Stop CI running two suites at once, and retry rate limits

CI failed on the delegation branch with a 429 from the proxy: token
limit 200000, 17399 remaining. Not a defect — the live delegation
tests are token-hungry, and every push to a PR branch fired two
identical suites concurrently, since the push and pull_request events
both matched.

- Push now only triggers on main. A PR branch is already covered by
  the pull_request event, so this halves both the wall time and the
  tokens spent per branch
- A 429 is retried once before being surfaced. Losing a ten-turn
  delegation to a transient limit wastes far more than waiting out
  the window, and retrying forever would hide a real ceiling. The
  sleep is injectable, so the existing 429 test no longer waits 20
  seconds for real

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

nisse-dev/src/nisse_dev/llm.py

@@ -12,6 +12,7 @@ config change cannot split a task across two planners.
 
 import json
 import os
+import time
 from collections.abc import Mapping
 from dataclasses import asdict, dataclass
 from typing import Any, ClassVar, Protocol
@@ -33,6 +34,14 @@ class LLMError(RuntimeError):
     pass
 
 
+# A rate limit is a transient condition, not a bad request. Losing a
+# ten-turn delegation to one wastes far more tokens than waiting out the
+# window, so retry once before surfacing it (A13's caps still bound the
+# total).
+RATE_LIMIT_STATUS = 429
+RATE_LIMIT_RETRY_S = 20.0
+
+
 class LLMClient(Protocol):
     def complete(
         self,
@@ -82,6 +91,7 @@ class LiteLLMClient:
         *,
         timeout_s: float = 120.0,
         transport: httpx.BaseTransport | None = None,
+        sleep: Any = time.sleep,
     ) -> None:
         self._http = httpx.Client(
             base_url=base_url.rstrip("/"),
@@ -90,6 +100,7 @@ class LiteLLMClient:
             transport=transport,
         )
         self._renderer = OpenAIChatRenderer()
+        self._sleep = sleep
 
     @classmethod
     def from_env(cls, env: Mapping[str, str] = os.environ) -> "LiteLLMClient":
@@ -107,10 +118,9 @@ class LiteLLMClient:
         system: str | None = None,
     ) -> list[CanonicalEvent]:
         body = self._renderer.render(events, tools, model, system=system)
-        try:
-            response = self._http.post("/chat/completions", json=body)
-        except httpx.HTTPError as exc:
-            raise LLMError(f"LLM request failed: {exc}") from exc
+        response = _post_with_rate_limit_retry(
+            self._http, "/chat/completions", body, self._sleep
+        )
         if response.status_code != 200:
             raise LLMError(
                 f"LLM request returned {response.status_code}: {response.text[:500]}"
@@ -176,6 +186,7 @@ class AnthropicPassthroughClient:
         timeout_s: float = 300.0,
         max_tokens: int = 4096,
         transport: httpx.BaseTransport | None = None,
+        sleep: Any = time.sleep,
     ) -> None:
         self._http = httpx.Client(
             base_url=base_url.rstrip("/"),
@@ -189,6 +200,7 @@ class AnthropicPassthroughClient:
         )
         self._renderer = AnthropicMessagesRenderer()
         self._max_tokens = max_tokens
+        self._sleep = sleep
 
     @classmethod
     def from_env(
@@ -210,10 +222,9 @@ class AnthropicPassthroughClient:
         body = self._renderer.render(
             events, tools, model, system=system, max_tokens=self._max_tokens
         )
-        try:
-            response = self._http.post("/v1/messages", json=body)
-        except httpx.HTTPError as exc:
-            raise LLMError(f"passthrough request failed: {exc}") from exc
+        response = _post_with_rate_limit_retry(
+            self._http, "/v1/messages", body, self._sleep
+        )
         if response.status_code != 200:
             raise LLMError(
                 f"passthrough returned {response.status_code}: {response.text[:500]}"
@@ -251,3 +262,17 @@ class AnthropicPassthroughClient:
 
     def close(self) -> None:
         self._http.close()
+
+
+def _post_with_rate_limit_retry(
+    http: httpx.Client, path: str, body: dict[str, Any], sleep: Any
+) -> httpx.Response:
+    for attempt in (1, 2):
+        try:
+            response = http.post(path, json=body)
+        except httpx.HTTPError as exc:
+            raise LLMError(f"LLM request failed: {exc}") from exc
+        if response.status_code != RATE_LIMIT_STATUS or attempt == 2:
+            return response
+        sleep(RATE_LIMIT_RETRY_S)
+    raise AssertionError("unreachable")