智能体级联：终端自己挑出还活着的那个

$ agent --status
  OK   claude / claude-opus-5         api.anthropic.com reachable, claude-opus-5 answered
  OK   claude / claude-sonnet-5       api.anthropic.com reachable, claude-sonnet-5 answered
  OK   claude-proxy / claude-opus-5   claude-opus-5 answered
  OK   claude-proxy / claude-sonnet-5 claude-sonnet-5 answered
  OK   agy                            antigravity answered on Gemini 3.6 Flash (Low)
  OK   gemini                         localhost:8317 answered for gemini-3.1-pro-low

# Each rung: backend | model to probe | model to run with
# An empty run-model means "let the CLI use its configured default", which keeps
# the profile's opus[1m] (and its 1M context) instead of downgrading it to plain
# opus just to name it explicitly.
RUNGS=(
  "claude|$AGENT_OPUS_MODEL|"
  "claude|$AGENT_SONNET_MODEL|sonnet"
  "claude-proxy|$AGENT_OPUS_MODEL|$AGENT_OPUS_MODEL"
  "claude-proxy|$AGENT_SONNET_MODEL|$AGENT_SONNET_MODEL"
  "agy||"
  "gemini||"
)

$ agent -p "explain this bug"
[agent] Claude Code (claude-opus-5) unavailable — claude-opus-5 unavailable: {"error":...}
[agent] using Claude Code (claude-sonnet-5)

# ...the session continues on Sonnet, inside Anthropic, with no vendor switch.

# Real /v1/messages call for ONE model. This is what distinguishes "Opus is
# capped" from "Anthropic is down" — no model list can tell you that.
probe_model() {
  local m="$1" body
  body=$(curl -sS --max-time "$PROBE_TIMEOUT" \
    "$AGENT_PROXY_URL/v1/messages" \
    -H "Authorization: Bearer $AGENT_PROXY_KEY" \
    -H 'content-type: application/json' \
    -d "{\"model\":\"$m\",\"max_tokens\":1,\"messages\":[{\"role\":\"user\",\"content\":\"hi\"}]}")
  case "$body" in
    *'"type":"message"'*) REASON="$m answered"; return 0 ;;
  esac
  REASON="$m unavailable: $(printf '%s' "$body" | tr -d '\n' | cut -c1-140)"
  return 1
}

start=$SECONDS
run_rung "$backend" "$rmodel" "$@"
rc=$?
elapsed=$(( SECONDS - start ))

# Clean exit, or the user interrupted it — either way, done.
if [ $rc -eq 0 ] || [ $rc -eq 130 ]; then
  exit $rc
fi

# Survived long enough to have been genuinely used: a real error, not a rung
# that never started. Do not silently rerun the work somewhere else.
if [ $elapsed -ge $FASTFAIL_SECONDS ]; then
  exit $rc
fi

warn "$(label "$backend" "$pmodel") exited $rc after ${elapsed}s — treating as unavailable"

# Healthy — every non-Anthropic rung answers
$ agent --check-fallback
all provider-independent fallbacks OK: agy — antigravity answered...; gemini — ...
rc=0

# One rung rotted while the other still works. This is the case that used to
# pass silently, and the whole reason the check exists.
$ GEMINI_API_KEY=broken agent --check-fallback
DEGRADED: still covered by agy — antigravity answered on Gemini 3.6 Flash (Low)
but a rung died: gemini — gemini call failed: {"error":"Invalid API key"}
rc=1

agent                          # auto-pick the best live rung
agent --use gemini             # force a backend
agent --use claude:sonnet      # force a backend AND a model
agent --use claude-proxy:opus  # opus/sonnet/haiku map to full ids per backend
agent --list                   # backend names
agent --status                 # probe every rung and report
agent --check-fallback         # exit 1 if a non-Anthropic rung is missing

agent -p "..."                 # flags pass straight through to the chosen CLI