharacteristicRebuildResult(
repository=repository,
analysis_run=summary.analysis_run,
dry_run=dry_run,
confirmed=confirm,
cleared_approved=False,
previous_counts=previous_counts,
previous_ids=previous_ids,
candidate_counts={},
)
graph = self.store.get_candidate_graph(repository_id, summary.analysis_run.id)
candidate_counts = self._candidate_counts(graph)
cleared = False
if not dry_run:
self.store.clear_approved_characteristics(repository_id)
self.store.update_repository_status(repository_id, "analyzed")
cleared = True
action = (
"rebuild_characteristics_from_scratch"
if cleared
else "dry_run_rebuild_characteristics_from_scratch"
)
self.store.create_review_decision(
repository_id,
summary.analysis_run.id,
action=action,
notes=(
f"Previous approved counts: {previous_counts}. "
f"Previous approved IDs: {previous_ids}. "
f"New candidate counts: {candidate_counts}."
),
)
return CharacteristicRebuildResult(
repository=repository,
analysis_run=summary.analysis_run,
dry_run=dry_run,
confirmed=confirm,
cleared_approved=cleared,
previous_counts=previous_counts,
previous_ids=previous_ids,
candidate_counts=candidate_counts,
)
def approve_candidate_graph(
self,
repository_id: int,
analysis_run_id: int,
*,
notes: str = "",
action: str = "approve_candidate_graph",
) -> RepositoryAbilityMap:
graph = self.store.get_candidate_graph(repository_id, analysis_run_id)
pending_abilities = [
ability for ability in graph.abilities if ability.status == "candidate"
]
for ability in pending_abilities:
approved_ability_id = self._ensure_approved_ability(repository_id, ability)
for capability in ability.capabilities:
if capability.status != "candidate":
continue
approved_capability_id = self._ensure_approved_capability(
repository_id,
approved_ability_id,
ability.name,
capability,
)
for feature in capability.features:
if feature.status != "candidate":
continue
self.store.create_feature(
repository_id,
approved_capability_id,
name=feature.name,
type=feature.type,
location=feature.location,
confidence=feature.confidence,
source_refs=feature.source_refs,
primary_class=feature.primary_class,
attributes=feature.attributes,
)
for evidence in capability.evidence:
if evidence.status != "candidate":
continue
self.store.create_evidence(
repository_id,
approved_capability_id,
type=evidence.type,
reference=evidence.reference,
strength=evidence.strength,
target_kind=evidence.target_kind,
target_id=self._approved_evidence_target_id(
evidence,
approved_capability_id,
),
reference_kind=evidence.reference_kind,
reference_id=evidence.reference_id,
source_refs=evidence.source_refs,
)
if pending_abilities:
self.store.mark_candidate_graph_status(
repository_id,
analysis_run_id,
"approved",
)
self.store.create_review_decision(
repository_id,
analysis_run_id,
action=action,
notes=notes,
)
self.store.update_repository_status(repository_id, "indexed")
return self.store.get_ability_map(repository_id)
def trusted_auto_approve_candidate_graph(
self,
repository_id: int,
analysis_run_id: int,
*,
notes: str = "",
) -> RepositoryAbilityMap:
graph = self.store.get_candidate_graph(repository_id, analysis_run_id)
approved_count = 0
skipped_count = 0
approved_reasons: list[str] = []
skipped_reasons: list[str] = []
for ability in graph.abilities:
if ability.status != "candidate":
continue
candidate_capabilities = [
capability
for capability in ability.capabilities
if capability.status == "candidate"
]
safe_capabilities = []
for capability in candidate_capabilities:
safe, reason = self._trusted_auto_approve_capability_decision(capability)
if safe:
safe_capabilities.append(capability)
approved_reasons.append(f"{capability.name}: {reason}")
else:
skipped_reasons.append(f"{capability.name}: {reason}")
skipped_count += len(candidate_capabilities) - len(safe_capabilities)
if not safe_capabilities:
continue
approved_ability_id = self._ensure_approved_ability(repository_id, ability)
for capability in safe_capabilities:
self._create_approved_capability_subtree(
repository_id,
approved_ability_id,
capability,
)
self.store.mark_candidate_capability_status(
repository_id,
analysis_run_id,
capability.id,
"approved",
)
approved_count += 1
if len(safe_capabilities) == len(candidate_capabilities):
self.store.mark_candidate_ability_status(
repository_id,
analysis_run_id,
ability.id,
"approved",
)
if approved_count:
self.store.update_repository_status(repository_id, "indexed")
self.store.create_review_decision(
repository_id,
analysis_run_id,
action="trusted_auto_approve_candidate_graph",
notes=(
f"{notes} Auto-approved {approved_count} safe candidate "
f"capability(s); left {skipped_count} for review."
f"{self._trusted_auto_approve_notes(approved_reasons, skipped_reasons)}"
).strip(),
)
return self.store.get_ability_map(repository_id)
def _trusted_auto_approve_capability_safe(
self,
capability: CandidateCapability,
) -> bool:
safe, _reason = self._trusted_auto_approve_capability_decision(capability)
return safe
def _trusted_auto_approve_capability_decision(
self,
capability: CandidateCapability,
) -> tuple[bool, str]:
gate_outcomes = evaluate_candidate_capability_quality(capability)
blocking_outcomes = blocking_quality_gate_outcomes(gate_outcomes)
if blocking_outcomes:
criteria = ", ".join(
sorted({outcome.criterion_id for outcome in blocking_outcomes})
)
return False, f"quality gates require review ({criteria})"
has_source_refs = bool(capability.source_refs) or any(
feature.source_refs for feature in capability.features
)
if not has_source_refs:
return False, "missing source references"
if capability.primary_class == "repository-structure":
return False, "structural/dependency context requires curator review"
utility_relationships = self._candidate_utility_relationships(capability)
eligible_relationships = {"owned", "facade", "adapter"}
if not utility_relationships:
return False, "missing utility relationship"
if not (utility_relationships & eligible_relationships):
relationships = ", ".join(sorted(utility_relationships))
return False, f"utility relationship is not eligible ({relationships})"
if capability.primary_class == "llm-integration":
return True, "eligible LLM utility relationship with source support"
if capability.primary_class in {"interface", "API", "CLI", "callable", "api", "cli"}:
if capability.confidence >= 0.55:
return True, "owned interface with sufficient confidence"
return False, "owned interface confidence below trusted threshold"
if capability.features:
if capability.confidence >= 0.55:
return True, "eligible utility relationship with feature support"
return False, "feature-backed capability confidence below trusted threshold"
if capability.confidence >= 0.75:
return True, "eligible utility relationship with high confidence"
return False, "capability confidence below trusted threshold"
def _candidate_utility_relationships(
self,
capability: CandidateCapability,
) -> set[str]:
return {
attribute.removeprefix("utility-")
for attribute in capability.attributes
if attribute.startswith("utility-")
}
def _trusted_auto_approve_notes(
self,
approved_reasons: list[str],
skipped_reasons: list[str],
) -> str:
details: list[str] = []
if approved_reasons:
details.append("Approved: " + "; ".join(approved_reasons) + ".")
if skipped_reasons:
details.append("Skipped: " + "; ".join(skipped_reasons) + ".")
if not details:
return ""
return " " + " ".join(details)
def _approved_counts(self, repository_id: int) -> dict[str, int]:
ability_map = self.store.get_ability_map(repository_id)
capabilities = [
capability
for ability in ability_map.abilities
for capability in ability.capabilities
]
features = [
feature
for capability in capabilities
for feature in capability.features
]
evidence = [
item
for capability in capabilities
for item in capability.evidence
]
return {
"abilities": len(ability_map.abilities),
"capabilities": len(capabilities),
"features": len(features),
"evidence": len(evidence),
}
def _approved_ids(self, repository_id: int) -> dict[str, list[int]]:
ability_map = self.store.get_ability_map(repository_id)
capabilities = [
capability
for ability in ability_map.abilities
for capability in ability.capabilities
]
features = [
feature
for capability in capabilities
for feature in capability.features
]
evidence = [
item
for capability in capabilities
for item in capability.evidence
]
return {
"abilities": [ability.id for ability in ability_map.abilities],
"capabilities": [capability.id for capability in capabilities],
"features": [feature.id for feature in features],
"evidence": [item.id for item in evidence],
}
def _candidate_counts(self, graph: CandidateGraph) -> dict[str, int]:
capabilities = [
capability
for ability in graph.abilities
for capability in ability.capabilities
]
features = [
feature
for capability in capabilities
for feature in capability.features
]
evidence = [
item
for capability in capabilities
for item in capability.evidence
]
return {
"abilities": len(graph.abilities),
"capabilities": len(capabilities),
"features": len(features),
"evidence": len(evidence),
}
def accept_candidate_ability(
self,
repository_id: int,
analysis_run_id: int,
candidate_ability_id: int,
*,
notes: str = "",
) -> RepositoryAbilityMap:
graph = self.store.get_candidate_graph(repository_id, analysis_run_id)
ability = next(
(
item
for item in graph.abilities
if item.id == candidate_ability_id and item.status == "candidate"
),
None,
)
if ability is None:
raise ValueError(f"candidate ability {candidate_ability_id} is not pending")
approved_ability_id = self._ensure_approved_ability(repository_id, ability)
for capability in ability.capabilities:
if capability.status == "candidate":
self._create_approved_capability_subtree(
repository_id,
approved_ability_id,
capability,
)
self.store.mark_candidate_ability_status(
repository_id,
analysis_run_id,
candidate_ability_id,
"approved",
)
self._record_candidate_acceptance(
repository_id,
analysis_run_id,
"accept_candidate_ability",
notes or f"Accepted candidate ability: {ability.name}",
)
return self.store.get_ability_map(repository_id)
def accept_candidate_capability(
self,
repository_id: int,
analysis_run_id: int,
candidate_capability_id: int,
*,
notes: str = "",
) -> RepositoryAbilityMap:
graph = self.store.get_candidate_graph(repository_id, analysis_run_id)
parent_ability, capability = self._candidate_capability_with_parent(
graph,
candidate_capability_id,
)
if capability.status != "candidate":
raise ValueError(
f"candidate capability {candidate_capability_id} is not pending"
)
approved_ability_id = self._ensure_approved_ability(repository_id, parent_ability)
self._create_approved_capability_subtree(
repository_id,
approved_ability_id,
capability,
)
self.store.mark_candidate_capability_status(
repository_id,
analysis_run_id,
candidate_capability_id,
"approved",
)
self._record_candidate_acceptance(
repository_id,
analysis_run_id,
"accept_candidate_capability",
notes or f"Accepted candidate capability: {capability.name}",
)
return self.store.get_ability_map(repository_id)
def accept_candidate_feature(
self,
repository_id: int,
analysis_run_id: int,
candidate_feature_id: int,
*,
notes: str = "",
) -> RepositoryAbilityMap:
graph = self.store.get_candidate_graph(repository_id, analysis_run_id)
parent_ability, parent_capability, feature = self._candidate_feature_with_parent(
graph,
candidate_feature_id,
)
if feature.status != "candidate":
raise ValueError(f"candidate feature {candidate_feature_id} is not pending")
approved_ability_id = self._ensure_approved_ability(repository_id, parent_ability)
approved_capability_id = self._ensure_approved_capability(
repository_id,
approved_ability_id,
parent_ability.name,
parent_capability,
)
self.store.create_feature(
repository_id,
approved_capability_id,
name=feature.name,
type=feature.type,
location=feature.location,
confidence=feature.confidence,
source_refs=feature.source_refs,
primary_class=feature.primary_class,
attributes=feature.attributes,
)
self.store.mark_candidate_feature_status(
repository_id,
analysis_run_id,
candidate_feature_id,
"approved",
)
self._record_candidate_acceptance(
repository_id,
analysis_run_id,
"accept_candidate_feature",
notes or f"Accepted candidate feature: {feature.name}",
)
return self.store.get_ability_map(repository_id)
def accept_candidate_evidence(
self,
repository_id: int,
analysis_run_id: int,
candidate_evidence_id: int,
*,
notes: str = "",
) -> RepositoryAbilityMap:
graph = self.store.get_candidate_graph(repository_id, analysis_run_id)
parent_ability, parent_capability, evidence = (
self._candidate_evidence_with_parent(graph, candidate_evidence_id)
)
if evidence.status != "candidate":
raise ValueError(
f"candidate evidence {candidate_evidence_id} is not pending"
)
approved_ability_id = self._ensure_approved_ability(repository_id, parent_ability)
approved_capability_id = self._ensure_approved_capability(
repository_id,
approved_ability_id,
parent_ability.name,
parent_capability,
)
self.store.create_evidence(
repository_id,
approved_capability_id,
type=evidence.type,
reference=evidence.reference,
strength=evidence.strength,
target_kind=evidence.target_kind,
target_id=self._approved_evidence_target_id(
evidence,
approved_capability_id,
),
reference_kind=evidence.reference_kind,
reference_id=evidence.reference_id,
source_refs=evidence.source_refs,
)
self.store.mark_candidate_evidence_status(
repository_id,
analysis_run_id,
candidate_evidence_id,
"approved",
)
self._record_candidate_acceptance(
repository_id,
analysis_run_id,
"accept_candidate_evidence",
notes or f"Accepted candidate support: {evidence.reference}",
)
return self.store.get_ability_map(repository_id)
def diff_analysis_runs(
self,
repository_id: int,
base_analysis_run_id: int,
target_analysis_run_id: int,
) -> AnalysisRunDiff:
repository = self.store.get_repository(repository_id)
base_run = self.store.get_analysis_run(repository_id, base_analysis_run_id)
target_run = self.store.get_analysis_run(repository_id, target_analysis_run_id)
base_graph = self.store.get_candidate_graph(repository_id, base_analysis_run_id)
target_graph = self.store.get_candidate_graph(repository_id, target_analysis_run_id)
approved_map = self.store.get_ability_map(repository_id)
return AnalysisRunDiff(
repository=repository,
base_run=base_run,
target_run=target_run,
facts=self._diff_items(
self._fact_index(
self.store.list_observed_facts(repository_id, base_analysis_run_id)
),
self._fact_index(
self.store.list_observed_facts(repository_id, target_analysis_run_id)
),
),
chunks=self._diff_items(
self._chunk_index(
self.store.list_content_chunks(repository_id, base_analysis_run_id)
),
self._chunk_index(
self.store.list_content_chunks(repository_id, target_analysis_run_id)
),
),
candidates=self._diff_items(
self._candidate_index(base_graph.abilities),
self._candidate_index(target_graph.abilities),
),
approved_entries=self._diff_items(
self._approved_index(approved_map.abilities),
self._candidate_index(target_graph.abilities),
),
)
def build_dependency_graph(self, repository_id: int) -> DependencyGraph:
repository = self.store.get_repository(repository_id)
ability_map = self.store.get_ability_map(repository_id)
edges: list[DependencyEdge] = []
scope_key = self._dependency_key("scope", ability_map.scope.id)
for ability in ability_map.abilities:
ability_key = self._dependency_key("ability", ability.id)
edges.append(
self._dependency_edge(
source_kind="ability",
source_id=ability.id,
source_key=ability_key,
target_kind="scope",
target_id=ability_map.scope.id,
target_key=scope_key,
dependency_type="summarizes",
strength="strong",
source="approved_characteristic",
)
)
for capability in ability.capabilities:
capability_key = self._dependency_key("capability", capability.id)
edges.append(
self._dependency_edge(
source_kind="capability",
source_id=capability.id,
source_key=capability_key,
target_kind="ability",
target_id=ability.id,
target_key=ability_key,
dependency_type="realizes",
strength="strong",
source="approved_characteristic",
)
)
edges.extend(
self._capability_dependency_edges(
capability,
capability_key=capability_key,
)
)
return DependencyGraph(
repository=repository,
scope=ability_map.scope,
edges=edges,
)
def analyze_dependency_impact(
self,
repository_id: int,
base_analysis_run_id: int,
target_analysis_run_id: int,
) -> DependencyImpactAnalysis:
diff = self.diff_analysis_runs(
repository_id,
base_analysis_run_id,
target_analysis_run_id,
)
graph = self.build_dependency_graph(repository_id)
changed_facts = [
item
for section in (
diff.facts.added,
diff.facts.removed,
diff.facts.changed,
diff.facts.weakened,
)
for item in section
]
changed_fact_keys = [item.key for item in changed_facts]
fact_reasons = {
item.key: f"{item.change_type} fact {item.key}" for item in changed_facts
}
adjacency: dict[str, list[DependencyEdge]] = {}
for edge in graph.edges:
adjacency.setdefault(edge.source_key, []).append(edge)
queue: list[tuple[str, int, str]] = [
(key, 0, fact_reasons[key]) for key in changed_fact_keys
]
impacts_by_key: dict[str, DependencyImpactItem] = {}
visited_edges: set[tuple[str, str]] = set()
while queue:
source_key, depth, inherited_reason = queue.pop(0)
for edge in adjacency.get(source_key, []):
edge_marker = (edge.source_key, edge.target_key)
if edge_marker in visited_edges:
continue
visited_edges.add(edge_marker)
impact_depth = depth + 1
reason = (
f"{inherited_reason} -> {edge.target_kind} depends on "
f"{edge.source_kind} via {edge.dependency_type}"
)
current = impacts_by_key.get(edge.target_key)
if current is None:
impacts_by_key[edge.target_key] = DependencyImpactItem(
item_kind=edge.target_kind,
item_id=edge.target_id,
item_key=edge.target_key,
name=self._dependency_display_name(
repository_id,
edge.target_kind,
edge.target_id,
),
freshness_state="stale",
ownership=edge.target_ownership,
recommended_action=self._recommended_action(
edge.target_ownership
),
impact_depth=impact_depth,
reasons=[reason],
)
else:
impacts_by_key[edge.target_key] = replace(
current,
impact_depth=min(current.impact_depth, impact_depth),
reasons=[*current.reasons, reason],
)
queue.append((edge.target_key, impact_depth, reason))
impacts = sorted(
impacts_by_key.values(),
key=lambda item: (item.impact_depth, item.item_kind, item.item_id),
)
max_depth = max((item.impact_depth for item in impacts), default=0)
return DependencyImpactAnalysis(
repository=diff.repository,
base_run=diff.base_run,
target_run=diff.target_run,
changed_fact_keys=changed_fact_keys,
impacts=impacts,
max_depth=max_depth,
scope_impacted=any(item.item_kind == "scope" for item in impacts),
propagation_breadth=len(impacts),
graph=graph,
)
def dependency_graph_elements(
self,
repository_id: int,
*,
base_analysis_run_id: int | None = None,
target_analysis_run_id: int | None = None,
profile_id: int | None = None,
rules: list[dict[str, Any]] | None = None,
manual_overrides: dict[str, str] | None = None,
use_latest_profile: bool = True,
) -> dict[str, object]:
impact = None
if base_analysis_run_id is not None or target_analysis_run_id is not None:
if base_analysis_run_id is None or target_analysis_run_id is None:
raise ValueError(
"base_analysis_run_id and target_analysis_run_id must be provided together"
)
impact = self.analyze_dependency_impact(
repository_id,
base_analysis_run_id,
target_analysis_run_id,
)
graph = impact.graph
else:
graph = self.build_dependency_graph(repository_id)
impact_by_key = (
{item.item_key: item for item in impact.impacts} if impact is not None else {}
)
changed_fact_keys = set(impact.changed_fact_keys) if impact is not None else set()
ability_map = self.store.get_ability_map(repository_id)
facts_by_id = {fact.id: fact for fact in self.store.list_observed_facts(repository_id)}
characteristic_index = self._dependency_characteristic_index(ability_map)
nodes: dict[str, dict[str, object]] = {}
edge_sources: dict[str, DependencyEdge] = {}
profile = (
self.store.get_dependency_graph_profile(repository_id, profile_id)
if profile_id is not None
else self.store.latest_dependency_graph_profile(repository_id)
if use_latest_profile and not rules and not manual_overrides
else None
)
merged_rules = [*(profile.filter_rules if profile is not None else []), *(rules or [])]
merged_overrides = {
**(profile.manual_overrides if profile is not None else {}),
**(manual_overrides or {}),
}
graph_edges = [
display_edge
for edge in graph.edges
if (display_edge := self._dependency_display_edge(edge, facts_by_id))
is not None
]
def ensure_node(kind: str, key: str, item_id: int | None) -> None:
if key in nodes:
return
impact_item = impact_by_key.get(key)
is_changed_fact = key in changed_fact_keys
detail = characteristic_index.get(key, {})
fact = facts_by_id.get(item_id) if kind == "fact" and item_id else None
if fact is not None:
detail = {
"name": fact.name,
"label": (
f"{fact.path} ({fact.kind})"
if key.startswith("fact:document:")
else f"{fact.name} ({fact.kind}, {fact.path})"
),
"description": fact.value,
"primaryClass": fact.metadata.get("source_role", fact.kind),
"attributes": self._dependency_fact_attributes(fact),
"confidence": fact.metadata.get("confidence"),
"path": fact.path,
"value": fact.value,
"metadata": fact.metadata,
"sourceReferences": [
{
"fact_id": fact.id,
"path": fact.path,
"kind": fact.kind,
"name": fact.name,
"line": fact.metadata.get("line"),
}
],
}
nodes[key] = {
"data": {
"id": key,
"key": key,
"stableKey": key,
"kind": kind,
"layer": self._dependency_layer(kind),
"label": detail.get("label")
or self._dependency_node_label(repository_id, kind, key, item_id),
"reviewState": "accepted",
"name": detail.get("name")
or self._dependency_node_label(repository_id, kind, key, item_id),
"description": detail.get("description", ""),
"primaryClass": detail.get("primaryClass", kind),
"attributes": detail.get("attributes", []),
"confidence": detail.get("confidence"),
"visualSize": self._dependency_node_size(detail.get("confidence")),
"ownership": self._ownership_for_kind(kind),
"freshnessState": (
impact_item.freshness_state
if impact_item is not None
else "changed"
if is_changed_fact
else "current"
),
"recommendedAction": (
impact_item.recommended_action if impact_item is not None else ""
),
"impactDepth": (
impact_item.impact_depth if impact_item is not None else None
),
"reasons": impact_item.reasons if impact_item is not None else [],
"path": detail.get("path", ""),
"value": detail.get("value", ""),
"metadata": detail.get("metadata", {}),
"sourceReferences": detail.get("sourceReferences", []),
},
"classes": " ".join(
class_name
for class_name in (
kind,
"stale" if impact_item is not None else "current",
"changed" if is_changed_fact else "",
)
if class_name
),
}
for edge in graph_edges:
ensure_node(edge.source_kind, edge.source_key, edge.source_id)
ensure_node(edge.target_kind, edge.target_key, edge.target_id)
edges = []
for index, edge in enumerate(graph_edges):
edge_id = f"{edge.source_key}->{edge.target_key}:{index}"
source_data = nodes[edge.source_key]["data"]
target_data = nodes[edge.target_key]["data"]
edge_sources[edge_id] = edge
edges.append(
{
"data": {
"id": edge_id,
"key": edge_id,
"stableKey": edge_id,
"kind": "edge",
"layer": "dependency",
"reviewState": "accepted",
"source": edge.source_key,
"target": edge.target_key,
"sourceKind": edge.source_kind,
"targetKind": edge.target_kind,
"sourceLayer": self._dependency_layer(edge.source_kind),
"targetLayer": self._dependency_layer(edge.target_kind),
"dependencyType": edge.dependency_type,
"strength": edge.strength,
"edgeWidth": self._dependency_edge_width(edge.strength),
"edgeSource": edge.source,
"sameLayer": edge.same_layer,
"freshnessState": (
"stale"
if edge.target_key in impact_by_key
else "changed"
if edge.source_key in changed_fact_keys
else "current"
),
"sourceMetadata": {
"key": edge.source_key,
"kind": edge.source_kind,
"layer": self._dependency_layer(edge.source_kind),
"name": source_data.get("name", edge.source_key),
},
"targetMetadata": {
"key": edge.target_key,
"kind": edge.target_kind,
"layer": self._dependency_layer(edge.target_kind),
"name": target_data.get("name", edge.target_key),
},
"label": edge.dependency_type,
},
"classes": " ".join(
class_name
for class_name in (
edge.dependency_type,
edge.strength,
"same-layer" if edge.same_layer else "",
)
if class_name
),
}
)
elements = [*nodes.values(), *edges]
visibility = self._evaluate_dependency_visibility(
elements,
merged_rules,
merged_overrides,
)
hidden_node_ids = {
element["data"]["id"]
for element in nodes.values()
if visibility[element["data"]["id"]]["displayState"] == "hide"
}
blurred_node_ids = {
element["data"]["id"]
for element in nodes.values()
if visibility[element["data"]["id"]]["displayState"] == "blur"
}
visible_elements: list[dict[str, object]] = []
hidden_elements: list[dict[str, object]] = []
orphaned_overrides = sorted(
key for key in merged_overrides if key not in visibility
)
for element in elements:
element_id = element["data"]["id"]
state = visibility[element_id]
if "source" in element["data"] and (
element["data"]["source"] in hidden_node_ids
or element["data"]["target"] in hidden_node_ids
):
state = {
**state,
"displayState": "hide",
"visibilityReason": "connected-node-hidden",
}
connected_to_blurred = (
"source" in element["data"]
and (
element["data"]["source"] in blurred_node_ids
or element["data"]["target"] in blurred_node_ids
)
)
element["data"].update(state)
element["data"]["connectedToBlurred"] = connected_to_blurred
element["classes"] = " ".join(
part
for part in (
element.get("classes", ""),
f"display-{state['displayState']}",
"connects-blurred" if connected_to_blurred else "",
"manual-override" if state["visibilitySource"] == "manual" else "",
"rule-derived" if state["visibilitySource"] == "rule" else "",
)
if part
)
if state["displayState"] == "hide":
hidden_elements.append(element)
else:
visible_elements.append(element)
return {
"repository": asdict(graph.repository),
"scope": asdict(graph.scope),
"mode": (
profile.default_mode
if profile is not None and impact is None
else "impact"
if impact is not None
else "full"
),
"profile": asdict(profile) if profile is not None else None,
"metrics": {
"node_count": len(
[
element
for element in visible_elements
if "source" not in element["data"]
]
),
"edge_count": len(
[
element
for element in visible_elements
if "source" in element["data"]
]
),
"hidden_count": len(hidden_elements),
"blurred_count": len(
[
element
for element in visible_elements
if element["data"]["displayState"] == "blur"
]
),
"propagation_breadth": impact.propagation_breadth if impact else 0,
"max_depth": impact.max_depth if impact else 0,
"scope_impacted": impact.scope_impacted if impact else False,
},
"filter": {
"rules": merged_rules,
"manual_overrides": merged_overrides,
"orphaned_overrides": orphaned_overrides,
"precedence": "later rules override earlier rules; manual overrides win last",
"connected_edge_behavior": "edges connected to hidden nodes are hidden",
},
"changed_fact_keys": impact.changed_fact_keys if impact else [],
"elements": visible_elements,
"hidden_elements": hidden_elements,
"impacts": [asdict(item) for item in impact.impacts] if impact else [],
}
def list_dependency_graph_profiles(
self,
repository_id: int,
) -> list[DependencyGraphViewProfile]:
return self.store.list_dependency_graph_profiles(repository_id)
def get_dependency_graph_profile(
self,
repository_id: int,
profile_id: int,
) -> DependencyGraphViewProfile:
return self.store.get_dependency_graph_profile(repository_id, profile_id)
def create_dependency_graph_profile(
self,
repository_id: int,
*,
name: str,
description: str = "",
default_mode: str = "full",
filter_rules: list[dict[str, Any]] | None = None,
manual_overrides: dict[str, str] | None = None,
) -> DependencyGraphViewProfile:
self._validate_dependency_graph_profile_payload(
default_mode,
filter_rules or [],
manual_overrides or {},
)
return self.store.create_dependency_graph_profile(
repository_id,
name=name,
description=description,
default_mode=default_mode,
filter_rules=filter_rules or [],
manual_overrides=manual_overrides or {},
)
def update_dependency_graph_profile(
self,
repository_id: int,
profile_id: int,
*,
name: str | None = None,
description: str | None = None,
default_mode: str | None = None,
filter_rules: list[dict[str, Any]] | None = None,
manual_overrides: dict[str, str] | None = None,
) -> DependencyGraphViewProfile:
if default_mode is not None or filter_rules is not None or manual_overrides is not None:
current = self.store.get_dependency_graph_profile(repository_id, profile_id)
self._validate_dependency_graph_profile_payload(
default_mode or current.default_mode,
filter_rules if filter_rules is not None else current.filter_rules,
manual_overrides
if manual_overrides is not None
else current.manual_overrides,
)
return self.store.update_dependency_graph_profile(
repository_id,
profile_id,
name=name,
description=description,
default_mode=default_mode,
filter_rules=filter_rules,
manual_overrides=manual_overrides,
)
def duplicate_dependency_graph_profile(
self,
repository_id: int,
profile_id: int,
*,
name: str | None = None,
) -> DependencyGraphViewProfile:
profile = self.store.get_dependency_graph_profile(repository_id, profile_id)
return self.store.create_dependency_graph_profile(
repository_id,
name=name or f"{profile.name} Copy",
description=profile.description,
default_mode=profile.default_mode,
filter_rules=profile.filter_rules,
manual_overrides=profile.manual_overrides,
)
def delete_dependency_graph_profile(
self,
repository_id: int,
profile_id: int,
) -> None:
self.store.delete_dependency_graph_profile(repository_id, profile_id)
def approve_analysis_run_changes(
self,
repository_id: int,
analysis_run_id: int,
*,
notes: str = "",
) -> RepositoryAbilityMap:
graph = self.store.get_candidate_graph(repository_id, analysis_run_id)
self.store.replace_approved_from_candidate_graph(repository_id, graph)
self.store.mark_candidate_graph_status(repository_id, analysis_run_id, "approved")
self.store.create_review_decision(
repository_id,
analysis_run_id,
action="approve_analysis_run_changes",
notes=notes,
)
self.store.update_repository_status(repository_id, "indexed")
return self.store.get_ability_map(repository_id)
def _create_approved_capability_subtree(
self,
repository_id: int,
approved_ability_id: int,
capability: CandidateCapability,
) -> int:
approved_capability_id = self.store.create_capability(
repository_id,
approved_ability_id,
name=capability.name,
description=capability.description,
inputs=capability.inputs,
outputs=capability.outputs,
confidence=capability.confidence,
primary_class=capability.primary_class,
attributes=capability.attributes,
)
for feature in capability.features:
if feature.status != "candidate":
continue
self.store.create_feature(
repository_id,
approved_capability_id,
name=feature.name,
type=feature.type,
location=feature.location,
confidence=feature.confidence,
source_refs=feature.source_refs,
primary_class=feature.primary_class,
attributes=feature.attributes,
)
for evidence in capability.evidence:
if evidence.status != "candidate":
continue
self.store.create_evidence(
repository_id,
approved_capability_id,
type=evidence.type,
reference=evidence.reference,
strength=evidence.strength,
target_kind=evidence.target_kind,
target_id=self._approved_evidence_target_id(
evidence,
approved_capability_id,
),
reference_kind=evidence.reference_kind,
reference_id=evidence.reference_id,
source_refs=evidence.source_refs,
)
return approved_capability_id
def _ensure_approved_ability(
self,
repository_id: int,
candidate_ability: CandidateAbility,
) -> int:
ability_map = self.store.get_ability_map(repository_id)
for ability in ability_map.abilities:
if ability.name == candidate_ability.name:
return ability.id
return self.store.create_ability(
repository_id,
name=candidate_ability.name,
description=candidate_ability.description,
confidence=candidate_ability.confidence,
primary_class=candidate_ability.primary_class,
attributes=candidate_ability.attributes,
)
def _ensure_approved_capability(
self,
repository_id: int,
approved_ability_id: int,
approved_ability_name: str,
candidate_capability: CandidateCapability,
) -> int:
ability_map = self.store.get_ability_map(repository_id)
for ability in ability_map.abilities:
if ability.name != approved_ability_name:
continue
for capability in ability.capabilities:
if capability.name == candidate_capability.name:
return capability.id
return self.store.create_capability(
repository_id,
approved_ability_id,
name=candidate_capability.name,
description=candidate_capability.description,
inputs=candidate_capability.inputs,
outputs=candidate_capability.outputs,
confidence=candidate_capability.confidence,
primary_class=candidate_capability.primary_class,
attributes=candidate_capability.attributes,
)
def _candidate_capability_with_parent(
self,
graph: CandidateGraph,
candidate_capability_id: int,
) -> tuple[CandidateAbility, CandidateCapability]:
for ability in graph.abilities:
for capability in ability.capabilities:
if capability.id == candidate_capability_id:
return ability, capability
raise ValueError(f"candidate capability {candidate_capability_id} was not found")
def _approved_evidence_target_id(
self,
evidence: CandidateEvidence,
approved_capability_id: int,
) -> int | None:
if evidence.target_kind == "capability":
return approved_capability_id
return evidence.target_id
def _candidate_feature_with_parent(
self,
graph: CandidateGraph,
candidate_feature_id: int,
) -> tuple[CandidateAbility, CandidateCapability, CandidateFeature]:
for ability in graph.abilities:
for capability in ability.capabilities:
for feature in capability.features:
if feature.id == candidate_feature_id:
return ability, capability, feature
raise ValueError(f"candidate feature {candidate_feature_id} was not found")
def _candidate_evidence_with_parent(
self,
graph: CandidateGraph,
candidate_evidence_id: int,
) -> tuple[CandidateAbility, CandidateCapability, CandidateEvidence]:
for ability in graph.abilities:
for capability in ability.capabilities:
for evidence in capability.evidence:
if evidence.id == candidate_evidence_id:
return ability, capability, evidence
raise ValueError(f"candidate evidence {candidate_evidence_id} was not found")
def _record_candidate_acceptance(
self,
repository_id: int,
analysis_run_id: int,
action: str,
notes: str,
) -> None:
self.store.create_review_decision(
repository_id,
analysis_run_id,
action=action,
notes=notes,
)
self.store.update_repository_status(repository_id, "indexed")
def reject_candidate_ability(
self,
repository_id: int,
analysis_run_id: int,
candidate_ability_id: int,
*,
notes: str = "",
) -> CandidateGraph:
self.store.reject_candidate_ability(
repository_id,
analysis_run_id,
candidate_ability_id,
)
self.store.create_review_decision(
repository_id,
analysis_run_id,
action="reject_candidate_ability",
notes=notes,
)
self.store.update_repository_status(repository_id, "reviewing")
return self.store.get_candidate_graph(repository_id, analysis_run_id)
def reject_candidate_capability(
self,
repository_id: int,
analysis_run_id: int,
candidate_capability_id: int,
*,
notes: str = "",
) -> CandidateGraph:
self.store.reject_candidate_capability(
repository_id,
analysis_run_id,
candidate_capability_id,
)
self.store.create_review_decision(
repository_id,
analysis_run_id,
action="reject_candidate_capability",
notes=notes,
)
self.store.update_repository_status(repository_id, "reviewing")
return self.store.get_candidate_graph(repository_id, analysis_run_id)
def reject_candidate_feature(
self,
repository_id: int,
analysis_run_id: int,
candidate_feature_id: int,
*,
notes: str = "",
) -> CandidateGraph:
self.store.reject_candidate_feature(
repository_id,
analysis_run_id,
candidate_feature_id,
)
self.store.create_review_decision(
repository_id,
analysis_run_id,
action="reject_candidate_feature",
notes=notes,
)
self.store.update_repository_status(repository_id, "reviewing")
return self.store.get_candidate_graph(repository_id, analysis_run_id)
def reject_candidate_evidence(
self,
repository_id: int,
analysis_run_id: int,
candidate_evidence_id: int,
*,
notes: str = "",
) -> CandidateGraph:
self.store.reject_candidate_evidence(
repository_id,
analysis_run_id,
candidate_evidence_id,
)
self.store.create_review_decision(
repository_id,
analysis_run_id,
action="reject_candidate_evidence",
notes=notes,
)
self.store.update_repository_status(repository_id, "reviewing")
return self.store.get_candidate_graph(repository_id, analysis_run_id)
def edit_candidate_ability(
self,
repository_id: int,
analysis_run_id: int,
candidate_ability_id: int,
*,
name: str,
description: str,
confidence: float,
primary_class: str = "ability",
attributes: Sequence[str] = (),
notes: str = "",
) -> CandidateGraph:
self.store.update_candidate_ability(
repository_id,
analysis_run_id,
candidate_ability_id,
name=name,
description=description,
confidence=confidence,
primary_class=primary_class,
attributes=list(attributes),
)
self.store.create_review_decision(
repository_id,
analysis_run_id,
action="edit_candidate_ability",
notes=notes,
)
self.store.update_repository_status(repository_id, "reviewing")
return self.store.get_candidate_graph(repository_id, analysis_run_id)
def edit_candidate_capability(
self,
repository_id: int,
analysis_run_id: int,
candidate_capability_id: int,
*,
name: str,
description: str,
confidence: float,
primary_class: str = "capability",
attributes: Sequence[str] = (),
notes: str = "",
) -> CandidateGraph:
self.store.update_candidate_capability(
repository_id,
analysis_run_id,
candidate_capability_id,
name=name,
description=description,
confidence=confidence,
primary_class=primary_class,
attributes=list(attributes),
)
self.store.create_review_decision(
repository_id,
analysis_run_id,
action="edit_candidate_capability",
notes=notes,
)
self.store.update_repository_status(repository_id, "reviewing")
return self.store.get_candidate_graph(repository_id, analysis_run_id)
def edit_candidate_feature(
self,
repository_id: int,
analysis_run_id: int,
candidate_feature_id: int,
*,
name: str,
type: str,
location: str,
confidence: float,
primary_class: str | None = None,
attributes: Sequence[str] = (),
notes: str = "",
) -> CandidateGraph:
self.store.update_candidate_feature(
repository_id,
analysis_run_id,
candidate_feature_id,
name=name,
type=type,
location=location,
confidence=confidence,
primary_class=primary_class,
attributes=list(attributes),
)
self.store.create_review_decision(
repository_id,
analysis_run_id,
action="edit_candidate_feature",
notes=notes,
)
self.store.update_repository_status(repository_id, "reviewing")
return self.store.get_candidate_graph(repository_id, analysis_run_id)
def relink_candidate_capability(
self,
repository_id: int,
analysis_run_id: int,
candidate_capability_id: int,
*,
target_ability_id: int,
notes: str = "",
) -> CandidateGraph:
self.store.relink_candidate_capability(
repository_id,
analysis_run_id,
candidate_capability_id,
target_ability_id,
)
self.store.create_review_decision(
repository_id,
analysis_run_id,
action="relink_candidate_capability",
notes=notes,
)
self.store.update_repository_status(repository_id, "reviewing")
return self.store.get_candidate_graph(repository_id, analysis_run_id)
def relink_candidate_feature(
self,
repository_id: int,
analysis_run_id: int,
candidate_feature_id: int,
*,
target_capability_id: int,
notes: str = "",
) -> CandidateGraph:
self.store.relink_candidate_feature(
repository_id,
analysis_run_id,
candidate_feature_id,
target_capability_id,
)
self.store.create_review_decision(
repository_id,
analysis_run_id,
action="relink_candidate_feature",
notes=notes,
)
self.store.update_repository_status(repository_id, "reviewing")
return self.store.get_candidate_graph(repository_id, analysis_run_id)
def relink_candidate_evidence(
self,
repository_id: int,
analysis_run_id: int,
candidate_evidence_id: int,
*,
target_capability_id: int,
notes: str = "",
) -> CandidateGraph:
self.store.relink_candidate_evidence(
repository_id,
analysis_run_id,
candidate_evidence_id,
target_capability_id,
)
self.store.create_review_decision(
repository_id,
analysis_run_id,
action="relink_candidate_evidence",
notes=notes,
)
self.store.update_repository_status(repository_id, "reviewing")
return self.store.get_candidate_graph(repository_id, analysis_run_id)
def merge_candidate_ability(
self,
repository_id: int,
analysis_run_id: int,
source_ability_id: int,
*,
target_ability_id: int,
notes: str = "",
) -> CandidateGraph:
self.store.merge_candidate_ability(
repository_id,
analysis_run_id,
source_ability_id,
target_ability_id,
)
self.store.create_review_decision(
repository_id,
analysis_run_id,
action="merge_candidate_ability",
notes=notes,
)
self.store.update_repository_status(repository_id, "reviewing")
return self.store.get_candidate_graph(repository_id, analysis_run_id)
def merge_candidate_capability(
self,
repository_id: int,
analysis_run_id: int,
source_capability_id: int,
*,
target_capability_id: int,
notes: str = "",
) -> CandidateGraph:
self.store.merge_candidate_capability(
repository_id,
analysis_run_id,
source_capability_id,
target_capability_id,
)
self.store.create_review_decision(
repository_id,
analysis_run_id,
action="merge_candidate_capability",
notes=notes,
)
self.store.update_repository_status(repository_id, "reviewing")
return self.store.get_candidate_graph(repository_id, analysis_run_id)
def merge_candidate_feature(
self,
repository_id: int,
analysis_run_id: int,
source_feature_id: int,
*,
target_feature_id: int,
notes: str = "",
) -> CandidateGraph:
self.store.merge_candidate_feature(
repository_id,
analysis_run_id,
source_feature_id,
target_feature_id,
)
self.store.create_review_decision(
repository_id,
analysis_run_id,
action="merge_candidate_feature",
notes=notes,
)
self.store.update_repository_status(repository_id, "reviewing")
return self.store.get_candidate_graph(repository_id, analysis_run_id)
def merge_candidate_evidence(
self,
repository_id: int,
analysis_run_id: int,
source_evidence_id: int,
*,
target_evidence_id: int,
notes: str = "",
) -> CandidateGraph:
self.store.merge_candidate_evidence(
repository_id,
analysis_run_id,
source_evidence_id,
target_evidence_id,
)
self.store.create_review_decision(
repository_id,
analysis_run_id,
action="merge_candidate_evidence",
notes=notes,
)
self.store.update_repository_status(repository_id, "reviewing")
return self.store.get_candidate_graph(repository_id, analysis_run_id)
def add_ability(
self,
repository_id: int,
*,
name: str,
description: str = "",
confidence: float = 1.0,
primary_class: str = "ability",
attributes: Sequence[str] = (),
) -> int:
self.store.get_repository(repository_id)
return self.store.create_ability(
repository_id,
name=name,
description=description,
confidence=confidence,
primary_class=primary_class,
attributes=list(attributes),
)
def update_ability(
self,
repository_id: int,
ability_id: int,
*,
name: str | None = None,
description: str | None = None,
confidence: float | None = None,
primary_class: str | None = None,
attributes: Sequence[str] | None = None,
) -> RepositoryAbilityMap:
self.store.update_ability(
repository_id,
ability_id,
name=name,
description=description,
confidence=confidence,
primary_class=primary_class,
attributes=list(attributes) if attributes is not None else None,
)
return self.store.get_ability_map(repository_id)
def delete_ability(
self,
repository_id: int,
ability_id: int,
) -> RepositoryAbilityMap:
self.store.delete_ability(repository_id, ability_id)
return self.store.get_ability_map(repository_id)
def add_capability(
self,
repository_id: int,
ability_id: int,
*,
name: str,
description: str = "",
inputs: Sequence[str] = (),
outputs: Sequence[str] = (),
confidence: float = 1.0,
primary_class: str = "capability",
attributes: Sequence[str] = (),
) -> int:
self.store.ensure_ability(repository_id, ability_id)
return self.store.create_capability(
repository_id,
ability_id,
name=name,
description=description,
inputs=list(inputs),
outputs=list(outputs),
confidence=confidence,
primary_class=primary_class,
attributes=list(attributes),
)
def update_capability(
self,
repository_id: int,
capability_id: int,
*,
name: str | None = None,
description: str | None = None,
inputs: Sequence[str] | None = None,
outputs: Sequence[str] | None = None,
confidence: float | None = None,
primary_class: str | None = None,
attributes: Sequence[str] | None = None,
) -> RepositoryAbilityMap:
self.store.update_capability(
repository_id,
capability_id,
name=name,
description=description,
inputs=list(inputs) if inputs is not None else None,
outputs=list(outputs) if outputs is not None else None,
confidence=confidence,
primary_class=primary_class,
attributes=list(attributes) if attributes is not None else None,
)
return self.store.get_ability_map(repository_id)
def delete_capability(
self,
repository_id: int,
capability_id: int,
) -> RepositoryAbilityMap:
self.store.delete_capability(repository_id, capability_id)
return self.store.get_ability_map(repository_id)
def add_feature(
self,
repository_id: int,
capability_id: int,
*,
name: str,
type: str,
location: str = "",
confidence: float = 1.0,
primary_class: str | None = None,
attributes: Sequence[str] = (),
) -> int:
self.store.ensure_capability(repository_id, capability_id)
return self.store.create_feature(
repository_id,
capability_id,
name=name,
type=type,
location=location,
confidence=confidence,
primary_class=primary_class,
attributes=list(attributes),
)
def update_feature(
self,
repository_id: int,
feature_id: int,
*,
name: str | None = None,
type: str | None = None,
location: str | None = None,
confidence: float | None = None,
primary_class: str | None = None,
attributes: Sequence[str] | None = None,
) -> RepositoryAbilityMap:
self.store.update_feature(
repository_id,
feature_id,
name=name,
type=type,
location=location,
confidence=confidence,
primary_class=primary_class,
attributes=list(attributes) if attributes is not None else None,
)
return self.store.get_ability_map(repository_id)
def delete_feature(
self,
repository_id: int,
feature_id: int,
) -> RepositoryAbilityMap:
self.store.delete_feature(repository_id, feature_id)
return self.store.get_ability_map(repository_id)
def add_evidence(
self,
repository_id: int,
capability_id: int,
*,
type: str,
reference: str,
strength: str = "medium",
target_kind: str = "capability",
target_id: int | None = None,
reference_kind: str = "source",
reference_id: int | None = None,
) -> int:
self.store.ensure_capability(repository_id, capability_id)
return self.store.create_evidence(
repository_id,
capability_id,
type=type,
reference=reference,
strength=strength,
target_kind=target_kind,
target_id=target_id,
reference_kind=reference_kind,
reference_id=reference_id,
)
def update_evidence(
self,
repository_id: int,
evidence_id: int,
*,
type: str | None = None,
reference: str | None = None,
strength: str | None = None,
target_kind: str | None = None,
target_id: int | None = None,
reference_kind: str | None = None,
reference_id: int | None = None,
) -> RepositoryAbilityMap:
self.store.update_evidence(
repository_id,
evidence_id,
type=type,
reference=reference,
strength=strength,
target_kind=target_kind,
target_id=target_id,
reference_kind=reference_kind,
reference_id=reference_id,
)
return self.store.get_ability_map(repository_id)
def delete_evidence(
self,
repository_id: int,
evidence_id: int,
) -> RepositoryAbilityMap:
self.store.delete_evidence(repository_id, evidence_id)
return self.store.get_ability_map(repository_id)
def update_scope(
self,
repository_id: int,
*,
name: str | None = None,
description: str | None = None,
confidence: float | None = None,
) -> RepositoryAbilityMap:
self.store.update_scope(
repository_id,
name=name,
description=description,
confidence=confidence,
)
return self.store.get_ability_map(repository_id)
def ability_map(self, repository_id: int) -> RepositoryAbilityMap:
return self.store.get_ability_map(repository_id)
def compare_repositories(self, repository_ids: Sequence[int]) -> dict[str, object]:
maps = [self.store.get_ability_map(repository_id) for repository_id in repository_ids]
ability_groups: dict[str, list[dict[str, object]]] = {}
capability_groups: dict[str, list[dict[str, object]]] = {}
for ability_map in maps:
repository = ability_map.repository
for ability in ability_map.abilities:
ability_groups.setdefault(ability.name.lower(), []).append(
{
"repository_id": repository.id,
"repository_name": repository.name,
"confidence": ability.confidence,
"confidence_label": ability.confidence_label,
"capabilities": [
{
"name": capability.name,
"confidence": capability.confidence,
"confidence_label": capability.confidence_label,
"evidence_count": len(capability.evidence),
}
for capability in ability.capabilities
],
"_name": ability.name,
}
)
for capability in ability.capabilities:
capability_groups.setdefault(capability.name.lower(), []).append(
{
"repository_id": repository.id,
"repository_name": repository.name,
"ability_name": ability.name,
"capability_name": capability.name,
}
)
abilities = [
{
"name": repositories[0]["_name"],
"repositories": [
{
key: value
for key, value in repository.items()
if key != "_name"
}
for repository in repositories
],
}
for repositories in ability_groups.values()
]
unique_capabilities = [
entries[0]
for entries in capability_groups.values()
if len({entry["repository_id"] for entry in entries}) == 1
]
return {
"repositories": [asdict(ability_map.repository) for ability_map in maps],
"abilities": sorted(abilities, key=lambda item: item["name"]),
"unique_capabilities": sorted(
unique_capabilities,
key=lambda item: (item["repository_name"], item["capability_name"]),
),
}
def detect_capability_gaps(
self,
*,
desired_ability: str,
desired_capabilities: Sequence[str],
repository_ids: Sequence[int] | None = None,
) -> dict[str, object]:
repositories = (
[self.store.get_repository(repository_id) for repository_id in repository_ids]
if repository_ids is not None
else self.store.list_repositories()
)
maps = [self.store.get_ability_map(repository.id) for repository in repositories]
desired = [capability.strip() for capability in desired_capabilities if capability.strip()]
capability_matches: dict[str, list[dict[str, object]]] = {name.lower(): [] for name in desired}
duplicate_index: dict[str, set[str]] = {}
weak: list[dict[str, object]] = []
for ability_map in maps:
repository = ability_map.repository
for ability in ability_map.abilities:
for capability in ability.capabilities:
key = capability.name.lower()
duplicate_index.setdefault(key, set()).add(repository.name)
if key in capability_matches:
capability_matches[key].append(
{
"repository_id": repository.id,
"repository_name": repository.name,
"capability": capability,
}
)
strengths = {evidence.strength for evidence in capability.evidence}
if "strong" not in strengths:
weak.append(
{
"capability": capability.name,
"repository_id": repository.id,
"repository_name": repository.name,
"evidence_count": len(capability.evidence),
"strongest_evidence": self._strongest_evidence(strengths),
"confidence": capability.confidence,
"confidence_label": capability.confidence_label,
}
)
matched = [
{
"capability": name,
"repositories": [
match["repository_name"]
for match in capability_matches[name.lower()]
],
}
for name in desired
if capability_matches[name.lower()]
]
missing = [name for name in desired if not capability_matches[name.lower()]]
duplicates = [
{
"capability": capability,
"repositories": sorted(repositories),
}
for capability, repositories in duplicate_index.items()
if len(repositories) > 1 and capability in capability_matches
]
return {
"desired_ability": desired_ability,
"matched_capabilities": matched,
"missing_capabilities": missing,
"weakly_evidenced_capabilities": weak,
"duplicate_capabilities": duplicates,
}
def export_registry_entry(self, repository_id: int) -> str:
ability_map = self.store.get_ability_map(repository_id)
lines = [
"repository:",
f" name: {self._yaml_scalar(ability_map.repository.name)}",
f" url: {self._yaml_scalar(ability_map.repository.url)}",
f" branch: {self._yaml_scalar(ability_map.repository.branch)}",
f" status: {self._yaml_scalar(ability_map.repository.status)}",
"abilities:",
]
for ability in ability_map.abilities:
lines.extend(
[
f" - name: {self._yaml_scalar(ability.name)}",
f" description: {self._yaml_scalar(ability.description)}",
f" confidence: {ability.confidence}",
f" confidence_label: {self._yaml_scalar(ability.confidence_label)}",
" capabilities:",
]
)
for capability in ability.capabilities:
lines.extend(
[
f" - name: {self._yaml_scalar(capability.name)}",
f" description: {self._yaml_scalar(capability.description)}",
f" confidence: {capability.confidence}",
f" confidence_label: {self._yaml_scalar(capability.confidence_label)}",
f" inputs: {self._yaml_list(capability.inputs)}",
f" outputs: {self._yaml_list(capability.outputs)}",
" features:",
]
)
for feature in capability.features:
lines.extend(
[
f" - name: {self._yaml_scalar(feature.name)}",
f" type: {self._yaml_scalar(feature.type)}",
f" location: {self._yaml_scalar(feature.location)}",
f" confidence: {feature.confidence}",
f" confidence_label: {self._yaml_scalar(feature.confidence_label)}",
]
)
lines.append(" evidence:")
for evidence in capability.evidence:
lines.extend(
[
f" - type: {self._yaml_scalar(evidence.type)}",
f" reference: {self._yaml_scalar(evidence.reference)}",
f" strength: {self._yaml_scalar(evidence.strength)}",
]
)
return "\n".join(lines) + "\n"
def _strongest_evidence(self, strengths: set[str]) -> str | None:
for strength in ("strong", "medium", "weak"):
if strength in strengths:
return strength
return None
def _diff_items(
self,
base: dict[str, dict[str, object]],
target: dict[str, dict[str, object]],
) -> AnalysisRunDiffSection:
added: list[AnalysisRunDiffItem] = []
removed: list[AnalysisRunDiffItem] = []
changed: list[AnalysisRunDiffItem] = []
weakened: list[AnalysisRunDiffItem] = []
for key in sorted(target.keys() - base.keys()):
added.append(
AnalysisRunDiffItem(
change_type="added",
item_type=str(target[key]["item_type"]),
key=key,
target=target[key],
)
)
for key in sorted(base.keys() - target.keys()):
removed.append(
AnalysisRunDiffItem(
change_type="removed",
item_type=str(base[key]["item_type"]),
key=key,
base=base[key],
)
)
for key in sorted(base.keys() & target.keys()):
if base[key] == target[key]:
continue
item = AnalysisRunDiffItem(
change_type="weakened" if self._is_weakened(base[key], target[key]) else "changed",
item_type=str(target[key]["item_type"]),
key=key,
base=base[key],
target=target[key],
)
if item.change_type == "weakened":
weakened.append(item)
else:
changed.append(item)
return AnalysisRunDiffSection(
added=added,
removed=removed,
changed=changed,
weakened=weakened,
)
def _is_weakened(
self,
base: dict[str, object],
target: dict[str, object],
) -> bool:
base_confidence = base.get("confidence")
target_confidence = target.get("confidence")
if (
isinstance(base_confidence, int | float)
and isinstance(target_confidence, int | float)
and target_confidence < base_confidence
):
return True
base_strength = base.get("strength")
target_strength = target.get("strength")
strength_order = {"weak": 1, "medium": 2, "strong": 3}
return (
isinstance(base_strength, str)
and isinstance(target_strength, str)
and strength_order.get(target_strength, 0) < strength_order.get(base_strength, 0)
)
def _fact_index(self, facts: Sequence[ObservedFact]) -> dict[str, dict[str, object]]:
return {
f"fact:{fact.kind}:{fact.path}:{fact.name}": {
"item_type": "fact",
"id": fact.id,
"kind": fact.kind,
"path": fact.path,
"name": fact.name,
"value": fact.value,
"metadata": fact.metadata,
}
for fact in facts
}
def _dependency_characteristic_index(
self,
ability_map: RepositoryAbilityMap,
) -> dict[str, dict[str, object]]:
index: dict[str, dict[str, object]] = {
self._dependency_key("scope", ability_map.scope.id): {
"name": ability_map.scope.name,
"description": ability_map.scope.description,
"primaryClass": "scope",
"attributes": ["scope"],
"confidence": ability_map.scope.confidence,
"sourceReferences": [],
}
}
for ability in ability_map.abilities:
index[self._dependency_key("ability", ability.id)] = {
"name": ability.name,
"description": ability.description,
"primaryClass": ability.primary_class,
"attributes": ability.attributes,
"confidence": ability.confidence,
"sourceReferences": [],
}
for capability in ability.capabilities:
index[self._dependency_key("capability", capability.id)] = {
"name": capability.name,
"description": capability.description,
"primaryClass": capability.primary_class,
"attributes": capability.attributes,
"confidence": capability.confidence,
"sourceReferences": [],
}
for feature in capability.features:
index[self._dependency_key("feature", feature.id)] = {
"name": feature.name,
"description": feature.location,
"primaryClass": feature.primary_class or feature.type,
"attributes": feature.attributes,
"confidence": feature.confidence,
"path": feature.location,
"sourceReferences": [
asdict(source_ref) for source_ref in feature.source_refs
],
}
for evidence in capability.evidence:
index[self._dependency_key("evidence", evidence.id)] = {
"name": evidence.reference,
"description": evidence.type,
"primaryClass": evidence.type,
"attributes": [evidence.type, evidence.strength],
"confidence": self._evidence_confidence(evidence.strength),
"sourceReferences": [
asdict(source_ref) for source_ref in evidence.source_refs
],
}
return index
def _dependency_fact_attributes(self, fact: ObservedFact) -> list[str]:
attributes = [fact.kind]
for key in ("source_role", "classification", "language", "framework"):
value = fact.metadata.get(key)
if isinstance(value, str) and value:
attributes.append(value)
return sorted(set(attributes))
def _dependency_display_edge(
self,
edge: DependencyEdge,
facts_by_id: dict[int, ObservedFact],
) -> DependencyEdge | None:
if edge.source_kind != "fact" or edge.source_id is None:
return edge
fact = facts_by_id.get(edge.source_id)
if fact is None:
return edge
if self._suppress_dependency_fact(fact):
return None
display_key = self._dependency_fact_display_key(fact)
if display_key == edge.source_key:
return edge
return replace(edge, source_key=display_key)
def _suppress_dependency_fact(self, fact: ObservedFact) -> bool:
return (
fact.path.lower().endswith("scope.md")
and fact.metadata.get("source_role") == "derived_scope"
)
def _dependency_fact_display_key(self, fact: ObservedFact) -> str:
document_paths = {"readme.md", "scope.md"}
if fact.path.lower() in document_paths and fact.kind in {
"documentation",
"intent",
"scope",
}:
return f"fact:document:{fact.path}"
return f"fact:{fact.kind}:{fact.path}:{fact.name}"
def _dependency_node_size(self, confidence: object) -> int:
if not isinstance(confidence, int | float):
return 36
bounded = max(0.0, min(float(confidence), 1.0))
return int(28 + (bounded * 28))
def _dependency_edge_width(self, strength: str) -> int:
return {"weak": 1, "medium": 3, "strong": 5}.get(strength, 2)
def _dependency_layer(self, kind: str) -> str:
if kind in {"fact", "evidence", "feature", "capability", "ability", "scope"}:
return kind
return "dependency"
def _evaluate_dependency_visibility(
self,
elements: list[dict[str, object]],
rules: list[dict[str, Any]],
manual_overrides: dict[str, str],
) -> dict[str, dict[str, str]]:
visibility: dict[str, dict[str, str]] = {}
for element in elements:
data = element["data"]
element_id = str(data["id"])
state = "show"
source = "default"
reason = "default"
for index, rule in enumerate(rules):
action = str(rule.get("action", "show"))
if action not in {"show", "blur", "hide"}:
continue
if self._dependency_rule_matches(data, rule):
state = action
source = "rule"
reason = str(rule.get("name") or f"rule:{index}")
override = manual_overrides.get(element_id)
if override in {"show", "blur", "hide"}:
state = override
source = "manual"
reason = "manual-override"
visibility[element_id] = {
"displayState": state,
"visibilitySource": source,
"visibilityReason": reason,
}
return visibility
def _dependency_rule_matches(
self,
data: dict[str, Any],
rule: dict[str, Any],
) -> bool:
match = rule.get("match", rule)
if not isinstance(match, dict):
return False
for key, expected in match.items():
if key in {"action", "name", "description"}:
continue
if key == "text":
text = " ".join(
str(data.get(part, ""))
for part in ("label", "name", "description", "path", "value")
).lower()
if str(expected).lower() not in text:
return False
continue
if key == "path":
if str(expected).lower() not in str(data.get("path", "")).lower():
return False
continue
actual = data.get(key)
if key == "dependencyType":
actual = data.get("dependencyType")
elif key == "reviewState":
actual = data.get("reviewState")
elif key == "sameLayer":
actual = bool(data.get("sameLayer"))
elif key == "attributes":
actual_values = set(data.get("attributes") or [])
expected_values = expected if isinstance(expected, list) else [expected]
if not set(expected_values).intersection(actual_values):
return False
continue
elif key == "confidence":
if actual is None:
return False
threshold = float(expected)
if float(actual) < threshold:
return False
continue
if isinstance(expected, list):
if actual not in expected:
return False
elif actual != expected:
return False
return True
def _validate_dependency_graph_profile_payload(
self,
default_mode: str,
filter_rules: list[dict[str, Any]],
manual_overrides: dict[str, str],
) -> None:
if default_mode not in {"full", "impact", "path"}:
raise ValueError("default_mode must be one of full, impact, or path")
for rule in filter_rules:
action = rule.get("action")
if action not in {"show", "blur", "hide"}:
raise ValueError("filter rule action must be show, blur, or hide")
invalid = {
key: value
for key, value in manual_overrides.items()
if value not in {"show", "blur", "hide"}
}
if invalid:
raise ValueError("manual override values must be show, blur, or hide")
def _evidence_confidence(self, strength: str) -> float:
return {"strong": 0.9, "medium": 0.6, "weak": 0.3}.get(strength, 0.5)
def _capability_dependency_edges(
self,
capability,
*,
capability_key: str,
) -> list[DependencyEdge]:
edges: list[DependencyEdge] = []
for feature in capability.features:
feature_key = self._dependency_key("feature", feature.id)
edges.append(
self._dependency_edge(
source_kind="feature",
source_id=feature.id,
source_key=feature_key,
target_kind="capability",
target_id=capability.id,
target_key=capability_key,
dependency_type="supports",
strength="medium",
source="approved_characteristic",
)
)
for source_ref in feature.source_refs:
edges.append(
self._dependency_edge(
source_kind="fact",
source_id=source_ref.fact_id,
source_key=self._source_ref_fact_key(source_ref),
target_kind="feature",
target_id=feature.id,
target_key=feature_key,
dependency_type="observes",
strength="strong",
source="source_ref",
)
)
for evidence in capability.evidence:
evidence_key = self._dependency_key("evidence", evidence.id)
evidence_target_kind = evidence.target_kind or "capability"
evidence_target_id = evidence.target_id or capability.id
edges.append(
self._dependency_edge(
source_kind="evidence",
source_id=evidence.id,
source_key=evidence_key,
target_kind=evidence_target_kind,
target_id=evidence_target_id,
target_key=self._dependency_key(
evidence_target_kind,
evidence_target_id,
),
dependency_type="supports",
strength=evidence.strength or "medium",
source="approved_characteristic",
)
)
for source_ref in evidence.source_refs:
edges.append(
self._dependency_edge(
source_kind="fact",
source_id=source_ref.fact_id,
source_key=self._source_ref_fact_key(source_ref),
target_kind="evidence",
target_id=evidence.id,
target_key=evidence_key,
dependency_type="observes",
strength=evidence.strength or "medium",
source="source_ref",
)
)
if evidence.reference_kind in {"feature", "capability", "ability", "scope"}:
reference_id = evidence.reference_id
if reference_id is not None:
edges.append(
self._dependency_edge(
source_kind=evidence.reference_kind,
source_id=reference_id,
source_key=self._dependency_key(
evidence.reference_kind,
reference_id,
),
target_kind=evidence.target_kind,
target_id=evidence.target_id or capability.id,
target_key=self._dependency_key(
evidence.target_kind,
evidence.target_id or capability.id,
),
dependency_type="relates",
strength=evidence.strength or "medium",
source="approved_evidence",
)
)
return edges
def _dependency_edge(
self,
*,
source_kind: str,
source_id: int | None,
source_key: str,
target_kind: str,
target_id: int,
target_key: str,
dependency_type: str,
strength: str,
source: str,
) -> DependencyEdge:
return DependencyEdge(
source_kind=source_kind,
source_id=source_id,
source_key=source_key,
target_kind=target_kind,
target_id=target_id,
target_key=target_key,
dependency_type=dependency_type,
strength=strength,
source=source,
target_ownership=self._ownership_for_kind(target_kind),
same_layer=source_kind == target_kind,
)
def _dependency_key(self, kind: str, item_id: int) -> str:
return f"{kind}:{item_id}"
def _source_ref_fact_key(self, source_ref) -> str:
return f"fact:{source_ref.kind}:{source_ref.path}:{source_ref.name}"
def _ownership_for_kind(self, kind: str) -> str:
if kind == "fact":
return "deterministic"
if kind in {"evidence", "feature", "capability"}:
return "mixed"
return "curator_owned"
def _recommended_action(self, ownership: str) -> str:
if ownership == "deterministic":
return "recalculate"
return "review"
def _dependency_display_name(
self,
repository_id: int,
kind: str,
item_id: int,
) -> str:
ability_map = self.store.get_ability_map(repository_id)
if kind == "scope" and ability_map.scope.id == item_id:
return ability_map.scope.name
for ability in ability_map.abilities:
if kind == "ability" and ability.id == item_id:
return ability.name
for capability in ability.capabilities:
if kind == "capability" and capability.id == item_id:
return capability.name
for feature in capability.features:
if kind == "feature" and feature.id == item_id:
return feature.name
for evidence in capability.evidence:
if kind == "evidence" and evidence.id == item_id:
return evidence.reference
return f"{kind}:{item_id}"
def _dependency_node_label(
self,
repository_id: int,
kind: str,
key: str,
item_id: int | None,
) -> str:
if item_id is not None and kind != "fact":
return self._dependency_display_name(repository_id, kind, item_id)
if kind == "fact":
parts = key.split(":", 3)
if len(parts) == 4:
_, fact_kind, path, name = parts
return f"{name} ({fact_kind}, {path})"
if item_id is not None:
return f"{kind}:{item_id}"
return key
def _chunk_index(
self,
chunks: Sequence[ContentChunk],
) -> dict[str, dict[str, object]]:
return {
f"chunk:{chunk.kind}:{chunk.path}:{chunk.start_line}:{chunk.end_line}": {
"item_type": "chunk",
"kind": chunk.kind,
"path": chunk.path,
"start_line": chunk.start_line,
"end_line": chunk.end_line,
"text": chunk.text,
}
for chunk in chunks
}
def _candidate_index(
self,
abilities: Sequence[CandidateAbility],
) -> dict[str, dict[str, object]]:
index: dict[str, dict[str, object]] = {}
for ability in abilities:
ability_key = self._entry_key("ability", ability.name)
index[ability_key] = {
"item_type": "ability",
"name": ability.name,
"description": ability.description,
"confidence": ability.confidence,
"status": ability.status,
}
for capability in ability.capabilities:
capability_key = self._entry_key(
"capability",
ability.name,
capability.name,
)
index[capability_key] = {
"item_type": "capability",
"ability_name": ability.name,
"name": capability.name,
"description": capability.description,
"inputs": capability.inputs,
"outputs": capability.outputs,
"confidence": capability.confidence,
"status": capability.status,
}
self._index_candidate_leaves(index, ability, capability)
return index
def _index_candidate_leaves(
self,
index: dict[str, dict[str, object]],
ability: CandidateAbility,
capability: CandidateCapability,
) -> None:
for feature in capability.features:
key = self._entry_key(
"feature",
ability.name,
capability.name,
feature.name,
feature.type,
feature.location,
)
index[key] = self._feature_payload(
feature,
ability_name=ability.name,
capability_name=capability.name,
)
for evidence in capability.evidence:
key = self._entry_key(
"evidence",
ability.name,
capability.name,
evidence.type,
evidence.reference,
)
index[key] = self._evidence_payload(
evidence,
ability_name=ability.name,
capability_name=capability.name,
)
def _approved_index(self, abilities) -> dict[str, dict[str, object]]:
index: dict[str, dict[str, object]] = {}
for ability in abilities:
ability_key = self._entry_key("ability", ability.name)
index[ability_key] = {
"item_type": "ability",
"name": ability.name,
"description": ability.description,
"confidence": ability.confidence,
}
for capability in ability.capabilities:
capability_key = self._entry_key(
"capability",
ability.name,
capability.name,
)
index[capability_key] = {
"item_type": "capability",
"ability_name": ability.name,
"name": capability.name,
"description": capability.description,
"inputs": capability.inputs,
"outputs": capability.outputs,
"confidence": capability.confidence,
}
for feature in capability.features:
key = self._entry_key(
"feature",
ability.name,
capability.name,
feature.name,
feature.type,
feature.location,
)
index[key] = self._feature_payload(
feature,
ability_name=ability.name,
capability_name=capability.name,
)
for evidence in capability.evidence:
key = self._entry_key(
"evidence",
ability.name,
capability.name,
evidence.type,
evidence.reference,
)
index[key] = self._evidence_payload(
evidence,
ability_name=ability.name,
capability_name=capability.name,
)
return index
def _feature_payload(
self,
feature: CandidateFeature,
*,
ability_name: str,
capability_name: str,
) -> dict[str, object]:
return {
"item_type": "feature",
"ability_name": ability_name,
"capability_name": capability_name,
"name": feature.name,
"type": feature.type,
"location": feature.location,
"confidence": feature.confidence,
}
def _evidence_payload(
self,
evidence: CandidateEvidence,
*,
ability_name: str,
capability_name: str,
) -> dict[str, object]:
return {
"item_type": "evidence",
"ability_name": ability_name,
"capability_name": capability_name,
"type": evidence.type,
"reference": evidence.reference,
"strength": evidence.strength,
}
def _entry_key(self, *parts: str) -> str:
return ":".join(part.strip().lower() for part in parts)
def _yaml_list(self, values: Sequence[str]) -> str:
return "[" + ", ".join(self._yaml_scalar(value) for value in values) + "]"
def _yaml_scalar(self, value: object) -> str:
text = "" if value is None else str(value)
escaped = text.replace("\\", "\\\\").replace('"', '\\"')
return f'"{escaped}"'
def search(
self,
query: str,
*,
status: str | None = None,
language: str | None = None,
framework: str | None = None,
ability: str | None = None,
capability: str | None = None,
) -> list[SearchResult]:
text_results = self.store.search(
query,
status=status,
language=language,
framework=framework,
ability=ability,
capability=capability,
)
if self.embedding_provider is None:
return text_results
return self._hybrid_search(
query,
text_results,
status=status,
language=language,
framework=framework,
ability=ability,
capability=capability,
)
def _hybrid_search(
self,
query: str,
text_results: list[SearchResult],
*,
status: str | None,
language: str | None,
framework: str | None,
ability: str | None,
capability: str | None,
) -> list[SearchResult]:
query_vector = self.embedding_provider.embed(query)
candidates = self._semantic_candidates(
status=status,
language=language,
framework=framework,
ability=ability,
capability=capability,
)
by_key = {
self._search_result_key(result): replace(
result,
text_score=max(result.text_score, 1.0),
hybrid_score=max(result.hybrid_score, result.confidence),
)
for result in text_results
}
for text, result in candidates:
vector_score = max(
0.0,
cosine_similarity(query_vector, self.embedding_provider.embed(text)),
)
if vector_score < 0.18:
continue
text_match = by_key.get(self._search_result_key(result))
text_score = text_match.text_score if text_match is not None else 0.0
hybrid_score = (
0.55 * text_score
+ 0.35 * vector_score
+ 0.10 * result.confidence
)
ranked = replace(
text_match or result,
vector_score=max(vector_score, (text_match or result).vector_score),
text_score=text_score,
hybrid_score=max(hybrid_score, (text_match or result).hybrid_score),
matched_field=(text_match or result).matched_field or "semantic",
)
by_key[self._search_result_key(ranked)] = ranked
return sorted(
by_key.values(),
key=lambda result: (
-result.hybrid_score,
-result.vector_score,
-result.confidence,
result.repository_name.lower(),
result.match_type,
result.match_name.lower(),
),
)
def _semantic_candidates(
self,
*,
status: str | None,
language: str | None,
framework: str | None,
ability: str | None,
capability: str | None,
) -> list[tuple[str, SearchResult]]:
candidates: list[tuple[str, SearchResult]] = []
for repository in self.store.list_repositories():
if status and repository.status != status:
continue
facts = self.store.list_observed_facts(repository.id)
if not self._repository_matches_observed_filter(facts, "language", language):
continue
if not self._repository_matches_observed_filter(facts, "framework", framework):
continue
ability_map = self.store.get_ability_map(repository.id)
if not self._ability_map_matches_filter(
ability_map,
ability=ability,
capability=capability,
):
continue
candidates.extend(self._approved_entry_candidates(ability_map))
candidates.extend(self._content_chunk_candidates(repository, ability_map))
return candidates
def _approved_entry_candidates(
self,
ability_map: RepositoryAbilityMap,
) -> list[tuple[str, SearchResult]]:
candidates: list[tuple[str, SearchResult]] = []
repository = ability_map.repository
for ability in ability_map.abilities:
ability_text = f"{ability.name} {ability.description}"
candidates.append(
(
ability_text,
SearchResult(
repository_id=repository.id,
repository_name=repository.name,
match_type="ability",
match_name=ability.name,
confidence=ability.confidence,
confidence_label=ability.confidence_label,
match_description=ability.description,
matched_field="semantic",
ability_id=ability.id,
ability_name=ability.name,
),
)
)
for capability in ability.capabilities:
capability_text = " ".join(
[
ability.name,
capability.name,
capability.description,
" ".join(capability.inputs),
" ".join(capability.outputs),
]
)
candidates.append(
(
capability_text,
SearchResult(
repository_id=repository.id,
repository_name=repository.name,
match_type="capability",
match_name=capability.name,
confidence=capability.confidence,
confidence_label=capability.confidence_label,
match_description=capability.description,
matched_field="semantic",
ability_id=ability.id,
ability_name=ability.name,
capability_id=capability.id,
capability_name=capability.name,
),
)
)
return candidates
def _content_chunk_candidates(
self,
repository: Repository,
ability_map: RepositoryAbilityMap,
) -> list[tuple[str, SearchResult]]:
if not ability_map.abilities:
return []
chunks = self.store.list_content_chunks(repository.id)
candidates: list[tuple[str, SearchResult]] = []
for chunk in chunks:
candidates.append(
(
chunk.text,
SearchResult(
repository_id=repository.id,
repository_name=repository.name,
match_type="content_chunk",
match_name=f"{chunk.path}:{chunk.start_line}-{chunk.end_line}",
confidence=0.5,
confidence_label="medium",
match_description=chunk.text[:240],
matched_field="semantic",
source_reference=f"{chunk.path}:{chunk.start_line}",
),
)
)
return candidates
def _repository_matches_observed_filter(
self,
facts: Sequence[ObservedFact],
kind: str,
expected: str | None,
) -> bool:
if not expected:
return True
expected_lower = expected.lower()
return any(
fact.kind == kind and expected_lower in fact.name.lower()
for fact in facts
)
def _ability_map_matches_filter(
self,
ability_map: RepositoryAbilityMap,
*,
ability: str | None,
capability: str | None,
) -> bool:
if not ability and not capability:
return True
ability_lower = ability.lower() if ability else None
capability_lower = capability.lower() if capability else None
for approved_ability in ability_map.abilities:
ability_matches = (
ability_lower is None
or ability_lower in approved_ability.name.lower()
or ability_lower in approved_ability.description.lower()
)
if not ability_matches:
continue
if capability_lower is None:
return True
for approved_capability in approved_ability.capabilities:
if (
capability_lower in approved_capability.name.lower()
or capability_lower in approved_capability.description.lower()
):
return True
return False
def _search_result_key(self, result: SearchResult) -> tuple[object, ...]:
return (
result.repository_id,
result.match_type,
result.ability_id,
result.capability_id,
result.match_name,
result.source_reference,
)