← Files ClaraARCHIVED FILE
privacy/workstreams/variance-analysis.json
3.8 KB · Nov 21, 2026 · 00:11 UTC
{"display_name":"Variance Analysis","external_boundaries":[],"governed_paths":[".codex-plugin/plugin.json","skills","scripts","mcp","assets"],"governed_repository_paths":["plugins/clara/skills/reporting-engine/SKILL.md"],"governed_shared_paths":[],"model_context":{"classes":[{"content":"User instructions; all source column names and types; detected period or scenario values; mapping proposals and warnings; and at most the first 10 rows projected to candidate period, date, amount, units, discount, COGS, reporting-dimension and calculation-grain columns. The complete file is processed locally for inspection; unrelated columns are omitted from the built-in row preview. A separate targeted inspection may show at most 10 rows from no more than 12 explicitly named columns.","id":"variance-analysis-mapping-inspection","purpose":"Establish the comparison and candidate semantic mapping before calculation","runtime_profiles":["openai-codex","anthropic-cowork"]},{"content":"The complete selected population is calculated locally. The default model context contains mapped variance results, summaries, recipes, prepared-data lineage, standard and root-cause contexts, chart data and images, diagnostics, limitations and hypotheses, but not raw source rows, the original source filename or unmapped column names in the model-use manifest. Exact in-scope source matches can be produced only for a reason-recorded request using reviewed mapped filters and output columns and the exact sealed used-recipe bytes; every exact match is returned without sampling. The review widget payload contains at most the 50 largest driver rows plus artifact and follow-up metadata.","id":"variance-analysis-post-mapping-review","purpose":"Interpret the reconciled variance from reviewed mappings and complete deterministic calculations","runtime_profiles":["openai-codex","anthropic-cowork"]},{"content":"The first validation may receive the bounded review payload. When the stored run package matches, later render, save and apply calls use an expiring local token bound to the review_payload.json hash and run ID. Vera performs no automatic anonymization or pseudonymization.","id":"variance-analysis-review-decisions","purpose":"Render and record review decisions without repeatedly copying the full review package through MCP calls","runtime_profiles":["openai-codex","anthropic-cowork"]},{"content":"Repository and selected studio/client scope; scoped search queries; returned metadata and snippets; opened relevant passages; source IDs, links and locators; version, date and approval metadata when exposed; coverage and access limitations. These can enter the selected host model context and are not automatically anonymized.","id":"connected-studio-knowledge","purpose":"Consult relevant studio procedures, precedents or case evidence when requested","runtime_profiles":["openai-codex","anthropic-cowork"]}],"policy":"real_case_data_may_enter_selected_runtime_model_context"},"packaged_for_runtime":"openai-codex","public_explanations":{},"repository_source_review":{"path":"privacy/repository-source-reviews/workstream-variance-analysis.json","scope":"reviewed_repository_declaration_not_hosted_runtime","service_id":"workstream-variance-analysis"},"review":{"basis":"external_boundary_review_of_workflow_source","fingerprint_scope":"installed_client_and_repository_review_declaration","reviewed_at":"2026-11-04","reviewed_by":"privacy-surface-review","source_fingerprint":"f551f777bbd69f9748922ae26c8d1144113029f5bf3b921a75a3cc597016f692"},"role":"internal_engine","runtime_profiles":["openai-codex","anthropic-cowork"],"schema_version":3,"security_controls":[],"service_ids":["managed-python-runtime","operational-incidents","run-receipt-stamping","workflow-usage"],"source_contract_sha256":"2a35447017f57918aa0b2a3c4e85bf38cbf9b1523b0252ec37208359ed159e10","workstream":"variance-analysis"}
SHA-256: 13061a695e7939194a0af78709e9419fe2bbc2c60bcc47d984d46ca02e66797a