docs(compress): state that /v1/compress ignores system and tools

No behaviour change — this documents current behaviour and pins it.

The endpoint reads only messages/model/token_budget/config. Anthropic sends
`system` and `tools` out of band, and the endpoint accepts both without complaint
(200, no warning) and returns neither, so neither is compressed. The silence is
the hazard: an Anthropic-native caller has no signal that the fields did nothing,
and the request table listing four fields does not tell them a fifth was dropped.

Spells out the two consequences: the Anthropic system prompt is not compressed
here despite being resent every request, and tool-schema compaction /
tool-search deferral are unreachable through this route — on tool-heavy traffic
those can be the largest share of available savings, so run Headroom as the proxy
if you need them.

A test pins the contract so it cannot drift silently; if the endpoint ever starts
returning these fields, the test fails and points at the doc that must change with
it.

ruff clean; 25 compress-route tests pass.

docs/content/docs/proxy.mdx

@@ -445,6 +445,15 @@ So an Anthropic-native caller does not need to convert to OpenAI format first. B
 | `token_budget` | integer | no | Overrides the model's context limit. Used by callers that need to fit a tighter budget. |
 | `config` | object | no | Compression options, below. A non-object value is ignored rather than rejected. |
 
+<Callout type="warning" title="system and tools are ignored">
+Only the four fields above are read. Anthropic sends `system` and `tools` **out of band**, alongside `messages` — this endpoint accepts them without complaint (you get a `200`, no warning) and returns neither, so neither is compressed.
+
+Keep carrying both yourself and send them upstream unchanged. Two consequences worth knowing:
+
+- An Anthropic system prompt is not compressed here, even though it is resent on every request.
+- Tool-schema compaction and tool-search deferral are not reachable through this endpoint — on tool-heavy traffic those can be the largest share of available savings. Run Headroom as the proxy (rather than calling `/v1/compress`) if you need them.
+</Callout>
+
 `config` fields:
 
 | Field | Type | Default | Description |

tests/test_compress_route_tokenizer_by_model.py

@@ -212,6 +212,39 @@ def _compress(client, messages: list[dict], frozen: int | None = None) -> list[d
     return response.json()["messages"]
 
 
+def test_system_and_tools_are_accepted_and_ignored(client):
+    """Documented contract: only messages/model/token_budget/config are read.
+
+    Anthropic sends `system` and `tools` out of band. The endpoint takes them
+    without complaint and returns neither, so neither is compressed — callers must
+    keep carrying them. Pinned because the silence is the hazard: a caller has no
+    signal that the fields did nothing. If this ever starts returning them, the
+    contract changed and docs/content/docs/proxy.mdx needs updating with it.
+    """
+    response = client.post(
+        "/v1/compress",
+        json={
+            "messages": _anthropic_messages(),
+            "model": "claude-sonnet-4-6",
+            "system": "You are a coding agent. " * 200,
+            "tools": [
+                {
+                    "name": "read",
+                    "description": "Read a file from disk. " * 20,
+                    "input_schema": {"type": "object", "properties": {"path": {"type": "string"}}},
+                }
+            ],
+        },
+    )
+
+    assert response.status_code == 200, response.text
+    body = response.json()
+    assert "system" not in body
+    assert "tools" not in body
+    # Messages are still compressed normally alongside the ignored fields.
+    assert body["tokens_saved"] > 0
+
+
 def test_documented_loop_keeps_the_cached_prefix_byte_identical(client):
     """Feed back previous OUTPUT + frozen_message_count -> stable prefix every turn."""
     import json

wiki/proxy.md

@@ -274,6 +274,8 @@ Compression-only endpoint. Compresses messages without ever making a **completio
 
 **No format conversion.** `messages` may be OpenAI-shaped (`role: "tool"` + `tool_call_id`) or Anthropic-shaped (`tool_use` / `tool_result` content blocks); the same shape comes back. `model` selects the tokenizer and context limit — send the real name, including gateway-prefixed forms like `bedrock/anthropic.claude-3-5-sonnet`.
 
+**`system` and `tools` are ignored.** Anthropic sends both out of band. This endpoint accepts them without complaint (200, no warning) and returns neither, so neither is compressed — keep carrying them yourself. That means the Anthropic system prompt is not compressed here, and tool-schema compaction / tool-search deferral are not reachable through this route; run Headroom as the proxy if you need those.
+
 **Request:**
 ```json
 {