Fix rerank usageDetails note (PR review)

The 0060 conformance note said Langfuse usageDetails is an empty map
when usage is null, but the observer omits usageDetails entirely
(usage=None, so the adapter adds no usage_details), which fixture 142
asserts. Correct the note to 'omitted when usage = null'.

Author: chris-colinsky

conformance.toml

@@ -614,7 +614,7 @@ note = "Retrieval-provider embedding capability. The EmbeddingProvider protocol
 [proposals."0060"]
 status = "implemented"
 since = "0.16.0"
-note = "Retrieval-provider rerank protocol. The RerankProvider protocol (retrieval-provider §5) + the RerankResponse / ScoredDocument / RerankUsage / RerankRuntimeConfig response types (§6) + the RerankRuntimeConfig runtime config (§2) ship, alongside the CohereRerankProvider reference reranker against POST /v2/rerank (§8.4, Cohere-shape): the request body is {model, query, documents (string array), top_n from top_k}, return_documents is a silent no-op (the Cohere wire has no such field), and max_tokens_per_doc rides the extras pass-through bag. The provider parses {id, model?, results: [{index, relevance_score, document?}], meta.billed_units.{search_units, input_tokens}}, sorts results by relevance_score descending, reads the document echo only when present (never auto-filled), builds a RerankUsage record only when the provider surfaces >= 1 usage figure (else usage = null, never fabricated), and enforces the §6 invariants -- valid index into the input documents, no duplicate index, len(results) <= top_k when supplied -- raising provider_invalid_response otherwise. Pre-send validation raises provider_invalid_request on an empty query, an empty documents list, or top_k <= 0 (top_k MAY exceed len(documents)). The provider dispatches the typed RerankEvent / RerankFailedEvent (graph-engine §6) per rerank() call, mutually exclusive, alongside the §7-category exception on failure; RerankEvent.output_results is populated unconditionally on success (proposal 0089). The §7 categories reuse the shared llm-provider taxonomy. Both bundled observers render the rerank events (0060b): the OTelObserver emits an openarmature.rerank.complete span (observability §5.5.13, SpanKind.CLIENT) parented lineage-aware under the calling node, carrying the GenAI semconv subset (gen_ai.system / request.model / response.model / response.id + the conditional usage.input_tokens, gated by disable_genai_semconv) + the OA openarmature.rerank.query_length (UTF-8 bytes) / .document_count / .top_k (omitted when null) / .result_count identity attrs + the conditional .search_units + the payload-gated (disable_provider_payload) .query / .documents / .results (the results sourced from RerankEvent.output_results per proposal 0089) -- no gen_ai.operation.name (deferred, no upstream rerank coverage), not gated by disable_llm_spans; failure renders ERROR status + error.type + an exception event + openarmature.error.category. The LangfuseObserver renders a dedicated Retriever observation (asType retriever, §8.4.7) with model = response_model-or-model, usageDetails.{input, searchUnits} (empty map when usage = null), the openarmature_query_length / _document_count / _top_k / _result_count / _response_id metadata, and the payload-gated input {query, documents} + output results; failure renders an ERROR-level Retriever observation with error_category as statusMessage, error_type / error_message in metadata, and no output. Protocol fixtures 006-012 + observability fixtures 099-108 / 138 / 141 / 142 pass. The §11 rerank-metrics path (fixture 109) is proposal 0067's metrics surface (one GenAI instrument across LLM + embedding + rerank calls), tracked and deferred under 0067 (cf. 089), not part of 0060's own observability surface. Wire-format details (0090 Cohere rerank fixtures 028-031) are a separate proposal."
+note = "Retrieval-provider rerank protocol. The RerankProvider protocol (retrieval-provider §5) + the RerankResponse / ScoredDocument / RerankUsage / RerankRuntimeConfig response types (§6) + the RerankRuntimeConfig runtime config (§2) ship, alongside the CohereRerankProvider reference reranker against POST /v2/rerank (§8.4, Cohere-shape): the request body is {model, query, documents (string array), top_n from top_k}, return_documents is a silent no-op (the Cohere wire has no such field), and max_tokens_per_doc rides the extras pass-through bag. The provider parses {id, model?, results: [{index, relevance_score, document?}], meta.billed_units.{search_units, input_tokens}}, sorts results by relevance_score descending, reads the document echo only when present (never auto-filled), builds a RerankUsage record only when the provider surfaces >= 1 usage figure (else usage = null, never fabricated), and enforces the §6 invariants -- valid index into the input documents, no duplicate index, len(results) <= top_k when supplied -- raising provider_invalid_response otherwise. Pre-send validation raises provider_invalid_request on an empty query, an empty documents list, or top_k <= 0 (top_k MAY exceed len(documents)). The provider dispatches the typed RerankEvent / RerankFailedEvent (graph-engine §6) per rerank() call, mutually exclusive, alongside the §7-category exception on failure; RerankEvent.output_results is populated unconditionally on success (proposal 0089). The §7 categories reuse the shared llm-provider taxonomy. Both bundled observers render the rerank events (0060b): the OTelObserver emits an openarmature.rerank.complete span (observability §5.5.13, SpanKind.CLIENT) parented lineage-aware under the calling node, carrying the GenAI semconv subset (gen_ai.system / request.model / response.model / response.id + the conditional usage.input_tokens, gated by disable_genai_semconv) + the OA openarmature.rerank.query_length (UTF-8 bytes) / .document_count / .top_k (omitted when null) / .result_count identity attrs + the conditional .search_units + the payload-gated (disable_provider_payload) .query / .documents / .results (the results sourced from RerankEvent.output_results per proposal 0089) -- no gen_ai.operation.name (deferred, no upstream rerank coverage), not gated by disable_llm_spans; failure renders ERROR status + error.type + an exception event + openarmature.error.category. The LangfuseObserver renders a dedicated Retriever observation (asType retriever, §8.4.7) with model = response_model-or-model, usageDetails.{input, searchUnits} (omitted when usage = null), the openarmature_query_length / _document_count / _top_k / _result_count / _response_id metadata, and the payload-gated input {query, documents} + output results; failure renders an ERROR-level Retriever observation with error_category as statusMessage, error_type / error_message in metadata, and no output. Protocol fixtures 006-012 + observability fixtures 099-108 / 138 / 141 / 142 pass. The §11 rerank-metrics path (fixture 109) is proposal 0067's metrics surface (one GenAI instrument across LLM + embedding + rerank calls), tracked and deferred under 0067 (cf. 089), not part of 0060's own observability surface. Wire-format details (0090 Cohere rerank fixtures 028-031) are a separate proposal."
 
 # Spec v0.55.0 (proposal 0065; repo pins v0.55.1).  Failure-isolation
 # cause fidelity at non-node placements (pipeline-utilities §6.3 /