Address Greptile review: when sessionKey is undefined the fallback
matched any enabled cron job, which could silently suppress the guard
note due to jobs from unrelated sessions. Return false instead so the
note always appears when session scoping is not possible.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Before appending the "I did not schedule a reminder" guard note, check the
cron store for enabled jobs matching the current session key. This prevents
false positives when the agent references an existing cron created in a
prior turn (e.g. "I'll ping you when it's done" while a monitoring cron is
already running).
The check only fires on the rare path where the text matches commitment
patterns AND no cron was added in the current turn, so the added I/O is
negligible.
Closes#32228
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor(skills): use explicit skill-command scope APIs
* test(skills): cover scoped listing and telegram allowlist
* fix(skills): add mergeSkillFilters edge-case tests and simplify dead code
Cover unrestricted-co-tenant and empty-allowlist merge paths in
skill-commands tests. Remove dead ternary in bot-handlers pagination.
Add clarifying comments on undefined vs [] filter semantics.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor(skills): collapse scope functions into single listSkillCommandsForAgents
Replace listSkillCommandsForAgentIds, listSkillCommandsForAllAgents, and
the deprecated listSkillCommandsForAgents with a single function that
accepts optional agentIds and falls back to all agents when omitted.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(skills): harden realpathSync race and add missing test coverage
- Wrap fs.realpathSync in try-catch to gracefully skip workspaces that
disappear between existsSync and realpathSync (TOCTOU race).
- Log verbose diagnostics for missing/unresolvable workspace paths.
- Add test for overlapping allowlists deduplication on shared workspaces.
- Add test for graceful skip of missing workspaces.
- Add test for pagination callback without agent suffix (default agent).
- Clean up temp directories in skill-commands tests.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(telegram): warn when nativeSkillsEnabled but no agent route is bound
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: use runtime.log instead of nonexistent runtime.warn
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
The followup runner (which processes queued messages) was calling
runEmbeddedPiAgent without currentChannelId or currentThreadTs.
This meant the message tool's toolContext had no channel routing
info, causing reactions (and other target-inferred actions) to
fail with 'Action react requires a target' on queued messages.
Pass originatingTo as currentChannelId so the message tool can
infer the reaction target from context, matching the behavior
of the initial (non-queued) agent run.
The /\s+/g whitespace normalizer collapsed newlines along with spaces/tabs,
destroying paragraph structure in multi-line messages before they reached
the LLM. Use /[^\S\n]+/g to only collapse horizontal whitespace while
preserving line breaks.
Closes#32216
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds group context fields to MessageSentHookContext so hooks can
correlate sent events with received events for the same conversation.
Previously, message:received included isGroup/groupId but message:sent
did not, forcing hooks to use mismatched identifiers (e.g. groupId vs
numeric chat ID) when tracking conversations.
Fields are derived from MsgContext in dispatch-from-config and threaded
through route-reply and deliver via the mirror parameter.
Addresses feedback from matskevich (production user, 550+ events)
reported on PR #6797.
Adds two new internal hook events that fire after media/link processing:
- message:transcribed: fires when audio has been transcribed, providing
the transcript text alongside the original body and media metadata.
Useful for logging, analytics, or routing based on spoken content.
- message:preprocessed: fires for every message after all media + link
understanding completes. Gives hooks access to the fully enriched body
(transcripts, image descriptions, link summaries) before the agent sees it.
Both hooks are added in get-reply.ts, after applyMediaUnderstanding and
applyLinkUnderstanding. message:received and message:sent are already
in upstream (f07bb8e8) and are not duplicated here.
Typed contexts (MessageTranscribedHookContext, MessagePreprocessedHookContext)
and type guards (isMessageTranscribedEvent, isMessagePreprocessedEvent) added
to internal-hooks.ts alongside the existing received/sent types.
Test coverage in src/hooks/message-hooks.test.ts.
The `fromMe` flag from Baileys' WAMessage.key was only used for
access-control filtering and then discarded. This meant agents
could not distinguish owner-sent messages from contact messages
in DM conversations (everything appeared as from the contact).
Add `fromMe` to `WebInboundMessage`, store it during message
construction, and thread it through `buildInboundLine` →
`formatInboundEnvelope` so DM transcripts prefix owner messages
with `(self):`.
Closes#32061
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When enforceFinalTag is active (Google providers), stripBlockTags
correctly returns empty for text without <final> tags. However, the
handleMessageEnd fallback recovered raw text, bypassing this protection
and leaking internal reasoning (e.g. "**Applying single-bot mention
rule**NO_REPLY") to Discord.
Guard the fallback with enforceFinalTag check: if the provider is
supposed to use <final> tags and none were seen, the text is treated
as leaked reasoning and suppressed.
Also harden stripSilentToken regex to allow bold markdown (**) as
separator before NO_REPLY, matching the pattern Gemini Flash Lite
produces.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
After a drain loop empties the queue it deletes the key from
FOLLOWUP_QUEUES. If a new message arrives at that moment
enqueueFollowupRun creates a fresh queue object with draining:false
but never starts a drain, leaving the message stranded until the
next run completes and calls finalizeWithFollowup.
Fix: persist the most recent runFollowup callback per queue key in
FOLLOWUP_RUN_CALLBACKS (drain.ts). enqueueFollowupRun now calls
kickFollowupDrainIfIdle after a successful push; if a cached
callback exists and no drain is running it calls scheduleFollowupDrain
to restart immediately. clearSessionQueues cleans up the callback
cache alongside the queue state.
* feat(agents): support `thinkingDefault: "adaptive"` for Anthropic models
Anthropic's Opus 4.6 and Sonnet 4.6 support adaptive thinking where the
model dynamically decides when and how much to think. This is now
Anthropic's recommended mode and `budget_tokens` is deprecated on these
models.
Add "adaptive" as a valid thinking level:
- Config: `agents.defaults.thinkingDefault: "adaptive"`
- CLI: `/think adaptive` or `/think auto`
- Pi SDK mapping: "adaptive" → "medium" effort at the pi-agent-core
layer, which the Anthropic provider translates to
`thinking.type: "adaptive"` with `output_config.effort: "medium"`
- Provider fallbacks: OpenRouter and Google map "adaptive" to their
respective "medium" equivalents
Closes#30880
Made-with: Cursor
* style(changelog): format changelog with oxfmt
* test(types): fix strict typing in runtime/plugin-context tests
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
