gitea/agents
8
0
Fork 0
Code Issues 2 Pull Requests 1 Actions Packages Projects Releases Wiki Activity

@lead: issue #22 — per-agent skill scoping via permission.skill

Browse Source
This commit is contained in:
lead
2026-07-04 05:25:06 +00:00
parent e8e299872a
commit a79b49b55e
2 changed files with 48 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.gitea/workflows/agent.yml
+29 -9
View File
@@ -52,14 +52,20 @@ jobs:
TOKEN_LEAD: ${{ secrets.TOKEN_LEAD }}
TOKEN_QA: ${{ secrets.TOKEN_QA }}
run: |
# --- agent registry: model + capabilities + mode + role ---
# --- agent registry: model + capabilities + mode + role + skills ---
# `skills` is the allow-list of opencode Skills each agent may load. It scopes the
# `permission.skill` block written into opencode.json below 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.
cat > /tmp/agents.json <<'JSON'
{
"pm": {"model":"ollama-cloud/gemma4:cloud","vision":true, "mode":"comment","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", "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", "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", "desc":"Tech lead — the hardest problems, architecture, and final calls."},
"qa": {"model":"ollama-cloud/minimax-m3:cloud","vision":true, "mode":"comment","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."}
"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.
@@ -74,8 +80,10 @@ jobs:
model=$(jq -r --arg a "$name" '.[$a].model' /tmp/agents.json)
vision=$(jq -r --arg a "$name" '.[$a].vision' /tmp/agents.json)
mode=$(jq -r --arg a "$name" '.[$a].mode' /tmp/agents.json)
echo "Routing to @$name (model=$model vision=$vision mode=$mode)"
{ echo "name=$name"; echo "model=$model"; echo "vision=$vision"; echo "mode=$mode"; } >> "$GITHUB_OUTPUT"
# Compact JSON array of the skills this agent may load (scopes permission.skill below).
skills=$(jq -c --arg a "$name" '.[$a].skills // []' /tmp/agents.json)
echo "Routing to @$name (model=$model vision=$vision mode=$mode skills=$skills)"
{ echo "name=$name"; echo "model=$model"; echo "vision=$vision"; echo "mode=$mode"; echo "skills=$skills"; } >> "$GITHUB_OUTPUT"
# Act as the agent's own Gitea user when its token is set; else the built-in bot.
case "$name" in
@@ -108,6 +116,7 @@ jobs:
OLLAMA_URL: ${{ secrets.OLLAMA_URL }}
OLLAMA_CLOUD_API_KEY: ${{ secrets.OLLAMA_CLOUD_API_KEY }}
NAME: ${{ steps.prep.outputs.name }}
SKILLS: ${{ steps.prep.outputs.skills }} # JSON array of skills this agent may load
run: |
curl -fsSL https://opencode.ai/install | bash
echo "$HOME/.opencode/bin" >> "$GITHUB_PATH"
@@ -121,12 +130,23 @@ jobs:
npx -y playwright install --with-deps chromium || npx -y playwright install chromium || true
;;
esac
# Per-agent skill scoping. Skills are loaded on-demand by opencode: only a skill's one-line
# `description` ever appears in an agent's <available_skills> list, and the full SKILL.md
# body (curl/API how-to) is loaded ONLY when the agent calls the `skill` tool — it is never
# in any system prompt. To also hide the summary from agents that shouldn't use a skill, we
# deny all skills by default and allow only the ones in this agent's registry list. A denied
# skill is hidden entirely (name + description omitted), so e.g. @junior never sees gitea-api
# at all; it just knows from the roster that @senior/@lead can, and asks them.
SKILLS="${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).
jq -n --argjson mcp "$MCP" --arg url "$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:{"glm-5.2:cloud":{},"gemma4:cloud":{},"kimi-k2.7-code:cloud":{},"minimax-m3:cloud":{}}}
},
permission: $perm,
mcp: $mcp
}' > ~/.config/opencode/opencode.json
echo "opencode config (secrets masked):"; cat ~/.config/opencode/opencode.json
README.md
+19 -8
View File
@@ -5,16 +5,27 @@ Shared **AI dev-team** workflow for Gitea Actions, reusable across repos. It giv
## Agents
| Agent | Model | Vision | Mode | Role |
|-------|-------|:------:|------|------|
| `@pm` | `ollama-cloud/gemma4:cloud` | yes | comment | Product manager — research, plan, ask clarifying questions, and decide which dev should do the work. Comments only; never edits files. |
| `@junior` | `ollama-cloud/kimi-k2.7-code:cloud` | no | pr | 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` | `ollama-cloud/glm-5.2:cloud` | no | pr | Senior dev — complex, multi-file implementation (GLM-5.2 via Ollama Cloud, text-only). |
| `@lead` | `anthropic/claude-opus-4-8` | yes | pr | Tech lead — the hardest problems, architecture, and final calls. |
| `@qa` | `ollama-cloud/minimax-m3:cloud` | yes | comment | 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. |
| Agent | Model | Vision | Mode | Skills | Role |
|-------|-------|:------:|------|--------|------|
| `@pm` | `ollama-cloud/gemma4:cloud` | yes | comment | `gitea-api` | Product manager — research, plan, ask clarifying questions, and decide which dev should do the work. Comments only; never edits files. |
| `@junior` | `ollama-cloud/kimi-k2.7-code:cloud` | no | pr | — | 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` | `ollama-cloud/glm-5.2:cloud` | no | pr | `gitea-api`, `node1-ssh` | Senior dev — complex, multi-file implementation (GLM-5.2 via Ollama Cloud, text-only). |
| `@lead` | `anthropic/claude-opus-4-8` | yes | pr | `gitea-api`, `node1-ssh` | Tech lead — the hardest problems, architecture, and final calls. |
| `@qa` | `ollama-cloud/minimax-m3:cloud` | yes | comment | `gitea-api` | 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. |
`agent.yml`'s agent registry is the source of truth for this mapping — if you change a model
there, update this table too.
or an agent's skills there, update this table too.
### Per-agent skill scoping
Skills load **on-demand**: only a skill's one-line `description` ever appears in an agent's
`<available_skills>` list, and the full `SKILL.md` body (curl/API how-to) is fetched *only* when
the agent calls the `skill` tool — it is never baked into any system prompt. On top of that, each
agent's `skills` list in the registry drives an OpenCode `permission.skill` block that **denies all
skills by default and allows only the listed ones**. A denied skill is hidden entirely (its name and
description are omitted), so e.g. `@junior` never sees `gitea-api` — it just knows from the roster
that `@senior`/`@lead` can reach the Gitea API and asks them to. This keeps the "how it's done"
detail out of agents that shouldn't act on it while still letting them know the capability exists.
## Use it in a repo