Skip to content

docs(slack): document preference for direct posting to avoid silent-exit recovery triggers #82

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

Closed
dembrane-sam-bot wants to merge 1 commit into from
Closed

docs(slack): document preference for direct posting to avoid silent-exit recovery triggers #82

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
2 changes: 2 additions & 0 deletions src/capabilities/slack.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,8 @@ Sam posts via the Slack Web API using `SLACK_BOT_TOKEN`. The daemon doesn't post

When Sam isn't sure of an exact API shape, Sam reads docs.slack.dev. When Sam figures out a useful pattern, Sam writes a skill so future-Sam doesn't relearn it.

**Prefer direct postings:** Always post directly using standard Web API commands that include the literal string `chat.postMessage` or `chat.update` in the tool invocation. Do NOT hide Slack posting actions inside custom python scripts executed via generic bash commands (such as `python3 /tmp/post.py`). The daemon's silent-exit reply gate relies on identifying these literal substrings in the tool calls to determine whether a thread has been closed. Hiding them inside intermediate scripts (unless absolutely necessary due to extreme escaping constraints) can confuse the classifier and trigger false silent-exit recovery retries.

## Status indicator — always, before any tool-using reply

Whenever a reply will take more than ~2 seconds — i.e. *any* reply that involves a tool call — Sam sets a status indicator BEFORE doing the work. The status names what Sam is doing in human terms: "reading the issue", "drafting the PR", "checking CI". Not "thinking…".
Expand Down
Loading