- Each run's first text delta replaces the response artifact (append:false) and a resumed task
drops the previous run's response, so a failed/canceled continuation never keeps old text.
- Resumed is built from a fresh store read, history chronological (question, then answer),
timestamps on the TaskUpdater clock.
- Pool.Track refuses a second unfinished run of the same task; the pre-check rejects
continuations of a running task with UnsupportedOperation.
- Tests: continuation history, streaming continuation, response replacement, concurrent
continuation; busy test waits for the model call; TimeoutException in waits; push test
matches TASK_STATE_COMPLETED; harness cleans up on failed start.
A continued task (input-required -> new message) produced only status updates, so the SDK
answered 'Agent handler did not produce any response events'. The handler now enqueues the
resumed task (caller message and question in history, working) as the first event.
The guarded SocketsHttpHandler sets UseProxy = false: a proxy would make the connection and
skip the ConnectCallback address check.
While on, the admin's updates are routed as the target user's (allow-list,
chat, workspace, session, settings, jobs) and the target chat's output goes
to the admin's chat. The target's own updates are dropped with a notice that
an admin is working with their account. In memory; /impersonate 0 stops.
Claude Code 2.1.287 loads cc-plugin-* built-ins regardless of --setting-sources,
which tripped the fail-closed init check. Disable every known built-in in
--settings, and when init lists only built-ins that slipped through, disable them
process-wide and replay the request once. Other plugins still fail closed.
ChatRegistry -> JobScheduler -> IScriptEnvironment -> ChatRegistry made the host
fail at startup. CalendarScriptEnvironment now takes TelegramOptions and computes
the workspace with the new static ChatRegistry.WorkspaceFor(options, chatId).
token.json is sealed with AES-256-GCM (key derived from the OAuth client secret,
bound to the chat), so the agent's processes can read the file but not the
refresh token. Plain files, including VolcanicSecretary's refresh_token format,
are rewritten sealed on first read.
The scheduler gains IScriptEnvironment: extra per-run variables set after the
process environment filter and redacted from the run's output. The Telegram
host uses it to pass GOOGLE_ACCESS_TOKEN, refreshed to cover the job's timeout;
the refresh token and client secret never reach the script.
Each chat's jobs live in <workspace>/.volcanic/scheduler/jobs.json. On start the
scheduler loads every chat's file, moves the retired shared
<agentDir>/scheduler/jobs.json into them and renames it .migrated-<ts>.
A VolcanicSecretary jobs.json (bare array) in a chat's folder is converted
in place for that chat; the original is kept as .secretary-<ts>.
Also adds the VolcanicSecretary data migration plan.
Jobs are prompts or watchers. A reminder is a prompt the agent passes on, so
it lands in the transcript. Stored reminder jobs load as prompts
("Remind me: <text>"). Also records the Coolify deploy target in CLAUDE.md.
Tokens now live in <cwd>/.volcanic/google-calendar/token.json, as in the
VolcanicSecretary reference, instead of <agentDir>/google-calendar/<chat
key>/. GoogleCalendarOptions.TokenDirectory, when set, keeps the old
per-chat layout under that root. Spec, docs and CLAUDE.md updated.
Entrypoint drops the capability bounding set and sets no_new_privs. Security docs
and spec no longer claim the agent can't reach the secrets; docker exec fallbacks
use a clean environment. PLAYWRIGHT_ENABLED drops the nested compose default.
Tests pin the Dockerfile's Playwright install step and the compose model fallback.
Status implemented, verification intro rewritten, and a verification record of the final checks (dotnet build/test, both image variants, offline probes of uid, /proc environ and the diagnostics socket, playwright-mcp --version offline, headless Chromium as app, docker compose config, compose start with a fake token -> 401 -> exit 1). Open question 2 (Playwright compose default) marked resolved.
Image contents, build arguments, the environment table with what the agent's processes can't see, volumes, Coolify steps, first Claude login, updating (the npm layer is cached: build without cache or pin CLAUDE_CODE_VERSION), extensions, troubleshooting and security.
One bot service with init: true, 1 GB /dev/shm, three named volumes and every setting as an environment variable; PLAYWRIGHT_ENABLED follows INSTALL_PLAYWRIGHT. .env is git-ignored.
INSTALL_PLAYWRIGHT=true installs @playwright/mcp@0.0.82 globally and runs its own playwright dependency's installer (install --with-deps chromium) into /opt/ms-playwright, readable by all users. The build fails if playwright-mcp --version does not run.
Two-stage build, agent tools, Node 24, claude CLI, data dirs owned by app, DOTNET_EnableDiagnostics=0. Adds the MCP spec's deferred test that the Dockerfile's PLAYWRIGHT_MCP_VERSION equals PlaywrightPreset.DefaultPackage.
Spec change: the image keeps root as its user and the entrypoint drops to app with setpriv. With USER app, compose's docker-init (PID 1) runs as app and its /proc/1/environ exposes every secret to the agent's bash. The spec also lists the csprojs the restore layer copies (GoogleCalendar, Mcp, Scheduler included) and sets HOME=/home/app in the image.
The fake claude never starts the proposal bridge, so the test needs a
session with no active tools. Since the scheduler spec every chat
registers set_timezone, which made the provider wait for the bridge and
fail with mcp_startup on Linux (the test returns early on Windows).
- JobScheduler: a stored job whose zone lookup throws no longer fails StartAsync; timer re-armed under the lock;
a delivery cut off by shutdown isn't recorded (one-offs fire again after restart); CancelJobAsync in one step
- Schedules.ParseAt: ISO 8601 with a date only (no machine-clock date for a bare 09:00)
- core: a FollowUp prompt that loses the race to a starting run joins it as a follow-up, not steering
- Telegram: TimeZoneFor tolerates non-numeric targets; RunPromptAsync waits only when queued; one agent dir
- ScriptRunner: bad workspace paths are Failed, not exceptions; zone id helpers share TimeZoneIds.ToIana's rule
- tests: no wall-clock sleeps in scheduler tests; transcript-entry, disabled-scheduler and failing-prompt coverage
- docs: spec notes for the above; README row for the scheduler
