fix(compression): include system prompt + tool schemas in token estimates (#18265)

The user-visible /compress banner and the post-compression last_prompt_tokens
writeback both counted only the raw message transcript (chars/4). With a 15KB
system prompt and 30 tool schemas (~26KB), a 4-message transcript that looks
like ~45 tokens to the transcript-only estimator is really ~10.5K tokens of
request pressure — a 234x gap.

Two user-facing consequences:
- Banner shows 'Compressing … (~45 tokens)…' while compression is actually
  firing on 10K+ tokens of real pressure, confusing users about why
  compression triggered (reported by @codecovenant on X; #6217).
- Post-compression last_prompt_tokens writeback omits tool schemas, so the
  next should_compress() check compares real usage against a stale
  underestimate — compression triggers late, potentially past the model's
  context limit on small-context models (#14695).

Swap estimate_messages_tokens_rough() for estimate_request_tokens_rough()
at every user-visible banner and at the post-compression writeback.
estimate_request_tokens_rough() already existed for exactly this purpose
and includes system prompt + tool schemas.

Touched call sites:
- run_agent.py: post-compression last_prompt_tokens writeback, post-tool
  call should_compress() fallback when provider usage is missing
- cli.py: /compress banner + summary
- gateway/run.py: gateway /compress banner + summary
- tui_gateway/server.py: TUI /compress status + summary
- acp_adapter/server.py: ACP /compact before/after

Left intentionally alone:
- Session-hygiene fallback and the 'no agent' /status path in gateway/run.py
  — no agent instance is in scope to query for system prompt/tools, and the
  existing 30-50% overestimate wobble on hygiene is safety-accepted.
- Verbose-mode 'Request size' logging — informational only, already counts
  system prompt via api_messages[0].

Also relabels the feedback line from 'Rough transcript estimate' to
'Approx request size' so the metric label matches what it actually measures.

Credits: diagnoses from @devilardis (#14695) and @Jackten (#6217);
user report @codecovenant on X (2026-04-30).

Closes #14695
Closes #6217

cli.py

@@ -7343,10 +7343,20 @@ class HermesCLI:
         original_count = len(self.conversation_history)
         with self._busy_command("Compressing context..."):
             try:
-                from agent.model_metadata import estimate_messages_tokens_rough
+                from agent.model_metadata import estimate_request_tokens_rough
                 from agent.manual_compression_feedback import summarize_manual_compression
                 original_history = list(self.conversation_history)
-                approx_tokens = estimate_messages_tokens_rough(original_history)
+                # Include system prompt + tool schemas in the estimate —
+                # a transcript-only number understates real request pressure
+                # and can even appear to grow after compression because a
+                # dense handoff summary replaces many short turns (#6217).
+                _sys_prompt = getattr(self.agent, "_cached_system_prompt", "") or ""
+                _tools = getattr(self.agent, "tools", None) or None
+                approx_tokens = estimate_request_tokens_rough(
+                    original_history,
+                    system_prompt=_sys_prompt,
+                    tools=_tools,
+                )
                 if focus_topic:
                     print(f"🗜️  Compressing {original_count} messages (~{approx_tokens:,} tokens), "
                           f"focus: \"{focus_topic}\"...")
@@ -7378,7 +7388,11 @@ class HermesCLI:
                 ):
                     self.session_id = self.agent.session_id
                     self._pending_title = None
-                new_tokens = estimate_messages_tokens_rough(self.conversation_history)
+                new_tokens = estimate_request_tokens_rough(
+                    self.conversation_history,
+                    system_prompt=_sys_prompt,
+                    tools=_tools,
+                )
                 summary = summarize_manual_compression(
                     original_history,
                     self.conversation_history,