Forgejo 11.x rejects API tokens for git HTTP push while accepting them
for all other operations. Store bot passwords alongside tokens during
init and use password auth for git operations consistently.
- forge-setup.sh: persist bot passwords to .env (FORGE_PASS, etc.)
- forge-push.sh: use FORGE_PASS instead of FORGE_TOKEN for git remote URL
- entrypoint.sh: configure git credential helper with password auth
- entrypoint-llama.sh: use FORGE_PASS for git clone (fallback to FORGE_TOKEN)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Remove install_project_crons() function and cron daemon startup from
entrypoint-llama.sh. The llama container runs dev-poll via its while
loop only — cron is not suitable as it doesn't inherit Docker compose
env vars (ANTHROPIC_API_KEY, ANTHROPIC_BASE_URL, CLAUDE_CONFIG_DIR).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
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>
FORGE_TOKEN_OVERRIDE in compose env sets a per-agent token.
PRs, issue claims, and comments from the llama agent now show
dev-qwen instead of dev-bot.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Simple while-true loop that runs dev-poll with llama backend env vars.
No cron, no guard files, no activation state — just polls and spawns.
Repo auto-cloned on first start.
To be used with a separate agents-llama compose service that sets
ANTHROPIC_BASE_URL to the llama-server address.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
