Merge pull request 'Rate-limit only LLM-bound chat turns' (#3) from fix/rate-limit-llm-only into main

README.md

@@ -60,7 +60,7 @@ key stays on the server: it never goes to the browser, never into the repo, and
 | `AGENT_MARKET_LLM_MODELS` | comma-separated fallback chain, tried in order |
 | `AGENT_MARKET_LLM_TIMEOUT` / `_BUDGET` | hard cap per model attempt (12 s) and for the whole chain (28 s) |
 | `AGENT_MARKET_LLM_COOLDOWN` | how long a model that returned 429 gets skipped (60 s) |
-| `AGENT_MARKET_CHAT_RPM` / `_BURST` | per-IP token bucket on `/api/chat` (12/min, burst 6). `CF-Connecting-IP` is trusted only from loopback, i.e. the tunnel. |
+| `AGENT_MARKET_CHAT_RPM` / `_BURST` | per-IP token bucket on `/api/chat` turns that reach the LLM (12/min, burst 6). Deterministic UI events aren't limited. `CF-Connecting-IP` is trusted only from loopback, i.e. the tunnel. |
 
 `deploy.sh` loads `~/.config/agent-market/llm.env` and `~/.config/agent-market/<env>.env` if they exist. Both
 sit outside the repo. The box runs OpenRouter free models:

server.py

@@ -312,7 +312,9 @@ class H(BaseHTTPRequestHandler):
             return self._json(200, self._webhook(body))
         actor = self._actor(body)
         if path == "/api/chat":
-            ok, retry = rate_ok(self._client_ip())
+            # Only free-text turns reach the LLM; deterministic UI events (clicks, payments) are not limited.
+            llm_bound = not isinstance(body.get("event"), dict) or A.LLM_EVENTS
+            ok, retry = rate_ok(self._client_ip()) if llm_bound else (True, 0)
             if not ok:
                 return self._json(429, {"error": "rate_limited", "retry_after": retry, "agent": "rate-limit",
                                         "reply": f"You're sending messages quickly. Please wait about {retry}s and try again.",

tests/llm_proxy_check.sh

@@ -29,6 +29,8 @@ assert d["agent"]=="fallback" and d["llm_error"]=="all_models_failed" and d["act
 print("PASS all models rate-limited -> rule-based agent still renders", [a["type"] for a in d["actions"]])'
 curl -s localhost:18800/api/status | python3 -c '
 import json,sys; a=json.load(sys.stdin)["agent"]; assert set(a["cooling_down"])=={"busy-model","busy-model-2"}, a; print("PASS 429ed models put on cooldown")'
-CODES=$(for i in 1 2 3 4 5; do curl -s -o /dev/null -w '%{http_code} ' localhost:18801/api/chat -H 'Content-Type: application/json' -H 'CF-Connecting-IP: 203.0.113.9' -d '{"event":{"type":"landing"}}'; done)
-OTHER=$(curl -s -o /dev/null -w '%{http_code}' localhost:18801/api/chat -H 'Content-Type: application/json' -H 'CF-Connecting-IP: 203.0.113.10' -d '{"event":{"type":"landing"}}')
+CODES=$(for i in 1 2 3 4 5; do curl -s -o /dev/null -w '%{http_code} ' localhost:18801/api/chat -H 'Content-Type: application/json' -H 'CF-Connecting-IP: 203.0.113.9' -d '{"message":"show me bikes"}'; done)
+OTHER=$(curl -s -o /dev/null -w '%{http_code}' localhost:18801/api/chat -H 'Content-Type: application/json' -H 'CF-Connecting-IP: 203.0.113.10' -d '{"message":"show me bikes"}')
+EV=$(curl -s -o /dev/null -w '%{http_code}' localhost:18801/api/chat -H 'Content-Type: application/json' -H 'CF-Connecting-IP: 203.0.113.9' -d '{"event":{"type":"landing"}}')
+[[ "$EV" == "200" ]] && echo "PASS UI events (no LLM call) not rate-limited" || { echo "FAIL event limited: $EV"; exit 1; }
 [[ "$CODES" == "200 200 200 429 429 " && "$OTHER" == "200" ]] && echo "PASS per-IP rate limit (burst 3: $CODES; other IP $OTHER)" || { echo "FAIL rate limit: $CODES / $OTHER"; exit 1; }