docs(claude_desktop): document memory reduction

.github/workflows/agent-claude-changelog.yml

@@ -1,49 +0,0 @@
-name: Prepare Claude Desktop changelog
-
-on:
-  push:
-    branches:
-      - agent/claude-headroom-memory
-
-permissions:
-  contents: write
-
-jobs:
-  update-changelog:
-    if: github.actor != 'github-actions[bot]'
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v7.0.1
-        with:
-          ref: agent/claude-headroom-memory
-          fetch-depth: 0
-
-      - name: Prepend release note and remove this one-shot workflow
-        shell: bash
-        run: |
-          python3 - <<'PY'
-          from pathlib import Path
-
-          path = Path("claude_desktop/CHANGELOG.md")
-          text = path.read_text()
-          marker = "## 1.38 (02-08-2026)"
-          if marker not in text:
-              entry = """## 1.38 (02-08-2026)
-
-          - Reduce Claude Desktop add-on RAM use in three places without removing Headroom, RTK, TokenSave, Cowork, Dispatch, or the streamed desktop. Headroom's heavy HTTP proxy is no longer started at container boot: a standard-library TCP gate stays on port 8787, starts the real proxy on the first request, and stops it after 15 minutes without traffic (`HEADROOM_IDLE_TIMEOUT_SECONDS` remains overridable through `env_vars`). This releases the proxy's Python, ONNX Runtime, tokenizer, and Kompress model allocations while the add-on is idle; a later request starts a clean backend transparently.
-          - Prevent Headroom from loading a second Kompress model inside every Claude Desktop/Claude Code MCP process. The add-on now intercepts `headroom mcp serve` with a lightweight adapter that retains upstream MCP retrieval/statistics behavior but delegates `headroom_compress` to the shared proxy's loopback `/v1/compress` endpoint. The MCP process explicitly disables local Kompress and never imports `headroom.compress`, so only the proxy backend can own the ML runtime.
-          - Remove the add-on-wide `tmpfs: true` mount and undo the shared Selkies script's `/tmp/cache` redirection for this add-on. Electron/Chromium, Mesa, and application caches now live under the selected persistent home (`$HOME/.cache`) as reclaimable filesystem cache instead of RAM-backed cgroup shmem. Runtime sockets and XDG runtime state remain under `/run`.
-
-          """
-              path.write_text(entry + text)
-          PY
-          rm -f .github/workflows/agent-claude-changelog.yml
-
-      - name: Commit changelog
-        shell: bash
-        run: |
-          git config user.name "github-actions[bot]"
-          git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
-          git add claude_desktop/CHANGELOG.md .github/workflows/agent-claude-changelog.yml
-          git commit -m "docs(claude_desktop): document memory reduction"
-          git push origin HEAD:agent/claude-headroom-memory

claude_desktop/CHANGELOG.md

@@ -1,3 +1,9 @@
+## 1.38 (02-08-2026)
+
+- Reduce Claude Desktop add-on RAM use in three places without removing Headroom, RTK, TokenSave, Cowork, Dispatch, or the streamed desktop. Headroom's heavy HTTP proxy is no longer started at container boot: a standard-library TCP gate stays on port 8787, starts the real proxy on the first request, and stops it after 15 minutes without traffic (`HEADROOM_IDLE_TIMEOUT_SECONDS` remains overridable through `env_vars`). This releases the proxy's Python, ONNX Runtime, tokenizer, and Kompress model allocations while the add-on is idle; a later request starts a clean backend transparently.
+- Prevent Headroom from loading a second Kompress model inside every Claude Desktop/Claude Code MCP process. The add-on now intercepts `headroom mcp serve` with a lightweight adapter that retains upstream MCP retrieval/statistics behavior but delegates `headroom_compress` to the shared proxy's loopback `/v1/compress` endpoint. The MCP process explicitly disables local Kompress and never imports `headroom.compress`, so only the proxy backend can own the ML runtime.
+- Remove the add-on-wide `tmpfs: true` mount and undo the shared Selkies script's `/tmp/cache` redirection for this add-on. Electron/Chromium, Mesa, and application caches now live under the selected persistent home (`$HOME/.cache`) as reclaimable filesystem cache instead of RAM-backed cgroup shmem. Runtime sockets and XDG runtime state remain under `/run`.
+
  
 ## ubunturesolute-version-3a10bef7 (2026-08-01)
 - Update to latest version from linuxserver/docker-baseimage-selkies (changelog : https://github.com/linuxserver/docker-baseimage-selkies/releases)