public/galaxy
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

Keep long-running monitors polling after prose turns

Browse Source
This commit is contained in:
rkw6086
2026-08-06 23:50:51 -05:00
parent 17898e7d9b
commit 603437a24e
9 changed files with 143 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/src/ai/bedrock/request_translator.rs
+13 -8
View File
@@ -1496,10 +1496,13 @@ pub fn extract_system_prompt(
"This turn concerns a running or just-finished shell command. Act as its dedicated \
monitor while still following the user's steering messages. Use the command ID from \
the running-command context or tool result for every read/write operation. If the \
result says the command finished, report its outcome and stop polling. Otherwise, \
poll with `read_shell_command_output` and use short delays. Never choose a poll \
interval that crosses a user-specified deadline or stop condition. When an explicit \
stop condition is met, call `interrupt_shell_command` immediately, then poll briefly \
result says the command finished, report its outcome and stop polling. If it says the \
command is still running, the next assistant output MUST be a tool call: use \
`read_shell_command_output` with a short delay, or call `interrupt_shell_command` \
immediately when the user's explicit stop condition is met. Do not end a still-running \
monitor turn with prose, a status message, or a request for the user to say continue. \
Never choose a poll interval that crosses a user-specified deadline or stop condition. \
After an interrupt, poll briefly \
to verify the outcome. Never try to encode Ctrl+C as `C-c`, `^C`, `\\x03`, or \
`\\u0003` through `write_to_long_running_shell_command`; that tool is only for actual \
process input. Never start a duplicate command merely to check its state, and never \
@@ -2393,10 +2396,12 @@ fn long_running_command_content(snapshot: &api::LongRunningShellCommandSnapshot)
};
format!(
"Command is still running.\nCommand ID: {}\nCurrent terminal output:\n{}\n\
Continue monitoring with `read_shell_command_output` using command_id `{}`. \
Use `write_to_long_running_shell_command` with the same command_id only if input is \
required. If the user's explicit stop condition is met, use `interrupt_shell_command` \
with the same command_id. Do not report the command as complete while it is still running.",
The next assistant output MUST be a tool call: continue monitoring with \
`read_shell_command_output` using command_id `{}` and a short wait. Use \
`write_to_long_running_shell_command` with the same command_id only if input is required. \
If the user's explicit stop condition is met, use `interrupt_shell_command` immediately \
with the same command_id. Do not end this turn with prose or report the command as complete \
while it is still running.",
snapshot.command_id, output, snapshot.command_id
)
}