From 4a7c17fca59e3193dfb57aa545d1f68d41760670 Mon Sep 17 00:00:00 2001
From: Teknium <127238744+teknium1@users.noreply.github.com>
Date: Mon, 30 Mar 2026 17:04:31 -0700
Subject: [PATCH] fix(gateway): read custom_providers context_length in hygiene
 compression (#4085)

Gateway hygiene pre-compression only checked model.context_length from
the top-level config, missing per-model context_length defined in
custom_providers entries. This caused premature compression for custom
provider users (e.g. 128K default instead of 200K configured).

The AIAgent's own compressor already reads custom_providers correctly
(run_agent.py lines 1171-1189). This adds the same fallback to the
gateway hygiene path, running after runtime provider resolution so
the base_url is available for matching.
---
 gateway/run.py | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/gateway/run.py b/gateway/run.py
index 735832744..c42510709 100644
--- a/gateway/run.py
+++ b/gateway/run.py
@@ -2284,6 +2284,29 @@ class GatewayRunner:
                         _hyg_api_key = _hyg_runtime.get("api_key")
                     except Exception:
                         pass
+
+                # Check custom_providers per-model context_length
+                # (same fallback as run_agent.py lines 1171-1189).
+                # Must run after runtime resolution so _hyg_base_url is set.
+                if _hyg_config_context_length is None and _hyg_base_url:
+                    try:
+                        _hyg_custom_providers = _hyg_data.get("custom_providers")
+                        if isinstance(_hyg_custom_providers, list):
+                            for _cp in _hyg_custom_providers:
+                                if not isinstance(_cp, dict):
+                                    continue
+                                _cp_url = (_cp.get("base_url") or "").rstrip("/")
+                                if _cp_url and _cp_url == _hyg_base_url.rstrip("/"):
+                                    _cp_models = _cp.get("models", {})
+                                    if isinstance(_cp_models, dict):
+                                        _cp_model_cfg = _cp_models.get(_hyg_model, {})
+                                        if isinstance(_cp_model_cfg, dict):
+                                            _cp_ctx = _cp_model_cfg.get("context_length")
+                                            if _cp_ctx is not None:
+                                                _hyg_config_context_length = int(_cp_ctx)
+                                    break
+                    except (TypeError, ValueError):
+                        pass
             except Exception:
                 pass