avm/hassio-addons
1
0
Fork 0
mirror of https://github.com/alexbelgium/hassio-addons.git synced 2026-08-08 14:12:30 +02:00
Code Issues Packages Projects Releases Wiki Activity

docs(claude_desktop): document Selkies ingress fix

Browse Source
This commit is contained in:
Alexandre
2026-07-16 17:52:29 +02:00
parent 0ee96086c3
commit 0fc84fa6da
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
claude_desktop/CHANGELOG.md
View File

@@ -1,3 +1,7 @@
## 1.31 (16-07-2026)
- Fix Home Assistant ingress remaining on `Waiting for stream`: current Selkies WebSocket mode connects through `/api/websockets`, while the add-on inherited an older nginx template that proxied only `/websocket`. Replace the template rewrite with an explicit ingress server that proxies `/api/` to Selkies on port 8082, retains `/websocket` compatibility, and declares `ingress_port: 3001` so nginx always receives a valid listen port.
## 1.30 (16-07-2026)
- Compress large tool outputs automatically in every Claude Code session with a managed `PostToolUse` hook (new `headroom_auto_compress` option, enabled by default). Desktop-spawned sessions (cowork/dispatch) pin `ANTHROPIC_BASE_URL` to the production endpoint (headroom #869), so the transparent proxy never sees their traffic and compression there depended entirely on the model remembering to call the `headroom` MCP tools per the CLAUDE.md guidance — in practice most large outputs went uncompressed. The new `/usr/local/bin/headroom-posttooluse-compress.py` hook fires on `Bash`/`Grep`/`Glob`/`WebFetch` results over ~4000 characters, compresses them with Headroom's rule-based pipeline (SmartCrusher and friends; the Kompress ML path is disabled because its background model load can never complete inside a short-lived hook process), and swaps the result in via `hookSpecificOutput.updatedToolOutput` with a retrieval marker appended. Originals are stored in the shared CCR SQLite store (`~/.headroom/ccr_store.db` — the same one the headroom MCP server reads), so `mcp__headroom__headroom_retrieve` always recovers the full output; savings are recorded to the durable ledger (client `posttooluse-hook`) and show up in the existing gains report. The hook fails open (any error leaves the tool output untouched), never touches `stderr` fields so error text reaches the model verbatim, skips anything below a 50-token savings floor, and is registered idempotently in `~/.claude/settings.json` only after a `--self-test` confirms the interpreter can import headroom; disabling the option (or Headroom) removes the managed entry without touching user-defined hooks. Measured on a representative Home Assistant `states` dump: 10781 -> 2964 tokens (73% saved) at ~1.7 s hook overhead, with sub-100 ms pass-through for small outputs.