Merge pull request #222 from ServiceNow/add-claude-3.7

Add-claude-3.7 to repro journal

Author: recursix

main.py

@@ -14,6 +14,10 @@
     RANDOM_SEARCH_AGENT,
     AGENT_4o,
     AGENT_4o_MINI,
+    AGENT_o3_MINI,
+    AGENT_o1_MINI,
+    AGENT_37_SONNET,
+    AGENT_CLAUDE_SONNET_35,
 )
 from agentlab.experiments.study import Study
 

reproducibility_journal.csv

@@ -73,3 +73,4 @@ Leo Boisvert,GenericAgent-openai_o1-mini-2024-09-12,workarena_l1,0.4.1,2025-02-0
   M: src/agentlab/agents/generic_agent/agent_configs.py
   M: src/agentlab/analyze/agent_xray.py
   M: src/agentlab/llm/llm_configs.py",0.13.3,1d2d7160e5b7ec9954ecb48988f71eb56288dd29,"
+Leo Boisvert,GenericAgent-anthropic_claude-3.7-sonnet,workarena_l1,0.4.1,2025-02-25_02-32-09,d4f900c2-1de1-4e4b-a3ab-495ff2675fff,0.515,0.028,0,330/330,None,Linux (#68-Ubuntu SMP Mon Oct 7 14:34:20 UTC 2024),3.12.3,1.44.0,v0.4.0,c9d2ef9648435ef1119950ecb1a0734497ccc33b,,0.13.3,1d2d7160e5b7ec9954ecb48988f71eb56288dd29,

src/agentlab/agents/generic_agent/__init__.py

@@ -16,6 +16,7 @@
     AGENT_4o,
     AGENT_4o_MINI,
     AGENT_CLAUDE_SONNET_35,
+    AGENT_37_SONNET,
     AGENT_CLAUDE_SONNET_35_VISION,
     AGENT_4o_VISION,
     AGENT_4o_MINI_VISION,
@@ -36,6 +37,7 @@
     "RANDOM_SEARCH_AGENT",
     "AGENT_CUSTOM",
     "AGENT_CLAUDE_SONNET_35",
+    "AGENT_37_SONNET",
     "AGENT_4o_VISION",
     "AGENT_4o_MINI_VISION",
     "AGENT_CLAUDE_SONNET_35_VISION",

src/agentlab/agents/generic_agent/agent_configs.py

@@ -264,7 +264,10 @@
     chat_model_args=CHAT_MODEL_ARGS_DICT["openrouter/anthropic/claude-3.5-sonnet:beta"],
     flags=FLAGS_GPT_4o,
 )
-
+AGENT_37_SONNET = GenericAgentArgs(
+    chat_model_args=CHAT_MODEL_ARGS_DICT["openrouter/anthropic/claude-3.7-sonnet"],
+    flags=FLAGS_GPT_4o,
+)
 AGENT_o3_MINI = GenericAgentArgs(
     chat_model_args=CHAT_MODEL_ARGS_DICT["openai/o3-mini-2025-01-31"],
     flags=FLAGS_GPT_4o,

src/agentlab/llm/llm_configs.py

@@ -184,6 +184,14 @@
         max_new_tokens=2_000,
         temperature=1e-1,
     ),
+    "openrouter/anthropic/claude-3.7-sonnet": OpenRouterModelArgs(
+        model_name="anthropic/claude-3.7-sonnet",
+        max_total_tokens=200_000,
+        max_input_tokens=200_000,
+        max_new_tokens=8_192,
+        temperature=1e-1,
+        vision_support=True,
+    ),
     "openrouter/openai/o1-mini-2024-09-12": OpenRouterModelArgs(
         model_name="openai/o1-mini-2024-09-12",
         max_total_tokens=128_000,