Repository navigation
feat(mcp): queue standing, snooze-respecting sends, scheduled model changes, clearer delegate and thread-id errors - #94
Conversation
Codex Review Summary: ❌ FailedThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
chrisohearn
left a comment
There was a problem hiding this comment.
Independent Claude Opus review of 6b7205d (review of record)
Read-only review of the diff and source. No tests run (resource rule). The code matches a566769; 6b7205d adds only the 0017 decision record. GitHub reports MERGEABLE, with CI still pending.
P2
SnoozeDeferredDelivery.ts:105,118withOrchestrator.ts:15445and:15686/:15555: the sweep reuses the commandIdsnooze-deferred-release:<firstRunId>. Whenqueue.resumeis refused (for example "Continue the limited thread...", because a person snoozed a thread whose last run hit a usage limit), the refusal is saved as a rejected receipt. Every retry then replays that rejection, so the "retries in a minute" path is dead. The held turns stay held until someone acts in the app, becauselimit-resume(agent/server) does not release held runs. Fix: don't record this refusal, or derive the commandId per attempt. Add a test for a refused release.
P3
Orchestrator.ts:7003-7006:respectsSnoozechecks the rawsnoozedUntil, notisSnoozed(). A thread the sidebar shows as awake (woke on error, a pending request, a guest message) still holds agent sends until the stored date. The warning tells the sender, so this isn't blocking.Orchestrator.ts:15449: the sweep'squeue.resumereleases every held queued run on the thread, including holds made for other reasons (a missing worktree, background work). That is the same as a manual resume, but worth knowing.Orchestrator.ts:978,1005: runs queued before a schedule follow the scheduled selection even if they carry an explicit model pick. The doc covers only picks made after scheduling.threadReference.ts:40: ifmcp:Xis deleted and a liveXexists,Xis returned silently instead of "deleted". In practice this is very unlikely.Orchestrator.tsnear :6995: this conflicts textually with #93 (git merge-treeconfirms). The two changes are compatible: add #93'sserverNoticetoautomaticWakeand keeprespectsSnooze. BecauserespectsSnoozerequires!automaticWake, server notices keep the snooze under both. Whichever PR merges second resolves it.
Checks
- (a) Links: non-T3 hosts fail to parse, and v2 or hosted links to another environment are refused. Lookups go only through
getThreadShellin this environment. Reads have no per-thread grant, so nothing is widened. No path or SQL use of the input. - (b) Held turns persist in run payload, survive a restart (recovery keeps held queued runs), and stay out of
releaseUnattendedHoldsand the failure release. Every release path clears the flag. Release order is delivery order. The sweep is gated by DueHint and runs one grouped query per tick on the partial index. Usage-limit snoozes still wake (exactresetAtmatch, aslimitRecoverysets it). The exception is P2. - (c) The schedule is stored in the thread payload, so it survives a restart. It clears on the first start with no earlier queued run, or on a regular change. It touches no runtimeMode: MCP refuses
applyAtwithruntimeMode, andprovider.switchis refused. - (d) Error messages add ids, slugs, project paths and environment ids. No secrets. (e) Tool list +409 bytes (56426→56835); needs the
agent-context-increaselabel. (f) No migration files; the new fields are optional JSON.
Verdict: no blocking findings
…mcp: uuids 18 of Jarvis's 27 thread_not_found results were bare uuids of mcp: threads, likely from hosted links that escape mcp: as mcp%3A. Reads now resolve t3-thread:// v1 and v2 links, hosted links and bare uuids, say when a thread was deleted, and name the closest ids otherwise. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A send that queues behind a busy run now returns its queue position, the messages ahead of it, the active run and its age, and whether the queue is held. Same-thread waits run 17 to 49 minutes, and senders had no way to see why. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Three of six delegate_task failures in two days were a cross-project target.projectId, whose error never said that t3_thread_launch with projectId starts work in another project. That error now does, and the provider, driver, model, worktree and linked-project errors name the field at fault and list what is accepted. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…thread The Jarvis inbox always has a run going, so every effort change was refused as busy. With applyAt: "next_turn", the change is stored on the thread and the next turn starts with it. Messages queued before it start with it too, the way messages queued before a failover follow the thread. It clears once none of those wait. Reading the configuration shows the pending change, and scheduling the current model cancels it. Provider instance switches and runtime mode changes still need an idle thread. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…for outside agents Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A scheduled model or option that the provider rejects would fail each queued message in turn, so configure now checks it before scheduling. applyAt without modelSelection is now an error instead of a silent read. Also tests the queue standing a queued send returns. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…heduled change Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
On 2026-11-13 a worker's handoff woke two threads that were snoozed until 11-18 and 11-24, because any send or post ended a snooze. Agent sends and posts now leave a snoozed thread asleep by default. A send is held behind the thread's last run until the snooze ends or someone unsnoozes it, and a post is only recorded. Both results report snoozedUntil with a warning, and respectSnooze: false keeps the old waking behavior. Messages sent from the app still wake the thread. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A turn held for a snooze lost its hold whenever a later background run completed, and nothing stopped a released turn that failed from being released again by the sweep. Automatic releases now skip deferred turns, and any release clears the deferral. Usage-limit snoozes, which the server sets itself, still wake on a send. t3_thread_send_attachments keeps the snooze too, and the snooze notice reflects the thread's state after the send. The release sweep is now tested on the test clock. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
… model changes (0017) Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…ed model picks From the PR #94 review: - A refused queue.resume left a fixed command id whose rejected receipt every retry replayed. Each release attempt now gets its own id, and a usage-limit resume releases snooze-held turns once the thread is awake. - Snooze checks use isSnoozed, so a thread that woke on an error or a request stops holding agent messages. isSnoozed moves to SnoozeState.ts to avoid an import cycle. - A scheduled model change leaves queued messages that named a model alone, and later sends take the change, not an older queued pick. - A deleted thread asked for by its exact id is reported as deleted, not swapped for its bare uuid. - Shorter respectSnooze and applyAt text: the tool list grows 270 bytes, not 409. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
… tip Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
6b7205d to
cfe85b0
Compare
|
Coordinator: the agent-context-increase label on this PR is now the maintainer's decision on record. +270 bytes for the queue, snooze and schedule options, after an independent review with no blocking findings; paid evals waived (no spend). Workers: please don't apply this label yourselves; it's reserved for the coordinator after review. |
chrisohearn
left a comment
There was a problem hiding this comment.
Independent delta review of cfe85b0 (review of record, follows 6b7205d review)
Read-only review of the diff and source; no tests run. A range-diff against 6b7205d shows the 11 rebased commits are unchanged apart from the #93 conflict in Orchestrator.ts and the budget number. The new commits are 146946f (the review fixes) and cfe85b0 (budget only). GitHub reports MERGEABLE, with CI pending (budget check passes).
- P2 fixed.
SnoozeDeferredDelivery.ts:121now usessnooze-deferred-release:<firstRunId>:<nowMs>, so each attempt gets its own command id and a refusedqueue.resumeis retried every 60 s instead of replaying the rejected receipt. The test refusessnoozedonce, then retries it and asserts that the two commandIds differ.releaseUnattendedHolds(:3246-3272) now releases snooze-deferred runs onceisSnoozedis false and clears the flag, so a usage-limit resume releases them. No test covers that limit-resume path directly. - P3s fixed. Snooze checks use
isSnoozed(moved toSnoozeState.ts) in the send path, the release path and the sweep. The sweep also wakes onruntime-request.updated. Runs queued with a named model getexplicitModelSelectionand keep that model (test added). A deleted exactmcp:id now reports "was deleted" instead of resolving to its bare uuid (tests added). - #93 resolution OK.
serverNoticeis declared at:6996, above the settle block.automaticWake = notification || delegatedCompletion || serverNotice(:7023-7026). The guard isif (snoozedUntil != null && !automaticWake && !respectsSnooze). A server notice is therefore an automatic wake: it keeps the snooze and is never held. TherespectsSnoozeblock differs from 6b7205d only by the intendedisSnoozedterm. - Budget OK: base 57258, head 57528, so +270 bytes (was +409).
Non-blocking (P3):
queueTailModelSelection:threadAtRunStartclears the scheduled change once only explicit-pick runs remain queued before it. If no send has been queued after the schedule, a new agent send in that window inherits the older explicit pick, not the scheduled model.- A
respectSnooze: truesend to a thread thatisSnoozedshows as awake only because of a pending request or guest message now clears the stored snooze. The thread then does not re-snooze when the request resolves. Consider skipping the hold without unsnoozing.
Verdict: no blocking findings
… into tmp/r4-w4-94-on-tip # Conflicts: # apps/server/src/orchestration-v2/Orchestrator.ts # apps/server/src/provider/agentContextBudget.json # packages/contracts/src/orchestratorMcp.ts
… held Resuming a queue, an unfreeze included, released every queued run. That included turns an agent's send held for a snooze that still holds the thread. queue.resume now leaves those while the thread is snoozed. The snooze sweep only resumes awake threads, so it still releases them. The sweep also skips frozen threads, whose queue only an unfreeze resumes. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
chrisohearn
left a comment
There was a problem hiding this comment.
Independent merge-resolution check of b564470 (follows cfe85b0 review). Diff-only, blobless clone, no tests run.
- Merge bfe4be4:
--remerge-diffshows three conflicts (Orchestrator.ts, orchestratorMcp.ts, agentContextBudget.json) plus one extra edit (SnoozeDeferredDelivery.ts,$.frozen IS NULL). The other 29 #90 files match7eddc7fc51..f0e6e4a325line for line. Nothing from #90 or #94 was dropped (Orchestrator deletions = #90's own + the two resolved #94 lines). - (1)
frozenHold= frozen && !postOnly, whateverautomaticWake/respectSnoozesay, so server notices and snooze-respecting agent sends queue held (queueBehindRunfalls back to latestRun;queueHeldORs respectsSnooze || frozenHold).startNextQueuedRunalso returns early while frozen. Snoozed but unfrozen: onlyrespectsSnoozesends are held. - (2) The sweep skips frozen threads, so nothing lifts a freeze except the gated unfreeze. b564470 makes queue.resume keep
snoozeDeferredruns whileisSnoozed, so an unfreeze does not release a hold for a snooze still in force. Releases after wake are unchanged, and unfreezing emits thread.* events, so the sweep checks the thread again. That is the intended split, and the new ThreadFreeze test covers it. - Note (non-blocking): this also covers a user's plain queue.resume on a snoozed thread, which used to release those turns. queued-run.start with a runId still starts one, because
startNextQueuedRunpicks it by id regardless of queueHeld. - Contracts: the send result keeps #90's
held/frozenand #94'squeue/...SnoozeNotice. Budget: base 57258, #94 +270, #90 +670, so 58198 is additive and consistent. - (4) No other changes: the merge has only those regions, and b564470 has only the queue.resume filter and its test.
Verdict: no blocking findings
…ol-reliability t3_thread_configure reads its configuration only when none of modelSelection, runtimeMode, applyAt and acknowledgeOnly is given. Budget re-measured on the tip. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
chrisohearn
left a comment
There was a problem hiding this comment.
Independent merge-resolution check of c5992fb (follows b564470 check)
Read-only Claude Opus review run by the round-four coordinator. Codex hosted review is at its usage limit, so this is the review of record.
- Worked from a fresh blobless clone. No tests run locally. GitHub CI on this head is all green, including Agent context budget, Typecheck, Lint and Test Server 1-8. GitHub reports MERGEABLE/CLEAN.
- The merge parents are b564470 and a59003e. The old merge-base is f0e6e4a. The base side brings #86, #96 and #100.
git show --remerge-diffshows exactly three resolved regions: thet3_thread_configureread predicate inthread/handlers.ts,agentContextBudget.json, and one added line incore.test.ts. Nothing else changed beyond the clean merge.- I compared each changed file's diff on one side of the merge with its diff on the other side, in both directions. Outside those three regions every file matches. No #94 change is lost, and no #96, #86 or #100 change is dropped or altered.
- Predicate (
thread/handlers.ts:262-267): it reads only whenmodelSelection,runtimeMode,applyAtandacknowledgeOnlyare all undefined. Nothing that sets a field falls into the read path. The read result has bothscheduledModelSelection(#94) andacknowledgeOnly(#96). - Schema (
thread/tools.ts):applyAtandacknowledgeOnlyeach appear once. There are no duplicate fields, and the success union order is still correct. - Write paths:
acknowledgeOnlyis handled first and refusesmodelSelectionandruntimeMode.runtimeModeplusapplyAt,applyAtalone, andprovider.switchplusapplyAtare all refused. - Tests: the #94 busy-thread mock (
core.test.ts:1380) gained theacknowledgeOnlyread. The #96 and PeerForwarding mocks already had it. I found no other stale mock. - Budget: 57928 at the old base, plus 270 (#94) and 133 (#96), gives 58331, which matches the JSON. The two PRs edit different parts of the configure tool, so the sum is exact. The
agent-context-increaselabel is approved.
P1: None. P2: None.
P3 (follow-up, not blocking): thread/handlers.ts:129 (configureAcknowledgeOnly) does not refuse applyAt. {acknowledgeOnly: true, applyAt: "next_turn"} sets the mode now and silently ignores applyAt. Only combining the two PRs makes this pair possible. Nothing wrong is written. Fix: add || input.applyAt !== undefined to that guard, plus one refusal case in the configure test.
Verdict: merge
… model for default turns From the PR #94 delta review: - A default agent send to a thread that counted as awake only because of a pending request, guest message or error erased its dated snooze. It now delivers and keeps the stored snooze. So does a thread that has never run. The send's warning says it was delivered. - A scheduled model change was cleared once only explicit picks were ahead of it, so a later default message got the older pick. It now stays until a default-model turn starts with it, after everything queued before it, and a model named after the change replaces it. - Tests: a later completed run, such as a usage limit's resume, releases snooze-held turns only once the thread is awake. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
060bd88
into
integration/mcp-events-20261109
Round four, items 11, 11b, 14, 15 and 16 (ledger
r4/w4-tools). MCP tools failed or gave no useful feedback in five places where agents, mostly Jarvis, kept hitting them.In every acceptance check,
<deploy_ms>is the deploy time in epoch milliseconds.16.
t3_thread_resultandt3_thread_readaccept links and baremcp:uuidsEvidence. Jarvis's ChatGPT sign-in (
4d4ef9ba) gotthread_not_found27 times. The log stores no arguments, but request and response sizes identify the calls exactly:maxChars, answered with the existing "Did you meanmcp:<uuid>?" hint. Themcp:thread existed, and Jarvis retried anyway, in parallel bursts right afterportfolio_status.mcp:<uuid>with no live match. These remain open (see below).mcp:asmcp%3A, and a model drops that part. This is not verified.Change. A new fork-only file,
apps/server/src/mcp/threadReference.ts, resolves what was passed:t3-thread://v1 and v2 links, and hosted/threads/<env>/<id>links (percent-escaped ids included);mcp:thread, and the reverse.Only these two read tools resolve; write tools keep their exact-id checks. When nothing resolves, the error names the problem:
environmentId;t3_environment_linksandt3_thread_search.mcp:launch:ids already worked (106-byte requests succeed), and a test now covers them. The 9 unexplained misses stay open with no argument logging added: the new replies have distinct sizes ("deleted", "Closest", "not in this environment"), soresponse_byteswill show which case they are.Tests.
threadReference.test.tscovers every reference shape, a link to another environment, deleted, closest and unknown ids.OrchestratorMcpService.test.tsis updated for the new messages.Acceptance (read-only):
Pass:
bare_uuid_hintsis 0, and thenot_foundshare is well under the earlier 7.5% (20 of 341 overall).11.
t3_thread_sendreports where a queued message waitsEvidence. Waits come from queueing behind a busy run on the same thread: p50 is 17–19 minutes and p90 is 47–49. Idle starts take under 3 seconds at p90. Senders had no way to see this.
Change. When a send queues, the result gains an optional
queuefield:position(1 starts next) andmessagesAhead;activeRunIdandactiveRunAgeSeconds;heldwhen the queue waits for a resume.The order is the real delivery order, with automatic task completions first. The server reads only active and queued runs and their user messages. A failed read only leaves the field out, because the message is already queued.
t3_thread_postis not affected: post-only messages never create a run, so they never queue. Linked peers pass the field through, sinceRemoteDelegation.followUpspreads the result.Tests.
queueStanding.test.tscovers order, completion priority, held queues, no active run and a missing run.OrchestratorMcpService.test.tscovers the wiring and filters at a fixed clock.Acceptance. This one can't be read from the database. Check the next queued
t3_thread_sendto the Jarvis inbox while it runs: the result hasqueue.position,queue.messagesAheadandqueue.activeRunAgeSeconds.11b. Agent sends and posts keep a thread's snooze
Evidence. On 2026-11-13 a worker's evidence handoff woke two threads with dated holds, snoozed until 11-18 and 11-24 (
thread.unsnoozedat 02:21:12Z and 02:21:16Z, actor server). Nobody had released those holds. Everymessage.dispatchthat wasn't an automatic wake ended the snooze, post-only messages included.Change.
message.dispatchgainsrespectSnooze. On a snoozed thread:snoozeDeferred, and the snooze stays.SnoozeDeferredDelivery, resumes the queue once the snooze ends or someone wakes the thread. It uses the scheduler andDueHint, likeUsageLimitRecoveryWorker, and the partial queued-runs index keeps the query cheap.queue.resume, or an app message releasing held runs) clears the flag, so a later failure hold is never released by the sweep.releaseUnattendedHoldsand the preparation-retry release skip deferred turns, so a background run finishing during the snooze can't start them early.snoozeLimitedThreadsis on live). Those aren't anyone's hold.t3_thread_send,t3_thread_postandt3_thread_send_attachmentsdefault torespectSnooze: true. Send and post results carrysnoozedUntiland awarning, read from the thread after the dispatch, saying whether it was held, recorded, joined the running turn, or ended the snooze.respectSnooze: falsekeeps the old waking behavior.Why the MCP default is to respect the snooze. A snooze is a person's dated hold. The incident shows agents ending it with no intent to: relays, handoffs and supervisor nudges. An agent that must wake a thread can still say so with
respectSnooze: false, and the warning tells every sender what happened. The cost: a sender waiting on a snoozed thread now waits until it wakes. Repeated sends, such as supervisor nudges, each add a held turn, and all of them run at wake; the supervisor should skip snoozed rows.Tests.
runtimeLayer.test.ts: a held send and a post that keep the snooze, re-snoozing with a held turn, the real release query, and resume. A released turn loses its deferral.SnoozeDeferredDelivery.test.ts: the sweep on the test clock releases at snooze end and on a manual wake, exactly once, plus wake-time selection.OrchestratorMcpService.test.ts: the default, the override, and each warning.Acceptance (read-only):
Pass: after deploy, no unexplained
thread.unsnoozedevents from agent sends on threads with a future snooze. Held turns appear in the first count while their threads sleep, and leave it after they wake.Interaction with #93 (server notices keep a snooze). No double handling: the two paths cover disjoint messages.
postOnlywithcreationSource: "server") count as automatic wakes. They end no snooze, reopen nothing, and create no run.respectSnoozeand no automatic wake, and only MCP agent messages setrespectSnooze. A server notice therefore never becomes a held turn, andSnoozeDeferredDeliverynever sees one. The sweep only resumes heldsnoozeDeferredruns.automaticWakekeeps fix(server): stop labels for continued and provider-interrupted runs; server notices reopen nothing #93's three parts (notification, delegated completion,serverNotice), followed by this PR'srespectsSnoozeblock andif (... && !automaticWake && !respectsSnooze).apps/servertypecheck passed, and so did the focused files, includingRunStopandMcpEvents(275 tests), and the snooze, notice, post and model cases inruntimeLayer(38 tests).After review (6b7205d):
queue.resume(a limited provider, say) is no longer replayed from its rejected receipt. A usage limit's resume also releases snooze-held turns once the thread is awake. Tested: the sweep retries a refused release with a new id and then succeeds.isSnoozed, so a thread that woke on an error or a request stops holding agent messages and gets them released. Tested: a thread that failed after its snooze is released before its date.isSnoozedmoved toSnoozeState.ts, re-exported fromThreadSettlementService, to avoid an import cycle withOrchestrator.mcp:X) reports it as deleted instead of answering with a liveX.14.
t3_thread_configurecan schedule a model change on a busy threadEvidence.
invalid_requesterrors fromt3_thread_configureare the busy refusal on the Jarvis inbox. The 239-byte request matches{threadId: <inbox>, modelSelection: {codex_c12813c1…, gpt-6-luna, reasoningEffort: low}}byte for byte, and the 304-byte reply matchesOrchestratorProviderSelectionBusyError.~/.t3/worktrees/Codex Engineering Loop/t3-987e021a…. The thread's worktree path is~/.t3/scratch/2026-11-12-this-thread-is-the-inbox-a1c87c23. That workspace mismatch makes the switch plan restart the session, which a busy thread refuses.Change.
applyAt: "next_turn"onthread.model-selection.setand ont3_thread_configure:scheduledModelSelection(afterRunId,queuedThroughOrdinal) on the thread. It releases no session and applies nothing in-session.queuedRunFollowsThread). A run whose sender named a model keeps it (explicitModelSelectionon the run), and later implicit sends take the schedule rather than that older pick.queueTailModelSelection, and an idle start takes it too. Steers do not.{status: "scheduled", afterRunId, sequence};scheduledModelSelection;applyAtwithoutmodelSelection,applyAtwithruntimeMode(runtimeMode rules are unchanged), and switching provider instance (provider.switch), which still needs an idle thread.Known limits.
t3_queuehas no resume action. The acceptance check counts held runs on the inbox.Orchestrator.control-reads.test.ts). At the boundary it uses the existing explicit-pick switch path; the runtime-layer harness has no live sessions to restart.Tests.
Orchestrator.control-reads.test.ts: busy and idle, for both an instance switch and a session-restarting model change. The schedule is stored, and runs, sessions and outbox are untouched.runtimeLayer.test.ts: two runs queued before a schedule and one after. Each starts with the new model, and the schedule clears after the last earlier run starts.core.test.ts: the MCP result, the read view, and every refusal, including an unadvertised model.Acceptance (read-only):
Pass, after Jarvis schedules a lower effort (item 37):
modelSelectionshows the new effort once a run has started, andscheduledModelSelectionis null once the earlier queued runs have drained;15.
delegate_taskerrors name the field and the valid choicesEvidence. 6 of 24 calls failed, all in under 145 ms. The 240-second worst case is a normal
mode: "wait", not an error. Matched by reply size:RemoteDelegation);invalid_requeststays unmatched.Change. Each error now names the field and what is accepted:
t3_thread_launchwithprojectId: "<id>";t3_thread_launch);t3_project_listwith thatenvironmentId.Tests. The fork-only-driver delegation test is extended with the cross-project case, and the launch model test now expects the list.
Acceptance (read-only):
Pass: no repeated identical failures from one session. Each failure is followed by a corrected call or a
t3_thread_launch.Notes
Orchestrator.ts,ThreadManagementService.ts,runtimeLayer.ts,OrchestratorMcpService.ts,contracts/orchestrationV2.ts,contracts/orchestratorMcp.ts, the thread and attachment toolkit handlers,providerModels.ts,RemoteDelegation.ts,docs/user/outside-agents.mdanddocs/orchestration-v2/orchestrator-mcp-server.md. The new logic is in fork-only files:threadReference.ts,queueStanding.ts,snoozeNotice.tsandSnoozeDeferredDelivery.ts.applyAt, plusrespectSnoozeon send and post. Post's copy has no description, since its result warning explains it.agentContextBudget.jsonis updated. This needs theagent-context-increaselabel.docs/jarvis/decisions/0017-agent-sends-respect-snoozes-and-scheduled-model-changes.mdcovers the snooze default andapplyAt: "next_turn". Its number is provisional and settled at merge.mcp-tool-use --contextmeasured 74 tools. No existing case coversapplyAt,respectSnoozeor the new warning text. The fixes for items 16 and 11 are server behavior, which mocked eval tools can't exercise.apps/servertypecheck, all passing. Before the rule,check:changedfor items 11, 14, 15 and 16 passed (typecheck of 41 packages, 2,953 tests), and so did all ofsrc/orchestration-v2(2,789 tests). Hosted CI is the full gate.🤖 Generated with Claude Code