fix(context): clamp -1 post-compression sentinel in sibling status paths

Whole-bug-class follow-up to the tui_gateway fix: the same -1
last_prompt_tokens sentinel (parked by conversation_compression after a
compression) leaked into other status readers, producing a raw -1 or a
NEGATIVE usage_percent on the transitional turn:

- agent/context_engine.py get_status() (the ABC default every external
  context engine inherits) — highest blast radius
- gateway/slash_commands.py /usage context line
- cli.py session usage printout

All clamped to >=0, mirroring cli.py _get_status_bar_snapshot and the
tui_gateway fix. Adds an ABC get_status sentinel-clamp regression test.

cli.py

@@ -9261,7 +9261,7 @@ class HermesCLI(CLIAgentSetupMixin, CLICommandsMixin):
         total = agent.session_total_tokens
 
         compressor = agent.context_compressor
-        last_prompt = compressor.last_prompt_tokens
+        last_prompt = compressor.last_prompt_tokens if compressor.last_prompt_tokens > 0 else 0
         ctx_len = compressor.context_length
         pct = min(100, (last_prompt / ctx_len * 100)) if ctx_len else 0
         compressions = compressor.compression_count