74da62b336
The #920 per-entry drain quarantine dead-letters a render-refused digest entry and raises its fail-loud alarm to stderr/journal-LOCAL only. A dead-lettered entry is STORE-ACCOUNTED (§2.3), so the reconciler never re-flags it: journal-local-only visibility means an unattended operator can PERMANENTLY MISS a real obligation (G2a silent-degradation). digest.sh now ALSO routes the SAME per-entry quarantine alarm through WAKE_ALARM_SINK_CMD, reusing beacon.sh's (W6/#910) exact pluggable off-host alarm-sink adapter contract verbatim (operator target resolved by-name inside the adapter, fail-closed) -- in addition to, never instead of, the existing stderr diagnostic. Dedup: entries carry no per-entry wake_id (that field is the per-render ack copy-run id); the entry's durable identity is its store-allocated observed_seq (#908's sole monotonic allocator). A durable alarmed-set file under STATE_DIR (dead-letter-alarmed.set, atomic-written) records which observed_seqs have already been routed off-host, so a still-dead-lettered entry re-drained every timer tick -- or across a process restart -- is alarmed off-host EXACTLY ONCE. A new distinct dead-lettered entry (a new observed_seq) still routes its own one alarm. An unconfigured or unreachable WAKE_ALARM_SINK_CMD is a LOUD per-entry stderr diagnostic (mirrors beacon.sh's fail-closed wording) but does not itself fail the whole render -- per-entry fail-loud, never a whole-drain wedge, preserving #920's core no-head-of-line-blocking property. RED-FIRST: extends test-wake-digest-quarantine.sh with Q6-Q9, proven RED against the pre-fix stderr-only code (0 alarms ever captured; no off-host fail-closed diagnostic exists) and GREEN after the fix, while the pre-existing Q1-Q5 (#920) invariants remain green throughout. Bumps the wake component manifest to 0.6.6. Closes #924 Part of #892 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0158NZqN2n2ymKFeJAZ4GUCb
@mosaicstack/mosaic
CLI package for the Mosaic self-hosted AI agent platform.
Usage
mosaic wizard # First-run setup wizard
mosaic gateway install # Install the gateway daemon
mosaic config show # View current configuration
mosaic config hooks list # Manage Claude hooks
Headless / CI Installation
Set MOSAIC_ASSUME_YES=1 (or ensure stdin is not a TTY) to skip all interactive prompts. The following environment variables control the install:
Gateway configuration (mosaic gateway install)
| Variable | Default | Required |
|---|---|---|
MOSAIC_STORAGE_TIER |
local |
No |
MOSAIC_GATEWAY_PORT |
14242 |
No |
MOSAIC_DATABASE_URL |
(none) | Yes if tier=team |
MOSAIC_VALKEY_URL |
(none) | Yes if tier=team |
MOSAIC_ANTHROPIC_API_KEY |
(none) | No |
MOSAIC_CORS_ORIGIN |
http://localhost:3000 |
No |
Admin user bootstrap
| Variable | Default | Required |
|---|---|---|
MOSAIC_ADMIN_NAME |
(none) | Yes (headless) |
MOSAIC_ADMIN_EMAIL |
(none) | Yes (headless) |
MOSAIC_ADMIN_PASSWORD |
(none) | Yes (headless) |
MOSAIC_ADMIN_PASSWORD must be at least 8 characters. In headless mode a missing or too-short password causes a non-zero exit.
Example: Docker / CI install
export MOSAIC_ASSUME_YES=1
export MOSAIC_ADMIN_NAME="Admin"
export MOSAIC_ADMIN_EMAIL="admin@example.com"
export MOSAIC_ADMIN_PASSWORD="securepass123"
mosaic gateway install
Runtime launchers
mosaic claude # Launch Claude Code with Mosaic injection
mosaic yolo claude # …with --dangerously-skip-permissions
mosaic codex | opencode | pi
mosaic claudex (EXPERIMENTAL)
Runs GPT models inside the Claude Code harness by pointing Claude Code at a
local claude-code-proxy that
translates the Anthropic Messages API to a ChatGPT-subscription (Codex OAuth)
backend. This is not Anthropic Claude — model behavior, tool use, and output
quality may differ. Intended for evaluation, not production delivery.
mosaic claudex # launch (prompts through the proxy readiness gate)
mosaic yolo claudex # …with --dangerously-skip-permissions
mosaic claudex --print "hello" # trailing args are forwarded to Claude Code
Prerequisite: the claude-code-proxy binary must be installed and
authenticated (claude-code-proxy codex auth …). mosaic claudex runs a
preflight that verifies the binary, the OAuth state (triggering a device re-auth
if needed), and a trusted local listener before launching; it fails closed
if the proxy cannot be brought up with a verified identity.
Isolation (never touches your real Claude state). claudex always launches
against an isolated CLAUDE_CONFIG_DIR (default ~/.config/mosaic/claudex/home).
The ambient CLAUDE_CONFIG_DIR is deliberately ignored, and a guard proves the
resolved dir can never be — or live under — the real ~/.claude. A claudex
session therefore cannot mutate your normal Claude Code config.
No token leakage. claudex never reads the proxy's credential file. Claude
Code is handed only ANTHROPIC_AUTH_TOKEN=unused pointed at the loopback proxy;
the entire credential-bearing env family (ANTHROPIC_*, AWS_*, GOOGLE_CLOUD_*,
GOOGLE_APPLICATION_CREDENTIALS, *_TOKEN, *_KEY, *_SECRET, …) is stripped
from the composed environment. The Bedrock/Vertex routing switches
(CLAUDE_CODE_USE_BEDROCK, CLAUDE_CODE_USE_VERTEX, and the _SKIP_*_AUTH
pair) are force-removed regardless of value — otherwise their mere presence
would route Claude Code to the real Anthropic API via AWS/GCP and bypass the
proxy. The proxy holds the real OAuth credential.
Model tiers (override via env).
| Tier | Env var | Default |
|---|---|---|
| primary (opus/sonnet) | ANTHROPIC_MODEL |
gpt-5.6-sol |
| small/fast (haiku) | ANTHROPIC_SMALL_FAST_MODEL |
gpt-5.6-luna |
Operator-provided values win over the defaults. Additional overrides:
MOSAIC_CLAUDEX_CONFIG_DIR (isolated config dir), ANTHROPIC_BASE_URL (proxy
endpoint).
Hooks management
After running mosaic wizard, Claude hooks are installed in ~/.claude/hooks-config.json.
mosaic config hooks list # Show all hooks and enabled/disabled status
mosaic config hooks disable PostToolUse # Disable a hook (reversible)
mosaic config hooks enable PostToolUse # Re-enable a disabled hook
Set CLAUDE_HOME to override the default ~/.claude directory.