Document the project, the hardware, and the camera that is not there yet

README records the real starting state rather than an aspirational one: the
camera module is NOT detected. rpicam-hello reports no cameras and dmesg has no
sensor probe lines at all, while camera_auto_detect=1 is already set and the
libcamera userland is fully installed. Silence in dmesg is the diagnostic — a
sensor that is seen but misconfigured still probes — so this is cabling, not
config, and the doc says so instead of sending anyone to edit dtoverlay lines.

Also records the trap that /dev/video* nodes already exist on this Pi and belong
to the codec and ISP blocks, so they are not evidence of a camera.

AGENTS.md gives Codex the project-specific rules: it runs ON the target, so it
should test rather than reason about whether something would run; it must not
try to fix the camera in software; and claims about the stream need a command
that ran, because a 200 with no frames looks exactly like a working one.

AGENTS.md

@@ -0,0 +1,62 @@
+# Working in this repo
+
+Project instructions for Codex on `pi5`. The client-wide prompt lives in `~/.codex/AGENTS.md`; this
+file is the project-specific part.
+
+## Where you are
+
+**You are running on the target hardware.** `pi5` is the Raspberry Pi 5 this software is *for*, so
+you can test against the real camera, the real CPU and the real network — there is no emulation step
+and no deploy step. Use that: prefer running the thing over reasoning about whether it would run.
+
+Call `platform_info` if you need to confirm which machine you are on. It is client-local and reports
+this Pi, not `halogen`.
+
+## The camera is not detected yet
+
+`rpicam-hello --list-cameras` reports **"No cameras available!"**, and `dmesg` has no sensor probe
+lines. See README.md for the diagnosis.
+
+⚠ **This is a hardware/cabling problem, and you cannot fix it from software.** Do not add
+`dtoverlay=` lines, edit `/boot/firmware/config.txt`, or install packages to try to make it appear —
+`camera_auto_detect=1` is already correct, and a silent `dmesg` means the sensor is not being reached
+electrically. Report the state and ask the operator to reseat the cable.
+
+⚠ **Do not take `/dev/video*` as proof of a camera.** Those nodes are the Pi's codec and ISP blocks
+and exist with nothing attached.
+
+Until a sensor appears, work that does not depend on live capture is still available: the web UI
+shell, the streaming plumbing against a test pattern or a still image, project structure, tests.
+**Say plainly when you are working against a placeholder** rather than a real frame.
+
+## Constraints
+
+- **Python 3 with `picamera2`** is the expected capture path once a sensor exists. It is not
+  installed yet; install it via `apt` (`python3-picamera2`), not `pip` — it binds to system
+  libcamera, and the pip build will not match.
+- **Do not commit captured images or video.** Frames of a real room are not test fixtures. If a
+  fixture is genuinely needed, generate a synthetic one.
+- This is a **4-core Pi 5**. Face recognition must run on downscaled frames and off the capture
+  thread; a per-frame full-resolution model will not hold a live stream.
+- Prefer the **stdlib and system packages** over adding dependencies. Every dependency here is one
+  more thing that has to build on aarch64.
+
+## Verifying your work
+
+Claims about the camera or the stream must be backed by a command that ran:
+
+```bash
+rpicam-hello --list-cameras          # is a sensor present at all
+dmesg | grep -iE 'imx|ov5647|cfe'    # did it probe
+curl -sI http://localhost:<port>/    # is the server actually serving
+```
+
+⚠ **The absence of an error is not evidence something works.** A stream endpoint that returns 200
+with no frames, and a working one, look identical to `curl -o /dev/null`. Check what came back.
+
+## Git
+
+The remote is Gitea at `192.168.2.199:3005`, reachable from this Pi over SSH on port 2222.
+
+⚠ **`tea` (the Gitea CLI) is denied by policy** and is blocked by a `PreToolUse` hook. Ordinary
+`git` is fine. **Do not push** unless the operator asks — commit locally and say what is ready.

README.md

@@ -1,3 +1,71 @@
 # pi5-camera-webui
 
-Raspberry Pi 5 camera service: live MJPEG/WebRTC feed with a web UI, later face recognition. Codex-driven development on pi5.
+Camera service for a Raspberry Pi 5: a live video feed served over a small web UI, with face
+recognition planned as a later stage.
+
+Developed on the machine it runs on (`pi5`), with Codex as the coding client — see [AGENTS.md](AGENTS.md).
+
+## Hardware
+
+| | |
+|---|---|
+| Board | Raspberry Pi 5 Model B Rev 1.1 |
+| OS | Debian 12 (bookworm), aarch64 |
+| Camera | Pi camera module, connected to a CAM port |
+| Host | `pi5`, `192.168.2.154` |
+
+## ⚠ Current state: the camera is NOT detected
+
+Nothing is built yet, and **the camera is not visible to the system**, so start here:
+
+```console
+$ rpicam-hello --list-cameras
+No cameras available!
+```
+
+This is a *detection* problem, not a software one — the userland is already in place:
+
+- `camera_auto_detect=1` is set in `/boot/firmware/config.txt` (the correct default; nothing to add)
+- 12 `libcamera`/`rpicam` packages are installed
+- **`dmesg` contains no camera probe lines at all** — no sensor (`imx*`, `ov5647`), no CFE
+
+That last point is the diagnostic one. A camera that is seen but misconfigured still leaves probe
+messages; **silence means the sensor is not being reached electrically.** So check the physical
+connection before changing any config:
+
+1. The Pi 5 has **two CAM/DISP connectors, and they are interchangeable in shape** — a camera in a
+   DISP port looks correctly seated and will never appear.
+2. Ribbon **orientation**: contacts face the correct side at both ends (the board end and the camera
+   end are not the same way round).
+3. The connector latch is fully seated at both ends.
+4. The Pi 5 uses the **narrower 22-pin** connector — a 15-pin camera cable needs an adapter.
+
+Power off before reseating. Re-check with:
+
+```bash
+rpicam-hello --list-cameras     # should list a sensor
+dmesg | grep -iE 'imx|ov5647|cfe'
+```
+
+⚠ **Do not treat `/dev/video*` as evidence the camera works.** Those nodes exist on this Pi already
+and belong to the video codec and ISP blocks — they are present with no camera attached at all.
+
+`picamera2` is **not** installed yet (`import picamera2` fails); it is the expected capture library
+once a sensor is detected.
+
+## Planned stages
+
+1. **Capture** — confirm a sensor, grab a still, establish resolution/format.
+2. **Live feed** — MJPEG stream first (simplest thing that works in a browser); WebRTC later if
+   latency demands it.
+3. **Web UI** — single page showing the live feed, plus basic controls.
+4. **Face recognition** — detection first, recognition after; run it on a downscaled frame, not the
+   full stream.
+
+Each stage should be usable on its own before the next begins.
+
+## Development
+
+The model endpoint and MCP gateway live on `halogen` and are reachable from this Pi by name.
+Codex is installed and configured here; see [AGENTS.md](AGENTS.md) for how it is expected to work in
+this repo.