brain-of-reese/README.md

# 🧠 Brain of Reese

A chippy, honest **RAG chatbot** over the `~/Homelab` and `~/Deployments`
projects. Point it at your notes — markdown, YAML, JSON, Python, plain
text — ask it anything, and it retrieves the relevant chunks with
**hybrid search** (pgvector cosine ∪ Postgres full-text search, fused with
Reciprocal Rank Fusion), feeds the **whole relevant document** to a
**self-hosted LLM** (`turbo` via `https://aipi.reeseapps.com/v1`), and
streams a grounded answer back.

If it doesn't have notes for your question, it admits it:
*"I haven't done anything like that"* — plus suggestions for what it **does** know.

> **Updated your notes?** The knowledge base is refreshed by re-running the
> import — it's idempotent and only re-embeds what changed:
> ```bash
> uv run python -m scripts.import_docs --prune
> ```
> Details in [Updating the documents](#updating-the-documents).

- **Stack:** FastAPI · Pydantic v2 · SQLAlchemy 2 · Alembic · pgvector ·
  vanilla HTML/CSS/JS (no CDN) · Playwright E2E
- **Planning:** architecture, LOCKED decisions and the phase roadmap live
  in [`.agent/PLAN.md`](.agent/PLAN.md); per-story specs in
  [`.agent/user_stories/`](.agent/user_stories/).

---

## Development Setup

### Prerequisites
- [uv](https://docs.astral.sh/uv/)
- [Podman](https://podman.io/) (with the `podman compose` provider)
- Node.js is **not** needed locally (asset minification happens in the
  container build only)

### 1. Install dependencies
```bash
uv sync
```

### 2. Configure
```bash
cp .env.example .env
# edit .env — the defaults already match the local compose setup.
# BOR_LLM_API_KEY: your aipi key (falls back to $AIPI_KEY if unset)
```

### 3. Start the database (Postgres 17 + pgvector)
```bash
podman compose up -d db
podman compose ps          # wait until "healthy"
```

### 4. Apply migrations
```bash
uv run alembic upgrade head
```

### 5. Import your knowledge base
```bash
uv run python -m scripts.llm_probe      # sanity: models + 768-dim check
uv run python -m scripts.import_docs    # import the configured sources (below)
```

Two managed source kinds (one page, one registry) plus a manual override:

- **Git sources** — managed on the **admin Git sources page**
  (`/git-sources.html`) and stored in Postgres (see
  [Git-based sources](#git-based-sources)). `import_docs` clones each repo
  (first run) or pulls it (subsequent runs) into
  `BOR_SOURCES_DIR/<repo-name>/` (default `~/bor-sources`) and indexes the
  checkouts. While the stored list is empty, the `BOR_GIT_SOURCES` variable
  in `.env` is the fallback — the moment the page stores a source, the
  variable is ignored.
- **Local directory sources** (phase 38) — an existing, non-git directory
  on the server, registered on the *same* admin page (see
  [Local directory sources](#local-directory-sources)). No clone, no
  checkout copy: the directory is walked in place. There is **no env var
  for local paths** — the DB is the registry.
- **Manual directories** — `--source <path>` (repeatable) imports local
  directories directly and *always wins* over the stored sources (git and
  local) and the env fallback.
- If neither is set (stored list, `--source`, and `BOR_GIT_SOURCES` all
  empty), `import_docs` falls back to the **previous** default,
  `~/Homelab` + `~/Deployments` — kept only for backwards compatibility,
  now replaced by the managed sources; the UI Sync button instead fails
  loudly ("no sources configured (git or local)").

### 6. Run the app
```bash
uv run uvicorn app.main:app --reload
# → http://localhost:8000  (chat)   http://localhost:8000/sources.html (KB)
```

> 📝 **After this, day-to-day is just: edit markdown → re-run the import.**
> See [Updating the documents](#updating-the-documents) below.

## Using the UI

- **Chat** (`/`) — ask questions; answers stream in with **source chips**
  that cite the exact documents used. Clicking a chip opens that document
  in an **almost-fullscreen modal** on the same page (no new tab).
- **Document viewer** — the modal above *is* the viewer; the full text of
  any indexed document is served from the database (no filesystem access):
  markdown is rendered, every other format (`yaml`, `json`, `py`, `txt`, …)
  is shown as escaped monospace text. `/document.html?source=…&path=…`
  stays as the **full-page / direct-link** form (the modal's “Full page”
  button and the URL to share — it works without JS). Unknown documents
  get a designed not-found state with a link back to the index.
- **Sources** (`/sources.html`) — the indexed document list; the *Path*
  column opens each document in the same **almost-fullscreen modal** (no
  new tab). **Admin-only** — anonymous visitors see a sign-in gate instead
  (the catalog is what the login locks; the document viewer itself stays
  open to everyone).
- **Git sources** (`/git-sources.html`) — the admin-managed source
  registry: the git repositories the **Sync sources** button clones and
  indexes, **and** existing local directories it imports directly
  (phase 38 — one table with a `kind` discriminator, one page); **admin-only**
  (the same sign-in gate as Sources). Add or remove sources here — no
  `.env` editing, no restart. A local directory must be an absolute,
  existing directory at add-time (a missing/relative path is rejected
  inline, naming the path; so are duplicates); list rows carry a **Git**
  or **Local** badge. Adding/removing does not clone or prune on its
  own: the Sync button performs that (git + local together, one run,
  prune over the union), and a removed source's documents leave the index
  on the next sync.

## Thinking

The self-hosted `turbo` model reasons before it answers. That reasoning is
streamed with the turn as `thinking` SSE events and shown in a
**collapsible "Thinking" block** above the answer bubble: it opens and
fills in live while the model thinks, tucks itself away the moment the
first answer token lands, and stays click-toggleable afterwards. Thinking
persists with the message, so a reloaded conversation restores the block
(collapsed) alongside the answer. How much the model thinks — or whether
it thinks at all — is the model's call: turns without reasoning render
exactly as before.

To hide it, set `BOR_STREAM_THINKING=0` — the `thinking` events stop
(the per-turn log line still counts `thinking_chars`).

## Agent document tools (list + read)

Retrieval only puts the top documents in context. When an answer depends
on a file a note *references* ("the exact JSON shape is in
example-record-file.json"), the model can extend its own context with two
server-side tools — on **grounded** (high-relevance) turns only:

* **`list_documents`** — lists every indexed document, one
  `source/path — title` line each (the same order as the Sources page);
* **`read_document(source, path)`** — appends the **full** text of
  one more indexed document to the context (never truncated).

Each call the model requests is executed against Postgres only (no extra
LLM round trip) and streamed as an SSE `tool` frame ahead of the answer —
`{"type": "tool", "name": …, "argument": "source/path" | null}`. In the
chat, each call shows a **"calling tool" state** in addition to
"thinking": the send button keeps its busy state ("Calling tool…") and a
visible tool line (`🔎 Listing documents` / `📄 Reading source/path`) lands
above the answer, one per call, in order. The tool lines persist with the
message, so a reloaded conversation re-renders them. The read document is
reflected in the answer's **source chips** and in the `query_log` row.

The tools stay offered for the whole turn — the model may call them as
many times as it needs (re-lists included), bounded only by a round cap
that stops a pathological infinite loop:

| Env | Default | Meaning |
|---|---|---|
| `BOR_AGENT_MAX_ROUNDS` | `10` | hard cap on agent tool rounds per grounded turn — every call the model emits consumes a round; at the cap the loop forces one final no-tools answer |

`BOR_AGENT_MAX_ROUNDS=0` reproduces the pre-agent chat behavior exactly
(no `tools` in the request, no `tool` frames) — the kill switch.
Deflected turns run no tools at all — the low-relevance path is
unchanged.

## Admin & sign-in

Brain of Reese has exactly **one account: the admin (you)**. Signing in
unlocks the **full Sources catalog** and the **answer-tuning** controls;
everyone else stays anonymous and keeps **chat** and the **document
viewer** (any document an answer cites can be opened by its direct URL —
the catalog is gated, not the viewer).

### Setup (one-time)

```bash
python -c 'import secrets;print(secrets.token_hex(32))'   # → paste into .env
```

```env
BOR_ADMIN_PASSWORD=your-password        # plaintext — homelab scope, by design
BOR_SESSION_SECRET=<the hex from above> # signs the session cookie
```

**Fail-loud:** while either variable is empty the app refuses to start,
naming the missing one(s):

```
RuntimeError: Brain of Reese cannot start: admin auth is not configured.
Set the missing variable(s): BOR_ADMIN_PASSWORD, BOR_SESSION_SECRET …
```

### How it works

- `POST /api/login {"password": …}` → `204` + signed `bor_session` cookie
  (Starlette `SessionMiddleware` — an itsdangerous-signed cookie, no
  server-side store, no new service, no DB table); any mismatch → `401`
  `{"detail": "invalid password"}` (constant-time compare, one generic
  message — no user enumeration, there is only one user).
- `POST /api/logout` → `204` (session cleared and cookie expired;
  idempotent for anonymous callers).
- `GET /api/whoami` → `{"authenticated": bool, "role": "admin"|"anonymous"}`
  — the single source of truth for every UI gating decision.
- Cookie flags: `same_site="lax"`, `https_only` off — **no HTTPS
  enforcement on purpose** (homelab HTTP; the cookie is single-admin
  convenience, not a cloud boundary). Max age `BOR_SESSION_MAX_AGE`
  (default `43200` = 12 h, refreshed while active).
- Sign in from the chat header (**Sign in**) or `/login.html` directly;
  the header then offers **Sign out** (logout + reload).

### Who can do what

| Capability | Anonymous | Admin (signed in) |
|---|---|---|
| Chat (`/`) + suggestion chips | yes | yes |
| Document viewer (`/document.html?source=…&path=…`) | yes — any indexed doc by direct URL | yes |
| Sources catalog (`/sources.html`, `GET /api/docs`) | sign-in gate | full catalog |
| Tuning (Tune button, Tuning panel, `/api/steering`) | UI hidden | full |

The public API endpoints stay stateless — the signed cookie is the only
session state in the system.

## Tuning your answers

*Admin-only* — sign in first (see **Admin & sign-in** above); anonymous
visitors never see the Tune button or the Tuning panel.

If an answer isn't quite right — too chatty, wrong assumption, missing
context — **tune** Brain right there:

1. Press **“Tune”** in the meta row under any completed answer (deflected
   ones included).
2. Type a short instruction (1–2000 chars), e.g. *“be more concise”* or
   *“assume I'm on NixOS”*, and **Save**.

The note is stored in Postgres (`steering_notes`) and read into the
**system prompt of every subsequent chat turn** as a `<tuning>` section
(numbered, oldest first, capped at `BOR_STEERING_MAX_CHARS` chars —
default 8000, overflow marked `[…truncated…]`). With no stored notes the
prompt is byte-identical to the un-tuned one, so tuning is opt-in per
note.

List or remove notes at any time from the **“Tuning”** button in the chat
header (count badge, newest-first, per-note delete). The API is stateless
JSON if you prefer curl:

```bash
curl -s localhost:8000/api/steering                                  # list (newest first)
curl -s -X POST localhost:8000/api/steering \
     -H 'Content-Type: application/json' -d '{"note": "be more concise"}'
curl -s -X DELETE localhost:8000/api/steering/<note-id>              # remove
```

## Updating the documents

**This is the workflow you'll use most.** The knowledge base is refreshed by
**re-running the import**. It is idempotent and delta-based (sha256 per
file), so a refresh after a normal editing session takes seconds:

```bash
# After editing/adding/removing notes in your projects:
uv run python -m scripts.import_docs                 # re-index what changed
uv run python -m scripts.import_docs --prune         # also drop deleted/out-of-scope files

# Point it at extra directories (repeatable):
uv run python -m scripts.import_docs --source ~/SomeOtherDocs
```

With **git-based sources** (below) each run first pulls the latest commits
of your repos, so this same command is the whole update loop: commit in the
repo → re-run the import.

Then check the **Sources** page (`http://localhost:8000/sources.html`):
the *documents* / *chunks* counters and *last indexed* timestamp should
reflect the new files, and each document row shows when it was last
embedded.

- The import prints one line per file (`import: added|updated|unchanged|
  pruned …`) and ends with a greppable summary (`import: summary files=…
  added=… updated=… unchanged=… pruned=… chunks=… embed_batches=…
  formats=md:203,yaml:267,…`), so it is safe to run from a cron job or
  after every commit.
- Indexed formats (A9, revised 2026-08-27): **`md, markdown, txt,
  yaml, yml, json, py`**, the Podman quadlet family (**`container,
  network, volume, image, pod, kube, swap, os, endpoint`**), and **`j2`**
  Jinja templates (case-insensitive; narrow with `BOR_IMPORT_EXTENSIONS`).
  Any path with a
  **dot-prefixed component** — hidden files or vendored caches like
  `.esphome/.espressif/**` — is skipped, along with `.venv`,
  `node_modules`, `.git`, `__pycache__`, `.pytest_cache`, `dist`, `build`.
  `--prune` also drops documents whose files no longer match the filter —
  that's how previously imported junk leaves the index.
- Non-markdown files get format-aware chunking (YAML top-level keys /
  `---` docs, JSON top-level keys, Python top-level defs/classes via
  stdlib `ast`; quadlet unit files and `j2` templates are paragraph-
  packed as plain text) and their title comes from the file stem.
- Unchanged files are **not re-embedded** — only new/changed ones, so
  refreshes are cheap.
- After a run that **changed** the knowledge base (at least one document
  added or updated), the import also regenerates the stored **KB
  overview** — a plain-text outline of the KB's basic categories that
  every chat turn injects into the system prompt as `<knowledge_base>`
  (phase 31). The regeneration is best-effort and change-gated: unchanged
  re-imports and `--limit` debug runs skip it (no `lite` call), and a
  `lite`-model failure leaves the previous outline intact without failing
  the import. The summary line ends `overview=updated|skipped|failed`.
- To sanity-check the LLM backend (models + embedding dimension) after any
  aipi change: `uv run python -m scripts.llm_probe`.

### Git-based sources

Rather than pointing the import at local folders, point it at **git
repositories** — the notes live in the repos and `import_docs` keeps local
checkouts of them up to date for you.

**Where the list lives (phase 35):** the primary management surface is
the **admin Git sources page** (`/git-sources.html`) — add or remove
repositories there and the list is stored in Postgres (the `git_sources`
table). `BOR_GIT_SOURCES` in `.env` is the **empty-table fallback**: it
only applies while the stored list is empty, and is ignored once the page
has any row (the page becomes the source of truth — no `.env` editing, no
restart needed afterwards).

```env
# .env — the fallback list (fresh setups, or until the admin page
# stores a source; phase 35 demotes this variable, it does not remove it)
BOR_GIT_SOURCES=https://git.reeseapps.com/reese/homelab.git,git@github.com:reese/deployments.git
BOR_SOURCES_DIR=~/bor-sources   # default; each repo lands in <dir>/<repo-name>/
```

- The effective list (stored rows, else `BOR_GIT_SOURCES` while the stored
  list is empty) is a set of git repo URLs. Auth is whatever the machine
  supplies — `https://…` via the OS credential helper, or `git@host:repo.git`
  via your SSH key; no credentials are stored in the app or `.env`.
  Stored URLs are shape-validated on the page (`https://`, `ssh://`,
  `git@…` — scp-style `host:repo` is rejected).
- Every run **clones** each repo (first time, shallow `--depth 1`) or
  **pulls** it (`git pull --ff-only` — fast-forward only, so a diverged or
  broken checkout fails loudly instead of merging) into
  `BOR_SOURCES_DIR/<repo-name>/`, then indexes the checkouts exactly like
  any local directory (A9 format filter, hidden-dir skip, sha256 delta).
  `documents.source` is the repo directory name (e.g. `homelab`).
- **`--source <path>` overrides**: when the flag is given, the git
  sources (stored list *and* `BOR_GIT_SOURCES`) are ignored and the
  manual directory(ies) are imported.
- **A failed sync aborts the run**: if any repo cannot be cloned/pulled,
  `import_docs` exits non-zero naming the failing repo and imports
  **nothing** (no partial junk). Fix the URL/connectivity and re-run — the
  other checkouts stay on disk and are pulled as usual.

### Local directory sources

Not every set of notes lives in a git repo — a plain directory can be a
first-class source too (phase 38). It shares the git sources' **one
table** (the `git_sources` registry with a `kind` discriminator: `git` |
`local`, migration 0007), **one admin page**, and **one Sync button**:

- **Add it on the Git sources page** — the “Add a local directory” form
  next to the git form. Add-time validation fails loud: the path is
  trimmed, `~` is expanded, and must be an **absolute, existing directory
  on the server** — anything else (missing, relative, a file) is rejected
  with the path named inline; a duplicate path is rejected the same way.
  There is **no env var for local paths** — the DB is the local-source
  registry (`BOR_GIT_SOURCES` stays a git-only fallback).
- **Sync walks it directly** — no clone, no checkout copy: each run
  indexes the directory in place (A9 format filter, hidden-dir skip,
  sha256 delta), together with the git checkouts in the **same run**.
  `documents.source` is the directory's name. The directory is
  re-verified to exist **at sync time** (it may have moved or been
  deleted since add-time): a missing directory fails the run loudly,
  naming the path, and imports **nothing** (the same pre-import fail-loud
  as a failing git clone).
- **Pruning is over the union** — git checkouts and local directories are
  imported together with `prune=True`, so a file removed from a local
  directory, a repo, or a removed source leaves the index on that run.
  Removing the row on the page stops the directory being a source; its
  documents leave the index on the next sync (exactly like git sources).
- **`import_docs`** (no `--source`) resolves the stored git **and** local
  rows — git cloned/pulled as above, local walked directly — in one run;
  `--source` still wins over everything; while the table is empty,
  `BOR_GIT_SOURCES` is the git-only fallback; no git rows, no local rows,
  and no env URLs fails loudly ("no sources configured (git or local)").

### Sync from the UI

The **Sync sources** button on the **Sources** page — visible to the
**admin only** (anonymous visitors never see it) — runs the whole
git-source refresh in one click, in-process:

1. **clone/pull + walk** every configured source — the git sources (the
   admin-managed `git_sources` table; `BOR_GIT_SOURCES` only while that
   list is empty) through the same `clone_or_pull` the CLI uses (shallow
   clone on first run, `git pull --ff-only` afterwards), **and** the
   local directories registered on the same page, walked directly
   (re-verified to exist at sync time — a missing directory fails the run
   loudly, naming the path);
2. **re-import with prune** — the `--prune` equivalent, so files deleted
   upstream leave the index (the button is the canonical "mirror the
   repos" action); the sha256 delta still skips unchanged files, so an
   unchanged re-sync re-embeds nothing;
3. **regenerate the KB overview** (the `<knowledge_base>` outline every
   chat turn injects) — but only when the import actually changed the
   knowledge base.

- **Prerequisites:** at least one source must be configured — a git or
  local row on the admin Git sources page, or `BOR_GIT_SOURCES` in `.env`
  while the stored list is empty (git-only); **all** empty fails the sync
  loudly ("no sources configured (git or local)"), because the button
  targets the admin-managed registry (manual `--source` directories have
  no place in it) — and `git` must be on the app's `PATH` for git sources.
- **States:** clicking starts the run (`202`) and the button goes
  disabled with **Syncing…** (spinning icon) while the page polls
  `GET /api/sync/status` every 2 s. There is deliberately **no
  client-side timeout** — a clone + embed can legitimately take minutes,
  so the poll is the feedback loop and the server state is authoritative.
  On success the button settles to **Synced HH:MM** with the last result
  in a live region (`1 added`, `0 added · 1 unchanged`, …); on failure it
  re-enables (retry-ready) and a red error banner names the failure (git's
  stderr, with any embedded credentials masked).
- **One sync at a time:** a second trigger while a run is in flight gets
  `409` ("a sync is already running"); the UI adopts the in-flight run
  instead of starting a second one, and a page reload mid-sync re-attaches
  to it the same way.
- **Idempotent:** re-syncing unchanged repos is a no-op — fast-forward
  pull, hash skip, and the overview is left alone (its regeneration is
  change-gated).

## Caching / deploys

A deploy is a commit — and the browser must see it **without a hard
refresh** (the "the pages are too sticky" problem, phase 33). One
Starlette middleware (`app/core/caching.py`) applies the rule at the
transport layer:

- **HTML pages always revalidate.** Every page (`/`, `/sources.html`,
  `/document.html`, `/login.html`, `/tuning.html`) ships
  `Cache-Control: no-cache`, so each visit re-checks the page with the
  server — a page never lingers in the browser's cache unchecked.
- **Assets are versioned and cached for a year.** The pages reference
  their CSS/JS with a token (`/assets/styles.css?v=<token>`), and every
  `/assets/*` response ships
  `Cache-Control: public, max-age=31536000, immutable`. The token is what
  identifies the content, so long-term caching is safe: a new token means
  a new URL, which the browser fetches fresh.
- **The token is the deploy.** In a git checkout (the normal case) it is
  the short SHA of `HEAD` (`git rev-parse --short HEAD`), computed once
  per process start — so **every commit/deploy flips the token** and the
  versioned asset URLs change with it. A checkout without `.git` (or a git
  failure) falls back to a stable content hash of the `frontend/` tree
  (sorted path + mtime + size), so dev checkouts still bust; a missing
  static dir gets the placeholder token `dev`.
- **The API is untouched.** Nothing under `/api/*` — the SSE chat stream
  in particular — gains or loses a header or has its body read; the SSE
  endpoint's own `Cache-Control: no-cache` is set by the endpoint itself.

No CDN, no new services, no build-step change: the middleware rewrites
the asset references of the five known pages in flight. The unversioned
asset paths keep working too (the static mount ignores the query string),
so old tabs and direct links to `/assets/…` still resolve.

> **Deploy note:** the very first deploy onto this scheme needs one
> normal page visit, so the browser revalidates the HTML once and starts
> requesting the versioned assets; every commit after that is picked up
> automatically.

## Checking retrieval quality

Ask the *real* pipeline (live aipi embeddings + the current KB) whether a
question lands on the right document, with the gate verdict and per-document
cosine / FTS / fused scores:

```bash
uv run python -m scripts.eval_retrieval "How did I install gitlab?"
uv run python -m scripts.eval_retrieval --from-file questions.txt --top 8
```

Requires `AIPI_KEY` in the environment (same convention as
`scripts/llm_probe.py`) and an imported knowledge base.

## How retrieval works (hybrid)

Every question is embedded and also lexically tokenized (OR-joined, English
stemming) and searched **twice** against Postgres:

1. **Vector** — pgvector cosine top-N (default `BOR_HYBRID_VECTOR_CANDIDATES=100`)
2. **Lexical** — a stored `tsvector` (GIN-indexed) matched with `to_tsquery`,
   top-N by `ts_rank` (default `BOR_HYBRID_LEXICAL_CANDIDATES=30`)

The two ranked lists are fused with **Reciprocal Rank Fusion**
(`score = Σ 1/(k + rank)`, `BOR_RRF_K=60`) — a chunk in both lists scores
nearly double, which is what lets a name-your-tool question ("gitlab") find
its own document even when the question embeds close to generic templates.

The **honesty gate** (A8) then answers (HIGH) when the best cosine is ≥
`BOR_RELEVANCE_THRESHOLD` (default `0.62`) **or** at least one chunk matched
lexically (`fts_hits > 0`) — it deflects (LOW) only when *both* signals are
absent. The top `BOR_TOP_N_DOCS` full documents are still what the LLM sees.

`query_log` records every turn (`top_score` = best cosine, `fts_hits`,
`chunk_hits`, `deflected`, `sources`, `latency_ms`) — the raw material for
tuning: `psql … -c 'SELECT question, top_score, fts_hits, deflected FROM query_log ORDER BY created_at DESC LIMIT 20'`.

## Document summaries (non-markdown)

Raw yaml/json/py/txt embeds badly — flags and keys are not language, so
retrieval can miss exactly the documents that are all configuration. At
import time, every **non-markdown** A9 document is summarized by the aipi
`lite` model (one-shot `LLMClient.chat`, `BOR_LLM_SUMMARY_MODEL`, default
`lite`):

* the summary is stored on `documents.summary` **and** indexed as one
  extra embedded chunk (`chunks.is_summary`, position −1), so hybrid
  search has a natural-language target to hit instead of the raw text;
* the last line is a **code-deterministic** pointer — `Source:
  <source>/<path>` — appended by the app, never model-generated;
* the model only sees the first `BOR_SUMMARY_MAX_CHARS` (default 12000)
  characters of the document; overflow is cut and marked with the shared
  `[…truncated…]` marker.

A summary hit resolves through the normal chunk→document mapping: the
LLM receives the **full source document** (never the summary alone,
never truncated). Markdown files are natural language already and get no
summary. Summary generation is best-effort: if `lite` fails for a file,
the document is still indexed (without a summary), the failure is logged
and counted in the import summary line (`summaries=N summary_errors=N`).
On a chat turn, the per-turn log line records `summary_hits=N` — how many
summary chunks of the selected context the question landed on.

## Debugging

`debugpy` is **off by default** and *never imported* unless you opt in —
zero overhead in normal runs.

```bash
DEBUGPY=1 uv run uvicorn app.main:app
# → log line: debugpy: remote debugging ENABLED, listening on 0.0.0.0:5678
```

Then attach from VS Code (`.vscode/launch.json`):
```json
{
  "name": "Attach to Brain of Reese",
  "type": "debugpy",
  "request": "attach",
  "connect": { "host": "localhost", "port": 5678 },
  "pathMappings": [
    { "localRoot": "${workspaceFolder}", "remoteRoot": "/app" }
  ]
}
```
The port is non-blocking and attach-on-demand: the app keeps running
normally until you attach. Override the port with `DEBUGPY_PORT`.

## QA / Testing Environment

Three layers — the project rule is **one story, one phase, one Playwright
suite** (see `AGENTS.md`):

```bash
# Unit + integration (FastAPI TestClient)
uv run pytest

# Same, with the coverage gate (phases require >90% on app/)
uv run pytest --cov=app --cov-report=term-missing

# Lint + static types
uv run ruff check .
uv run pyright

# Playwright E2E — install the browser once:
uv run playwright install chromium

# Each story's E2E runs IN ISOLATION (DB must be up):
podman compose up -d db
uv run pytest tests/e2e/test_import_documents.py -v --no-cov
uv run pytest tests/e2e/test_chat_rag.py -v --no-cov
# ...one file per story in .agent/user_stories/ (see .agent/phases/todo/)
```

**Deterministic E2E:** by default the E2E app talks to a local **mock
aipi** (`tests/e2e/mock_llm.py`) whose embeddings are real
token-overlap vectors — so the cosine relevance threshold behaves like
production (on-topic questions answer, off-topic ones deflect).
To run E2E against the **live** self-hosted models instead:

```bash
E2E_REAL_LLM=1 uv run pytest tests/e2e/test_chat_rag.py -v --no-cov
```
(requires a real import of your docs first).

## Production Deployment

Build the multi-stage image (frontend minified by esbuild in the builder
stage, deps installed by `uv`, non-root runtime):

```bash
podman build -t brain-of-reese/app:latest .
```

Run standalone (bring your own Postgres + pgvector):
```bash
podman run -d --name brain-of-reese \
  -p 8000:8000 \
  -e BOR_DATABASE_URL=postgresql+psycopg://reese:SECRETPASSWORD@dbhost:5432/brain_of_reese \
  -e BOR_LLM_BASE_URL=https://aipi.reeseapps.com/v1 \
  -e BOR_LLM_API_KEY=$AIPI_KEY \
  brain-of-reese/app:latest
```
The entrypoint runs `alembic upgrade head` automatically on start.

Or run the whole stack from compose (app + db):
```bash
podman compose --profile prod up -d --build
```

Production hardening notes: app runs as non-root (uid 10001), slim image,
healthcheck on `/api/health`, debugpy off unless `DEBUGPY=1`, all assets
served locally (no CDN), `BOR_ENVIRONMENT=production`.

## Configuration reference

| Env | Default | Meaning |
|-----|---------|---------|
| `BOR_APP_NAME` | `Brain of Reese` | the display name everywhere (phase 39): every page `<title>`, the header brand, the chat status labels ("… is thinking"), the empty-state greeting, and the aria/placeholder text. Served to the frontend by `GET /api/config` and applied by `assets/brand.js`; a name starting `Brain of ` keeps the bold split (`Brain of <strong>rest</strong>`), any other name renders in normal weight. Unset ⇒ byte-identical to the default |
| `BOR_DATABASE_URL` | local compose URL | SQLAlchemy URL (psycopg) |
| `BOR_LLM_BASE_URL` | `https://aipi.reeseapps.com/v1` | OpenAI-compatible endpoint |
| `BOR_LLM_API_KEY` | — (falls back to `$AIPI_KEY`) | aipi API key |
| `BOR_LLM_CHAT_MODEL` | `turbo` | chat model |
| `BOR_LLM_EMBED_MODEL` | `embed` | embedding model |
| `BOR_LLM_SUMMARY_MODEL` | `lite` | one-shot (non-streaming) completions: document summaries at import (phase 30) and the KB overview (phase 31) |
| `BOR_EMBEDDING_DIM` | `768` | vector dimension (fixed at table creation) |
| `BOR_TOP_N_DOCS` | `2` | full documents fed to the LLM |
| `BOR_RELEVANCE_THRESHOLD` | `0.62` | answer when best cosine ≥ this **or** an FTS hit; below + no FTS ⇒ honest deflection |
| `BOR_HYBRID_VECTOR_CANDIDATES` | `100` | cosine list width for the RRF fusion |
| `BOR_HYBRID_LEXICAL_CANDIDATES` | `30` | FTS list width for the RRF fusion |
| `BOR_RRF_K` | `60` | RRF damping constant (`1/(k + rank)`) |
| `BOR_AGENT_MAX_ROUNDS` | `10` | hard cap on agent tool rounds per grounded turn — every call the model emits consumes a round; at the cap the loop forces one final no-tools answer (0 = no tools, the kill switch) |
| `BOR_IMPORT_EXTENSIONS` | `md,markdown,txt,yaml,yml,json,py,container,network,volume,image,pod,kube,swap,os,endpoint,j2` | csv of importable formats (may only narrow the A9 set) |
| `BOR_GIT_SOURCES` | — (empty) | csv of git repo URLs — **fallback while the admin Git sources page's list (Postgres `git_sources`) is empty**; the page is the primary management surface (see *Git-based sources*). **Git-only**: local directory sources have no env var — they are registered on the admin page (see *Local directory sources*) |
| `BOR_SOURCES_DIR` | `~/bor-sources` | where the git source repos are cloned/pulled (one subdirectory per repo) |
| `BOR_STEERING_MAX_CHARS` | `8000` | char budget for the `<tuning>` (steering notes) prompt section |
| `BOR_SUMMARY_MAX_CHARS` | `12000` | cap on document content sent to the `lite` summary model at import (see *Document summaries*) |
| `BOR_KB_OVERVIEW_MAX_CHARS` | `4000` | char budget for the `<knowledge_base>` (KB overview) prompt section |
| `BOR_OVERVIEW_INPUT_MAX_CHARS` | `40000` | cap on the document list sent to the `lite` model when generating the KB overview |
| `BOR_SUGGESTIONS` | built-in list | JSON list of onboarding chips |
| `BOR_ADMIN_PASSWORD` | *(required)* | the single admin's password (plaintext, `.env`); app refuses to start when empty |
| `BOR_SESSION_SECRET` | *(required)* | signing key for the `bor_session` cookie; `python -c 'import secrets;print(secrets.token_hex(32))'` |
| `BOR_SESSION_MAX_AGE` | `43200` | session-cookie lifetime in seconds (12 h, sliding) |
| `DEBUGPY` | `0` | `1` ⇒ attach-on-demand debugpy on `DEBUGPY_PORT` (default 5678) |
| `BOR_LOG_LEVEL` | `INFO` | app log level |

## Troubleshooting

- **`401` from aipi** — set `BOR_LLM_API_KEY` (or `$AIPI_KEY`).
- **`litellm.UnsupportedParamsError … encoding_format` from aipi** — the
  aipi proxy (litellm `openai_like`) rejects the `encoding_format` parameter
  that the `openai` SDK injects into every embeddings request. The app
  already works around this by POSTing a minimal `{model, input}` payload
  through the openai client's own httpx transport (`app/rag/llm.py` →
  `LLMClient._embed_batch`). If you see this, you are likely calling the
  endpoint with a different client — drop the parameter (or set
  `litellm.drop_params = True` on the proxy).
- **Embedding dimension mismatch** — aipi changed models; run
  `uv run python -m scripts.llm_probe`, update `BOR_EMBEDDING_DIM`, then
  drop + recreate the chunks table (new migration or manual `TRUNCATE
  chunks, documents`).
- **Honest deflection (the amber “I haven't done anything like that”
  bubble)** — every question passes the honesty gate: deflection happens
  only when the best cosine similarity is below
  `BOR_RELEVANCE_THRESHOLD` (default `0.62`) **and** no chunk matched the
  question lexically (`fts_hits = 0`). A weak cosine with a lexical hit
  (name-your-tool questions) still gets a grounded answer. When it does
  deflect, the LLM prompt carries weak-hit *titles only* (no document
  content), the reply opens with “I haven't done anything like that”, the
  bubble renders amber with “Maybe try” chips derived from the closest
  indexed titles, the SSE `done` event carries `deflected: true` +
  `suggestions[]`, and the `query_log` row records `deflected=true` + the
  weak `top_score` + `fts_hits`. This is a feature, not a bug — the KB
  simply has no notes that close; the chips always point at topics Brain
  really covers.
- **Answers deflect too often / too rarely** — tune
  `BOR_RELEVANCE_THRESHOLD` (lower = answers more, higher = more honest
  deflection): `0.0` ⇒ the gate leans entirely on FTS hits; `1.0` ⇒
  everything deflects unless a chunk matches lexically. The `embed` model's
  cosines cluster in a ~0.6–0.85 band on the live KB, so the default is
  `0.62`; after changing it, check the real scores:
  `psql … -c 'SELECT question, top_score, fts_hits, deflected FROM query_log ORDER BY created_at DESC LIMIT 20'`
- **KB offline banner in the chat** — Postgres isn't running:
  `podman compose up -d db`.
- **Stuck "Thinking…"** — the LLM is slow or down; a 120s client timeout
  turns it into an error banner automatically.