Make proxy upstream response-header timeout configurable

[mkalkere]

Changelog title

Proxy upstream response-header timeout is now configurable

Changelog body

• nvpair-proxy accepts --response-header-timeout (or the NVPAIR_PROXY_RESPONSE_HEADER_TIMEOUT environment variable) to raise the 120 s default when engines queue requests or load models slowly. Invalid values log a warning and keep the default.

Bumps

• services: patch
• nvpair-cluster-manager: none
• nvpair-engine-manager: none
• nvpair-errors: none
• nvpair-job-scheduler: none
• nvpair-manual-nodes: none
• nvpair-node-info: none
• nvpair-node-scanner: none
• nvpair-node-settings: none
• nvpair-proxy: patch
• nvpair-tui: none
• nvpair-ui-broker: none
• nvpair-workload-manager: none

Summary

Rebased onto the unified services/nvpair-proxy. The 120 s
ResponseHeaderTimeout on the upstream transport is now configurable:
--response-header-timeout flag first, then
NVPAIR_PROXY_RESPONSE_HEADER_TIMEOUT, then the 120 s default. A missing,
unparseable, or non-positive value logs a warning and keeps the default, so
a bad setting can never silently disable the timeout.

firstBodyTimeout tracks the same resolved value, since both bound the same
wait — how long an engine may take to start its work. Documented in
docs/proxy-response-header-timeout.mdx (new) and
services/nvpair-proxy/spec.md; troubleshooting entry added for the
502-after-120-seconds symptom.

Test plan

• go build ./..., go vet ./... — clean
• gofmt -l — clean
• go test -race -count=1 . — full nvpair-proxy suite green
• header_timeout_test.go: TestResolveResponseHeaderTimeout (flag >
  env > default precedence; invalid, zero, and negative values fall back),
  TestProxyTransportUsesConfiguredHeaderTimeout (the configured value
  reaches transports built after startup)

[Noah-Tervalon-Nvidia]

Heads up — develop has just taken a change that merges the Ollama and LM Studio
proxies into a single nvpair-proxy process, hosting one facade per enabled
engine. services/ollama-proxy/ and services/lmstudio-proxy/ are gone.

This PR edits files in those directories, so it will need updating before it can
merge. The good news is that the client-facing ollama-proxy: and
lmstudio-proxy: namespaces are unchanged — only the process behind them moved —
so the change should port across to services/nvpair-proxy/ fairly directly.

Apologies for the churn, and thanks for the contribution. Happy to help work out
where it lands if it isn't obvious.

[mkalkere]

Rebased onto the unified layout and pushed. The configurable header timeout is ported across to services/nvpair-proxy/:

• --response-header-timeout flag, then NVPAIR_PROXY_RESPONSE_HEADER_TIMEOUT, then the 120 s default; invalid values warn and keep the default.
• firstBodyTimeout tracks the same resolved value, since both bound the same wait.

Details in docs/proxy-response-header-timeout.mdx.