feat(agents): configurable LLM model + effort per-agent and per-project (ORCH-41) (#36)

src/config.py

@@ -78,6 +78,34 @@ class Settings(BaseSettings):
     agent_kill_grace_seconds: int = 20
     agent_timeout_overrides_json: str = ""
 
+    # ORCH-41: per-agent LLM model. Empty -> agent_model_default. Resolution order:
+    # project-override (projects_json agent_models) > ORCH_AGENT_MODEL_<AGENT> >
+    # agent_model_default > CLI default (no --model flag). Default is 4-8 because
+    # 4-7 == 4-8 in price (Slava 05.06); do NOT hardcode the version anywhere else.
+    agent_model_default: str = "claude-opus-4-8"
+    agent_model_analyst: str = ""
+    agent_model_architect: str = ""
+    agent_model_developer: str = ""
+    agent_model_reviewer: str = ""
+    agent_model_tester: str = ""
+    agent_model_deployer: str = ""
+
+    # ORCH-41: per-agent effort / reasoning level: low|medium|high|xhigh|max.
+    # Empty -> agent_effort_default. Same resolution order as model. Default split:
+    # thinking agents (analyst/architect/developer/reviewer) -> high; mechanical
+    # agents (tester/deployer) -> medium.
+    agent_effort_default: str = "high"
+    agent_effort_analyst: str = "high"
+    agent_effort_architect: str = "high"
+    agent_effort_developer: str = "high"
+    agent_effort_reviewer: str = "high"
+    agent_effort_tester: str = "medium"
+    agent_effort_deployer: str = "medium"
+
+    # ORCH-41: optional per-agent fallback model used when the primary is
+    # overloaded (--fallback-model, works with --print). Empty -> no flag.
+    agent_fallback_model: str = ""
+
     # L-2: run-log rotation. Old per-run logs in <data>/runs/*.log are pruned at
     # app startup (best-effort). A *.log is removed if it is older than
     # log_keep_days OR not within the log_keep_max most-recent logs (whichever