Skip to content

docs(governance): propose communication-protocol rule (Ask/Question/Propose/Alert)#795

Open
jordyamoedo wants to merge 2 commits into
SynkraAI:mainfrom
jordyamoedo:contrib/communication-protocol
Open

docs(governance): propose communication-protocol rule (Ask/Question/Propose/Alert)#795
jordyamoedo wants to merge 2 commits into
SynkraAI:mainfrom
jordyamoedo:contrib/communication-protocol

Conversation

@jordyamoedo

@jordyamoedo jordyamoedo commented Jun 15, 2026

Copy link
Copy Markdown

Summary

This proposes a communication-protocol rule for agents — submitted through the project's own governance/evolution-pipeline.md as an AuditFinding + FrameworkProposal (both PENDING your approval). Two governance YAML files; no code paths touched.

The gap

There's no shared protocol for how agents communicate when they hit a wall — insufficient context, a flawed requirement, a better alternative, or a risk. Without it, agents tend to execute blindly or stay silent to look efficient.

The proposal

Agents are specialists, not blind executors. Four modes:

  • ASK — when context is insufficient (missing acceptance criteria, unknown stack, ambiguous scope).
  • QUESTION — when a requirement is flawed (unfeasible, disproportionate, regression risk).
  • PROPOSE — when a better path exists (an existing pattern, a more specialized agent, a quick win).
  • ALERT — when a risk is identified, by severity (critical = HALT for explicit confirmation; high / medium / low).

Plus the anti-patterns to avoid: never assume unprovided context, never invent requirements, never execute silently under critical ambiguity, never deliver incomplete output without flagging it.

Why it's good for the project

  • It raises the quality of every agent in the framework — universal, not tied to any one workflow.
  • It's cheap and additive — one documentation rule.
  • It's freedom-preserving — posture/method guidance, advisory by nature, not a blocking gate.
  • Battle-tested in a production consumer fork, then generalized here (no project-specific content).

Submitted in the spirit of the framework's own evolution pipeline. Happy to follow up with refinements per your guidance.

Summary by CodeRabbit

  • New Features

    • Established formal communication protocol framework defining distinct operating modes for agent interactions and engagement patterns.
  • Documentation

    • Added audit findings documenting communication protocol framework analysis with impact assessment and implementation guidelines.
    • Added governance proposal for communication protocol framework adoption with migration and rollout guidance.

@vercel

vercel Bot commented Jun 15, 2026

Copy link
Copy Markdown

@jordyamoedo is attempting to deploy a commit to the SINKRA - AIOX Team on Vercel.

A member of the Team first needs to authorize it.

@github-actions github-actions Bot added the area: docs Documentation (docs/) label Jun 15, 2026
@coderabbitai

coderabbitai Bot commented Jun 15, 2026

Copy link
Copy Markdown

Review Change Stack

Walkthrough

Two new YAML files are added: an audit finding (AF-20260614-communication-protocol.yaml) documenting the absence of a shared agent communication protocol, and a governance proposal (PROP-20260614-communication-protocol.yaml) converting that finding into a proposed L2 framework rule defining four agent communication modes and an alert-severity ladder.

Changes

Communication Protocol Audit-to-Proposal Pipeline

Layer / File(s) Summary
Audit finding: communication protocol gap
audits/promoted/AF-20260614-communication-protocol.yaml
Introduces the full audit_finding record with metadata, anonymized project context, evidence, observed impact (medium blast radius), framework-candidate rationale, and a proposed disposition covering four communication modes (Ask/Question/Propose/Alert), an alert-severity ladder (critical → HALT; high/medium/low), and explicit anti-patterns.
Governance proposal: L2 communication-protocol rule
governance/proposals/PROP-20260614-communication-protocol.yaml
Adds PROP-20260614 referencing AF-20260614 as its source finding, targeting creation of a communication-protocol rule artifact in layer L2. Includes generalized agent-mode guidance, a non-breaking additive rollout plan, a low-cost/low-risk cost-benefit statement, and empty approval and implementation fields pending decision.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Suggested labels

area: docs, area: agents, area: core

Suggested reviewers

  • oalanicolas
  • Pedrovaleriolopez
🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed The title directly describes the primary change: proposing a communication-protocol governance rule with the four modes (Ask/Question/Propose/Alert). It clearly maps to both added YAML files and their shared objective.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.

✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

@github-actions

Copy link
Copy Markdown
Contributor

Welcome to aiox-core! Thanks for your first pull request.

What happens next?

  1. Automated checks will run on your PR
  2. A maintainer will review your changes
  3. Once approved, we'll merge your contribution!

PR Checklist:

Thanks for contributing!

@coderabbitai coderabbitai Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@audits/promoted/AF-20260614-communication-protocol.yaml`:
- Around line 31-32: The references section uses an invalid kind value "pattern"
which is not in the allowed list specified by the audit-finding template. Update
the kind field in the references section from "pattern" to
"existing-pattern-source" to comply with the template specification that only
allows: ADR, code, hook, governance-doc, existing-pattern-source,
voice-clone-finding, voice-clone-personas, handoff-contract, audit, or proposal.
🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

  • Push a commit to this branch (recommended)
  • Create a new PR with the fixes

ℹ️ Review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Run ID: e7e84277-8c0e-44bb-8566-56d7ef76d85e

📥 Commits

Reviewing files that changed from the base of the PR and between 77265d5 and 692d671.

📒 Files selected for processing (2)
  • audits/promoted/AF-20260614-communication-protocol.yaml
  • governance/proposals/PROP-20260614-communication-protocol.yaml

Comment on lines +31 to +32
- kind: pattern
path: "Agents are specialists, not blind executors — four modes"

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟡 Minor

🧩 Analysis chain

🌐 Web query:

What are the current allowed reference kinds in the aiox-core audit-finding schema?

💡 Result:

Based on the available documentation and codebase for aiox-core as of June 2026, there is no explicit entity titled "audit-finding schema" that defines a standardized list of "reference kinds." The aiox-core framework utilizes a multi-layered quality gate system [1][2] and specific workflow task definitions [3][4] to manage audits. Audit results and findings are typically structured as markdown reports (e.g., SCHEMA.md, DB-AUDIT.md) or processed via quality gate JSON schemas [3][1][5]. In these workflows, "references" are generally handled through: 1. Task and Action References: Workflows refer to external task definitions (e.g., db-schema-audit.md) and checklists (e.g., database-design-checklist.md) [5]. 2. Output Destinations: Findings are categorized by their output destination, which includes Memory, File, API, or Database [3]. 3. Quality Metrics: Automated audit metrics are governed by the quality-metrics.schema.json, which defines structure for layers, trends, and history, rather than specific "reference kinds" for findings [1]. If you are encountering a specific error message or schema validation requirement regarding "reference kinds," it may be related to custom implementation logic within your specific squad or project-level configuration, rather than a global schema definition in the core framework.

Citations:


🏁 Script executed:

#!/bin/bash

# Find the audit file mentioned in the review
find . -name "AF-20260614-communication-protocol.yaml" -o -name "*audit-finding-tmpl*" 2>/dev/null | head -20

Repository: SynkraAI/aiox-core

Length of output: 167


🏁 Script executed:

#!/bin/bash

# Search for governance templates directory
find . -type d -name "governance" 2>/dev/null | head -10

Repository: SynkraAI/aiox-core

Length of output: 94


🏁 Script executed:

#!/bin/bash

# Search for any files with "template" or "tmpl" in audit/promoted directory
find . -path "*/audits/promoted*" -type f 2>/dev/null | head -20

Repository: SynkraAI/aiox-core

Length of output: 242


🏁 Script executed:

#!/bin/bash
cat -n ./audits/promoted/AF-20260614-communication-protocol.yaml

Repository: SynkraAI/aiox-core

Length of output: 2309


🏁 Script executed:

#!/bin/bash
cat -n ./governance/templates/audit-finding-tmpl.yaml

Repository: SynkraAI/aiox-core

Length of output: 2532


Change reference kind from "pattern" to "existing-pattern-source".

The references section at lines 31–32 uses kind: pattern, but the audit-finding template specifies allowed kinds as: ADR | code | hook | governance-doc | existing-pattern-source | voice-clone-finding | voice-clone-personas | handoff-contract | audit | proposal (governance/templates/audit-finding-tmpl.yaml, lines 38–39).

Based on the reference content, existing-pattern-source is the appropriate kind. Update line 31 accordingly.

🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@audits/promoted/AF-20260614-communication-protocol.yaml` around lines 31 -
32, The references section uses an invalid kind value "pattern" which is not in
the allowed list specified by the audit-finding template. Update the kind field
in the references section from "pattern" to "existing-pattern-source" to comply
with the template specification that only allows: ADR, code, hook,
governance-doc, existing-pattern-source, voice-clone-finding,
voice-clone-personas, handoff-contract, audit, or proposal.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

area: docs Documentation (docs/)

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant