ai/byre
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 10 Wiki Activity

Audit of 0058e66

Browse Source
This commit is contained in:
Ian Gulliver
2026-10-21 10:12:35 -07:00
parent 4cedd4a1a9
commit 9afe016b06
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/operations.md
+2 -2
View File
@@ -24,7 +24,7 @@ byre runs its own tailnet node with `tsnet`; it doesn't use the Tailscale app. T
Tailscale identifies the connecting Mac, including requests from a web page opened there; network identity alone doesn't establish the user's intent. Cross-origin browser requests must not be allowed to change state through that identity. Native app and CLI access remains intentional.
The local status endpoint requires the bearer credential in `<data>/loopback-token`, regenerated on service startup. Loopback is reachable by other OS accounts, so it cannot protect the node’s sign-in URL by itself. The app reads the credential from the default data directory.
The local status endpoint requires the bearer credential in `<data>/loopback-token`, regenerated on service startup. Loopback is reachable by other OS accounts, so it cannot protect the node’s sign-in URL by itself.
A new node needs signing in: `curl -H "Authorization: Bearer $(cat "$HOME/Library/Application Support/byre/loopback-token")" <loopback>/api/tailnet` (`byre check` prints the loopback address) shows `NeedsLogin` and the `auth_url`, and the app on the same Mac shows it as **Sign in to Tailscale**. The tailnet must have MagicDNS and HTTPS certificates turned on (the DNS page of Tailscale's admin console); without certificates byre logs `tailnet has no https certificates` and serves only the loopback address until it is restarted.
@@ -80,7 +80,7 @@ Vendor setup and protocol quirks are in [Claude Code](claude-protocol.md), [Code
## Agent behavior
- A turn whose final message asks the human something in prose is bounced once, telling the agent to use `ask_human`. For Claude the bounce is a Stop hook that blocks the stop; Claude Code reports the block as a "Stop hook error" notification, which is expected. An agent told explicitly to ask in plain text will refuse the bounce.
- A turn that asks a question has no summary; everything the human needs belongs in the question's context. Other turns use their final message as the summary. There is no report tool: models already write a closing recap, so byre uses it rather than asking for a second one.
- A turn that asks a question has no summary; everything the human needs belongs in the question's context. Other turns use their final message as the summary; don't ask agents to write a second recap.
- A review covers the whole task against the default branch, so a newer one makes older ones moot. Findings reach the task's agent together, once the whole review workflow finishes; an individual reviewer finishing is not a completed review.
- An audit checks only the newest commit of the default branch, one at a time per project, so it doesn't run on every revision but the newest one is always audited eventually. byre never fetches for an audit, so a commit pushed outside byre is audited only once a byre merge has fetched it.
- The lead's `show` is refused for a few seconds after the human moves the pane, and only a refusal arranges the "hold is over" signal, so the lead's prompt tells it to call `show` at once whenever it wants to show something, never holding back in expectation of a refusal.