docs: bring README + docs area up to date (engines, RunPod, OCR, speech, embeddings)

The README had not been touched since the OCR/multi-engine work in August and
described roughly half of what the server does. Add the missing subsystems and
correct the ones that overstated the code:

- Inference engines: the per-model backend matrix (transformers/gguf/ds4/
  colibri/k3/kt/vllm/runpod) and how one is selected.
- RunPod: feature summary plus a full docs/runpod.md — pods vs serverless,
  per-model config keys, cold start, GPU fallback, stuck-boot retry, budgets
  and the ledger, the stale-pod reaper, spillover (with its real scope),
  observability and RunPod-only deployments.
- STT backends, per-model languages/translation, word timestamps, diarization
  and enrolled speaker recognition; embeddings families (BGE-M3 multi-vector,
  GME-Qwen2-VL, GeoCLIP, VPR) and /v1/rerank; the OCR subsystem and its
  schema store; LoRA training.
- API tables for /v1/ocr*, /v1/rerank, /v1/loras*, the audio/speaker routes
  and the two missing pipelines.
- models.json reference incl. multi-config (config_id/alias), the front/engine
  split, optional-subsystem requirements files, and a docs/ index.

Honesty fixes: /v1/pipelines/audio-music-dub is flagged as incomplete (only
the transcription step runs); spillover is documented as serverless-target /
direct-path only.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01R6iugoNeEgt9PkajKrFyq4

docs/README.md

+# CoderAI documentation
+
+Subsystem guides. The [top-level README](../README.md) is the overview and API
+reference; these are the deep dives.
+
+## Serving engines
+
+| Doc | Subject |
+|---|---|
+| [frontend-engine-split.md](frontend-engine-split.md) | The torch-free front proxy, engine subprocesses, routing and assignment |
+| [gguf-process-isolation.md](gguf-process-isolation.md) | Running GGUF models in isolated processes |
+| [process-isolation-plans.md](process-isolation-plans.md) | Design notes on isolation strategies |
+| [vllm.md](vllm.md) | vLLM as a first-class engine node (isolated venv, CUDA-only) |
+| [deepseek-ds4.md](deepseek-ds4.md) | DeepSeek-V4 via antirez's ds4 / DwarfStar |
+| [glm-colibri.md](glm-colibri.md) | GLM-5.2 (and DeepSeek-V4 / Kimi-K3) via the colibri C engine |
+| [kimi-k3.md](kimi-k3.md) | Kimi-K3 on CPU via kimi-k3-in-c |
+| [ktransformers.md](ktransformers.md) | ktransformers / SGLang CPU+GPU heterogeneous MoE |
+| [runpod.md](runpod.md) | Renting remote GPUs: pods, serverless, budgets, the reaper, spillover |
+
+## Subsystems
+
+| Doc | Subject |
+|---|---|
+| [ocr.md](ocr.md) | The `/v1/ocr` document-transcription subsystem |
+| [expressive-tts.md](expressive-tts.md) | Expressive text-to-speech |
+| [zimage-lora-training.md](zimage-lora-training.md) | LoRA training for image models |
+| [dtype-auto-selection.md](dtype-auto-selection.md) | How model dtype is chosen automatically |
+
+## Deployment
+
+| Doc | Subject |
+|---|---|
+| [reverse-proxy-nginx.md](reverse-proxy-nginx.md) | nginx at root, on a subdomain, or under a sub-path |