feat(proxy): engine-wide LLM admission control via vLLM gauges (#65)

Closes #64

Replaces the per-pod concurrency semaphore as the effective cap with admission gated on the vLLM engine's own scheduler gauges.

## Why

`internal/proxy/proxy.go:119` built a semaphore of 4 slots *inside each gateway process*, and `api-gateway` runs 3 replicas, so the advertised cap was 12 while the engine's `--max-num-seqs` is 4. Nothing coordinated replicas, and the mismatch was invisible because the queue never rejected anything (`queue_full_requests_total 0`).

Measured on the engine while investigating a 10-minute TTFT:

- `vllm:cache_config_info{num_gpu_blocks="9527",block_size="16"}` = **152,432 tokens** of KV capacity for the whole engine. PP=2 splits layers, so both ranks hold KV for the same tokens — not 2x that.
- Uncached prefill runs at **262 tok/s** contended, 525 tok/s over 7d (`vllm:request_prefill_time_seconds_sum/count`).
- One request showed `llm_ttft_seconds_sum 590.981 / count 5` at the gateway and a `(480, 960]` s entry in `vllm:request_prefill_time_seconds_bucket`, with engine-side generation throughput at 0.0-0.1 tok/s throughout: a 65k-token prompt costs ~250 s of prefill and starves every other request while it runs.
- `vllm:num_preemptions_total = 0`; KV peaked at `0.5399`.

Reading the engine's own gauges is global by construction, needs no lock and no new datastore, and it also accounts for callers that never pass the gateway — namespace `poimen` is admitted directly on 80/8080 by `llm-serving-ingress`, and `memory/crates/mem-cli/src/kv_warmer.rs` is such a caller. A distributed lock would have been blind to that traffic.

## Changes

- **new `internal/proxy/engine_state.go`** — 2s scrape of `http://<addr>/metrics` on its own client (the proxy transports carry socket options tuned for inference), hand-rolled exposition parse, `Healthy=false` after 3 consecutive failed polls with `engine_state_stale_total` counted once at the transition, and a startup self-check that raises `observer_degraded` and logs at error level instead of degrading to fail-open silently.
- **admission gate** (`internal/proxy/scheduler.go`) — parks while `kv_cache_usage_perc >= 0.90` or `running + waiting >= ADMISSION_MAX_INFLIGHT`, bounded by `ADMISSION_MAX_PARK_SECONDS`, then `503 + Retry-After: 5`. Unknown or unhealthy state fails **open** on purpose: a metrics outage must not become an inference outage.
- **parked streaming heartbeat** (`internal/proxy/proxy.go`) — `stream: true` requests get 200 + `text/event-stream` and a `: keep-alive` comment every 15s while parked, so a client idle timeout does not kill a request that is legitimately waiting. Non-streaming requests park silently.
- **`internal/proxy/router.go`** — extract only the top-level `model` field with a `json.Decoder` token walk instead of unmarshalling the whole body into `map[string]interface{}` (that built the entire `messages`+`tools` tree per request, ~300 KB for a 65k-token prompt). `MaxBodySize` now comes from `MAX_BODY_BYTES`; the model path previously inherited the 100 MB default at `proxy.go:93` against a 512Mi container limit.
- **`cmd/gateway/main.go`** — `GOMAXPROCS` from the cgroup CPU quota (cgroup v2 `cpu.max`, v1 fallback). The container is limited to `500m` while Go defaulted to the host core count and was being CFS-throttled.
- **`k8s/deployment.yaml`** — `ADMISSION_MAX_PARK_SECONDS=120`, `ADMISSION_OBSERVE_MODELS=reasoning`, `VLLM_MAX_QUEUE_DEPTH=8`, `MAX_BODY_BYTES=1048576`; corrected the `llm-client` comment (the NetworkPolicy selects by namespace now, not by that label).
- **deleted `k8s/configmap.yaml`** — absent from `k8s/kustomization.yaml`, and the live ConfigMap of that name carries an unrelated key (`gw-config-fixed.yaml`) plus a stale routing table.
- **`internal/observability/`** — `admission_parked_total`, `admission_rejected_total{reason}`, `engine_state_stale_total`, and gauges `vllm_requests_running` / `vllm_kv_usage_perc` (the gateway's own reading, deliberately mirroring the vLLM series so a disagreement is visible) and `observer_degraded`. Names follow the existing convention, which carries no prefix.

Out of scope here, in `riotpiao-poimen/homelab#51`: the engine flags (`--max-num-partial-prefills`, `--max-long-partial-prefills`, `--long-prefill-token-threshold`, `--max-num-batched-tokens`, `--max-num-seqs`, `--gpu-memory-utilization`) and the four dashboard panels in `generate-dashboards.py`.

## Verification

- `go build ./...` clean, `go vet ./...` clean.
- `go test ./...` — 368 tests, 0 failures (baseline on `main` is 368/0).
- `structural-check.sh` on the changed files — 0 errors, 1 pre-existing warning (`:latest` image tag).
- `go.mod` / `go.sum` byte-identical: no new dependency.

Not yet verified: the real-engine load test (2x65k + 15x8k against `reasoning`). That run also produces the number for `ADMISSION_MAX_PARK_SECONDS`, which today is the provisional 120; retuning it is a follow-up since it is env-only and needs no rebuild.

## Accepted risks

- **No tests were added** for the observer or the gate (deliberate: production is the test bed). The mitigation is the startup self-check, which is production self-diagnosis rather than a test, plus the `observer_degraded` alert. A parse failure that outlives the first poll logs and surfaces as a metric; it does not silently disable gating without a signal.
- **The cap is soft, not hard.** Between polls each replica may admit more than one request, so there is no clean bound. Exposure is low (~11,500 requests over 7d ≈ 1.4/min) and the engine remains the hard limit — a race parks requests in vLLM's queue rather than over-committing KV.
- **`ADMISSION_MAX_INFLIGHT` is manually coupled to `--max-num-seqs`** and can drift silently. It defaults to `VLLM_MAX_NUM_SEQS`, and startup logs the effective value.
- The first scrape waits one interval, so the first ~2s of admission is ungated (fail-open). Scraping at `Start()` instead would make the gateway contact every observed backend before any request needs one, which is wasted work and a surprising side effect.

## Rollback

Revert this commit and redeploy. The admission path is fail-open, so the code can also be neutralised without reverting by unsetting `ADMISSION_OBSERVE_MODELS`. Separately, the orphaned cluster object can be removed by hand: `kubectl delete cm -n api api-gateway-config` (not a code change, deliberately left to a human).

---------
Reviewed-on: #65
Co-authored-by: poimen <[email protected]>

k8s/deployment.yaml

@@ -21,9 +21,10 @@ spec:
       labels:
         app: api-gateway
         component: gateway
-        # Required by the llm-serving-default-deny NetworkPolicy, which admits
-        # only pods labelled llm-client=true (from any namespace) on port 8080.
-        # Without it every upstream dial times out and dispatch returns 502.
+        # The llm-serving-ingress NetworkPolicy in the llm-serving namespace now
+        # selects by namespace (kubernetes.io/metadata.name: api), not by this
+        # label. Kept for older NetworkPolicy revisions that still admit on
+        # llm-client=true.
         llm-client: "true"
       annotations:
         reloader.stakater.com/auto: "true"
@@ -67,6 +68,18 @@ spec:
           value: "5m"
         - name: LOG_LEVEL
           value: "info"
+        - name: ADMISSION_MAX_PARK_SECONDS
+          value: "120"
+        # Only backends that publish the vLLM scheduler gauges may be observed.
+        # `reasoning` is the only vLLM engine; ornith/qwen-cpu are Ollama and
+        # embeddings/rerank are TEI, so observing them would hold
+        # observer_degraded at 1 forever.
+        - name: ADMISSION_OBSERVE_MODELS
+          value: "reasoning"
+        - name: VLLM_MAX_QUEUE_DEPTH
+          value: "8"
+        - name: MAX_BODY_BYTES
+          value: "1048576"
         # OpenTelemetry tracing configuration
         - name: OTEL_EXPORTER_OTLP_ENDPOINT
           value: "otel-collector.tracing.svc.cluster.local:4317"