mcp-config/hermes: make the gateway's context limits actually reach the clients

Folds in the in-flight local-checkout work and fixes the context accounting
on top of it. Both halves are the same bug seen from two ends: clients were
sending requests larger than the backend's window and getting hard
ContextWindowExceededError 400s, intermittently, in a way that looked like
the model or the GPU misbehaving.

Already in flight here (unchanged in intent):
  - sync.sh prefers the LOCAL CHECKOUT over re-downloading from Gitea, and
    install.sh records the checkout path so it can be found. That recording
    is load-bearing: without it sync.sh cannot find the repo, silently falls
    back to Gitea, and every local edit to opencode.gateway.json is ignored.
    Observed on this box — ~/.config/mcp-sync/source did not exist, the
    default ~/.dotfiles is not where the checkout lives, and the Gitea base
    still served models:{}.
  - the hermes custom-provider wiring.

Fixed on top:

opencode had NO context limit on ANY gateway model, not a wrong one. Two
faults compounded. /model/info 403s for a day-to-day virtual key (only
management-scoped keys may read it), which sync.sh treats as best-effort and
falls back to names-only — as designed and as commented. But the merge then
did `prov["models"] = models`, replacing the map wholesale, so limits
declared in the base config were discarded too and there was no floor left.
Base specs are now a floor that live /model/info overrides field by field:
discovery still wins where present, so this adds no drift, and a 403 no
longer strips the limits. Verified: ornith 195584/32768, the qwens
261120/32768.

hermes' model map named `qwen3-vl-30b-a3b` at 262144 — a model the gateway
stopped serving when Ornith replaced it — while ornith-1.0-35b, the model
actually on cg-1 AND the only one with a window smaller than its neighbours
(196608), had no entry at all and inherited Hermes' default. The one model
needing a lower ceiling was the one not declaring one, which is exactly the
shape that fails only once a session grows.

NOTE for other boxes: hermes reads ~/.hermes/config.yaml, which install.sh
produces by MERGING gateway.yaml. Editing gateway.yaml alone changes nothing
until install.sh re-runs — this machine's live config was patched by hand.

Not addressed here, deliberately: the gateway-side context_window_fallback
(ai-k8s-iac). It is wired but inert while cg-2 is scaled down, so preventing
the oversized request client-side is what actually works today.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FoDK4wwB1Twty5gwiriYLf

skills/README.md

@@ -6,8 +6,11 @@ points opencode at it via `skills.paths`.
 
 Unlike models and MCP servers — which are discovered from the LiteLLM gateway
 at sync time — skills are plain files with nothing on the gateway to query, so
-**this repo is the source of truth**. Add a skill here, push to `main`, and it
-lands everywhere within the sync TTL (~1h, or immediately on a new shell).
+**this repo is the source of truth**. They are copied from the local checkout
+(the same source as the gateway config — see "Where the config comes from" in
+`mcp-config/README.md`), so no anonymous read of this repo is required. Add a
+skill here, push to `main`, and it lands everywhere within the sync TTL (~1h,
+or immediately on a new shell) once the checkout picks the commit up.
 
 > LiteLLM's `/v1/skills` is *not* an alternative: it is a passthrough to
 > Anthropic's Skills API (`?beta=true`), which lists skills on an Anthropic