diff --git a/CHANGELOG.md b/CHANGELOG.md
index 410fe2651..f5304d014 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -113,6 +113,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 * **wrap/doctor:** make the Claude Remote Control gate warning accurate and stop it firing for users who never had the feature ([#1779](https://github.com/headroomlabs-ai/headroom/issues/1779)). Claude Code 2.1.196 added a client-side check that **deterministically** disables first-party Remote Control (`/remote-control` / `/rc`) whenever `ANTHROPIC_BASE_URL` points at a non-`api.anthropic.com` host — which Headroom always does. The old notice hedged ("may hide the Remote Control menu"); it now states the disable as fact, names the `/rc` command, and detects the installed Claude Code version so the wording is exact (`2.1.196` when known, `2.1.196+` when not). The gate is upstream and RC's control-plane talks to `claude.ai` (not the API host), so Headroom cannot restore it — the warning tells you to run Claude without Headroom for RC sessions. The warning is suppressed for auth modes that never had Remote Control (API-key/PAYG via `ANTHROPIC_API_KEY`/`ANTHROPIC_AUTH_TOKEN`, and Bedrock/Vertex/Foundry cloud IAM) and on Claude Code builds older than 2.1.196 where RC is unaffected by a custom base URL. Both the `headroom wrap claude` launch banner and `headroom doctor` co-report the sibling base-URL gates Headroom *does* restore — on-demand tool loading (#746, automatic) and the 1M context window (#1158, via `--1m`) — and the wrap-side co-report is session-accurate: it says "already restored via --1m" when the flag is in effect and reports tool deferral OFF (not falsely "kept on") when the user chose `--tool-search false`/`ENABLE_TOOL_SEARCH=false`; the `ENABLE_TOOL_SEARCH=...` banner line got the same accuracy fix. `is_custom_anthropic_base_url` now recognizes scheme-less values (`myproxy.local:8080`, `127.0.0.1:8787`) as custom hosts and degrades gracefully on malformed URLs instead of crashing `doctor`. `doctor` resolves the Claude Code version lazily, so runs with no custom base URL never pay the `claude --version` subprocess. No request bytes are touched (cache-safe); this is UX/notice-only.
 * **install:** default the docker image to `ghcr.io/headroomlabs-ai/headroom:latest` instead of the dead `ghcr.io/chopratejas/headroom:latest`. After the repo moved to the `headroomlabs-ai` org, GHCR did not redirect the old package, so `headroom install` / `headroom init` and the install scripts pulled a frozen `0.27.0` image while current releases publish to the new path ([#1867](https://github.com/headroomlabs-ai/headroom/issues/1867)).
 * **transforms/content-router:** stop a profile-derived `read_protection_window` kwarg from weakening an explicit `--protect-tool-results` guarantee. `ContentRouter.apply()` computes `read_protection_window` from `protect_recent_reads_fraction`, where `0.0` (the sentinel `--protect-tool-results` sets) means "protect all excluded-tool output regardless of conversation depth" per #1374's documented contract — but the method then unconditionally overwrote that window with a `read_protection_window` kwarg whenever one was present. `proxy_pipeline_kwargs()` supplies that kwarg on every request from the active `AgentSavingsProfile.protect_recent` (the default `coding` profile sets `protect_recent=2`), so in practice only the last 2 messages ever kept read-protection and older excluded-tool output silently fell through to lossy compression. The runtime kwarg may now only narrow the window when `protect_recent_reads_fraction > 0`; it can no longer shrink the "protect everything" guarantee set by `--protect-tool-results`.
+* **proxy:** don't let a stray `HEADROOM_QDRANT_PORT` crash proxy startup. `ProxyConfig.memory_qdrant_port` used `qdrant_env.qdrant_env_port` as its field `default_factory`, and that function raises `ValueError` on a non-integer or out-of-range value. Because a `default_factory` runs on **every** `ProxyConfig()` construction, an inherited or typo'd `HEADROOM_QDRANT_PORT` crashed the proxy before it served a request — even though memory (and the qdrant backend) are off by default and unrelated to core proxying. The field now resolves the port through a fail-soft wrapper that falls back to the default (6333) with a warning; the strict `qdrant_env_port()` is unchanged for explicit qdrant setup.
 * **memory:** size the HNSW `index_batch` resize off the assigned-id high-water mark, not the live entry count. hnswlib never reclaims a slot on `mark_deleted` (used by remove/evict), so its usable capacity is bounded by the number of ids ever assigned (`_next_hnsw_id`). `index_batch` computed `required_capacity = len(self._memory_to_hnsw) + len(new_memories)` — the *live* count — which drops below `_next_hnsw_id` after deletion/eviction churn, so the resize was skipped and `add_items` raised `RuntimeError: number of elements exceeds the specified limit`, crashing the save path on the HNSW backend. It now resizes off `_next_hnsw_id`, matching the single-item `index()` guard.
 * **memory:** apply the `turn_id` scope filter even when `agent_id` is absent. In `SQLiteMemoryStore._build_query_conditions` the `turn_id` condition was nested inside the `agent_id` block, so a query filtered by `user_id` + `session_id` + `turn_id` (no `agent_id`) dropped the `turn_id` predicate entirely and returned every memory in the session instead of the single turn — an over-broad result that leaks sibling-turn memories into recall (and makes `count()` wrong for that scope). `agent_id` and `turn_id` are now applied independently.
 * **transforms:** stop the lossless `diff` fold from silently dropping lines out of non-diff content. `ContentRouter._lossless_first` tries every `compact_lossless` fold on all content, but the `diff` kind (`diff_strip_index`) is the only one with no exact-inverse check — it removes any line shaped like `index <hex>..<hex>`. Applied to arbitrary text/log/search payloads that happen to contain such a line, that line was deleted with no CCR marker, so it was unrecoverable — a violation of the lossless no-loss contract the method's own docstring promises. The `diff` fold now runs only when the strategy is `DIFF` or the content is diff-shaped (`_looks_like_diff`); genuine diffs still have their `index` bookkeeping folded.
diff --git a/headroom/proxy/models.py b/headroom/proxy/models.py
index 65474890f..4e959d929 100644
--- a/headroom/proxy/models.py
+++ b/headroom/proxy/models.py
@@ -6,6 +6,7 @@ Extracted from server.py to keep the codebase maintainable.
 
 from __future__ import annotations
 
+import logging
 from dataclasses import InitVar, dataclass, field
 from datetime import datetime
 from typing import Any, Literal
@@ -13,6 +14,30 @@ from typing import Any, Literal
 from headroom.memory import qdrant_env
 from headroom.providers.registry import ProviderApiOverrides
 
+logger = logging.getLogger(__name__)
+
+
+def _qdrant_env_port_or_default() -> int:
+    """Resolve ``HEADROOM_QDRANT_PORT``, falling back to the default on a bad value.
+
+    ``qdrant_env.qdrant_env_port`` raises on an invalid port (intended for
+    explicit qdrant setup). As a ``ProxyConfig`` field ``default_factory`` it
+    runs on EVERY ``ProxyConfig()`` construction, regardless of whether
+    memory/qdrant is enabled (both off by default), so a stray or typo'd
+    ``HEADROOM_QDRANT_PORT`` would crash proxy startup for an unrelated,
+    off-by-default subsystem. Fail soft here so config construction never raises.
+    """
+    try:
+        return qdrant_env.qdrant_env_port()
+    except ValueError:
+        logger.warning(
+            "Ignoring invalid HEADROOM_QDRANT_PORT; using default %d. "
+            "Set a valid 1-65535 port to override.",
+            qdrant_env.DEFAULT_QDRANT_PORT,
+        )
+        return qdrant_env.DEFAULT_QDRANT_PORT
+
+
 # =============================================================================
 # Data Models
 # =============================================================================
@@ -319,7 +344,7 @@ class ProxyConfig:
     # Qdrant connection (defaults resolve from HEADROOM_QDRANT_* env vars)
     memory_qdrant_url: str | None = field(default_factory=qdrant_env.qdrant_env_url)
     memory_qdrant_host: str = field(default_factory=qdrant_env.qdrant_env_host)
-    memory_qdrant_port: int = field(default_factory=qdrant_env.qdrant_env_port)
+    memory_qdrant_port: int = field(default_factory=_qdrant_env_port_or_default)
     memory_qdrant_api_key: str | None = field(default_factory=qdrant_env.qdrant_env_api_key)
     memory_neo4j_uri: str = "neo4j://localhost:7687"
     memory_neo4j_user: str = "neo4j"
diff --git a/tests/test_proxy_config_qdrant_port.py b/tests/test_proxy_config_qdrant_port.py
new file mode 100644
index 000000000..95b59467e
--- /dev/null
+++ b/tests/test_proxy_config_qdrant_port.py
@@ -0,0 +1,33 @@
+"""ProxyConfig construction must survive a bad HEADROOM_QDRANT_PORT.
+
+The port is resolved by a field default_factory that runs on every ProxyConfig()
+construction, so a stray/typo'd value must not crash proxy startup for an
+off-by-default subsystem."""
+
+from __future__ import annotations
+
+import pytest
+
+from headroom.memory import qdrant_env
+from headroom.proxy.models import ProxyConfig, _qdrant_env_port_or_default
+
+
+@pytest.mark.parametrize("bad", ["not-a-port", "70000", "0"])
+def test_bad_qdrant_port_falls_back_to_default(monkeypatch, bad):
+    monkeypatch.setenv("HEADROOM_QDRANT_PORT", bad)
+    assert _qdrant_env_port_or_default() == qdrant_env.DEFAULT_QDRANT_PORT
+
+
+def test_valid_qdrant_port_is_honored(monkeypatch):
+    monkeypatch.setenv("HEADROOM_QDRANT_PORT", "6444")
+    assert _qdrant_env_port_or_default() == 6444
+
+
+def test_proxyconfig_construction_survives_bad_qdrant_port(monkeypatch):
+    monkeypatch.setenv("HEADROOM_QDRANT_PORT", "not-a-port")
+
+    # Must not raise even though the port is unparseable (memory is off by
+    # default and unrelated to core proxying).
+    config = ProxyConfig()
+
+    assert config.memory_qdrant_port == qdrant_env.DEFAULT_QDRANT_PORT