Truto Customer Issue Debugger

Truto Customer Issue Debugger

Mission

Convert a customer issue into a support-ready root cause and next action. Optimize for fast triage from a short prompt while staying read-only unless the user asks for a fix.

Minimum Useful Input

Any two of these are enough to begin: profile/environment, account ID, tenant ID, integration slug, failing endpoint/resource/method, record ID, request body/query, time window, error text, expected behavior.

Ask for the account ID if the customer issue cannot be tied to an account by tenant_id or logs. Ask for a profile if active profile scope is not safe to assume.

Evidence Runbook

1. Scope:

   truto whoami -p "$PROFILE" -o json --no-color
   

2. Account and tool surface:

   truto accounts get "$ACCOUNT_ID" -p "$PROFILE" -o json --no-color
   truto accounts tools "$ACCOUNT_ID" -p "$PROFILE" -o json --no-color
   truto capabilities "$ACCOUNT_ID" --target account -p "$PROFILE" -o json --no-color
   

3. Config lineage:

   truto environment-integrations get "$ENV_INTEGRATION_ID" -p "$PROFILE" -o json --no-color
   truto environment-integrations show-override "$ENV_INTEGRATION_ID" -p "$PROFILE" -o json --no-color
   truto integrations get "$INTEGRATION_ID" -p "$PROFILE" -o json --no-color
   truto integrations tools "$INTEGRATION_SLUG_OR_ID" -p "$PROFILE" -o json --no-color
   

4. Docs and AI/tool exposure:

   truto docs list --integration-id "$INTEGRATION_ID" -p "$PROFILE" -o json --no-color
   truto docs list --environment-integration-id "$ENV_INTEGRATION_ID" -p "$PROFILE" -o json --no-color
   

5. Logs:

   truto logs --log-type unified_proxy_api --integrated-account-id "$ACCOUNT_ID" --start "$START" --end "$END" --limit 100 -p "$PROFILE" -o json --no-color
   

6. Reproduction:

   truto proxy "$RESOURCE" -m "$METHOD" -a "$ACCOUNT_ID" --query-json "$QUERY_JSON" -p "$PROFILE" -o json --no-color -v
   truto unified "$MODEL" "$UNIFIED_RESOURCE" -m "$METHOD" -a "$ACCOUNT_ID" --query-json "$QUERY_JSON" -p "$PROFILE" -o json --no-color -v
   truto custom "$PATH" -m "$HTTP_METHOD" -a "$ACCOUNT_ID" --query-json "$QUERY_JSON" -p "$PROFILE" -o json --no-color -v
   

Run only the reproduction type that matches the issue. Use custom to prove provider behavior when proxy config is suspect.

Triage Questions To Answer Internally

• Does the account belong to the expected integration/environment?
• Does the method exist in account tools and capabilities?
• Is the failure present in logs for the same time/account?
• Does proxy/raw behavior work while unified fails?
• Does the provider return the same error through custom/proxy?
• Are docs rows missing for a method expected to appear in AI/MCP/tool surfaces?
• Is the request invalid for provider docs, customer scopes, or provider plan?

Output

Return a customer-safe summary with: impact, failing operation, evidence, root-cause lane, who owns the fix, customer workaround if any, and exact next command or patch plan. Redact secrets and avoid dumping full provider payloads.