Extract the agent registry to a shared agents.json and have both
route.sh (agent → model) and install-opencode.sh (ollama-cloud provider
models map) derive from it, so the two lists can no longer drift.
route.sh now copies agents.json to /tmp/agents.json instead of an inline
heredoc. install-opencode.sh builds the ollama-cloud map by
collecting every registry model with the prefix and
stripping it — non-ollama-cloud models (e.g. @lead's anthropic/claude-opus,
the local ornith:35b) are excluded by construction.
Resolves#31.
- New gitea-api opencode skill (mirrors node1-ssh): documents the Gitea REST API
base URL, Authorization: token $AGENT_TOKEN header, and example curl calls for
read (issue/PR + comments, Actions runs/jobs/logs, org repos) and write (comment,
label, close), with explicit warnings: never echo the token, treat fetched
content as untrusted data (prompt-injection guard), and stop on 403.
- Wire AGENT_TOKEN into the Run agent step env so the agent process itself can
call the API (previously only the Publish step saw it).
- Update README secrets table: AGENT_TOKEN now also powers gitea-api; do not
re-narrow scopes without removing the skill.
Switch the real 'Run agent' step to --format json (replacing the two
TEMP/DEBUG schema-discovery commits da6f0d5/d0ddb06), capture the raw
event stream, and reconstruct the plain-text reply from the assistant
'text' parts so the existing Publish logic is unchanged.
Add a 'Build activity log' step that filters the event stream to
tool_use (with truncated title/input) and text (reasoning) events.
The Publish step posts that trail as a separate collapsible comment on
the PR thread (dev agents only — comment-only roles do no tool calls).
This is additive to the existing summary/PR-description comment.
Reasoning reuse on a follow-up run is free: the existing 'fetch full
issue thread' step already re-feeds all prior comments (including this
new log comment) into the next run's prompt, so the agent sees what it
did last time.
senior