FIX SOME BUGS

README.md

@@ -1,18 +1,52 @@
 # sjcode
 
-ein terminal coding agent, der die ollama API nutzt
+a terminal coding agent, powered by the ollama API
+
+## What makes it an agent
+
+The client is not a chat front end: the model can **really work in your
+codebase**. It runs shell commands, reads and edits files — on your machine,
+in the directory you started `./coder` from. Every model reply can contain
+tool calls; the client executes them and feeds the real output back to the
+model until the task is done.
+
+Tools the agent can use:
+
+| tool    | what it does                                     | asks first |
+|---------|--------------------------------------------------|------------|
+| `run`   | run one shell command in the project directory   | yes        |
+| `read`  | read a file (numbered lines, `start`/`limit`)    | no         |
+| `files` | list project files (skips `.git`, caches, ...)   | no         |
+| `write` | create a file, or overwrite a small one          | yes        |
+| `edit`  | exact-text replace in a file, shows a diff       | yes        |
+
+Before every `run`/`write`/`edit` you see exactly what will happen (command
+line, or a unified diff for file changes) and press Enter to allow it, `n` to
+decline, `a` to stop the agent — or just type a short instruction ("use ripgrep
+instead") and the model adapts. `--yes` (or `/auto` in the session) runs
+everything without asking; the sandbox keeps all file tools inside the project
+directory.
 
 ## Setup
 
 ```bash
-cp config.toml.example config.toml   # then edit port / model / limits
-python3 server/server.py             # starts the daemon + admin CLI
+cp server/config.toml.example server/config.toml   # then edit port/model/limits
+python3 server/server.py                            # starts the daemon + admin CLI
 ```
 
 `config.toml` is machine-local and git-ignored; `config.toml.example` is the
 template. On first start the daemon creates the SQLite database (`sjcode.db`).
 
-## Daemon (server.py)
+Pick a coder model in `[ollama] model` — one that follows structured output
+well, e.g. `qwen2.5-coder:7b` or bigger. The agent transcript is long, so the
+daemon requests a large context window from ollama:
+
+```toml
+[ollama]
+num_ctx = 16384   # context window; do not go below 8192 for agent mode
+```
+
+## Daemon (server/server.py)
 
 On startup it prints its settings and drops into a minimal admin CLI
 (accounts are stored in SQLite):
@@ -32,12 +66,18 @@ On startup it prints its settings and drops into a minimal admin CLI
 While the CLI runs, an HTTP API is served in the background:
 
 - `POST /login` — `{"username", "password"}` → `{"token", ...}`
-- `POST /chat`  — `{"token", "message", "model"?}` → `{"response", ...}`
+- `POST /chat`  — `{"token", "message", "model"?, "stream"?}` → reply as JSON,
+  or (with `"stream": true`) as NDJSON lines `{"chunk": ...}` ending with one
+  final `{"response", "used_minutes", "remaining_minutes", ...}` line
 - `GET  /models?token=...` — list ollama models
+- `GET  /status` — health check
 
 Every user row stores: `username`, `password_hash`, `last_logged_in`,
 `role`, `used_today` (minutes of AI usage; resets on a new day).
 
+`SJCODE_CONFIG=/path/to/config.toml` lets you run a second daemon (tests,
+staging) next to a regular one.
+
 ## Roles and limits
 
 In `config.toml` each role gets a daily limit in minutes:
@@ -56,6 +96,7 @@ Login and every chat request are blocked once `used_today` reaches the limit.
 ./coder                               # or: python3 client.py
 python3 client.py 10.0.0.5:8420       # explicit daemon address
 python3 client.py --model qwen3-coder # skip the model picker
+python3 client.py --yes               # auto-approve every tool call (careful)
 python3 client.py --no-probe          # skip the reachability check (use behind
                                       # HTTP proxies that answer on every port)
 ```
@@ -66,7 +107,10 @@ ones, or add a new one (`n`). Every server you use is saved in
 model, so the next start is just Enter-Enter. Addresses without a port use
 8420; `host:port`, `http(s)://...` URLs and IPv6 literals are accepted.
 
-After login and model choice you get the agent banner and a chat REPL.
+After login and model choice you get the agent banner and a REPL. Type tasks,
+not chat messages — "rename the function foo to bar in all files" is a task,
+"what is a monad" is just a question the agent answers in place.
+
 Commands:
 
 | command       | effect                                  |
@@ -76,14 +120,23 @@ Commands:
 | `/models`     | list models on the server               |
 | `/model <n>`  | switch model (saved for this server)    |
 | `/limit`      | remaining minutes today (last known)    |
+| `/auto`       | toggle confirmations (auto-approve all) |
+| `/state`      | auto mode, project dir, history size    |
+| `/cwd`        | show the project directory              |
 | `/clear`      | forget the conversation history         |
 | `/quit`       | exit                                    |
 
-Anything else is sent to the model. The client keeps the last few turns as
-context (the daemon API itself is stateless) and renders the reply in the
-agent style (`✓` lines for actions the model reports).
+The agent keeps the last few finished tasks as context. It stops after 30
+model round-trips per task; the daemon API itself is stateless.
 
 ## Requirements
 
 - Python 3.11+ (stdlib only; `tomllib` is included)
 - ollama listening on the address from `config.toml`
+
+## Tests
+
+```bash
+python3 -m unittest test_client.py -v   # unit tests (no network)
+python3 test_e2e.py                     # fake ollama + daemon + client
+```