Gadfly: agentic adversarial PR reviewer (initial extraction)

Standalone, Docker-packaged extraction of the agentic PR reviewer that runs in
Gitea Actions: reads the checked-out repo with read-only tools (read_file/grep/
find_files/get_diff), verifies findings before reporting, two-pass review +
adversarial recheck, posts one labeled comment per model. Advisory only.

- cmd/gadfly: reviewer binary (majordomo + Ollama Cloud), zero deps beyond stdlib + majordomo
- entrypoint.sh: container brains — trigger gating, PR clone, model loop (logic out of YAML)
- Dockerfile: multi-stage; build-time module token never reaches the final image
- .gitea/workflows/build-image.yml: tag v* → build & push image
- examples/: ~15-line consumer stub
- system prompt genericized + hardened to re-derive constants/formulas (semantic bugs)

Vibe-coded with Claude Code; see README disclosure. Advisory, never blocks merge.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

README.md

@@ -0,0 +1,101 @@
+# 🪰 Gadfly
+
+**An AI gadfly for your pull requests.** Gadfly is an *adversarial* code reviewer that
+runs in Gitea Actions: on every PR it reads your actual repository, hunts for real
+problems, verifies them against the code, and posts its findings as a comment. It does not
+praise your code. A gadfly does not let things slide.
+
+> ### 🤖 Heads up: this is a vibe-coded project
+> Gadfly was built almost entirely by an AI agent (Claude Code), prompts and all — the
+> reviewer's "brain" is a language model, and so was most of the author. It works and it's
+> tested, but treat it accordingly: **it is advisory only, it never blocks a merge, and you
+> should still review its reviews.** Issues and PRs welcome; expect the occasional
+> AI-flavored rough edge.
+
+## What makes it different
+
+Most LLM "review my diff" bots read the diff in isolation and hallucinate problems they
+can't actually see — a "missing import" that's three lines above the hunk, a "broken
+caller" in a file they never opened. Gadfly is **agentic**: the model has read-only tools
+over the checked-out repo and is *required* to use them before reporting anything.
+
+- **Tools:** `read_file`, `list_dir`, `grep`, `find_files`, `get_diff`.
+- **Verify-before-claiming discipline:** baked into the system prompt — open the file,
+  grep the symbol, or drop the finding.
+- **Two passes:** a *review* pass drafts findings, then an adversarial *recheck* pass
+  independently re-verifies each one against the code and drops the ones it can't confirm,
+  recomputing the verdict. This is what kills "confident but wrong."
+- **Semantic-bug hunting:** it's told not to trust a plausible-looking constant, conversion
+  factor, or formula — re-derive the expected value, because that's where real bugs hide.
+
+Every review leads with a one-line verdict: **No material issues found**, **Minor issues**,
+or **Blocking issues found**.
+
+## Turn it on for a repo
+
+Gadfly ships as a container image, so consuming repos don't build anything — they just run
+it. Drop one file in your repo and set a couple of secrets/vars:
+
+1. Copy [`examples/adversarial-review.yml`](examples/adversarial-review.yml) to
+   `.gitea/workflows/adversarial-review.yml` in your repo.
+2. Add repo config:
+   - **secret** `OLLAMA_CLOUD_API_KEY` — your [Ollama Cloud](https://ollama.com) key (empty
+     ⇒ Gadfly posts a harmless "not configured" notice instead of reviewing).
+   - **var** `OLLAMA_REVIEW_MODELS` *(optional)* — comma-separated model ids
+     (default `qwen3-coder:480b-cloud,gpt-oss:120b-cloud`). One comment per model.
+   - **var** `GADFLY_ALLOWED_USERS` *(optional)* — who may re-trigger via comment; empty ⇒
+     any repo collaborator.
+
+`GITEA_TOKEN` is provided automatically by Actions; comments post as the `gitea-actions`
+user, scoped to that repo — no bot account needed.
+
+### Triggers
+
+1. A **new/reopened/ready** non-draft PR — automatic.
+2. Commenting **`@gadfly review`** on a PR — re-review on demand (gated to allowed users).
+3. **workflow_dispatch** — manual, with a `pr_number` input.
+
+(Pushing new commits does *not* auto-re-review — comment `@gadfly review` after pushing
+fixes. This keeps usage down.)
+
+## How it's packaged
+
+```
+cmd/gadfly/            the agentic reviewer binary (majordomo + Ollama Cloud); zero deps beyond stdlib + majordomo
+scripts/run.sh         fetches the PR diff, runs the reviewer, upserts one labeled comment
+scripts/system-prompt.txt  the reviewer persona + verification discipline
+entrypoint.sh          the container brains: trigger gating, clone, model loop (logic lives here, not in YAML)
+Dockerfile             multi-stage; the build-time module token never reaches the final image
+.gitea/workflows/build-image.yml   tags v* → build & push the image
+examples/              the ~15-line stub a consuming repo drops in
+```
+
+The image is published to `gitea.stevedudenhoeffer.com/steve/gadfly`. Push a `v*` tag to
+build and publish a new version (and `:latest`).
+
+## Configuration (advanced)
+
+The reviewer binary reads these (the stub/entrypoint set sane defaults):
+
+| Env | Default | Meaning |
+|-----|---------|---------|
+| `OLLAMA_API_KEY` | — | Ollama Cloud bearer key (required for real reviews) |
+| `GADFLY_MODEL` | — | model id |
+| `GADFLY_MAX_STEPS` | 24 | review-pass tool-step cap |
+| `GADFLY_RECHECK` | on | set `0`/`false` to skip the recheck pass |
+| `GADFLY_RECHECK_MAX_STEPS` | 16 | recheck-pass step cap |
+| `GADFLY_TIMEOUT_SECS` | 300 | overall deadline (both passes) |
+| `GADFLY_MAX_DIFF_CHARS` | 60000 | diff chars embedded in the prompt (full diff via `get_diff`) |
+| `GADFLY_TRIGGER_PHRASE` | `@gadfly review` | comment phrase that re-triggers |
+| `GADFLY_ALLOWED_USERS` | *(collaborators)* | comma-separated allow-list for comment triggers |
+
+## Building locally
+
+```sh
+go build ./cmd/gadfly      # needs read access to the private majordomo module
+go test ./...
+```
+
+## License
+
+MIT — see [LICENSE](LICENSE).