Merge dev into dual-ssd-mirror: resolve #298/#192-era conflicts

Combined resolution: mir_pread/st_prefetch_rep (this PR) now carry dev's
DISK-CLASS accounting unwind (dc_wall_exit) and O_DIRECT prefetch skip
(g_direct); direct-path keeps dc_direct=1 plus the mirror read counters.
Verified: clean build, token-exact tiny models unchanged, test_st_mirror
and test_st_pread pass.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

docs/ENVIRONMENT.md

@@ -114,6 +114,15 @@ Per-drive byte counts are reported in a `MIRROR:` stats line. Combine with `DIRE
 | `COLI_CUDA_SHARED_W4A16_MIN_ROWS` | `32` | Min row count to engage the shared-MLP W4A16 kernel. |
 | `COLI_METAL_UNTRACKED` | off (Metal only) | `=1` sets `MTLResourceHazardTrackingModeUntracked` on Metal buffers (reduces hazard-tracking overhead). |
 
+> **Windows note.** On Windows, a bare `coli chat` / `coli run` / `coli serve`
+> (no `--gpu`/`--vram`/`--auto-tier`) **auto-enables the GPU** when it detects a
+> CUDA build (`coli_cuda.dll` next to the engine) and at least one GPU via
+> `nvidia-smi`. The expert-tier VRAM budget is then sized automatically from the
+> card's free VRAM (same computation as `--auto-tier`). If `nvidia-smi` is not on
+> `PATH` the run falls back to CPU with a warning — pass `--vram N` (or add
+> `nvidia-smi` to `PATH`) to enable CUDA in that case. `--gpu none` forces
+> CPU-only. (Linux/macOS behaviour is unchanged: pass a flag to enable CUDA.)
+
 ---
 
 ## Advanced / experimental / debug

docs/grammar-draft.md

@@ -83,3 +83,27 @@ this implementation adds: forced spans as a **draft source verified in the targe
 own forward** (lossless even under a wrong grammar, composes with MTP/n-gram in one
 union batch), deployed where the win is denominated in expert I/O rather than
 forward passes.
+
+## Server usage: `response_format` (OpenAI API)
+
+The gateway (`openai_server.py`) turns `response_format` into a **per-request**
+grammar carried to the engine over the `SUBMIT` protocol (optional 7th header
+field, `gbytes`; 6-field headers from older clients remain valid — the field is
+additive and back-compatible in both directions):
+
+```jsonc
+{"response_format": {"type": "json_object"}}                       // generic JSON grammar
+{"response_format": {"type": "json_schema",
+                     "json_schema": {"schema": { ... }}}}          // compiled by schema_gbnf.h
+{"response_format": {"type": "gbnf", "grammar": "root ::= ..."}}   // raw GBNF (extension)
+```
+
+Semantics are identical to `GRAMMAR=`/`SCHEMA=`: a **draft source, never a
+sampling constraint**. A schema outside the supported subset, or malformed GBNF,
+costs the speedup — never the request, never the output. Drafting engages for
+greedy requests (`temperature: 0`); sampled requests run undrafted. Compile
+overhead is negligible: ~8 µs/request for a typical schema, ~18 µs at the
+32-level nesting cap (measured, M3 Max). Grammar payloads are capped at 1 MiB.
+As with MTP (#100), a drafted greedy run may differ from an undrafted one in
+near-tie tokens (the verify forward has a different batch shape); each output
+is a valid greedy stream of its own forward shapes.

docs/quickstart.md

@@ -42,11 +42,31 @@ engine needs.
 You have two options.
 
 **Option A — download a prebuilt binary (no compiler needed).**
-Grab the latest `colibri-<version>-windows-x86_64.zip` from the
-[Releases page](https://github.com/JustVugg/colibri/releases), unzip it, and
-skip to [step 3](#3-get-the-model). Python 3 (from
-[python.org](https://www.python.org/downloads/)) is still needed if you want to
-convert a model yourself.
+Grab `colibri-<version>-windows-x86_64.zip` from the
+[Releases page](https://github.com/JustVugg/colibri/releases) and unzip it.
+Inside you'll find:
+
+| File | What it is |
+|---|---|
+| `colibri-<version>-windows-x86_64.exe` | **the engine** — the C program that actually runs the model |
+| `coli` | the command-line launcher (`chat`, `serve`, `convert`, `doctor`, …) |
+| `openai_server.py`, `resource_plan.py`, `doctor.py` | Python support for the API server and placement planner |
+
+Two setup steps:
+
+1. **Rename the engine to `glm.exe`** so the launcher can find it (it looks for a
+   binary named `glm`):
+   ```powershell
+   Rename-Item colibri-*-windows-x86_64.exe glm.exe
+   ```
+2. **Install Python 3** from [python.org](https://www.python.org/downloads/) — the
+   `coli` launcher and the API gateway are Python scripts (the engine itself is
+   pure C and needs nothing).
+
+Then continue to [step 3](#3-get-the-model). Prefer to skip the launcher? You can
+run the engine directly — `.\glm.exe` reads the model path from the `SNAP`
+environment variable (see [docs/windows.md](windows.md)) — but `coli chat` is the
+easy path.
 
 **Option B — build from source with MSYS2.**
 Install [MSYS2](https://www.msys2.org/), open the **UCRT64** shell, and run: