* fix(slack): route DM thread replies to main session instead of thread-scoped session
DM thread replies (user replies inside a thread under a bot message in a
DM) were routed to a thread-specific session key instead of the user's
main DM session. This caused the agent to never receive the inbound on
the expected session, making the bot appear unresponsive.
The root cause was in prepare-routing.ts: canonicalThreadId for
isDirectMessage was set to threadTs when isThreadReply was true, creating
a session key like agent:main:slack:direct:u3🧵<ts>. DM threads
are a UI affordance — not a session boundary — so all DM messages should
route to the main DM session regardless of thread_ts.
Also adds a diagnostic logVerbose warning when assistant_app_thread
message_changed events fail sender resolution (Case 2 of #82390),
which was previously completely silent.
Fixes#82390
* chore(slack): polish DM thread routing PR
* test(slack): update DM thread routing contract
* test(slack): flatten non-main DM thread expectations
* fix(slack): preserve bound DM thread routes
* test(slack): align DM thread session fixtures
* fix(slack): keep flattened DM thread metadata scoped
* fix(slack): preserve DM thread delivery routes
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Fixes#82576.
Keeps post-compaction token totals fresh across stale usage updates and adds regression coverage for the repeated auto-compaction loop. Also includes maintainer fixups needed to keep the touched CI lanes green: guarded GitHub Copilot device-flow fetches, dead-session metadata recreation, and current cron stale-data expectations.
Co-authored-by: njuboy11 <njuboy11@users.noreply.github.com>
* Fix bundled channel dist-runtime setup roots
Resolve bundled channel generated entries from dist-runtime before falling back to source paths, and select the dist-runtime plugin root as the boundary root for packaged setup modules. This keeps the fs-safe module open boundary check intact while preventing packaged bundled setup entries from being checked against the source extensions root.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Repair session store validation test fixtures
Update current-main tests that wrote persisted session entries without valid session IDs after session store loading started filtering invalid entries. Keep the fixture-only repair separate from the bundled channel loader fix.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Repair pairing and cron validation fixtures
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Route WebChat image attachments through the configured imageModel when the active session model cannot accept images, while keeping one-turn image auth and fallback state ephemeral.
Thanks @frankekn.
Threads the runtime config through buildKnownAgentRunFailureReplyPayload
into resolveExternalRunFailureTextForConversation so the documented
agents.defaults.silentReply / surfaces.<id>.silentReply policy is
consulted before silencing failure copy in groups/channels. Default
policy (group: allow, direct: disallow, internal: allow) preserves the
existing 'groups stay quiet on generic runner failure' behavior; opting
into silentReply.group: disallow now lets the run-failure copy reach
the chat instead of disappearing.
Resolves an internal inconsistency: route-reply.ts already routes
NO_REPLY-style payloads through resolveSilentReplyPolicy(), but the
failure-fallback path in agent-runner-execution.ts hardcoded silence on
chat type alone, ignoring the operator-visible knob.
Refs #82060.
* feat: attach recent inbound history images
* fix: bound recent history media downloads
* fix: preserve sticker history media
* fix: enforce history media cap for stickers
* refactor: name agent turn attachments generically
* refactor: share pending history media recording
* fix: gate historical media attachment visibility
* fix: avoid media runtime on text-only turns
* fix: preserve fallback history media selection
* fix: avoid sparse media history index collisions
* fix: skip history images for current non-image media
* test: import history media type directly
* test: satisfy agent media runtime mock lint
* fix: respect mocked Slack media fetches
* fix: settle history media recording races
Keep queued system-event owner downgrades as structured runtime metadata while rendering the model-visible prompt as plain `System:` lines.
This preserves least-privilege wakeups for webhook/node/exec/cron/reaction/hook producers, keeps legacy `trusted: false` compatibility for installed plugins and older hosts, and updates representative gateway, agent, cron, plugin, and OpenGrep coverage.
Summary:\n- Add optional per-agent bootstrap profile overrides for contextInjection, bootstrapMaxChars, and bootstrapTotalMaxChars.\n- Resolve per-agent bootstrap profile settings before agents.defaults and thread the resolved session agent through embedded, compact, CLI, and /context diagnostic paths.\n- Update schema/help/docs/changelog plus focused runtime, schema, and /context regression coverage.\n\nVerification:\n- Local focused auto-reply tests and formatter checks passed.\n- Local pnpm check:changed passed before landing follow-ups.\n- Local Node 24 pnpm check:test-types passed after merging latest main into the PR branch.\n- GitHub PR state CLEAN at 0ff12062840f42daf2666c5fabb127c3f7631669.\n- ClawSweeper re-review completed successfully with no actionable repair finding.\n\nFixes #69966.
