coulomb/repo-scoping
2
0
Fork 0
generated from coulomb/repo-seed
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

utility relationships understanding of INTENT.md vs. SCOPE.md and documentation.

Browse Source
This commit is contained in:
Bernd Worsch
2026-05-02 17:33:58 +02:00
parent 11c5beba58
commit d9df4da12a
7 changed files with 311 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

104
src/repo_registry/candidate_graph/generator.py
View File

@@ -74,6 +74,7 @@ class CandidateGraphGenerator:
credential_configs = self._facts(facts, "credential_config")
provider_registries = self._facts(facts, "provider_registry")
fallback_policies = self._facts(facts, "fallback_policy")
intent_facts = self._facts(facts, "intent")
ability_primary_class, ability_attributes = self._ability_classification(
repository,
facts,
@@ -103,6 +104,9 @@ class CandidateGraphGenerator:
capabilities.append(
self._interface_capability(interfaces, tests, examples, docs, chunks)
)
capabilities.extend(
self._intent_capabilities(intent_facts, chunks, tests, examples, docs)
)
promotable_llm_providers = self._promotable_llm_facts(llm_providers)
promotable_provider_registries = self._promotable_llm_facts(provider_registries)
promotable_fallback_policies = self._promotable_llm_facts(fallback_policies)
@@ -139,11 +143,11 @@ class CandidateGraphGenerator:
languages=languages,
docs=docs,
),
source_refs=self._source_refs(manifests + frameworks + languages),
primary_class="repository-structure",
attributes=self._structure_attributes(
manifests,
frameworks,
source_refs=self._source_refs(manifests + frameworks + languages),
primary_class="repository-structure",
attributes=self._structure_attributes(
manifests,
frameworks,
languages,
),
evidence=self._evidence(tests, examples, docs),
@@ -284,6 +288,91 @@ class CandidateGraphGenerator:
evidence=self._evidence(tests, examples, docs),
)
def _intent_capabilities(
self,
intent_facts: list[ObservedFact],
chunks: list[ContentChunk],
tests: list[ObservedFact],
examples: list[ObservedFact],
docs: list[ObservedFact],
) -> list[CandidateCapabilityDraft]:
intent_chunks = [
chunk
for chunk in chunks
if chunk.kind == "intent"
and (
chunk.metadata.get("source_role") == "intent_summary"
or chunk.path.lower().endswith("intent.md")
)
]
if not intent_chunks:
return []
source_refs = self._source_refs(intent_facts)
capabilities: list[CandidateCapabilityDraft] = []
seen: set[str] = set()
for item in self._intent_capability_items(intent_chunks):
name = self._intent_capability_name(item)
key = name.lower()
if not name or key in seen:
continue
seen.add(key)
capabilities.append(
CandidateCapabilityDraft(
name=name,
description=(
"Reviewable intended capability extracted from repository "
f"intent: {item}"
),
inputs=[],
outputs=[name],
confidence=self._confidence(
0.45,
[
(0.15, bool(source_refs)),
(0.10, bool(tests)),
(0.05, bool(examples)),
(0.05, bool(docs)),
],
),
source_refs=source_refs,
primary_class="intent-capability",
attributes=[
"intent-derived",
"utility-owned",
"review-required-intent",
],
evidence=self._evidence(tests, examples, docs),
)
)
return capabilities
def _intent_capability_items(self, chunks: list[ContentChunk]) -> list[str]:
items: list[str] = []
in_capability_section = False
for chunk in sorted(chunks, key=lambda item: (item.path, item.start_line)):
for raw_line in chunk.text.splitlines():
line = raw_line.strip()
if not line:
continue
if line.startswith("#"):
heading = line.lstrip("#").strip().lower()
in_capability_section = "capabilit" in heading
continue
if not in_capability_section:
continue
item = re.sub(r"^(?:[-*]|\d+[.)])\s+", "", line).strip()
item = re.sub(r"^(?:capability|intended capability)\s*:\s*", "", item, flags=re.I)
if item and item != line or raw_line.lstrip().startswith(("-", "*")):
items.append(item)
return items
def _intent_capability_name(self, text: str) -> str:
candidate = re.split(r"\s+-\s+|\s*:\s*|[.!?]\s+", text.strip(), maxsplit=1)[0]
candidate = candidate.strip(" .:-")
if not candidate:
return ""
return self._title_from_words(candidate.split()[:8])
def _interface_features(
self,
interfaces: list[ObservedFact],
@@ -437,7 +526,7 @@ class CandidateGraphGenerator:
def _interface_attributes(self, interfaces: list[ObservedFact]) -> list[str]:
feature_types = {self._feature_type(fact) for fact in interfaces}
attributes = ["api" if item == "API" else "cli" if item == "CLI" else "callable" for item in feature_types]
return self._unique(["surface", *attributes])
return self._unique(["surface", *attributes, "utility-owned"])
def _feature_attributes(
self,
@@ -467,6 +556,9 @@ class CandidateGraphGenerator:
"manifest" if manifests else "",
*[fact.name for fact in frameworks],
*[fact.name for fact in languages],
"utility-dependency" if manifests or frameworks else "",
"utility-tooling" if languages and not (manifests or frameworks) else "",
"review-required-structural-context",
]
)

75
src/repo_registry/core/service.py
View File

@@ -489,6 +489,8 @@ class RegistryService:
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
@@ -497,11 +499,14 @@ class RegistryService:
for capability in ability.capabilities
if capability.status == "candidate"
]
safe_capabilities = [
capability
for capability in candidate_capabilities
if self._trusted_auto_approve_capability_safe(capability)
]
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
@@ -536,6 +541,7 @@ class RegistryService:
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)
@@ -544,23 +550,64 @@ class RegistryService:
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]:
has_source_refs = bool(capability.source_refs) or any(
feature.source_refs for feature in capability.features
)
if not has_source_refs:
return False
return False, "missing source references"
if capability.primary_class == "repository-structure":
return False
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 bool(
{"utility-owned", "utility-facade", "utility-adapter"}
& set(capability.attributes)
)
return True, "eligible LLM utility relationship with source support"
if capability.primary_class in {"interface", "API", "CLI", "callable", "api", "cli"}:
return capability.confidence >= 0.55
if capability.confidence >= 0.55:
return True, "owned interface with sufficient confidence"
return False, "owned interface confidence below trusted threshold"
if capability.features:
return capability.confidence >= 0.55
return capability.confidence >= 0.75
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)