Bump default max_tokens for AI agents from 2000 to 8192

The 2000-token default in _get_max_tokens() was causing the history
agent to fail with "Model token limit (2000) exceeded before any
response was generated" on histories with more than a handful of
datasets. The cap was an artifact of an earlier era -- every backend
we currently support (Maverick / Llama-3.3-70B at 131k context, Qwen3
at 32k, gpt-oss-120b at ~128k, plus the Anthropic and OpenAI
providers) handles 8k output comfortably with plenty of headroom for
the prompt. 8k is high enough that the common agents (history,
error_analysis, orchestrator) don't truncate mid-answer, but still
well under the smallest window we point at (Qwen3's 32k) so a runaway
response can't blow up the total context. Per-agent overrides via
inference_services.<agent>.max_tokens still work the same way; this
only changes the fallback when nothing is configured.

lib/galaxy/agents/base.py

@@ -686,7 +686,10 @@ class BaseGalaxyAgent(ABC):
         return self._get_agent_config("temperature", 0.7)
 
     def _get_max_tokens(self) -> int:
-        return self._get_agent_config("max_tokens", 2000)
+        # 8192 leaves headroom on the smallest backend we point at (Qwen3-32B,
+        # 32k total) while being big enough that most agents -- history in
+        # particular -- don't get truncated mid-answer at the default.
+        return self._get_agent_config("max_tokens", 8192)
 
     async def _call_agent_from_tool(
         self,