# doubleo7

A local-first, multi-agent deep-research CLI: give it a topic, it searches
the web, cross-checks what it finds, and writes up a cited report — entirely
on infrastructure you control, with no cloud LLM API key and no query ever
leaving your machine.

```
$ doubleo7 "trends in AI customer-support chatbots"
🔎 Researching...
🧐 Reviewing findings...
✍️  Writing report...

# AI Customer-Support Chatbots: 2025–2026 Trends
...
```

## Why this exists

This started as a "does deep research actually work end-to-end" exercise and
turned into a small case study in building an *agentic* system that survives
contact with reality: models that hit their turn budget mid-task, search
providers that rate-limit, and reviewers that reject good-faith work. The
[case study](./docs/case-study.md) walks through what broke and how each
failure was fixed, not just papered over.

## Architecture

Four small agents, each with one job, coordinated by plain Rust control
flow — not a framework's agent graph, not an LLM deciding when to stop —
plus an optional retrieval step when `--doc` documents are supplied:

```
┌────────────┐   excerpts   ┌─────────────┐  approve/reject  ┌──────────┐
│  retriever │ ───────────► │  researcher │ ───────────────► │ reviewer │
│(--doc only)│              │ (tool-using)│ ◄─────────────── │          │
└────────────┘              └──────┬──────┘   gaps/feedback  └────┬─────┘
                                   │ turn budget exhausted        │ approved,
                                   │ mid-investigation            │ or out of rounds
                                   ▼                              ▼
                            ┌──────────────┐              ┌──────────────┐
                            │ summarizer   │──findings───►│    writer    │──► report
                            │ (recovery)   │              │              │
                            └──────────────┘              └──────────────┘
```

- **retriever** (only when `--doc` paths are given) — chunks and embeds
  user-supplied documents with a dedicated embedding model, then retrieves
  the excerpts most relevant to the topic once up front and folds them into
  the researcher's task, cited with the same footnote scheme as web sources.
- **researcher** — a tool-calling agent (`search_web`, `fetch_page`) that
  gathers and cross-checks evidence, capped at a fixed model-call budget so
  a confused model can't loop forever.
- **reviewer** — a separate, fresh-context agent that checks the researcher's
  conclusions actually follow from its cited sources, and either approves
  the findings or hands back concrete gaps for another pass.
- **writer** — turns approved (or partial) findings into a structured,
  footnoted report, streamed to the terminal as it's generated.
- **summarizer** (recovery path) — only runs when the researcher exhausts
  its turn budget before concluding on its own. It reconstructs a proper
  findings dump from the raw tool-call transcript rather than the run
  simply failing; see the case study for why this exists and how it
  degrades gracefully if the summarizer call itself fails.

Everything runs against local models via [Ollama](https://ollama.com) and a
self-hosted [SearXNG](https://searx.space) instance for search — no OpenAI/
Anthropic/Google API key, no third-party search API, nothing about the
research topic leaves the host it runs on. That's a deliberate constraint,
not a limitation: it's the same shape a privacy-sensitive customer
deployment would need.

## Running it

Prerequisites:
- [Ollama](https://ollama.com) running locally with a tool-calling-capable
  model pulled (the researcher and reviewer/writer models are configured in
  [`src/models.rs`](./src/models.rs))
- A local [SearXNG](https://docs.searxng.org/) instance with its JSON API
  enabled (defaults to `http://localhost:8080`, overridable via
  `SEARXNG_URL`)

```
cargo run -- "your research topic"

# or, with tracing spans on stderr instead of the progress spinner:
cargo run -- -l info "your research topic"

# give the researcher your own documents to draw on, alongside the web —
# repeatable, and a directory contributes every file directly inside it
# (one level deep, not recursive):
cargo run -- --doc ./notes.txt --doc ./research-docs/ "your research topic"
```

Uploaded documents are chunked (see `documents.rs`), embedded with a
dedicated embedding model (see `EMBEDDING_MODEL` in
[`src/models.rs`](./src/models.rs)) into an in-memory vector index, then the
excerpts most relevant to the topic are retrieved and folded into the
researcher's task alongside anything it finds on the web — the same
footnote-citation scheme applies to both.

Known limitation: retrieval returns a fixed top-N chunks
(`retrieval::TOP_N_EXCERPTS`). A document with several chunks that all read
as similar to the query — several incident reports, several revisions of
the same section — can crowd out the one chunk that actually answers it,
since only the top N by similarity are ever returned regardless of how many
plausible candidates exist. Reproduced deliberately (a 13.7 KB / 12-chunk
document with 6 near-identical "incident report" sections, only one of
which had the real answer, was built specifically to stress this — the top
5 slots filled entirely with distractors and the answer chunk was
excluded), so it's a real edge case, not a hypothetical. Not fixed for now
since it takes a document engineered to trigger it, but worth knowing if a
report seems to be missing something you know is in an uploaded document.

## Installing (Arch/Manjaro)

[`packaging/PKGBUILD`](./packaging/PKGBUILD) builds and installs `doubleo7`
as a proper pacman package (`doubleo7-git`), pulling source straight from
this repo's git history rather than a crates.io release:

```
cd packaging
makepkg -si
```

`-s` resolves `makedepends` (`cargo`, `git`) via pacman first, `-i`
installs the resulting package after building it. To pick up upstream
changes later, just rerun the same command from a checkout with the latest
commits — `pkgver()` derives its version from `git rev-list`/`git
rev-parse`, so `makepkg` detects the new commit, rebuilds, and `pacman -U`
replaces the old install in place. Uninstall with `sudo pacman -R
doubleo7-git`.

Note: Manjaro's default `CFLAGS`/`LDFLAGS` hardening flags corrupt the
vendored C build inside `aws-lc-sys` (a transitive TLS dependency), causing
a symbol-mismatch link error — `PKGBUILD`'s `build()` unsets them before
invoking `cargo build` to work around it.

## Project layout

Split one concern per file rather than one large module:

| File | Responsibility |
|---|---|
| `main.rs` | Argument parsing, logging setup, and the single top-level call — no orchestration logic |
| `research.rs` | The research/review round loop |
| `researcher.rs` | The tool-calling research phase |
| `review.rs` | The reviewer agent |
| `summarizer.rs` | Max-turns recovery: reconstructs findings via a model call |
| `writer.rs` | Turns findings into the final streamed report |
| `history.rs` | Pure, unit-tested helpers for parsing a rig chat history into usable text |
| `documents.rs` | Resolves `--doc` paths into embeddable documents |
| `retrieval.rs` | Embeds documents into an in-memory vector index and retrieves relevant excerpts |
| `tools.rs` | `search_web` (SearXNG) and `fetch_page` tool implementations |
| `stream.rs` | Drains a streaming prompt response to the terminal |
| `progress.rs` | The terminal spinner and per-phase emoji |
| `models.rs`, `cli.rs`, `observability.rs` | Small shared config: model names, CLI args, tracing setup |

## Testing

```
cargo test               # unit tests — pure functions, no network
cargo test -- --ignored  # + a live smoke test against SearXNG
cargo clippy --all-targets
```

CI (`.forgejo/workflows/ci.yml`) runs formatting, lint, build, and the unit
test suite on every push and PR.