# agents

Shared **AI dev-team** workflow for Gitea Actions, reusable across repos. It gives any repo the
`@pm` / `@junior` / `@senior` / `@lead` / `@qa` agents driven from issues and comments.

## 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.yml`'s agent registry is the source of truth for this mapping — if you change a model
there, update this table too.

## Use it in a repo

Add `.gitea/workflows/ai-agent.yml` to the consuming repo:

```yaml
name: ai-agent
on:
  issue_comment:
    types: [created]
  issues:
    types: [opened]
jobs:
  agent:
    uses: ffaerber/agents/.gitea/workflows/agent.yml@main
    secrets: inherit
```

That's the whole per-repo footprint. All the logic (agent registry, routing, delegation,
reactions, PR/issue plumbing) lives here in `agent.yml`.

## Required secrets (per repo, or org-level for all)

| Secret | For |
|--------|-----|
| `ANTHROPIC_API_KEY` | `@lead` (and `@pm`/`@senior`/`@qa` if on Claude) |
| `OLLAMA_URL`, `OLLAMA_CLOUD_API_KEY` | local ornith / Ollama Cloud (gemma4, kimi-k2.7-code, glm-5.2, minimax-m3) |
| `AGENT_TOKEN` | PAT (issue+repo write) used to post the delegation comment that fires the next agent |
| `TOKEN_PM`,`TOKEN_SENIOR`,`TOKEN_JUNIOR`,`TOKEN_LEAD`,`TOKEN_QA` | optional — post/commit as each agent's own Gitea user (falls back to the bot) |

`GITEA_TOKEN` is auto-provided. Tip: set these once at the **org** level so every repo inherits
them via `secrets: inherit`.

## Also add to each consuming repo

- **`AGENTS.md`** — the repo's own conventions (copy `AGENTS.template.md` from here and adapt). The
  agent reads the *caller* repo's `AGENTS.md`, so each repo can differ.
- The bot users (`pm`,`senior`,…) as **collaborators** (needed on private repos, and enables
  `@name` autocomplete).

## Maintaining

Change agent behavior once, here. Callers pin `@main` (or pin a tag for stability). History is the
changelog — see `git log`.