refactor: unify agent history and harden runtime diagnostics

Preserve user guidance through history compression, stabilize Flash index targets, and retire withdrawn checks without applying stale verdicts.

Improve runtime diagnostics, tool responses, and history rendering. Simplify documentation and comments.

Validation: 2076 tests passed in the full suite; 381 affected tests and 26 frontend tests passed after cleanup. Ruff and the quality ratchet passed.

artemis/agents/diagnoser/diagnoser.py

@@ -356,9 +356,10 @@ class Diagnoser:
         if submit_tool:
             submit_tool.invoke(args)
 
-        outcome = f"Analysis: {analysis} | Actionable Steps: "
-        for step in steps:
-            outcome += f"{step} "
+        outcome = f"Analysis: {analysis}"
+        if steps:
+            numbered = "\n".join(f"{i}. {step}" for i, step in enumerate(steps, start=1))
+            outcome += f"\nActionable steps:\n{numbered}"
         return outcome
 
     def _max_iteration_outcome(self, response, outcome: str) -> str: