Skip to content

docs(agents): add chittyagent-google to agent interaction table #135

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
chitcommit wants to merge 1 commit into
base: main
Choose a base branch
from
Open

docs(agents): add chittyagent-google to agent interaction table #135

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions AGENTS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,6 +58,7 @@ Authentication: Bearer service token. See [SECURITY.md](SECURITY.md).
| `chittyagent-connect` | Outbound (runtime) | Mercury Bank proxy — every bank API call routes through ChittyConnect |
| `chittyagent-canon` | Inbound (CI) | Audits this repo for canonical pattern adherence |
| `chittyagent-cloudflare` | Outbound (admin) | Hyperdrive, KV, Email Service, WAF rules |
| `chittyagent-google` | Outbound (runtime) | Google Workspace MCP gateway — Gmail (bank notifications, evidence), Drive (document storage), Sheets (export targets), Calendar (scheduling). Hybrid: dynamic MCP discovery + static gap-fillers |

@coderabbitai coderabbitai Bot Jun 21, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

⚠️ Potential issue | 🟠 Major | ⚡ Quick win

Document trust level and audit trail for the chittyagent-google integration.

Per the requirement stated in this file (line 98) and the established learning, new agent integrations that write to financial state must document their trust level (L0–L4) and audit trail before merging. The chittyagent-google entry handles "bank notifications, evidence"—evidence storage implies writes to ChittyFinance's state—but lacks both pieces of information.

Compare to chittyagent-schema (line 56): "Trust level: L1 — writes suggested_coa_code only, never coa_code" and "Audit: Every suggestion writes to classification_audit".

Add similar clarity: specify what financial state the agent can/cannot write, and document the audit/logging mechanism for those writes.

📋 Suggested format for the entry (fill in trust level and audit trail details) 
-| `chittyagent-google` | Outbound (runtime) | Google Workspace MCP gateway — Gmail (bank notifications, evidence), Drive (document storage), Sheets (export targets), Calendar (scheduling). Hybrid: dynamic MCP discovery + static gap-fillers |
+| `chittyagent-google` | Outbound (runtime) | Google Workspace MCP gateway — Gmail (bank notifications, evidence), Drive (document storage), Sheets (export targets), Calendar (scheduling). Hybrid: dynamic MCP discovery + static gap-fillers. **Trust level: [L0–L4?] — writes [which fields/records]**. **Audit: [how are evidence writes logged?]** |

You'll need to coordinate with the implementation PR author (chittyos/chittyentity#510) to fill in the bracketed sections.

📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change
| `chittyagent-google` | Outbound (runtime) | Google Workspace MCP gateway — Gmail (bank notifications, evidence), Drive (document storage), Sheets (export targets), Calendar (scheduling). Hybrid: dynamic MCP discovery + static gap-fillers |
| `chittyagent-google` | Outbound (runtime) | Google Workspace MCP gateway — Gmail (bank notifications, evidence), Drive (document storage), Sheets (export targets), Calendar (scheduling). Hybrid: dynamic MCP discovery + static gap-fillers. **Trust level: [L0–L4?] — writes [which fields/records]**. **Audit: [how are evidence writes logged?]** |
🤖 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 `@AGENTS.md` at line 61, The `chittyagent-google` entry in the AGENTS.md file
is missing required trust level (L0–L4) and audit trail documentation for its
financial state writes. Update the `chittyagent-google` table entry to include:
a trust level specification (following the L0–L4 scale), a clear statement of
what financial state the agent can and cannot write (for example, which fields
it can modify versus which are read-only), and the name of the audit trail or
logging mechanism that records those writes. Use the `chittyagent-schema` entry
as a reference format, which documents trust level as "L1 — writes
`suggested_coa_code` only, never `coa_code`" and audit as "Every suggestion
writes to `classification_audit`". Coordinate with the implementation author to
fill in the specific trust level and audit details for the Google Workspace
integration.

Source: Learnings

| `chittyagent-notion` | Outbound (state) | Project + Actions DB updates from session lifecycle hooks |

## ChittyOS Subagents Useful for Development
Expand Down
Loading