[claude] Add agent emotional state simulation (#1013) (#1144)

Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>

config/agents.yaml

@@ -16,6 +16,8 @@
 #   prompt_tier   "full" (tool-capable models) or "lite" (small models)
 #   max_history   Number of conversation turns to keep in context
 #   context_window  Max context length (null = model default)
+#   initial_emotion Starting emotional state (calm, cautious, adventurous,
+#                   analytical, frustrated, confident, curious)
 #
 # ── Defaults ────────────────────────────────────────────────────────────────
 
@@ -103,6 +105,7 @@ agents:
     model: qwen3:30b
     prompt_tier: full
     max_history: 20
+    initial_emotion: calm
     tools:
       - web_search
       - read_file
@@ -136,6 +139,7 @@ agents:
     model: qwen3:30b
     prompt_tier: full
     max_history: 10
+    initial_emotion: curious
     tools:
       - web_search
       - read_file
@@ -151,6 +155,7 @@ agents:
     model: qwen3:30b
     prompt_tier: full
     max_history: 15
+    initial_emotion: analytical
     tools:
       - python
       - write_file
@@ -196,6 +201,7 @@ agents:
     model: qwen3:30b
     prompt_tier: full
     max_history: 10
+    initial_emotion: adventurous
     tools:
       - run_experiment
       - prepare_experiment