Setting up the browser view failed on every container, and re-running it
reproduced the same broken state, because the setup destroyed its own work.
`install_packages` ran two `npm install --no-save` commands into
/workspace, which has no package.json. With no manifest, npm treats the
command line as the whole statement of what the tree should contain and
prunes the rest, so installing `playwright` second removed the
`@playwright/cli` installed first: "removed 3 packages", leaving an empty
node_modules/@playwright/ behind playwright and playwright-core. That
empty directory is exactly what the pane then reported as missing. The
second install now names both specs; the first one is already present, so
it costs nothing and is only there to stop npm pruning it.
Two failures were waiting behind that one:
Nothing in the tree ever configured the browser, so playwright-cli fell
back to channel `chrome` — system Google Chrome — with the Chromium
sandbox on. These containers forbid unprivileged user namespaces, so it
aborted with "Failed to move to new namespace ... Operation not
permitted"; on a base image without Google Chrome the same default failed
as "Chromium distribution 'chrome' is not found". entrypoint.sh now seeds
~/.playwright/cli.config.json on every start, which is the only way to
reach existing projects: ~/.playwright is inside the home volume, so an
image copy would reach new projects only.
The launch check passed for a configuration the viewer never uses. It
launched bundled chromium with no channel, which resolves to
chromium-headless-shell, while the viewer's config pins
chrome-for-testing — the full chromium build, a separate download. A
container could pass every check and still fail in the pane with 'Browser
"chrome-for-testing" is not installed', which is what a stale
chromium-1217 against a wanted chromium-1237 did. Chromium is now
verified on both channels, the sandbox setting is stated rather than
inherited from a default, and a failure names the channel.
triple-c-playwright-heal repairs all of it on a container that is already
broken, including the missing socat that makes the pane report
"127.0.0.1 sent an invalid response" while the container side is
perfectly healthy. It verifies by launching a browser rather than
trusting the preceding steps — which is how the stale-revision case was
found — and lives in /usr/local/bin so a fix to it can still reach an
existing project.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Every scheduled task failed with "Not logged in · Please run /login" while
the container's OAuth credential sat there, valid, the whole time.
The entrypoint snapshots the environment into ~/.claude/scheduler/.env so
cron jobs get more than cron's minimal env. It runs as root, and HOME was
in the capture list, so the file recorded HOME=/root. The task runner then
sources that file with `set -a`, overwriting the HOME cron gave the job.
`claude -p` looks for its credential under $HOME, finds no /root/.claude,
and exits 1. Logging still worked — SCHEDULER_DIR is expanded before the
sourcing — which is why this presents as a well-formed log of a task that
never authenticated.
Drop HOME from the captured set and write it explicitly instead; cron does
still need one. Then restore HOME across the source in the task runner too:
.env lives on the home volume, so every project created before this ships
keeps a stale copy of it until its container restarts, and the runner is
what has to survive that.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Behind a TLS-terminating corporate proxy every HTTPS call inside a container
fails — npm, pip, git, curl, the browser-view pane, and Claude Code's own API
requests. There was no mechanism at all: installing the certificate by hand
inside a container is lost on Reset and had to be repeated per project.
A global CA path in AppSettings with a per-project override on Project, taking
either a single certificate file or a directory. It is bind-mounted read-only
at /tmp/.host-ca (mirroring /tmp/.host-ssh and /tmp/.host-aws) and applied by
entrypoint.sh on every start, so it survives recreation, migration and Reset.
Four things this gets right that are easy to get wrong:
* update-ca-certificates globs *.crt case-sensitively, so a .pem that is merely
copied in is ignored in silence. Certificates are renamed, by
container_cert_name() in Rust and a mirrored few lines of shell.
* The system store only serves curl/git/apt. Node — and so Claude Code itself —
needs NODE_EXTRA_CA_CERTS, Python needs REQUESTS_CA_BUNDLE/SSL_CERT_FILE, and
Chromium reads neither: it wants ~/.pki/nssdb, seeded with certutil
(libnss3-tools, added to the image).
* Those vars are set from Rust at creation, never exported by the entrypoint —
a terminal is a docker exec and sees nothing the entrypoint exported. They are
emitted empty when no CA is configured, since docker commit bakes env into the
snapshot image.
* triple-c.ca-fingerprint hashes the certificate bytes as well as the path, so
a CA rotated in at the same location still forces a recreation.
Verified end to end against a real container and a self-signed CA: curl, node,
python and git all complete a TLS handshake against a server signed by it and
all three fail in the same container without it; the env vars are visible from
a docker exec session; the store is cleaned when the setting is cleared.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01KSP2KNPhuWKQ4DL5TZEn3k
Projects were pinned to the image they were first created from. Both
create paths preferred triple-c-snapshot-<id>:latest whenever it
existed, and container_needs_recreation compared the container's live
image against the triple-c.image label — which create_container wrote
from the same image it created from. A tautology that could never fire.
The only escape was Reset, which calls remove_project_volumes and
destroys the login, skills and transcripts.
Measured consequences on this host: real projects are missing socat (so
the auth bridge cannot tunnel) and bubblewrap (so sandbox mode does not
work), plus Mission Control and triple-c-sso-refresh, and sit 61
packages behind the base including ca-certificates, openssl and curl.
Detection. create_container now writes triple-c.base-image-id (the image
ID, not RepoDigests, which local-built and custom images do not have)
and triple-c.create-image. container_needs_recreation takes the expected
create-image and compares against the latter, so the check means
something. base-image-id is deliberately NOT compared: a base bump would
otherwise silently recreate from the snapshot, consuming the "you should
migrate" signal without migrating. Staleness is surfaced, never acted on
automatically.
Migration keeps the volumes. /home/claude and ~/.claude are volumes and
the image's copy is seed-only — permanently masked after first mount —
so the login, ~/.claude.json, skills, transcripts, scheduler tasks, SSH
keys, cargo, uv, ruff and Claude Code itself re-attach untouched. Only
root-level state is rebuilt: apt packages are replayed against the new
base rather than copied, so no stale libc is dragged forward, and
/usr/local, /opt and the non-bind-mounted parts of /workspace are copied
verbatim with tar --skip-old-files so they can never clobber a newer
base binary.
docker diff is not used: on a snapshot-derived container it reports only
changes since the last commit. Raw image-vs-image diffing is filtered
through dpkg ownership because it otherwise lies — 8,677 raw path
differences on a real project reduced to 2 genuinely user-authored
files, both loose /workspace-root files.
Crash safety. snapshot:latest keeps pointing at the old image until the
final commit, so any crash before it self-heals on next start. Later
crashes are caught by reconcile_project_statuses. The rollback pin is a
docker tag: 0.057s and 0 bytes. Rollback restores the system layer only
— volumes are never touched — and the UI says so rather than implying a
time machine.
Fixes an infinite recreation loop shipped with the MCP removal. docker
commit propagates labels to the image, so a container created from a
snapshot inherited its non-empty triple-c.mcp-fingerprint and the
one-shot shim recreated it again on every start, forever. Lineage labels
are now always written explicitly.
Documents the second, separate bug this uncovered: Dockerfile changes
under /home/claude never reach an existing project, migration or not,
because the volume masks them. Anything that must stay upgradable
belongs in /usr/local/bin or /opt, or must be seeded by entrypoint.sh.
145 Rust tests, 227 frontend tests, both builds clean.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Four features, plus a latent bug fix.
llama.cpp backend. Claude Code only ever speaks the Anthropic Messages
API — confirmed empirically by pointing it at a logging server, which
received POST /v1/messages?beta=true. llama-server implements that
natively (verified in its README, alongside --port default 8080), so
this is a plain base-URL backend with no translation shim, the same
shape as Ollama. Its --api-key defaults to none, so the auth token is a
placeholder Claude Code requires and llama-server ignores.
Model alias fix. ANTHROPIC_DEFAULT_HAIKU_MODEL is documented as "also
used for background functionality", and Triple-C set none of the alias
vars. So on every custom-endpoint backend, Claude Code resolved `haiku`
to an Anthropic model id and sent it to a local server that does not
have it — background features failed silently. All four
ANTHROPIC_DEFAULT_{OPUS,SONNET,HAIKU,FABLE}_MODEL vars are now pinned to
the backend's configured model, with an optional Haiku override, and
blanked for Anthropic and Bedrock so those keep Claude Code's defaults.
The deprecated ANTHROPIC_SMALL_FAST_MODEL is never emitted. Existing
Ollama and OpenAI-Compatible containers are recreated once so the new
env reaches them; the snapshot is preserved.
Model gateway. Optional LiteLLM sibling container, off by default,
mirroring stt.rs — this is what makes real OpenAI usable, since
api.openai.com has no /v1/messages. Pinned to v1.96.0 by tag and digest:
the 1.82.7/1.82.8 malware was PyPI-only and never affected the official
images, which is precisely why this builds FROM the image rather than
pip-installing, but 1.84.0 is still the floor for proxy CVEs (API-key
SQLi, Host-header auth bypass, MCP auth bypass). Binds 0.0.0.0 because
project containers consume it, and therefore always sets a master_key —
LiteLLM without one accepts any key. The provider key lives in the OS
keychain and is uploaded into a volume, never an image layer or label.
URL relay. A container-side xdg-open/BROWSER shim opens URLs in the
host's browser. Uses an OSC sequence to /dev/tty rather than a printed
sentinel, because the shim usually runs as a grandchild of a process
capturing its children's output. Degrades to printing the URL when no
terminal is attached, so scheduled tasks do not hang. Only http/https,
with control characters rejected before new URL() — which strips
newlines, so java\nscript: would otherwise parse as javascript:. Nothing
auto-opens; the user confirms. The web terminal shows a tap-to-open
banner instead, since that browser may be a phone across a tunnel.
Browser view. A Project Home tab that watches and takes over the browser
Claude drives with Playwright, using Playwright's own dashboard. Zero
image cost — Playwright stays user-installed. It does not reuse the auth
bridge's PortForward, which binds an unauthenticated port: correct for a
throwaway OAuth listener, wrong for mouse and keyboard control of a
browser in a passwordless-sudo container. Instead a token-gated loopback
proxy checks Host, then token or a forbidden-header origin signal,
before a byte reaches the container. Host ports are confined to
47820..=47827 so CSP frame-src can enumerate them rather than widening
to a wildcard, with a test asserting the two agree.
188 frontend tests, 107 Rust tests, both builds clean.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Permission modes: replaces the binary full_permissions flag with a
PermissionMode enum (Plan/Default/AcceptEdits/Bypass). Flag mapping is
defined once in PermissionMode::cli_args() and used by the terminal, the
web terminal, and the scheduler:
Plan -> --permission-mode plan
Default -> (no flag)
AcceptEdits -> --permission-mode acceptEdits
Bypass -> --dangerously-skip-permissions
Choices verified against `claude --permission-mode` on 2.1.226.
full_permissions is retained and effective_permission_mode() falls back
to it, so existing projects.json needs no migration.
Bug fix: triple-c-task-runner ran `claude -p ... --dangerously-skip-
permissions` unconditionally, ignoring the project's setting entirely.
It now reads TRIPLE_C_PERMISSION_MODE, which is injected into the
container, added to the reserved env blocklist, propagated through the
entrypoint's cron env filter, and tracked by a new
triple-c.permission-mode label so a change forces recreation.
Introspection: new commands/inspect_commands.rs exposes read-only views
into the container over docker exec — Claude sessions (parsed from
~/.claude/projects/<cwd>/<uuid>.jsonl), installed capabilities (skills,
agents, commands, hooks, plugins, natively-configured MCP servers), and
the triple-c-scheduler task list, logs and notifications.
Task/session ids are validated against a strict allowlist and every
parameterized call runs as a bare argv vector via bollard, so no shell
is involved. Stopped containers return empty results rather than errors.
No UI yet; that lands with the Project Home view.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Completes the removal begun in the previous commit.
Backend: deletes models/mcp_server.rs, storage/mcp_store.rs and
commands/mcp_commands.rs, the McpStore on AppState, the four IPC
handlers, Project::enabled_mcp_servers, build_mcp_servers_json(),
compute_mcp_fingerprint(), the MCP_SERVERS_JSON env injection, the
mcp-fingerprint label, and the whole MCP container lifecycle.
create_container() and container_needs_recreation() lose their
mcp_servers/network_name parameters.
Container: entrypoint.sh no longer merges MCP_SERVERS_JSON into
~/.claude.json. MCP_SERVERS_JSON stays in the reserved env blocklist.
Security: the Docker socket is no longer auto-mounted for stdio+Docker
MCP servers — it now mounts only when allow_docker_access is set.
Migration: old containers were created with
network_mode=triple-c-net-<projectId> and refuse to start once that
network is gone. docker/network.rs becomes docker/legacy_cleanup.rs with
label-driven, best-effort removal of leftover MCP containers and the
per-project network, called on both delete and recreate.
container_needs_recreation() now forces a rebuild for any container
carrying a non-empty triple-c.mcp-fingerprint label or attached to a
triple-c-net-* network, moving it onto the default bridge. Both can be
dropped a release later.
Docs: drops the MCP sections from README/HOW-TO-USE/TECHNICAL and adds a
short note pointing at Claude Code's native `claude mcp` / `/mcp` /
.mcp.json instead.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
git rejects `--global` and `--file` together ("error: only one config
file at a time"), so the credential helper and user.name/user.email
were never written — /home/claude/.gitconfig was left nonexistent and
containers had no git identity or HTTPS token helper.
Drop `--global` and keep `--file /home/claude/.gitconfig`, which is the
intended target: the entrypoint runs as root at that point, so
`--global` would have resolved to /root/.gitconfig, and the existing
`chown claude:claude /home/claude/.gitconfig` already assumes the
--file path.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
- M1 (race): don't mount the host AWS dir for static-credential Bedrock.
sync_bedrock_credentials() is the sole writer of ~/.aws/credentials in
that mode, and mounting /tmp/.host-aws let the entrypoint's
`rm -rf ~/.aws; cp -a` race that write at startup (only when a global
aws_config_path was also set). Static keys + AWS_REGION env are
self-sufficient and don't need the host config, so skipping the mount
removes the dual-writer entirely.
- L-a: exit codes are now read via wait_for_exec_exit(), which polls
inspect_exec until the exec reports finished, so a non-zero tar/cred
exit isn't missed by reading exit_code too early. The backup only fails
on a definitively non-zero code (falls back to the empty-output check
if undeterminable).
- L-b: fixed two comments that referenced the old
write_bedrock_static_credentials name (now sync_bedrock_credentials).
- L-c: entrypoint only rewrites ~/.claude.json when awsAuthRefresh is
actually present, avoiding a needless jq reformat on every non-SSO
start.
- L-d: backup script traps EXIT to remove its mktemp staging dir even
when tar fails, so failed backups don't accumulate temp dirs (with the
sanitized config copy) in the container.
L-e (drop routing) is a non-issue: the layout is tabbed, so only one
terminal pane is ever visible; the active-guard routing is correct.
Verified the race fix, trap cleanup, grep guard, and exit-code polling.
cargo check / tsc / vitest all pass.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
When a project switched backends (e.g. Bedrock -> Anthropic), the
recreated container kept authenticating against Bedrock, and SSO kept
firing after switching away. Three root causes, all fixed:
1. Recreation builds the new container from a `docker commit` snapshot.
commit always bakes the previous container's full ENV into the image
(an empty commit Config does NOT strip it, and the commit API cannot
remove env). So CLAUDE_CODE_USE_BEDROCK=1 / AWS_* survived into the
new container. Fix: create_container now explicitly clears every
managed auth key the active backend does not set (MANAGED_AUTH_KEYS),
so create-time env overrides the stale baked-in values.
2. awsAuthRefresh was written into ~/.claude.json (persisted home
volume) and never removed, so Claude Code kept invoking
triple-c-sso-refresh after switching to a non-SSO backend. Fix:
entrypoint now deletes awsAuthRefresh when AWS_SSO_AUTH_REFRESH_CMD
is unset, idempotent both ways.
3. Static/session AWS creds were baked into Config.Env at create time,
so a stop/start kept stale creds and rotated keys never refreshed
without a full recreation. Fix: static creds are no longer injected
as env vars; write_bedrock_static_credentials() writes
~/.aws/credentials (0600, secrets via exec env not argv) on every
start, and removes a stale ~/.aws/config left from a prior profile/SSO
session. Static creds also dropped from the bedrock fingerprint so a
key rotation refreshes in place instead of forcing recreation.
Adds exec_oneshot_env() for env-carrying one-shot execs.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add a time-bounded `claude update` to entrypoint.sh that runs as the
claude user before the container is marked ready, so every terminal
session launches the latest CLI. Non-fatal and capped at 120s so an
offline/slow network never blocks container readiness; PATH covers both
~/.claude/bin and ~/.local/bin install locations.
Add flex-shrink-0 to the FileManagerModal header/footer so a long file
list can't squeeze them and the scroll region stays robust.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds first-class support for Claude Code CLI features (2.1.71-2.1.110):
- New ClaudeCodeSettings struct with per-project and global defaults for
TUI mode, effort level, focus mode, thinking summaries, session recap,
auto-scroll, env scrub, and 1-hour prompt caching
- Settings injected as env vars (CLAUDE_CODE_NO_FLICKER, etc.) and
~/.claude/settings.json entries via entrypoint.sh merge block
- New ClaudeCodeSettingsModal component for configuring settings
- Session naming support (-n flag passed to claude CLI, shown in tabs)
- Relaxed reserved prefix filter: CLAUDE_CODE_* env vars now allowed in
custom env vars UI for power users
- Global SSH key path, git name, and git email now used as fallbacks
when per-project values are not set, with UI in SettingsPanel
- Fingerprint-based change detection triggers container recreation when
Claude Code settings change
- Updated README, HOW-TO-USE, and CLAUDE.md documentation
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The mission-control (Flight Control) project is being closed upstream.
This embeds the project files directly in the repo under container/mission-control/,
bakes them into the Docker image at /opt/mission-control, and copies them into place
at container startup instead of git cloning from GitHub.
Also adds missing osc52-clipboard, audio-shim, and triple-c-sso-refresh to the
programmatic Docker build context in image.rs.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
SSO login was broken in containers due to three issues: the sso_session
indirection format not being resolved by Claude Code's AWS SDK, SSO
detection only checking sso_start_url (missing sso_session), and the
OAuth callback port not being accessible from inside the container.
This fix runs SSO login on the host OS (where the browser and ports work
natively) by having the container emit a marker that the Tauri app
detects in terminal output, triggering host-side `aws sso login`. The
entrypoint also inlines sso_session properties into profile sections and
injects awsAuthRefresh into Claude Code config for mid-session refresh.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add reconcile_project_statuses command that checks actual Docker container
state on startup, preserving Running status for containers that are genuinely
still running and resetting stale statuses to Stopped
- Add is_container_running helper using Docker inspect API
- Frontend calls reconciliation after Docker is confirmed available
- Update TECHNICAL.md project structure, auth modes, and file listings to
match current codebase
- Update README.md and HOW-TO-USE.md with MCP servers, Mission Control,
file manager, bash shells, clipboard/audio shims, and progress modal docs
- Add workflow file self-triggers to CI path filters for build-app.yml
and build.yml
- Install Mission Control skills to ~/.claude/skills/ in entrypoint
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When enabled, the entrypoint clones mission-control into ~/mission-control
(persisted on the home volume) and symlinks it to /workspace/mission-control.
Flight Control global and project instructions are programmatically appended
to CLAUDE.md. Container recreation is triggered on toggle change.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When using AWS Profile auth (SSO) with Bedrock, expired SSO sessions
caused Claude Code to spin indefinitely. Three root causes fixed:
1. Mount host .aws at /tmp/.host-aws (read-only) and copy to
/home/claude/.aws in entrypoint, mirroring the SSH key pattern.
This gives AWS CLI writable sso/cache and cli/cache directories.
2. For Bedrock Profile projects, wrap the claude command in a bash
script that validates credentials via `aws sts get-caller-identity`
before launch. If SSO session is expired, runs `aws sso login`
with the auth URL visible and clickable in the terminal.
3. Non-SSO profiles with bad creds get a warning but Claude still
starts. Non-Bedrock projects are unaffected.
Note: existing containers need a rebuild to pick up the new mount path.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add Model Context Protocol (MCP) server configuration support. Users can
define MCP servers globally (new sidebar tab) and enable them per-project.
Enabled servers are injected into containers as MCP_SERVERS_JSON env var
and merged into ~/.claude.json by the entrypoint.
Backend: McpServer model, McpStore (JSON + atomic writes), 4 CRUD commands,
container injection with fingerprint-based recreation detection.
Frontend: MCP sidebar tab, McpPanel/McpServerCard components, useMcpServers
hook, per-project MCP checkboxes in ProjectCard config.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Introduces a cron-based scheduler that lets Claude set up recurring and
one-time tasks inside containers. Tasks run as separate Claude Code agents
and persist across container recreation via the named volume.
New files:
- container/triple-c-scheduler: CLI for add/remove/enable/disable/list/logs/run/notifications
- container/triple-c-task-runner: cron wrapper with flock, logging, notifications, auto-cleanup
Key changes:
- Dockerfile: add cron package and COPY both scripts
- entrypoint.sh: timezone setup, cron daemon, crontab restore, env saving
- container.rs: init=true for zombie reaping, TZ env, scheduler instructions, timezone recreation check
- image.rs: embed scheduler scripts in build context
- app_settings.rs + types.ts: timezone field
- settings_commands.rs: detect_host_timezone via iana-time-zone crate
- SettingsPanel.tsx: timezone input with auto-detection
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Enable restrictive Content Security Policy in tauri.conf.json instead
of null (disabled), restricting scripts/connects to self + Tauri IPC
- Fix shell injection in entrypoint.sh by replacing su -c with direct
git config --file writes, preventing names with quotes (e.g. O'Brien)
from breaking startup or enabling code execution
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Support per-project environment variables injected into containers,
plus global and per-project Claude Code instructions written to
~/.claude/CLAUDE.md inside the container on start. Reserved env var
prefixes are blocked, and changes trigger automatic container recreation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Support pulling images from registry (default: repo.anhonesthost.net/cybercovellc/triple-c/triple-c-sandbox:latest),
local builds, or custom images via a new settings UI. Add global AWS configuration
(config path auto-detect, profile picker, region) that serves as defaults overridable
per-project for Bedrock auth.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Entrypoint now runs as root to remap the container's claude user
UID/GID to match the host user, fixing bind mount permission errors
on WSL
- SSH keys are mounted read-only to a staging path (/tmp/.host-ssh)
and copied to ~/.ssh with correct permissions by the entrypoint
- Exec sessions explicitly run as the claude user
- Host UID/GID detected automatically and passed as env vars
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Tauri v2 desktop app (React/TypeScript + Rust) for managing
containerized Claude Code environments. Includes Gitea Actions
workflow for building and pushing the sandbox container image,
and a BUILDING.md guide for manual app builds on Linux and Windows.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
