agents

8 Commits

Author	SHA1	Message	Date
senior	59a60740fa	retro #83 : LEARNINGS.md — agent-add checklist, prompt-heredoc discipline, one-round bounce ci / lint (pull_request) Successful in 11s Details Distilled from issue #83 / PR #84 (adding @intern): - missed agent.yml trigger gate (broke all @intern comments until round 3) - 2 of 8 touched files missed on first pass - stray leading-space edits to run-agent.sh prompt heredoc bounced 2 rounds - @qa quoted the fix-attempt trigger string, inflating bounce counter 1/3 -> 3/3 - @qa split whitespace + gate findings across rounds, hitting the 3-round cap	2026-07-06 08:09:26 +00:00
senior	767a3341fd	feat(publish): one comment per agent run (issue #38 ) Merge the activity-log comment into the main reply comment and merge the sub-issues-created comment into the pm reply, so each agent run posts exactly one comment (reply + tool calls & reasoning inline).	2026-07-04 08:42:56 +00:00
senior	cafd36eae1	fix(agent): single source of truth for model IDs (route.sh + install-opencode.sh) 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.	2026-07-04 07:20:25 +00:00
senior	fdf966c765	@senior: issue #14 — add gitea-api skill + expose AGENT_TOKEN to the agent process - 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.	2026-07-03 11:07:38 +00:00
senior	173ee612bd	@senior: issue #10 — wire up read-only ssh node1 alias in agent workflow	2026-07-03 09:13:42 +00:00
senior	402ccd7a6b	@senior: issue #8 — list agents + models in README, update routing & allow-list	2026-07-02 15:38:52 +00:00
senior	92ad8ef436	@senior: issue #4 — one PR per run, post activity log to the PR thread	2026-07-02 13:51:21 +00:00
senior	15285d228f	Post opencode activity log (tool calls + reasoning) as a PR comment (#2 ) 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.	2026-07-02 13:17:14 +00:00