0f0fa7f1ea
Invert the delivery verdict from negative to positive evidence. Previously, success was declared by the ABSENCE of a draft snippet on a prompt line: if the `❯|^>|│ >` glyph matched nothing (busy-receiver draft on an unmatched line, or wrong-pane drift), an UNSUBMITTED message read as "✓ delivered" exit 0 — a silent worker->lead relay stall (filed by UC-LEAD, PR #3046: three review verdicts reported delivered but never surfaced for ~50 min). Fix: success now requires POSITIVE evidence — either the queued banner, or the REPL input box located AND clear of the message tail. If the input box cannot be located, status is `unconfirmed` -> exit 2 + stderr ("could not confirm submission ... may be UNDELIVERED"). The near-dead `*)` indeterminate default also flips from silently returning 0 to exit 2. Bracketed-paste and double-Enter delivery mechanics are unchanged; queued/draft/delivered semantics are preserved, only the failure-mode default direction changes. Adds `test-send-message-verdict.sh`: 3 real tmux-pane fixtures (delivered / unconfirmed-glyphless / draft) locking the fail-loud verdict logic, and upgrades `test-send-message-socket.sh` fixtures from a glyphless bash prompt to `❯`-prompt REPLs so the patched binary can read delivery positively. Reproduce-first evidence (baseline vs patched, glyphless-pane fixture): baseline: rc=0, stdout "✓ delivered to =noglyph" (silent false positive) patched: rc=2, stderr "could not confirm submission ... may be UNDELIVERED" Test results after port: test-send-message-verdict.sh -> PASS=3 FAIL=0 test-send-message-socket.sh -> ok Firewall: grep -niE 'jason|woltje|jarvis' on changed files = 0 hits; tools/quality/scripts/verify-sanitized.sh -> sanitization gate passed. shellcheck: 1 pre-existing SC2034 finding (unused loop var `attempt`, present identically in baseline) carried through; 0 new findings. Part of #891
@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.