Add read-only introspection endpoints: /health, /info, /config

[shagghiesuperstar]

What

Three small read-only HTTP endpoints on the ds4-server for operators, dashboards, and load balancers that need server state without paying for a model call:

GET /health   status, uptime, in-flight clients, context, model, kv cache
GET /info     engine identity snapshot
GET /config   read-only reflection of server_config

Sample response (live ds4-server):

{"status":"ok","uptime_s":9,"clients_in_flight":1,"context_length":131072,"default_max_tokens":393216,"model":"DeepSeek V4 Flash","kv_cache":{"enabled":true,"dir":"/Volumes/OWC_MODELS_TB5/DS4/cache","budget_bytes":53687091200}}

Why

The server previously exposed only the OpenAI/Anthropic endpoints and /v1/models. There is no way for an operator to ask "is this server healthy?" or "what is the active context length?" without either issuing a chat call (expensive) or scraping /v1/models (wrong shape, counts as a model registry hit).

Downstream consumers (a small open-source web dashboard I maintain, shagghiesuperstar/ds4-dashboard) currently fall back on speculative probes (/telem, /metrics) that always 404. /health makes that path deterministic.

How

• start_time (time_t) added to struct server, set in main() next to the other init lines.
• Three send_* helpers added right after send_models/send_model, mirroring their style: buf assembly, http_response, no allocations past buf, no model access.
• Three new dispatch branches in client_main, placed before the /v1/models/ prefix branch so /health, /info, /config cannot be shadowed.
• All fields used are already exposed through public ds4 engine API or directly on struct server. No new headers, no new dependencies.

Tested

• make ds4-server clean (no warnings under -Wall -Wextra -std=c99).
• ./ds4_test --server passes (added two new unit tests covering dispatch disjointness and JSON shape).
• Live-tested against a running ds4-server:
  • GET /health, GET /info, GET /config return valid JSON.
  • GET /v1/models and POST /v1/chat/completions unchanged.
  • Unknown paths still return 404.

Diff size

151 lines added (150 in ds4_server.c, 1 in .gitignore for the test_q4k_dot test binary that was missing from the ignore list).

Happy to split into separate PRs per endpoint, or rename them (/v1/health, etc.) if you'd prefer them grouped under a versioned prefix.

[shagghiesuperstar]

Following up with a purely technical angle prompted by ecosystem activity:

PR #374 (mcmalayalam's /health for llama-swap integration) landed recently — it adds a minimal health endpoint specifically because llama-swap needed a way to know when DS4 is ready to serve. That's independent, third-party confirmation that these endpoints aren't hypothetical: the ecosystem already hit the wall without them.

This PR extends beyond #374's scope in two ways that matter for production deployments:

/info — Client-side model discovery without hitting /v1/models. Any orchestrator (llama-swap, OpenRouter-style routers, multi-instance load balancers) needs to know context_length and default_max_tokens before sending requests. Currently they have to either parse CLI flags or probe via a chat completion — both fragile.

/config — Configuration-drift detection across multi-instance fleets. In any deployment with >1 server instance, you need to verify that all instances share identical config. Without a read-only config reflection endpoint, the only way to check is comparing launchd plists or CLI invocations — error-prone and unobservable at runtime.

All three endpoints remain zero-cost (no inference, no allocations beyond buf, no model access) — same footprint as the existing dispatch logic.

If you'd prefer a narrower merge, I can rebase to just /info and /config since #374 already covers the basic health-check. Either way, the code is written and tested.