Adds a server-side "small model" capability: direct, cheap LLM calls that
reuse the user's existing OpenCode provider logins — the mechanism OpenCode
uses internally for titles and summaries but does not expose through the
SDK or plugins. Zero new dependencies; plain fetch with per-provider wire
formats, credentials never leave the server.
Core (packages/web/server/lib/small-model):
- Resolution mirrors OpenCode's session scoping: explicit settings override
→ small_model from the OpenCode config → family scan within the session's
provider → the session's own model. The global provider scan only serves
callers without a session context, and background callers forbid it
entirely (restrictToPreferredProvider), so conversation content never
reaches a provider the user didn't pick — explicit choices excepted.
- Per-provider auth replicating OpenCode's plugin loaders: GitHub Copilot
(device token as bearer, no exchange), ChatGPT plan via the codex
Responses API (single-flight OAuth refresh written back to auth.json),
Anthropic messages, Google generateContent, generic OpenAI-compatible.
- OpenCode's free models (opencode/big-pickle, *-free) are never called
directly; unauthenticated providers are skipped by design.
- Prompt clamping to the model's catalog context limit; thinking disabled
where a wire switch exists (Z.AI/GLM, MiniMax-M3, Gemini Flash); robust
content parsing with a clear error when a thinking model spends its whol
budget on reasoning.
- Settings → Sessions gains a Small Model group: use-default checkbox plus
an override picker limited to authenticated providers, persisted with
web/desktop/VS Code sanitization parity.
Consumers:
- Session assist: a server-side watcher on the global SSE hub generates a
short recap and one suggested follow-up after a session idles quietly fo
a minute, stored on session metadata (openchamber.assist). Freshness is
keyed to the last assistant message id, so new activity invalidates the
payload everywhere with no extra writes. The chat shows the recap under
the last message after five quiet minutes and the suggestion as a
dismissible chip above the composer (tap fills the input, never sends).
Gated by a new Chat setting (default on) that is a hard generation
switch. Language is anchored to the conversation itself, with a
script-mismatch guard against model/backend language hallucination.
- TTS: a third input mode, summarized — long replies are condensed to
spoken prose before playback on any TTS engine.
- Git: commit-message and PR generation moved off the active chat session
onto the small model fed with real diffs and the commit list (bodies
included), with a session-transport fallback for free-model-only setups.
- Notes: Add to notes distills long selections into 1-3 dense sentences
preserving exact identifiers, with verbatim fallback on failure.
Fixes along the way:
- The global event watcher now starts unconditionally; it was gated behind
the desktop-notify env, leaving the server-side event hub dead in
packaged apps.
- OpenCode re-emits message.updated for old user messages after idle; the
watcher no longer mistakes those for new activity.
- Session metadata merges from a fresh read right before the PATCH, so
writes made during the generation window (suggestion dismissals, review
links) are preserved; the assist runtime stops during graceful shutdown.
openchamber # Start on port 3000
openchamber --port 8080# Custom port
openchamber --lan --port 3000# Listen on LAN (0.0.0.0)
openchamber --ui-password secret # Password-protect UI
openchamber startup enable# Start at login as a native serviceOPENCHAMBER_UI_PASSWORD=secret openchamber startup enable# Save service password env
openchamber startup status # Show startup service status
openchamber startup disable # Remove startup service
openchamber tunnel help# Tunnel lifecycle commands
openchamber tunnel providers # Show provider capabilities
openchamber tunnel profile add --provider cloudflare --mode managed-remote --name prod-main --hostname app.example.com --token <token>
openchamber tunnel start --profile prod-main
openchamber tunnel start --provider cloudflare --mode quick --qr
openchamber tunnel start --provider cloudflare --mode managed-local --config ~/.cloudflared/config.yml
openchamber tunnel status --all # Show tunnel state across instances
openchamber tunnel stop --port 3000# Stop tunnel only (server stays running)
openchamber connect-url --port 3000# Add this server to OpenChamber Desktop
openchamber connect-url --server http://host:3000 --qr
openchamber connect-url --port 3000 --qr
openchamber logs # Follow latest instance logsOPENCODE_PORT=4096OPENCODE_SKIP_START=true openchamber # Connect to external OpenCode serverOPENCODE_HOST=https://myhost:4096 OPENCODE_SKIP_START=true openchamber # Connect via custom host/HTTPS
openchamber stop # Stop server
openchamber update # Update to latest version
startup enable snapshots your current environment into the native service so startup behaves like you launched openchamber from the same shell. This preserves provider tokens, PATH, SSH agent settings, and other CLI auth/config env vars. Use --no-env-snapshot for a minimal service env.
Tunnel behavior notes
One active tunnel per running OpenChamber instance (port).
Starting a different tunnel mode/provider on the same instance replaces the active tunnel.
Replacing or stopping a tunnel revokes existing connect links and invalidates remote tunnel sessions.
Connect links are one-time tokens; generating a new link revokes the previous unused link.
Connect other OpenChamber apps
Use connect-url when a web/API server should be added to OpenChamber Desktop or another OpenChamber app. If no server is running on the selected port, OpenChamber starts one first.
--api-only starts API routes without serving browser UI assets. --lan binds the server so other machines can reach it. --server is the address saved into the Desktop connection link. --ui-password protects browser access if UI routes are enabled elsewhere; the generated client token is what Desktop uses for API access.
This creates a remote client token and prints an openchamber://connect?... link. The link contains the server URL, token, label, and payload version. In OpenChamber Desktop, paste it in Settings -> Remote Instances -> Direct Instances -> Import Link to add that server as an Instance.
If the server was started with --lan or --host 0.0.0.0, connect-url automatically advertises a detected LAN IP instead of 127.0.0.1. Use --server <url> when you want to advertise a specific DNS name, Tailscale address, reverse proxy URL, or HTTPS endpoint.
If you are exposing the server beyond localhost, start it with a password:
Generating a client token does not automatically password-protect the hosted browser UI. --ui-password protects browser access; the client token lets another OpenChamber app connect to this server.
Security note: binding to 0.0.0.0 exposes the server on all network interfaces — use only on trusted networks and protect with firewall rules or --ui-password.
Managed-local path note: OPENCHAMBER_TUNNEL_CONFIG must use a container path under /home/openchamber/.... If the config file references credentials-file, ensure that JSON path is also mounted and reachable inside the container.
Data directory: mount data/ for persistent storage. Ensure permissions:
openchamber # Runs in background by default
openchamber stop # Stop background server
systemd service (VPN / LAN access)
Use --foreground to keep the CLI process alive so systemd (or any other process manager) can track and restart it. Combine with OPENCODE_HOST to connect to an OpenCode instance running as a separate service.
Why set PATH and SSH_AUTH_SOCK?
systemd user services start with a minimal environment — no shell profile is sourced.
Without an explicit PATH, OpenCode won't find tools installed via Homebrew, npm, or ~/.local/bin.
Without SSH_AUTH_SOCK, git operations over SSH (push, pull, clone) will fail.
%t expands to $XDG_RUNTIME_DIR (e.g. /run/user/1000), where most SSH agents write their socket.
--host 0.0.0.0 is required to listen on all interfaces (the default is 127.0.0.1). Use --host <ip> or OPENCHAMBER_HOST=<ip> to bind to a specific interface instead.
What makes the web version special
Remote access - Cloudflare tunnel with QR onboarding. Scan from your phone, start coding.
Bohdan Triapitsyn
28f0736d69
