Make provenance and evidence traceability first-class for proto (canonical protobuf definitions cross-service contracts)

[haasonsaas]

Summary

Carry source, decision, and output provenance through the main workflow so downstream agents can audit and cite it.

This issue was generated from an org-wide EvalOps mining pass on 2026-05-10 07:57 UTC. It combines live GitHub repo signals with a per-repo arXiv search. Treat the research links as grounding for a concrete implementation, not as a request for a literature review.

Repo Evidence

• Repository description: Canonical protobuf definitions for EvalOps cross-service contracts — 14 packages covering identity, metering, governance, approvals, entities, memory, prompts, skills, events, and more
• Tree signals: 0 docs files, 6 workflows, 31 proto files, 37 test-like files.
• README.md:15 includes latent-spec language: - Generate Go, TypeScript, and Python packages from one set of definitions. - Catch breaking contract changes at compile time, not in production. - Keep wire encoding efficient with protobuf binary format.
• README.md:16 includes latent-spec language: - Catch breaking contract changes at compile time, not in production. - Keep wire encoding efficient with protobuf binary format. - Support Connect-RPC service definitions for typed cross-service calls.
• README.md:41 includes latent-spec language: | entities/v1 | Canonical entity resolution, search, links, correlation graph | entities, pipeline, parker, connectors, ensemble | | governance/v1 | Safety evaluation, PII detection, retention, legal holds | governance, approvals, objectives, ensemble, chat | | notifications/v1 | Notification delivery, preference
• README.md:48 includes latent-spec language: | workflows/v1 | Multi-agent workflow orchestration, DAG execution, compensation | objectives, ensemble, maestro, approvals, governance | | prompts/v1 | Prompt versioning, deployment tracking, eval linkage, resolution | prompts, llm-gateway, fermata, maestro, ensemble | | registry/v1 | Agent presence, capability
• README.md:53 includes latent-spec language: ### Contract Ownership
• README.md:229 includes latent-spec language: proto also publishes the generated TypeScript contract surface from the repo root as @evalops/proto.

Research Grounding

Repo axes: research, evaluation, tooling, security

Search keywords: proto, chat, ensemble, approvals, objectives, registry, governance, maestro, entities, gen, pipeline, prompts

• arXiv:2506.19773v2 Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study (Nandana Mihindukulasooriya, Niharika S. D'Souza, Faisal Chowdhury, Horst Samulowitz), 2025.
• arXiv:2503.11118v1 UMB@PerAnsSumm 2025: Enhancing Perspective-Aware Summarization with Prompt Optimization and Supervised Fine-Tuning (Kristin Qi, Youxiang Zhu, Xiaohui Liang), 2025.
• arXiv:2507.03620v1 Is It Time To Treat Prompts As Code? A Multi-Use Case Study For Prompt Optimization Using DSPy (Francisca Lemos, Victor Alves, Filipa Ferraz), 2025.
• arXiv:2412.15298v1 A Comparative Study of DSPy Teleprompter Algorithms for Aligning Large Language Models Evaluation Metrics to Human Evaluation (Bhaskarjit Sarmah, Kriti Dutta, Anna Grigoryan, Sachin Tiwari, Stefano Pasquali, Dhagash Mehta), 2024.
• arXiv:2604.04869v1 Optimizing LLM Prompt Engineering with DSPy Based Declarative Learning (Shiek Ruksana, Sailesh Kiran Kurra, Thipparthi Sanjay Baradwaj), 2026.
• arXiv:2507.14241v3 Promptomatix: An Automatic Prompt Optimization Framework for Large Language Models (Rithesh Murthy, Ming Zhu, Liangwei Yang, Jielin Qiu, Juntao Tan, Shelby Heinecke), 2025.
• arXiv:2310.03714v1 DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines (Omar Khattab, Arnav Singhvi, Paridhi Maheshwari, Zhiyuan Zhang, Keshav Santhanam, Sri Vardhamanan), 2023.
• arXiv:2508.04660v1 Multi-module GRPO: Composing Policy Gradients and Prompt Optimization for Language Model Programs (Noah Ziems, Dilara Soylu, Lakshya A Agrawal, Isaac Miller, Liheng Lai, Chen Qian), 2025.
• arXiv:2602.00997v1 Error Taxonomy-Guided Prompt Optimization (Mayank Singh, Vikas Yadav, Eduardo Blanco), 2026.
• arXiv:2602.13757v2 Assessing the Case for Africa-Centric AI Safety Evaluations (Gathoni Ireri, Cecil Abungu, Jean Cheptumo, Sienka Dounia, Mark Gitau, Stephanie Kasaon), 2026.

What To Build

• Add stable identifiers for source records, derived decisions, and emitted outputs.
• Thread those identifiers through logs/events/API responses without leaking secrets.
• Provide a query or debug surface that reconstructs the chain for one completed workflow.

Acceptance Criteria

• A short design note names the repo-specific workflow, threat or correctness model, and the research assumptions being adopted.
• A runnable check, fixture, or verifier exercises the new contract in CI or an equivalent local command documented in the repo.
• The implementation emits or stores enough evidence for a downstream agent/operator to cite inputs, decisions, and outputs.
• At least one negative/degraded-mode case is covered so failures are observable rather than silently accepted.
• Documentation links the new behavior to the relevant EvalOps platform primitive or explicitly records why this repo remains standalone.

Notes

• Generated issue 2/5 for evalops/proto by evalops_org_miner.py.
• Before implementation, confirm the sampled latent-spec snippets still match main; this issue intentionally cites exact file paths/lines where the mining pass saw them.