Compare commits

..
Author SHA1 Message Date
lead d1b98e7975 @lead: issue #33 2026-07-04 07:35:14 +00:00
10 changed files with 47 additions and 93 deletions
+1
Submodule .agents-workflow added at b3deee7412
+2 -5
View File
@@ -1,9 +1,6 @@
name: ai-agent
run-name: "ai-agent · #${{ github.event.issue.number }}" # quotes required: bare # starts a YAML comment
# Standard caller for the shared AI-agent workflow (ffaerber/agents). Copy this file VERBATIM into
# any repo that should get the agents — it is identical in every repo. All logic + scripts live in
# agents/.gitea/workflows/; scripts are fetched from @main at run time. The `jobs.agent` wrapper is
# required: a reusable (workflow_call) workflow can only be invoked from a caller job, not top-level.
# Thin caller so the agents work on THIS repo too (their own workflow). Same shared logic.
# New issues opened by ffaerber auto-start @pm; @mention an agent in a comment to route on replies.
on:
issue_comment:
types: [created]
-7
View File
@@ -1,7 +0,0 @@
{
"pm": {"model":"ollama-cloud/gemma4:cloud","vision":true, "mode":"comment","skills":["gitea-api"],"desc":"Product manager — research, plan, ask clarifying questions, and decide which dev should do the work. Comments only; never edits files."},
"junior": {"model":"ollama-cloud/kimi-k2.7-code:cloud","vision":false,"mode":"pr", "skills":[],"desc":"Junior dev — small, low-risk changes (mostly YAML/compose/config). Text-only, cannot read images. Defers complex or image tasks to @senior or @lead."},
"senior": {"model":"ollama-cloud/glm-5.2:cloud","vision":false,"mode":"pr", "skills":["gitea-api","node1-ssh"],"desc":"Senior dev — complex, multi-file implementation (GLM-5.2 via Ollama Cloud, text-only)."},
"lead": {"model":"anthropic/claude-opus-4-8","vision":true, "mode":"pr", "skills":["gitea-api","node1-ssh"],"desc":"Tech lead — the hardest problems, architecture, and final calls."},
"qa": {"model":"ollama-cloud/minimax-m3:cloud","vision":true, "mode":"comment","skills":["gitea-api"],"desc":"QA — verifies things work. Drives a headless browser (Playwright) to open a URL/web app, click through it, screenshot, and report bugs or confirm behavior. Comments findings; opens no PRs."}
}
+12 -10
View File
@@ -1,9 +1,7 @@
#!/usr/bin/env bash
# Build the activity log — the list of TOOL CALLS the agent made — into /tmp/activity_log.md.
# Only dev agents (mode=pr) get an activity-log comment — comment-only roles (pm/qa) do no tool calls.
# NOTE: we deliberately DO NOT include the agent's prose text parts. That final "here's what I did"
# text is just a restatement of the PR description (already published as the PR body), not a tool
# call — so it was noise in a section titled "tool calls". The log is the record of ACTIONS taken.
# Build activity log (tool calls + reasoning) from the event stream into /tmp/activity_log.md.
# Only dev agents (mode=pr) get an activity-log comment — comment-only roles (pm/qa)
# do no tool calls, so a trail would be empty/noise.
#
# Required env (provided by the workflow step): MODE
set -u
@@ -13,12 +11,16 @@ if [ "$MODE" != "pr" ]; then
fi
jq -r '
def trunc(n): if length > n then (.[0:n] + "…") else . end;
select(.type=="tool_use") |
(.part.tool // "?") as $t |
((.part.state.title // (.part.state.input | tojson | trunc(160)) // "")) as $title |
"🔧 **" + $t + "**: `" + ($title | trunc(240)) + "`"
select(.type=="tool_use" or .type=="text") |
if .type=="text" then
"💬 " + ((.part.text // "") | trunc(4000))
else
(.part.tool // "?") as $t |
((.part.state.title // (.part.state.input | tojson | trunc(160)) // "")) as $title |
"🔧 **" + $t + "**: `" + ($title | trunc(240)) + "`"
end
' /tmp/events.jsonl > /tmp/activity_log.md 2>/dev/null || true
n=$(wc -l < /tmp/activity_log.md 2>/dev/null || echo 0)
echo "activity log: $n tool calls"
echo "activity log: $n entries"
[ "$n" -eq 0 ] && : > /tmp/activity_log.md
head -3 /tmp/activity_log.md
+2 -8
View File
@@ -28,16 +28,10 @@ SKILLS="${SKILLS:-[]}"
PERM=$(jq -nc --argjson s "$SKILLS" '
{skill: ( {"*":"deny"} + (reduce $s[] as $k ({}; . + {($k):"allow"})) )}')
# Two ollama providers: local self-hosted (ornith) + Ollama Cloud (gemma4/kimi-k2.7-code/glm-5.2/minimax-m3).
# The ollama-cloud `models:` map is DERIVED from agents.json (the single source of truth, shared with
# route.sh) so every model an agent is routed to is always declared in the provider config. Only the
# `ollama-cloud/` provider prefix models participate — e.g. `anthropic/claude-opus-4-8` (@lead) is a
# built-in provider and `ornith:35b` is local-only, neither belongs here. See issue #31.
AGENTS_JSON="${SCRIPTS:-$(dirname -- "$0")}/agents.json"
CLOUD_MODELS=$(jq -r '[.[] | .model | select(startswith("ollama-cloud/")) | sub("^ollama-cloud/";"")] | map({(.):{}}) | add // {}' "$AGENTS_JSON")
jq -n --argjson mcp "$MCP" --argjson perm "$PERM" --argjson cloud "$CLOUD_MODELS" --arg url "$OLLAMA_URL" --arg ckey "$OLLAMA_CLOUD_API_KEY" '{
jq -n --argjson mcp "$MCP" --argjson perm "$PERM" --arg url "$OLLAMA_URL" --arg ckey "$OLLAMA_CLOUD_API_KEY" '{
provider: {
ollama: {npm:"@ai-sdk/openai-compatible", options:{baseURL:($url+"/v1")}, models:{"ornith:35b":{}}},
"ollama-cloud": {npm:"@ai-sdk/openai-compatible", options:{baseURL:"https://ollama.com/v1", apiKey:$ckey}, models:$cloud}
"ollama-cloud": {npm:"@ai-sdk/openai-compatible", options:{baseURL:"https://ollama.com/v1", apiKey:$ckey}, models:{"glm-5.2:cloud":{},"gemma4:cloud":{},"kimi-k2.7-code:cloud":{},"minimax-m3:cloud":{}}}
},
permission: $perm,
mcp: $mcp
+17 -33
View File
@@ -18,25 +18,14 @@ hdr=(-H "Authorization: token $TOK" -H "Content-Type: application/json")
post() { curl -sS -w 'comment -> HTTP %{http_code}\n' -X POST "${hdr[@]}" \
"$API/issues/$NUM/comments" -d "$(jq -nc --arg b "$1" '{body:$b}')"; }
# drop machine-readable markers: DELEGATE / CLOSE_ISSUE, and the BEGIN_SUBTASKS..END_SUBTASKS and
# BEGIN_PR_DESCRIPTION..END_PR_DESCRIPTION blocks (the PR description is published separately).
# drop machine-readable markers (DELEGATE / CLOSE_ISSUE / the BEGIN_SUBTASKS..END_SUBTASKS block)
reply=$(awk '
/^[[:space:]]*BEGIN_SUBTASKS/{s=1}
/^[[:space:]]*BEGIN_PR_DESCRIPTION/{p=1}
/^[[:space:]]*DELEGATE:[[:space:]]*@/{next}
/^[[:space:]]*CLOSE_ISSUE[[:space:]]*$/{next}
s{ if(/^[[:space:]]*END_SUBTASKS/){s=0}; next }
p{ if(/^[[:space:]]*END_PR_DESCRIPTION/){p=0}; next }
{print}
' /tmp/agent_out.md 2>/dev/null)
# Strip a leading self-header the model sometimes emits ("🤖 **@pm**" on its own line) so we don't
# double it when we prepend our own. Removes a leading run of such header lines and blank lines.
reply=$(printf '%s' "$reply" | awk '
BEGIN{s=1}
s && /^[^A-Za-z0-9]*\*\*@[A-Za-z]+\*\*[[:space:]]*$/ {next}
s && /^[[:space:]]*$/ {next}
{s=0; print}
')
[ -z "$reply" ] && reply="_(Made changes without a text summary — see the diff below.)_"
# Prefer the agent's clean delimited PR description; fall back to the whole reply.
prdesc=$(awk '/BEGIN_PR_DESCRIPTION/{f=1;next} /END_PR_DESCRIPTION/{f=0} f' /tmp/agent_out.md)
@@ -50,6 +39,7 @@ if [ "$MODE" != "pr" ]; then
# Visible comment: the reply text, or a sensible line if the agent only emitted a marker.
msg="$reply"
case "$msg" in ""|"_(Made changes"*) msg=$([ -n "$target" ] && echo "Handing off to @$target." || echo "_(no further comment)_") ;; esac
post "$(printf '🤖 **@%s**\n\n%s' "$NAME" "$msg")"
# Close the issue if the agent flagged it (maintainer said it's not needed / duplicate).
if grep -qiE '^[[:space:]]*CLOSE_ISSUE[[:space:]]*$' /tmp/agent_out.md; then
echo "closing issue #$NUM"
@@ -58,9 +48,6 @@ if [ "$MODE" != "pr" ]; then
fi
# BREAKDOWN: from a BEGIN_SUBTASKS block, create a milestone + one sub-issue per line
# (linked to this issue). Sub-issues are NOT auto-started — maintainer mentions agents later.
# Process subtasks first so we can append the created-issues list to the SAME comment as
# the reply (issue #38 — one comment per run).
subtext=""
if grep -qiE '^[[:space:]]*BEGIN_SUBTASKS' /tmp/agent_out.md; then
block=$(awk '/^[[:space:]]*BEGIN_SUBTASKS/{f=1;next} /^[[:space:]]*END_SUBTASKS/{f=0} f' /tmp/agent_out.md)
ms=$(printf '%s\n' "$block" | sed -nE 's/^[[:space:]]*milestone:[[:space:]]*//Ip' | head -1)
@@ -88,9 +75,8 @@ if [ "$MODE" != "pr" ]; then
echo "created sub-issue #${n:-?}: $title"
[ -n "$n" ] && links="$links\n- #$n$title"
done < /tmp/subtasks.txt
subtext=$(printf '\n\n---\n🤖 **@%s** — created sub-issues%s (mention an agent on each when ready):%b' "$NAME" "${ms:+ under milestone **$ms**}" "$links")
post "$(printf '🤖 **@%s** — created sub-issues%s (mention an agent on each when ready):%b' "$NAME" "${ms:+ under milestone **$ms**}" "$links")"
fi
post "$(printf '🤖 **@%s**\n\n%s%s' "$NAME" "$msg" "$subtext")"
# Auto-delegate: if the plan names a teammate, trigger them via AGENT_TOKEN (a PAT, so it
# fires a new workflow run — the built-in token cannot). Never targets @pm or self, so the
# chain always terminates at a dev. The '🤖' guard on the trigger stops status-comment loops.
@@ -137,16 +123,6 @@ git fetch -q origin 2>/dev/null || true
prbody=$(printf '%s\n\n---\nResolves #%s · 🤖 @%s' "$prdesc" "$NUM" "$NAME")
owner=${GITHUB_REPOSITORY%%/*}
# Post the agent's activity trail (tool calls + reasoning) inline in the same comment so
# each run produces exactly ONE comment (issue #38). Computed once here so every dev-agent
# exit path (no-changes, PR-open-failed, normal) appends it to the single reply comment.
activity=""
if [ -s /tmp/activity_log.md ]; then
entries=$(wc -l < /tmp/activity_log.md 2>/dev/null || echo 0)
log=$(cat /tmp/activity_log.md)
activity=$(printf '\n\n<details>\n<summary>🔧 activity — %s tool calls</summary>\n\n%s\n\n</details>' "$entries" "$log")
fi
# One PR per run: publish ONLY this run's own branch ($BRANCH), never sibling
# ai/issue-N-* branches. This removes the multi-PR ambiguity that left the
# activity log stranded on the triggering issue instead of the PR thread.
@@ -154,7 +130,7 @@ br="$BRANCH"
ahead=$(git rev-list --count "origin/main..origin/$br" 2>/dev/null || echo 0)
if [ "${ahead:-0}" -eq 0 ]; then
# No changes on this branch — a plan / questions / analysis only.
post "$(printf '🤖 **@%s**\n\n%s%s' "$NAME" "$reply" "$activity")"
post "$(printf '🤖 **@%s**\n\n%s' "$NAME" "$reply")"
exit 0
fi
@@ -172,7 +148,7 @@ if [ -z "$url" ]; then
url=$(printf '%s' "$resp" | jq -r '.html_url // empty' 2>/dev/null)
prnum=$(printf '%s' "$resp" | jq -r '.number // empty' 2>/dev/null)
fi
[ -z "$url" ] && { echo "PR open/lookup failed for $br — posting reply on issue instead"; post "$(printf '🤖 **@%s**\n\n%s%s' "$NAME" "$reply" "$activity")"; exit 0; }
[ -z "$url" ] && { echo "PR open/lookup failed for $br — posting reply on issue instead"; post "$(printf '🤖 **@%s**\n\n%s' "$NAME" "$reply")"; exit 0; }
# Posts to the PR thread when we have a PR number, else to the origin issue ($NUM).
prpost() {
@@ -184,9 +160,17 @@ prpost() {
}
if [ "$NEW" = "true" ]; then
prpost "$prnum" "$(printf '🤖 **@%s** — ✅ PR ready for review — @ffaerber please review & merge:\n- %s%s' "$NAME" "$url" "$activity")"
prpost "$prnum" "$(printf '🤖 **@%s** — ✅ PR ready for review — @ffaerber please review & merge:\n- %s' "$NAME" "$url")"
else
# Resume: just link the PR — its body and the diff already carry the description, so we don't
# repeat the full write-up in the comment (the reasoning trail below shows what this run did).
prpost "$prnum" "$(printf '🤖 **@%s** — pushed an update to the PR:\n- %s%s' "$NAME" "$url" "$activity")"
# Resume (comment is on a PR thread): include the write-up here too.
prpost "$prnum" "$(printf '🤖 **@%s** — updated branch/PR:\n- %s\n\n%s' "$NAME" "$url" "$prdesc")"
fi
# Post the agent's activity trail (tool calls + reasoning) as a separate comment so
# it is visible on the PR thread. Additive — kept here even when nothing changed, so a
# follow-up run (re-trigger) can see what this run did via the fetched issue thread.
if [ -s /tmp/activity_log.md ]; then
entries=$(wc -l < /tmp/activity_log.md 2>/dev/null || echo 0)
log=$(cat /tmp/activity_log.md)
prpost "$prnum" "$(printf '🤖 **@%s** — activity log (%s entries):\n<details>\n<summary>tool calls & reasoning</summary>\n\n%s\n\n</details>' "$NAME" "$entries" "$log")"
fi
+10 -13
View File
@@ -10,18 +10,21 @@
set -eu
# --- agent registry: model + capabilities + mode + role + skills ---
# The registry is the SINGLE SOURCE OF TRUTH, kept in agents.json next to this
# script. install-opencode.sh derives its ollama-cloud provider `models:` map
# from the same file, so an agent's model can never be missing from the provider
# config — drift is impossible by construction. See issue #31.
# `skills` is the allow-list of opencode Skills each agent may load. It scopes the
# `permission.skill` block written into opencode.json (see install-opencode.sh) so an agent only
# ever sees (and can load) the skills relevant to its role. Skills NOT listed here are hidden from
# that agent entirely — not even the one-line summary appears in its <available_skills>, so the
# full API/how-to detail never reaches an agent that shouldn't act on it. A teammate can still learn
# *that* another agent has a capability from the roster and ask them to use it.
AGENTS_JSON="${SCRIPTS:-$(dirname -- "$0")}/agents.json"
cp "$AGENTS_JSON" /tmp/agents.json
cat > /tmp/agents.json <<'JSON'
{
"pm": {"model":"ollama-cloud/gemma4:cloud","vision":true, "mode":"comment","skills":["gitea-api"],"desc":"Product manager — research, plan, ask clarifying questions, and decide which dev should do the work. Comments only; never edits files."},
"junior": {"model":"ollama-cloud/kimi-k2.7-code:cloud","vision":false,"mode":"pr", "skills":[],"desc":"Junior dev — small, low-risk changes (mostly YAML/compose/config). Text-only, cannot read images. Defers complex or image tasks to @senior or @lead."},
"senior": {"model":"ollama-cloud/glm-5.2:cloud","vision":false,"mode":"pr", "skills":["gitea-api","node1-ssh"],"desc":"Senior dev — complex, multi-file implementation (GLM-5.2 via Ollama Cloud, text-only)."},
"lead": {"model":"anthropic/claude-opus-4-8","vision":true, "mode":"pr", "skills":["gitea-api","node1-ssh"],"desc":"Tech lead — the hardest problems, architecture, and final calls."},
"qa": {"model":"ollama-cloud/minimax-m3:cloud","vision":true, "mode":"comment","skills":["gitea-api"],"desc":"QA — verifies things work. Drives a headless browser (Playwright) to open a URL/web app, click through it, screenshot, and report bugs or confirm behavior. Comments findings; opens no PRs."}
}
JSON
# On a new issue, @pm auto-assesses. On a comment, route by the @mention.
# A comment event has a comment id (CID); an issue-opened event does not. (event_name is unreliable
# here — see agent.yml: this reusable workflow sees it as 'workflow_call'.)
@@ -55,13 +58,7 @@ if [ -n "$IS_PR" ]; then # comment on a PR -> resume its bra
ref=$(curl -s -H "Authorization: token $GT" "$API/pulls/$NUM" | jq -r .head.ref)
git fetch origin "$ref" && git checkout "$ref"
{ echo "branch=$ref"; echo "new=false"; } >> "$GITHUB_OUTPUT"
elif git ls-remote --exit-code --heads origin "ai/issue-$NUM" >/dev/null 2>&1; then
# comment on an issue whose branch ALREADY exists (a prior run / open PR) -> RESUME it, so new
# commits fast-forward onto the same branch and update its PR. Branching fresh from main here would
# be rejected on push as non-fast-forward and the new work would be silently lost (see issue #17).
git fetch origin "ai/issue-$NUM" && git checkout "ai/issue-$NUM"
{ echo "branch=ai/issue-$NUM"; echo "new=false"; } >> "$GITHUB_OUTPUT"
else # comment on an issue, no branch yet -> new branch
else # comment on an issue -> new branch
git checkout -b "ai/issue-$NUM"
{ echo "branch=ai/issue-$NUM"; echo "new=true"; } >> "$GITHUB_OUTPUT"
# For dev agents, publish the branch immediately and tell the maintainer where to watch.
+1 -4
View File
@@ -10,10 +10,7 @@ set -u
[ -z "$CMT" ] && CMT="(a new issue was just opened — assess it)"
THREAD=$(cat /tmp/thread.md 2>/dev/null); [ -z "$THREAD" ] && THREAD="(no prior comments)"
DESC=$(jq -r --arg a "$NAME" '.[$a].desc' /tmp/agents.json)
# Include each teammate's skills so an agent (esp. @pm) can route by capability — e.g. only
# @senior/@lead hold node1-ssh, so a node1 task must not go to @junior. Skill *names* only; the
# scoped how-to detail stays hidden per the permission.skill allow-list.
ROSTER=$(jq -r 'to_entries | map("- @\(.key): \(.value.desc) (vision: \(.value.vision); skills: \(.value.skills | if length>0 then join(", ") else "none" end))") | join("\n")' /tmp/agents.json)
ROSTER=$(jq -r 'to_entries | map("- @\(.key): \(.value.desc) (vision: \(.value.vision))") | join("\n")' /tmp/agents.json)
if [ "$VISION" = "true" ]; then CAP="You CAN read images attached to the issue."; else CAP="You CANNOT read images — you are a text-only model."; fi
NOTE=""
if [ "$VISION" != "true" ] && [ "${HAS_IMAGES:-0}" -gt 0 ]; then
-1
View File
@@ -1,2 +1 @@
.env
.agents-workflow/
+2 -12
View File
@@ -29,18 +29,10 @@ detail out of agents that shouldn't act on it while still letting them know the
## Use it in a repo
**The standard caller is one file, identical in every repo.** Copy this repo's own
[`.gitea/workflows/ai-agent.yml`](.gitea/workflows/ai-agent.yml) verbatim into the consuming repo —
it is the source of truth, and `agents` itself uses the same file:
Add `.gitea/workflows/ai-agent.yml` to the consuming repo:
```yaml
name: ai-agent
run-name: "ai-agent · #${{ github.event.issue.number }}" # quotes required: bare # starts a YAML comment
# Standard caller for the shared AI-agent workflow (ffaerber/agents). Copy this file VERBATIM into
# any repo that should get the agents — it is identical in every repo. All logic + scripts live in
# agents/.gitea/workflows/; scripts are fetched from @main at run time. The `jobs.agent` wrapper is
# required: a reusable (workflow_call) workflow can only be invoked from a caller job, not top-level.
# `run-name` titles each run by the triggering issue (e.g. "ai-agent · #42") in the Actions list.
on:
issue_comment:
types: [created]
@@ -52,9 +44,7 @@ jobs:
secrets: inherit
```
That's the whole per-repo footprint, and it's the minimum a caller can be: the `on:` triggers must
live in each repo (a reusable workflow can't declare its callers' triggers) and the `jobs.agent`
wrapper is mandatory for `workflow_call`. Everything else (agent registry, routing, delegation,
That's the whole per-repo footprint. All the logic (agent registry, routing, delegation,
reactions, PR/issue plumbing) lives here in `agent.yml`.
## Repo layout