Commit Graph
13 Commits
Author SHA1 Message Date
lead df0f6d6543 @lead: issue #16 — fully-automatic autopilot (label-gated @pm auto-delegate + @qa merge) 2026-07-04 19:23:20 +00:00
Felix FaerberandClaude Opus 4.8 0a89309ff1 fix(activity-log): tool calls only — drop the agent's prose summary
The activity <details> was labelled 'tool calls & reasoning' but included the agent's final prose
summary ('Added the whoami service... Exposed via Traefik... Pushed to branch...'), which is just a
restatement of the PR description and not a tool call. Emit only tool_use events; relabel to
'N tool calls'. The what-changed narrative lives in the PR description; this section is the record of
actions taken.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-04 14:40:59 +03:00
Felix FaerberandClaude Opus 4.8 81882ee3ec fix(publish): de-dup agent comments (no repeated PR desc, no doubled header)
Batches the remaining comment-noise cleanups on top of the activity-log fix:
- Resume comment no longer re-posts the full PR description (## Summary/## Changes) — the PR body and
  diff already carry it; the comment just links the PR (the reasoning trail shows what the run did).
- Strip a leading self-header the model sometimes emits ("🤖 **@pm**" on its own line, sometimes
  twice) before we prepend our own, so headers aren't doubled.
- Also drop the BEGIN_PR_DESCRIPTION block from the plain reply text, and simplify the activity
  block's summary (it repeated "🤖 **@name** — activity log").

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-04 14:24:37 +03:00
Felix FaerberandClaude Opus 4.8 1987ba792d fix(activity-log): strip the PR-description block from the reasoning trail
The 'tool calls & reasoning' activity log dumped each text part verbatim, including the agent's
BEGIN_PR_DESCRIPTION..END_PR_DESCRIPTION block — which is already published as the PR description, so
it appeared twice (e.g. homelab PR #117). Strip that block from text parts, and drop a text entry
that becomes empty after stripping.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-04 14:12:32 +03:00
Felix FaerberandClaude Opus 4.8 d803ee7cf5 fix(route): resume an existing ai/issue-N branch instead of losing re-triggered work
When an agent was re-triggered on an issue that already had a branch/open PR, route.sh created a
fresh branch from main (git checkout -b), so the push back was rejected non-fast-forward and the new
commits were silently dropped (|| true) -- the run reported success and re-announced the stale PR,
but the work was gone (observed on issue #17 run #88). Resume the existing branch when it exists, so
new commits fast-forward onto it and update its PR; only branch from main when none exists.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-04 13:21:04 +03:00
ffaerber 649cd4ea9b Merge pull request 'fix(routing): expose agent skills in the roster' (#40) from fix/roster-skills into main 2026-07-04 11:00:39 +02:00
Felix FaerberandClaude Opus 4.8 509b10ac57 fix(routing): expose agent skills in the roster so pm routes by capability
The homelab health-check test mis-routed a node1 inspection to @junior (skills: []), which cannot
reach node1 — only @senior/@lead hold node1-ssh. Root cause: the roster shown to agents listed
desc + vision but not skills, so @pm had no way to route by capability (despite a comment claiming
it could). Add each teammate's skill names to the roster line. Names only; the scoped how-to detail
stays hidden via permission.skill.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-04 11:56:27 +03:00
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
ffaerber 13148ea68c Merge pull request 'Single source of truth for agent model IDs (fixes #31)' (#32) from ai/issue-31 into main 2026-07-04 09:43:28 +02:00
lead 423a060816 fix(agent): run step scripts from outside the workspace so agents can't break the run
Stage the shared scripts into $RUNNER_TEMP and point $SCRIPTS there for every
step, so an agent that commits/deletes the in-tree .agents-workflow checkout no
longer destroys the scripts the post-agent steps run (issue #33). Scrub any
in-tree .agents-workflow artifact before publishing, and add a failure-safe
rescue step that opens a PR for pushed work when a run fails.
2026-07-04 07:34:53 +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
Felix FaerberandClaude Opus 4.8 b3deee7412 fix(agent): route issue-opened events (event_name is workflow_call in reusable wf)
The shared agent.yml is a reusable (workflow_call) workflow, so on Gitea
github.event_name evaluates to 'workflow_call' — not the original 'issues'/
'issue_comment'. route.sh branched on EVENT == "issues", so issue-opened runs
scanned the empty comment body and skipped the @pm fallback, exiting 1 with
"no known agent mentioned" (runs #393/#394). Comment runs were unaffected
because the @mention lives in $BODY.

Discriminate on the comment id (CID) instead, which IS reliably forwarded in
the event payload: empty => issue-opened (scan issue body, default @pm), set
=> comment (scan comment body). Also add .gitignore for .env.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-04 10:02:50 +03:00
lead 36ba91cdd8 @lead: externalize agent.yml inline scripts into .gitea/workflows/scripts/*.sh
Rebased onto the per-agent skill-scoping change so PR #25 carries both:
- route.sh keeps the registry 'skills' allow-list and emits skills as a step output
- install-opencode.sh writes the permission.skill block (deny-all + allow listed)

Pure refactor otherwise: each step's shell moves to its own file, called via
bash "$SCRIPTS/<name>.sh". The two extracted SKILL.md bodies are byte-identical to
main; routing/config/publish behavior is unchanged. Because this is a reusable
workflow (workflow_call) the runtime checkout is the caller's repo, so agent.yml now
checks THIS repo out into .agents-workflow/ (pinned @main) and points $SCRIPTS there.
2026-07-04 05:54:27 +00:00