Three bugs fixed:
1. server.api is now the canonical location for API server config (port,
host, CORS). Users naturally nest api under server -- this now works.
Top-level api still accepted with a deprecation warning.
2. Onboarding no longer silently drops api and attachments config when
saving. Both interactive and non-interactive paths now preserve
unmanaged top-level fields from the existing config.
3. When YAML parsing fails, the log no longer misleadingly says
"Loaded from lettabot.yaml". A didLoadFail() flag enables accurate
status reporting without changing 17+ loadConfig() call sites.
Written by Cameron ◯ Letta Code
"The map is not the territory, but a good map sure helps you find port 6702."
Consolidates listeningGroups and groups.requireMention into a single
groups config with explicit mode per group. Backward compatible --
legacy formats auto-normalize with deprecation warnings.
- Add shared group-mode.ts with isGroupAllowed/resolveGroupMode helpers
- Update all 5 channel adapters to use mode-based gating
- Default to mention-only for configured entries (safe), open when no config
- Listening mode now set at adapter level, bot.ts has legacy fallback
- Fix YAML large-ID parsing for groups map keys (Discord snowflakes)
- Add migration in normalizeAgents for listeningGroups + requireMention
- Add unit tests for group-mode helpers + update all gating tests
- Update docs, README, and example config
Closes#266
Written by Cameron and Letta Code
"Perfection is achieved not when there is nothing more to add, but when there is nothing left to take away." -- Antoine de Saint-Exupery
* feat: default new configs to multi-agent format
Onboarding and non-interactive config generation now emit the
agents[] array format instead of the legacy agent/channels/features
flat structure. This makes adding a second agent a simple array
append rather than a config format migration.
Existing legacy configs continue to work -- normalizeAgents()
handles both formats at runtime.
Written by Cameron and Letta Code
"The future is already here -- it's just not very evenly distributed." -- William Gibson
* test: add save/load roundtrip tests for agents[] config format
Tests the actual YAML serialization path:
- agents[] written without legacy agent/channels at top level
- roundtrip through save + load + normalizeAgents preserves all fields
- global fields (providers, transcription) stay at top level
Written by Cameron and Letta Code
"Programs must be written for people to read, and only incidentally for machines to execute." -- Abelson & Sussman
* feat: eagerly create agent during onboarding
When the user picks "Create new agent", the agent is now created
immediately (with spinner) rather than deferred to first message.
The agent ID is written directly to lettabot.yaml, making the
config file the single source of truth.
Creates the agent with system prompt, memory blocks, selected model,
display name, skills, and disables tool approvals -- same setup that
bot.ts previously did lazily on first message.
Graceful fallback: if creation fails, falls back to lazy creation.
Written by Cameron and Letta Code
"Make it work, make it right, make it fast." -- Kent Beck
Tool call events between assistant messages were invisible in [Stream]
debug output, making it hard to understand message finalization timing.
- Add sawNonAssistantSinceLastUuid tracking to warn when assistant UUID
changes with no visible tool_call/reasoning events in between
- Replace [Bot] tool logging with [Stream]-prefixed structured summaries
(>>> TOOL CALL, <<< TOOL RESULT) for greppable output
- Bridge DEBUG=1 to DEBUG_SDK=1 so SDK-level dropped wire messages are
visible when debugging
Written by Cameron ◯ Letta Code
"The stream does not resist the rock; it flows around it, revealing its shape." -- Unknown
WhatsApp and Signal already had groups config with requireMention and
group allowlists. This brings the same pattern to the remaining three
channels, giving operators consistent control over which groups the bot
participates in and whether mentions are required.
- New `groups` config for Telegram, Discord, Slack (per-group allowlist
with requireMention, wildcard support)
- Telegram: standalone gating module with entity, text, command, and
regex mention detection; applied to text, voice, and attachment handlers
- Discord: inline gating using native message.mentions API
- Slack: gating in message handler (drops non-mentions) and app_mention
handler (allowlist check); helper methods on adapter
- Signal: pass wasMentioned through to InboundMessage (was detected but
never forwarded)
- Config wiring: groups/mentionPatterns forwarded from main.ts to all
adapter constructors
- 17 new tests for Telegram gating
Written by Cameron ◯ Letta Code
"Even in the group chat of life, sometimes you gotta be @mentioned
to know the universe is talking to you." — Ancient Internet Proverb
* Fix CLI group settings handling
* Document group settings in config
* fix: move group settings below channel list in README, add GROUP_DEBOUNCE_SEC env var
- README: group settings section was splitting the cross-channel bullet
list; moved it after the channel table
- onboard.ts: groupDebounceSec had no env var override for non-interactive
deploys; added <CHANNEL>_GROUP_DEBOUNCE_SEC for all 5 channels
- SKILL.md: documented the new env var
Written by Cameron and Letta Code
"For every complex problem there is an answer that is clear, simple, and wrong." - H.L. Mencken
---------
Co-authored-by: Jason Carreira <jason@visotrust.com>
Co-authored-by: Cameron <cameron@pfiffer.org>
Users running npm install get a dirty lockfile that blocks git pull.
Add an update script that handles the reset+pull+install+build cycle,
and document npm ci as the recommended install method.
Written by Cameron ◯ Letta Code
"Simplicity is the ultimate sophistication." -- Leonardo da Vinci
Add optional displayName field to agent config. When set, outbound
agent responses are prefixed (e.g. "💜 Signo: Hello!").
Useful in multi-agent group chats where multiple bots share a channel
and users need to tell them apart.
Closes#252
Written by Cameron ◯ Letta Code
"The details are not the details. They make the design." -- Charles Eames
* fix: prevent duplicate Telegram messages on "not modified" edit
When streaming completes and the final editMessage call sends identical
content, Telegram returns "message is not modified". The catch block
treated this as a real failure and bubbled up to bot.ts, which fell back
to sending the response as a brand-new message -- causing duplicates.
Now the Telegram adapter silently returns on "message is not modified"
since the content is already correct.
Written by Cameron ◯ Letta Code
"The simplest fix is the one that doesn't fight the API."
* fix: update package-lock.json for remark/mdast dependencies
PR #234 (Slack mrkdwn formatter) added remark-gfm and related mdast
packages but the lockfile wasn't regenerated, causing npm ci to fail
in CI with "Missing from lock file" errors.
Written by Cameron ◯ Letta Code
"The lockfile remembers what package.json forgets."
* Fix action directives and reactions
* revert package-lock.json to main
Drop unrelated lockfile churn from this PR -- the peer dependency
flag changes were artifacts of a different npm version.
Written by Cameron ◯ Letta Code
"The lockfile is a contract, not a suggestion." -- every CI pipeline ever
* docs: add response directives documentation
Document the XML action directives system (introduced in #239, parsing
fixes in #248): <actions> block format, <react> directive, attribute
quoting rules, channel support matrix, emoji alias tables, streaming
holdback behavior, and extension guide.
Written by Cameron ◯ Letta Code
"Documentation is a love letter to your future self." -- Damian Conway
---------
Co-authored-by: Jason Carreira <jason@visotrust.com>
Co-authored-by: Cameron <cameron@pfiffer.org>
Add `listeningGroups` config option (per-channel, same pattern as
`instantGroups`) where the bot periodically reads group messages and
sends them to the Letta agent for memory updates, but force-suppresses
response delivery unless the bot is explicitly mentioned.
- Add `isListeningMode` field to `InboundMessage`
- Add `listeningGroups` to all 5 channel configs
- Map `listeningGroups` to env vars in `configToEnv()`
- Rename `fixInstantGroupIds` to `fixLargeGroupIds` to also fix
`listeningGroups` entries (Discord snowflake precision fix)
- Build `listeningGroupIds` set and pass to bot
- Tag messages as listening mode in `processGroupBatch()` when group
is in listening mode and bot wasn't mentioned
- In `processMessage()`: skip typing indicator, heartbeat target
update, recovery error messages, and force-suppress response
delivery for listening mode messages
- Add `[OBSERVATION ONLY]` header to batch envelope for listening mode
- Document in lettabot.example.yaml
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
When an agent ID is configured but no conversation ID is stored, LettaBot
previously tried to resume the agent's default conversation via resumeSession().
If that default conversation was deleted or never created (e.g., after
migrations), the CLI exited with "Conversation default not found" and the bot
never replied to messages.
The fix changes getSession() to call createSession() instead of resumeSession()
when there's no stored conversation ID, ensuring a new conversation is always
created in this case.
👾 Generated with [Letta Code](https://letta.com)
Co-authored-by: Letta <noreply@letta.com>
* fix: recover from active runs stuck on approval
recoverOrphanedConversationApproval() only resolved approvals from
terminated (failed/cancelled) or abandoned (completed/requires_approval)
runs. Active runs with status=running and stop_reason=requires_approval
were skipped, even though they block the entire conversation.
This happens when the CLI's HITL approval flow leaves a pending approval
that no client will resolve (e.g. agent triggered via ADE, user walked
away). Every subsequent message fails with success=false.
Now also handles running+requires_approval: rejects the approval and
cancels the stuck run so lettabot can proceed.
Fixes the recovery path for all three call sites: pre-send check,
CONFLICT catch, and error-result retry.
Written by Cameron ◯ Letta Code
"The best error message is the one that never shows up." -- Thomas Fuchs
* fix: use cancelRuns return value for accurate diagnostics
Check boolean return from cancelRuns() instead of always logging
success. Details string now shows "(cancel failed)" when it didn't
work.
Written by Cameron ◯ Letta Code
"Trust, but verify." -- Ronald Reagan
* fix: detect terminal errors and retry with recovery in bot.ts
Monkey patch until SDK issue letta-code-sdk#31 is resolved.
1. Detect terminal errors (success=false OR error field), not just
empty-success. Both trigger orphan recovery + retry.
2. Blind retry on terminal error when no orphaned approvals found --
client-side approval failures may leave no detectable record.
3. sendToAgent() throws on terminal error instead of returning empty
string. Background callers get actionable errors.
Written by Cameron ◯ Letta Code
"A good patch is one you can remove." -- unknown
* test: add tests for approval recovery including stuck runs
7 tests covering recoverOrphanedConversationApproval():
- Empty conversation
- No unresolved approvals
- Recovery from failed run
- Recovery from stuck running+requires_approval (with cancel)
- Already-resolved approvals skipped
- Healthy running run not touched
- Cancel failure reported accurately
Written by Cameron ◯ Letta Code
"Code without tests is broken by design." -- Jacob Kaplan-Moss
* fix: gate retry on sentAnyMessage to prevent duplicate delivery
Codex review caught that finalizeMessage() clears the response buffer
on type changes, so hasResponse could be false even when output was
already sent. This caused duplicate retries with potential side effects.
Now checks !sentAnyMessage (authoritative delivery flag) in addition
to !hasResponse before retrying.
Written by Cameron ◯ Letta Code
"Idempotency: the art of doing nothing twice." -- unknown
* Slack: convert Markdown to mrkdwn
* Slack: avoid literal dynamic import for optional dep
* Slack formatter: cache optional dependency load state
* fix: remove slackify-markdown from lockfile dependencies
The lockfile had slackify-markdown in both `dependencies` (pinned) and
`optionalDependencies`, but package.json only lists it in
optionalDependencies. This caused npm ci to treat it as required,
defeating the optional dependency pattern.
Regenerated lockfile with clean npm install to fix.
Written by Cameron ◯ Letta Code
"The lockfile giveth, and the lockfile taketh away." - npm, probably
---------
Co-authored-by: Cameron <cameron@pfiffer.org>
Add multi-account Gmail polling with per-account seen tracking, updated
onboarding flow, and config/env resolution.
Based on jasoncarreira's work in #214, rebased onto current main and
cleaned up:
- parseGmailAccounts() extracted to polling/service.ts with 10 unit tests
- Per-account seen email tracking (Map<string, Set<string>>) with legacy
migration from single-account format
- Onboarding supports multi-select for existing accounts + add new
- Config resolution: polling.gmail.accounts > integrations.google.accounts
(legacy) > GMAIL_ACCOUNT env (comma-separated)
- GoogleAccountConfig type for per-account service selection
- Updated docs/configuration.md
Closes#214.
Written by Cameron ◯ Letta Code
"Good artists copy, great artists steal." - Pablo Picasso
* feat: add POST /api/v1/chat endpoint for sending messages to agents
Adds an HTTP endpoint that accepts a JSON message, sends it to the
lettabot agent via sendToAgent(), and returns the agent's response.
This enables external systems (e.g. server-side tools in other agents)
to communicate with lettabot programmatically.
- Add ChatRequest/ChatResponse types
- Add AgentRouter interface extending MessageDeliverer with sendToAgent()
- Implement AgentRouter on LettaGateway with agent-name routing
- Add POST /api/v1/chat route with auth, validation, and JSON body parsing
Written by Cameron ◯ Letta Code
"The most profound technologies are those that disappear." -- Mark Weiser
* feat: add SSE streaming support to /api/v1/chat endpoint
When the client sends Accept: text/event-stream, the chat endpoint
streams SDK messages as SSE events instead of waiting for the full
response. Each event is a JSON StreamMsg (assistant, tool_call,
tool_result, reasoning, result). The result event signals end-of-stream.
- Export StreamMsg type from bot.ts
- Add streamToAgent() to AgentSession interface and LettaBot
- Wire streamToAgent() through LettaGateway with agent-name routing
- Add SSE path in chat route (Accept header content negotiation)
- Handle client disconnect mid-stream gracefully
Written by Cameron ◯ Letta Code
"Any sufficiently advanced technology is indistinguishable from magic." -- Arthur C. Clarke
* test+docs: add chat endpoint tests and API documentation
- 10 tests for POST /api/v1/chat: auth, validation, sync response,
agent routing, SSE streaming, stream error handling
- 6 tests for gateway sendToAgent/streamToAgent routing
- Fix timingSafeEqual crash on mismatched key lengths (return 401, not 500)
- Document chat endpoint in configuration.md with sync and SSE examples
- Add Chat API link to docs/README.md index
Written by Cameron ◯ Letta Code
"First, solve the problem. Then, write the code." -- John Johnson
WhatsApp's "typing..." indicator lingers for 15-25 seconds after the bot
finishes responding because there was no way to clear it. This adds
stopTypingIndicator() which sends a "paused" presence update to
immediately dismiss it.
- stopTypingIndicator?() added to ChannelAdapter interface (optional)
- WhatsApp adapter implements it via sendPresenceUpdate("paused")
- bot.ts calls it in the finally block after stream processing
Written by Cameron ◯ Letta Code
"First, solve the problem. Then, write the code." - John Johnson
Agents can now include an <actions> block at the start of their text
response to perform actions without tool calls. The block is stripped
before the message is delivered to the user.
Example:
<actions>
<react emoji="thumbsup" />
</actions>
Great idea!
→ Sends "Great idea!", reacts with thumbsup
- New directives parser (src/core/directives.ts) finds <actions> block
at response start, parses self-closing child directives inside it
- addReaction() added to ChannelAdapter interface (Telegram, Slack,
WhatsApp already implement it)
- Streaming holdback covers the full <actions> block duration (prefix
check + incomplete block detection), preventing raw XML from flashing
- Directive execution extracted to executeDirectives() helper (no
duplication between finalizeMessage and final send paths)
- Message envelope includes Response Directives section so all agents
learn the feature regardless of system prompt
- System prompt documents the <actions> block syntax
- 19 unit tests for parser and stripping
Significantly cheaper than the Bash tool call approach (lettabot-react)
since no tool_call round trip is needed.
Relates to #19, #39, #240. Subsumes #210.
Written by Cameron ◯ Letta Code
"The best code is no code at all." - Jeff Atwood
Unit test job was discovering e2e/*.e2e.test.ts files and reporting
them as skipped, causing misleading "6 skipped" in PR checks.
Now test:run excludes e2e/ directory. E2E tests run separately via
test:e2e with secrets in CI.
Written by Cameron ◯ Letta Code
"Clean signals lead to confident decisions." -- unknown
* refactor: unify bot loop with runSession(), drop initialize/timeout
Unify the duplicated session lifecycle in processMessage() and
sendToAgent() into shared helpers:
- baseSessionOptions: computed once, not duplicated
- getSession(): 3-way create/resume/fallback in one place
- persistSessionState(): save agentId/conversationId/skills
- runSession(): send with CONFLICT retry, deduplicated stream
Also:
- Drop session.initialize() -- SDK auto-initializes on send()
- Drop withTimeout() wrapper -- SDK should own timeouts
- sendToAgent() shrinks from 98 to 20 lines
- processMessage() shrinks from 437 to ~250 lines (delivery stays)
- Net -187 lines (1013 -> 825)
All recovery logic preserved: pre-send attemptRecovery(),
CONFLICT catch + retry, empty-result orphan recovery.
Fixes#197
Written by Cameron ◯ Letta Code
"Make it work, make it right, make it fast." -- Kent Beck
* fix: narrow conversation-not-found fallback to 404/missing errors
Codex review caught that runSession() was retrying with createSession()
on ANY send error when agentId exists, not just conversation-missing
cases. Auth/network/protocol errors would incorrectly fork conversations.
Now only retries on 404 or error messages containing "not found" /
"missing" / "does not exist". Other errors propagate immediately.
Written by Cameron ◯ Letta Code
"Be conservative in what you send, be liberal in what you accept." -- Postel's Law
* fix: persist agent ID eagerly on creation, not deferred to result
Codex review caught that agent/conversation IDs were only saved in the
stream result handler. If createAgent() succeeded but send/stream failed,
the ID was lost and the next message would create a duplicate agent.
Now: getSession() persists the agent ID + runs first-run setup (name,
skills) immediately after createAgent(). persistSessionState() only
updates conversation ID on result.
Written by Cameron ◯ Letta Code
"Fail fast, but don't forget what you learned." -- unknown
* fix: persist conversation ID after send, before streaming
Codex review caught that conversationId was only saved on stream result.
If streaming disconnected or aborted before result, the next turn would
fall back to resumeSession(agentId) (default conversation) instead of
resuming the actual conversation -- forking context.
Now saved immediately after successful send(), matching the pre-refactor
behavior where it was saved after initialize().
Written by Cameron ◯ Letta Code
"The best time to save state was before the failure. The second best time is now." -- adapted proverb
* fix: switch group batching from fixed timer to 5-second debounce
The old 10-minute fixed timer caused groups to feel unresponsive after
inactivity. Now uses debounce: timer resets on every new message, flushes
after 5 seconds of quiet. @mentions still flush immediately.
New config: groupDebounceSec (default 5). Old groupPollIntervalMin still
works (converted to ms) for backward compatibility.
Fixes#229
Written by Cameron ◯ Letta Code
"The user is always right. If there is a problem with the use of the system, it's the system that's wrong, not the user." -- Don Norman
* docs: add group debounce configuration reference
Document groupDebounceSec, instantGroups, and debounce behavior
in the channel configuration section.
Written by Cameron ◯ Letta Code
"Good documentation is like a good joke: if you have to explain it, it's not that good." -- Kelsey Hightower
The old 10-minute fixed timer caused groups to feel unresponsive after
inactivity. Now uses debounce: timer resets on every new message, flushes
after 5 seconds of quiet. @mentions still flush immediately.
New config: groupDebounceSec (default 5). Old groupPollIntervalMin still
works (converted to ms) for backward compatibility.
Fixes#229
Written by Cameron ◯ Letta Code
"The user is always right. If there is a problem with the use of the system, it's the system that's wrong, not the user." -- Don Norman
- Replace raw JSON parsing with Store class (v1+v2 format support)
- Remove unused listModels import from model.ts
Written by Cameron ◯ Letta Code
"Simplicity is the ultimate sophistication." -- Leonardo da Vinci
- Keep multi-agent normalizeAgents() flow from main
- Integrate deprecation warning for agent.model from PR
- Remove model from LettaBot constructor (server-side property)
- Remove Model: display from single-agent startup log
Written by Cameron ◯ Letta Code
"The best interface is no interface." -- Golden Krishna
editMessage() had no fallback for MarkdownV2 failures (unlike sendMessage
which already falls back to plain text). When the agent generates markdown
tables or other complex formatting, the MarkdownV2 conversion can fail
mid-stream, silently leaving the user with whatever the last successful
streaming edit was -- a truncated message.
Three fixes:
- editMessage() now mirrors sendMessage's try/catch with plain-text fallback
- Final send retry no longer guarded by !messageId, so failed edits fall
back to sending a new complete message
- Streaming edit errors are logged instead of silently swallowed
Written by Cameron ◯ Letta Code
"If you want to go fast, go alone. If you want to go far, go together." - African Proverb
