Commit Graph
14 Commits
Author SHA1 Message Date
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
Felix FaerberandClaude Opus 4.8 1fd32f0ff6 fix: quote run-name so the issue number is not eaten as a YAML comment
Bare '#' starts a YAML comment, so run-name resolved to 'ai-agent ·' with the number dropped.
Quote the value.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-04 12:33:27 +03:00
Felix FaerberandClaude Opus 4.8 729a14f8bd chore: title agent runs by issue number (run-name)
Without run-name, Gitea titles each ai-agent run by main's head commit, so runs aren't identifiable
in the Actions list. Add `run-name: ai-agent · #${{ github.event.issue.number }}` to the standard
caller (both the file and the README stub) so each run shows its issue.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-04 12:29:09 +03:00
Felix FaerberandClaude Opus 4.8 658c10fc35 chore: standardize the ai-agent caller stub (identical in every repo)
The caller workflow had drifted between repos (run-name, stale SHA comment, trigger ordering,
different comment text) though all were functionally the same `uses: agent.yml@main`. Define one
canonical stub: make this repo's own ai-agent.yml the reference and update the README "Use it in a
repo" block to match it verbatim, noting that the on: triggers and the jobs.agent wrapper are the
irreducible minimum for a reusable (workflow_call) workflow.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-04 12:17:13 +03:00
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
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
Felix FaerberandClaude Opus 4.8 d0ddb06ccb DEBUG: post captured --format json schema as an issue comment (findable + fetchable)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-02 15:21:48 +03:00
Felix FaerberandClaude Opus 4.8 da6f0d5b92 TEMP: debug step to capture opencode --format json event schema
Runs a tiny Sonnet probe and dumps the raw events to the Actions log so we can build the
PR-progress parser against the real schema. Removed once captured.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-02 15:14:37 +03:00
Felix FaerberandClaude Opus 4.8 6b5c1bb888 Dogfood: add thin caller + AGENTS.md so agents work on the agents repo itself
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-02 10:47:15 +03:00
Felix FaerberandClaude Opus 4.8 c594080ffc Add PM breakdown skill: feature -> milestone + sub-issues (plan/approve/create gate)
@pm proposes a milestone + sub-tasks and asks for approval; on 'yes' it emits a BEGIN_SUBTASKS
block, and the workflow creates the milestone + one sub-issue per line (each 'Part of #<feature>').
Sub-issues are not auto-started — maintainer @mentions an agent on each when ready.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-02 10:32:57 +03:00
Felix FaerberandClaude Opus 4.8 f6df3f24af Add reusable AI-agent workflow + docs + AGENTS template
Reusable workflow (on: workflow_call) moved from homelab; consuming repos add a thin caller
(uses: ffaerber/agents/.gitea/workflows/agent.yml@main, secrets: inherit).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-02 07:20:54 +03:00