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

run_agent.py

@@ -9101,9 +9101,14 @@ class AIAgent:
 
         # Update token estimate after compaction so pressure calculations
         # use the post-compression count, not the stale pre-compression one.
-        _compressed_est = (
-            estimate_tokens_rough(new_system_prompt)
-            + estimate_messages_tokens_rough(compressed)
+        # Use estimate_request_tokens_rough() so tool schemas are included —
+        # with 50+ tools enabled, schemas alone can add 20-30K tokens, and
+        # omitting them delays the next compression cycle far past the
+        # configured threshold (issue #14695).
+        _compressed_est = estimate_request_tokens_rough(
+            compressed,
+            system_prompt=new_system_prompt or "",
+            tools=self.tools or None,
         )
         self.context_compressor.last_prompt_tokens = _compressed_est
         self.context_compressor.last_completion_tokens = 0
@@ -13223,7 +13228,13 @@ class AIAgent:
                         # causing premature compression.  (#12026)
                         _real_tokens = _compressor.last_prompt_tokens
                     else:
-                        _real_tokens = estimate_messages_tokens_rough(messages)
+                        # Include tool schemas — with 50+ tools enabled
+                        # these add 20-30K tokens the messages-only
+                        # estimate misses, which can skip compression
+                        # past the configured threshold (#14695).
+                        _real_tokens = estimate_request_tokens_rough(
+                            messages, tools=self.tools or None
+                        )
 
                     if self.compression_enabled and _compressor.should_compress(_real_tokens):
                         self._safe_print("  ⟳ compacting context…")