fix: clear stale session IDs before each llama poll
Some checks failed
ci/woodpecker/push/ci Pipeline failed
Some checks failed
ci/woodpecker/push/ci Pipeline failed
Local llama does not support claude --resume (no server-side session storage). Stale .sid files from failed runs cause agent_run to exit instantly on every retry, creating an infinite 1-second failure loop. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
parent
59b4cafcfc
commit
8122f2dd5d
1 changed files with 5 additions and 2 deletions
|
|
@ -30,9 +30,12 @@ fi
|
|||
|
||||
log "Entering poll loop (interval: ${POLL_INTERVAL:-300}s)"
|
||||
|
||||
# Run dev-poll in a loop as agent user
|
||||
# Export FORGE_TOKEN so the child process inherits the override
|
||||
while true; do
|
||||
# Clear stale session IDs before each poll.
|
||||
# Local llama does not support --resume (no server-side session storage).
|
||||
# Stale .sid files cause agent_run to exit instantly on every retry.
|
||||
rm -f /tmp/dev-session-*.sid 2>/dev/null || true
|
||||
|
||||
su -s /bin/bash agent -c "
|
||||
export FORGE_TOKEN='${FORGE_TOKEN}'
|
||||
cd /home/agent/disinto && \
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue