fix(gateway): close billing, limit, routing and translation gaps

Billing:
- Passthrough SSE streams now bill the usage the upstream reports.
  The gateway falls back to a request-size estimate only on a 2xx
  stream or a truncated JSON body.
- A unified stream that fails after it starts is estimated, not
  billed at zero.
- Billing uses the built-in LiteLLM price table and honours
  modelMeta free: true.
- Pricing entries are validated. Cost arithmetic rounds the total and
  saturates on overflow.
- Gemini thinking tokens count as completion tokens.

Limits and storage:
- A rejected request rolls back its counts on the other scopes, so one
  user cannot lock out a group.
- Redis EXPIRE replies are checked. Keys recreated without a TTL are
  repaired at once.
- A mutating pipeline is not retried after reply bytes arrive.
- History, model totals and target usage report a store outage.

Routing and translation:
- Discovered ids with a provider-like prefix are listed only in
  owner/id form, so listing and routing agree.
- Anthropic and Gemini discovery follows pagination.
- The developer role maps to system.
- stream_options.include_usage is honoured on translated streams.
- tool_choice none keeps tools when history holds tool blocks.
- refusal maps to content_filter. Data URI parameters are stripped.

Streaming, retry and failover:
- SSE accepts CR, LF and CRLF line ends. This closes a CR injection
  path.
- Retry-After is never jittered. A cancelled wait returns the
  context error.
- The watchdog timer stops at end of body.
- Oversized bodies return 413.
- A failed stream ends with an error event.
- Failover restores pre-existing headers. Client cancels do not count
  as provider successes.

Also: "admin" is a reserved provider name. metrics.path must start
with "/". Pricing warnings go to the right gateway instance. The admin
targets view sends access as null or [] so the two states differ.
Upstream organisation headers are stripped. The users-file reload
error is logged once per error. Dead code is removed, and test-only
helpers move to test files.

Claude-Session: https://claude.ai/code/session_01V5jYJNxpDFdJkyyExpADrv

target_health_test.go

@@ -15,6 +15,31 @@ import (
 	"github.com/stretchr/testify/require"
 )
 
+// stateOf reports (kind, name)'s current targetHealthState — see
+// targetHealthState's own doc comment (target_health.go) for the exact
+// unknown/healthy/unhealthy rule. Test-only (finding 18 fix, review-
+// routes.md): it has zero production call sites — every production
+// reader goes through snapshot (admin.go's targets view, metrics.go),
+// which already applies the identical stateForLocked rule this helper
+// reuses — so it was moved here from target_health.go rather than kept
+// as unused production API surface. Every test in this package that
+// wants a bare state value (not snapshot's fuller struct) uses this,
+// including mcp_a2a_test.go and mcp_federation_test.go, which reach it
+// as an ordinary package-scoped method the same way they would if it
+// still lived in the non-test file.
+func (t *targetHealthTracker) stateOf(kind, name string) targetHealthState {
+	if t == nil {
+		return targetHealthUnknown
+	}
+	t.mu.Lock()
+	defer t.mu.Unlock()
+	e, ok := t.entries[targetHealthKey{kind: kind, name: name}]
+	if !ok {
+		return targetHealthUnknown
+	}
+	return t.stateForLocked(e)
+}
+
 // --- targetHealthTracker: state machine ---
 
 func TestTargetHealthTracker_NeverRecorded_ReadsUnknown(t *testing.T) {