docs: restructure around source-of-truth pages

- CONTEXT.md glossary
- README reduced to intro, quickstart and doc index
- new architecture.md, gateway.md (from proxy-key-onboarding.md),
  operations.md; network-access.md rewritten
- coding-cli-setup: stale OMNIROUTE_PORT:-4000 endpoint, terms and
  duplicated per-slot/classifier explanations fixed
- research/README.md index; proxy-request-priority.md moved there as
  superseded

Every doc names keys instead of restating values and links its source.

Refs #55 (#56, #57, #59, #60)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

docs/coding-cli-setup/opencode.md

@@ -2,6 +2,8 @@
 
 [← back to overview](index.md)
 
+> **Source of truth:** [OpenCode's docs](https://opencode.ai/docs/) for config keys; the [overview](index.md) for the gateway endpoint and context size. If this page disagrees with them, they win.
+
 Confirmed project: **`anomalyco/opencode`** (renamed from `sst/opencode` — don't confuse with the unrelated `opencode-ai/opencode` Go TUI). Docs: https://opencode.ai/docs/
 
 **Install**:
@@ -15,17 +17,17 @@ curl -fsSL https://opencode.ai/install | bash
 {
   "$schema": "https://opencode.ai/config.json",
   "provider": {
-    "aiproxy": {
+    "llm-server": {
       "npm": "@ai-sdk/openai-compatible",
-      "name": "AI proxy (local)",
+      "name": "LLM-Server gateway",
       "options": {
-        "baseURL": "http://<ai-box>:${OMNIROUTE_PORT:-4000}/v1",
-        "apiKey": "<opencode-cli virtual key>"
+        "baseURL": "http://<server>:<OMNIROUTE_API_PORT>/v1",
+        "apiKey": "<opencode-cli API key>"
       },
       "models": {
         "qwen3.8-27b-local": {
           "name": "Qwen3.8-27B",
-          "limit": { "context": 131072, "output": 8192 }
+          "limit": { "context": <LLAMA_CTX_SIZE / LLAMA_PARALLEL>, "output": 8192 }
         }
       }
     }
@@ -33,13 +35,13 @@ curl -fsSL https://opencode.ai/install | bash
 }
 ```
 
-Set `limit.context` to the *per-slot* context this stack actually serves — `LLAMA_CTX_SIZE / LLAMA_PARALLEL` from `.env` (262144 / 2 = 131072 by default), not raw `LLAMA_CTX_SIZE` and not a value assumed from the model card: llama.cpp divides `--ctx-size` across concurrent slots, so each request only gets one slot's share. OpenCode uses this for its own context-management bookkeeping, not the server.
+`limit.context` is the per-slot context ([overview](index.md)). OpenCode uses it for its own context bookkeeping; the server doesn't read it.
 
-Select the model with `aiproxy/qwen3.8-27b-local`.
+Select the model with `llm-server/qwen3.8-27b-local`.
 
 **OpenCode-specific risks** (on top of the shared Qwen3.8-27B tool-calling risk — see [overview](index.md)):
-- Requires llama.cpp's `--jinja` flag (already set) — without it, OpenCode's unconditional tool-call scaffolding gets a 500.
+- Relies on the backend's `--jinja` flag ([architecture → llama-server](../architecture.md#llama-server)); without it, OpenCode's unconditional tool-call scaffolding gets a 500.
 - [anomalyco/opencode#20669](https://github.com/anomalyco/opencode/issues/20669) (closed as "not planned" — a live, unfixed risk): OpenCode's `bash` tool crashes if the model omits the optional `description` field on a tool call; some local backends return `finish_reason: tool_calls` with an empty array, which can hang the agent loop instead of stopping cleanly.
 - Thinking-mode handling (`options.reasoningEffort`) is undocumented for models that emit inline `<think>` tags rather than a native reasoning API field — expect no effect from that config on this model; untested.
 
-Further reading: `docs/research/opencode-cli-setup.md`.
+Further reading: [`research/opencode-cli-setup.md`](../research/opencode-cli-setup.md) (its base URL example predates the gateway), [`research/opencode-auto-compact.md`](../research/opencode-auto-compact.md).