- 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
ChatSettingsStore keeps each chat's IANA zone in <AgentDir>/telegram/chat-settings.json;
ChatTimeZoneService is the one path for a change (store, live session, scheduler re-evaluation,
reply text). ChatRegistry.TimeZoneFor now reads the store and new sessions start in the chat's zone.
/timezone, the set_timezone tool (ChatSettingsExtension), /status zone line, DEFAULT_TIMEZONE.
The store updates its cache under the write gate so the last file written is the newest state.
Spec: a skipped one-off fires after the next start; the late note's placement and no-exit-code failure wording are pinned down; IsDeliverable is part of the watcher invariant and must not create a session; saves snapshot inside a serialising gate.
Spec: on Windows the command goes through Arguments like the bash tool, since cmd.exe doesn't parse ArgumentList quoting; the workspace is created if missing, and a timeout vs cancellation outcome is spelled out.
jobs.json is { "version": 1, "jobs": [...] } in VolcanicJson camelCase,
written to jobs.json.<pid>.tmp and moved into place through one semaphore.
A corrupt file is renamed jobs.json.corrupt-<timestamp> and loading starts
empty. Each entry is deserialised on its own, so an entry with an unknown
kind or a missing required field is dropped with a warning like any other
invalid job instead of setting the whole file aside.
- A speech or download timeout (TaskCanceledException nobody asked for) is a failure
with the user notice, not a silent shutdown; OpenAiSpeechToText maps it to
"the request timed out."; UpdateRouter only treats the caller's cancellation as shutdown.
- send: WorkspacePaths resolves the real path component by component (realpath),
closing the directory-link-inside-target bypass; `.` reports a directory.
- Image documents are attached inline only when their magic bytes are JPEG/PNG/GIF/WebP,
under the detected type.
- Audio goes to STT as an ASCII audio.<ext> name.
- MCP Browser section mentions send only when it is active.
- RunInOrderAsync takes a cancellation token; queued work is skipped once disposal gives up;
SendReplyAsync stays private behind ReplyInOrderAsync.
- Speech HttpClient handler recycles pooled connections; BuiltInTools.Send();
IExtensionHost.Channel is abstract; WorkspacePaths in its own file.
- Tests: timeouts, symlink chains (Linux), sniffing, channel delivery failures,
queued-work cancellation, gated voice ordering. Spec and docs updated.
telegram-bot.md: what you can send, files from the agent, speech settings, security notes. ui-integration.md: document/voice input rows and a new section 5 on IChatChannel. architecture, extensions and CLAUDE.md list IChatChannel. Drop the interim paragraph from the message-context spec; mark the attachments spec implemented with resolved questions.
Content step 3 (InboundMedia.AddSpeechAsync): voice and audio go through ISpeechToText, the transcript is echoed as '🎤 …' and prompted as '[Voice message] …'. Spec §4 edited: audio is transcribed from the file step 2 saved (one download); an oversize or undownloadable voice note sends its notice and isn't prompted.
Content step 2 (InboundMedia.AddFilesAsync, InboxFiles): files land in <cwd>/inbox/<date>-<safe name>[-N], image documents within Telegram:InlineImageMaxBytes are attached inline, oversize files and failed downloads get a notice and no run. Documents, videos, audio and voice are accepted; the unsupported reply is now 'I can read text, photos, files and voice messages.'
Spec: Updates helpers are named DocumentMessage/VideoMessage/VoiceMessage/AudioMessage; the getFile 'file is too big' notice reads 'over 20 MB'; the too-large inline note is a parenthesised suffix after the size; size formats spelled out.
Spec 5: the HttpClient registration is named as AddHttpClient<ISpeechToText, OpenAiSpeechToText>() (package Microsoft.Extensions.Http), which is how Program.cs registers it.
Add TelegramLimits, TelegramChatChannel (every delivery through
ChatRenderer.RunInOrderAsync, auto photo falls back to a document on a 400)
and wire it into ChatRegistry as AgentSessionOptions.Channel and
ChatContext.Channel. Spec: SendTextAsync names its failure text
("Telegram did not accept the message.") and throws when any chunk fails.
SendTool (Tool<SendArgs>, sequential) confines the path to the workspace including symlinked files and parent directories (WorkspacePaths), checks caption, photo and document limits before sending, and picks Document for non-photo extensions (.gif included) or oversized images under kind auto. Not registered yet; that is the next task.
Adds the host-agnostic IChatChannel contract (ChatFile, ChatDelivery, ChatChannelLimits, ChatDeliveryException) to Abstractions/Ui, AgentSessionOptions.Channel, AgentSession.Channel and IExtensionContext.Channel. IExtensionHost.Channel is an internal plumbing default member that ExtensionContext forwards. Test support: FakeChatChannel and the TestHost builder's Channel.
- redact /mcp output, and stderr lines as they arrive (log, errors, tail)
- take host servers by name: configuration binding sorts keys anyway
- dispose kills the tree only without an exit code and only if the pid's
start time matches the spawn (no kill of a reused pid)
- idle timer generation guards stale callbacks; catalogue check runs in
the background with a 10 s cap; shutdown stops servers concurrently
- stop resets a failed status; /mcp shows an exited process; ordinal names
- spec: ${workspace} in command, ordering, dispose and /mcp wording
The fake logs its start only after the .NET runtime is up; under full-suite
load that took over 1 s, the client killed it first and the start entry was
missing.
The TZ test checks TZ is absent on Windows: the process policy never sets TZ there (process-environment-hook spec §3). Spec testing bullet and plan updated to match.
Spec: /mcp shows no pid (the SDK doesn't expose it) and never shows env values; the prompt section follows the server's own tools; the built-in collision check covers inactive built-ins.
McpServerConnection starts the session's server lazily through
PrepareProcessAsync, applies the call timeout, reports exits with the
stderr tail and restarts on the next call, stops when idle, and supports
StopAsync (reusable) and idempotent DisposeAsync. McpTool exposes a
catalogue entry as an ITool and maps results with McpResultMapper.
Spec change (§5, Decisions): ModelContextProtocol.Core 2.2.0 does not send
notifications/cancelled when a request's token fires (verified against the
fake server), so calls go out through SendRequestAsync with their own
request id and the connection sends notifications/cancelled itself on abort
and timeout. Also documents exit detection, StopAsync vs DisposeAsync and
JSON-RPC errors as ordinary error results, per the plan.
McpProcess starts a server through the SDK stdio client under the startup
timeout and keeps a stderr tail for its errors. McpCatalogCache runs one shared
discovery per server config in a temp dir, with the environment from the process
spawn policy. It keeps successes for the process lifetime and failures for 60 s.
Deviation from the plan: the discovery process is disposed and its temp dir
deleted in the background, after the catalogue is returned. SDK 2.2 waits the
whole ShutdownTimeout (5 s) with stdin still open before it kills the process,
so an awaited dispose held every first activation for 5 s. A new test
(Discovery_returns_without_waiting_for_the_server_shutdown) covers this. Spec
section 3 gets the new GetAsync signature, the detached discovery and the
background cleanup. Section 5 now describes the SDK's shutdown order correctly.
- log an unknown stored zone once even when the tool description reads it first
- serialise the flow's token write with /calendar_disconnect under the flow gate
- a cancelled or expired pending flow is cleared, not re-sent or shown
- chat keys anchor with \z so a trailing newline is hashed
- a timeMax date includes that whole day (spec updated)
- dispose the flow's CancellationTokenSource, drop ConnectFlow.Token, Begin is a plain write
- GoogleCalendarOptions.IsConfigured replaces the host's copy of the rule; StoredToken is internal
- test BotSetupService's menu through DI, tokens absent from tool results
- Telegram.Tests csproj reference placed as in telegram-message-context; ChatHost passes calendar by name
- docs: per-event timeZone, both config sources for /calendar_*
Spec: the fake uses the SDK's server API from ModelContextProtocol.Core and gains the tools and modes the tests need (weird_name_x, a >48-char name, builtin-clash, --output-dir browser tools, die message and exit code, count-starts details, slow cancellation log).
- /resume discards the inbox once the id names one conversation, before any await
- /stop discards input still waiting in the window
- a forwarded message is never a command or a pending answer
- ChatInbox.DrainAsync is an internal test helper
- tests: /resume and /stop drop buffered text, forwarded /new is content,
a failing flush doesn't stop later batches; no wall-clock sleep in the drain test
- spec and user docs: timestamp exception for extension commands, command
ordering, InputDebounce=0 wording
McpOptions/McpServerConfig/PlaywrightOptions with ApplyEnvironment (PLAYWRIGHT_* variables, quote-aware ExtraArgs split) and Validate; ShellWords; mcpServers from the user settings.json. New project in the solution and referenced by the extension tests.
