fix(llm): RateLimitError retryable + retry tenacity 3→5 + backoff fino a 30s

Run phase2-5-qwen25-prompt-mut-003 fallito a gen 5 (76 evals done, $0.061
spesi) per HTTP 429 RateLimit upstream da DeepInfra su qwen-2.5-72b.
RateLimitError NON era in _RETRYABLE_EXCEPTIONS quindi tenacity falliva
subito, propagando il 429 a propose() e all'orchestrator (run failed).

Tre fix:
1) Aggiunto openai.RateLimitError a _RETRYABLE_EXCEPTIONS.
2) Bumpato stop_after_attempt(3) → 5 e wait_exponential max 10s → 30s.
   Più tempo per il rate limit upstream di sbloccare prima di rinunciare.
3) hypothesis.py: try/except RateLimitError in propose() come per
   EmptyCompletionError — anche se tenacity esaurisce i 5 retry, il genome
   viene marcato fitness=0 e il loop esterno continua senza crash totale.

Test: aggiornato test_completion_retries_on_connection_error per
assert call_count == 5 (era 3). Tutti 182 verdi.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/multi_swarm/agents/hypothesis.py

@@ -3,6 +3,8 @@ from __future__ import annotations
 import re
 from dataclasses import dataclass, field
 
+import openai
+
 from ..genome.hypothesis import HypothesisAgentGenome
 from ..llm.client import CompletionResult, EmptyCompletionError, LLMClient
 from ..protocol.parser import ParseError, Strategy, parse_strategy
@@ -282,6 +284,12 @@ class HypothesisAgent:
                 errors.append(f"empty_completion: {e}")
                 last_raw = ""
                 continue
+            except openai.RateLimitError as e:
+                # Provider upstream rate limited oltre i retry tenacity.
+                # Marca genome come fallito senza propagare l'eccezione al run.
+                errors.append(f"rate_limit: {e}")
+                last_raw = ""
+                continue
             completions.append(completion)
             last_raw = completion.text
 

src/multi_swarm/llm/client.py

@@ -26,11 +26,14 @@ class EmptyCompletionError(RuntimeError):
     pass
 
 
-# Errori transient: retry. RateLimit/Auth/InvalidRequest: NO retry.
+# Errori transient: retry. Auth/InvalidRequest: NO retry.
+# RateLimitError (HTTP 429) ora retryable: provider OpenRouter come DeepInfra
+# applicano rate limit upstream temporaneo, recuperabile con backoff.
 _RETRYABLE_EXCEPTIONS: tuple[type[BaseException], ...] = (
     openai.APIConnectionError,
     openai.APITimeoutError,
     openai.InternalServerError,
+    openai.RateLimitError,
     EmptyCompletionError,
 )
 
@@ -79,8 +82,8 @@ class LLMClient:
         self._client = OpenAI(api_key=openrouter_api_key, base_url=openrouter_base_url)
 
     @retry(
-        stop=stop_after_attempt(3),
+        stop=stop_after_attempt(5),
-        wait=wait_exponential(multiplier=1.0, min=2.0, max=10.0),
+        wait=wait_exponential(multiplier=2.0, min=2.0, max=30.0),
         retry=retry_if_exception_type(_RETRYABLE_EXCEPTIONS),
         reraise=True,
     )

tests/unit/test_llm_client.py

@@ -75,7 +75,7 @@ def test_completion_retries_on_connection_error(mocker):
     with pytest.raises(openai.APIConnectionError):
         client.complete(g, system="sys", user="usr")
 
-    assert fake_openai.chat.completions.create.call_count == 3
+    assert fake_openai.chat.completions.create.call_count == 5
 
 
 def test_completion_uses_custom_model_tier_c(mocker):