Repository navigation
feat(server): goal mode for Scient Agent - #924
Merged
4 commits merged intoNov 14, 2026
Merged
4 commits merged into
4 commits merged into
Conversation
Scient Agent now reports the prompt-cache entry each reply confirmed (tier, touch time, lifetime) on its message_end. Desktop turns a one-hour entry into promptCacheExpiresAt on the turn's token usage, the field the Claude path already fills. Idle compaction then works for Scient Agent as it does for Claude: "Before the cache expires" sends /compact two minutes before the cache lapses on a thread over 200,000 tokens, and "When you return" offers the Compact chip once the cache has expired. A five-minute entry carries no expiry, so a short pause never triggers a compaction, and a cache that never expires reports none. Scient Agent instances get the same "Compact idle threads" override as Claude ones, and the setting text names both. Agents that do not report the entry keep today's behaviour. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The event schemas dropped promptCache, so idle compaction never saw the cache expiry in the live app. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This was referenced Nov 14, 2026
Contributor
Thread transfer impact✅ Thread transfer remains within every enforced ceiling.
Other scenariosAll 64 scenario measurements match All 64 scenario measurements
Baseline: Scenario and decoded snapshot size10 historical turns, 5 command tools per turn, 878.9 KiB retained MCP result per historical turn, and a 1.05 MiB retained result in the measured turn.
Updated in place by a trusted workflow. PR artifacts are strictly validated and never executed. |
/goal now works with Scient Agent as it does with Codex and Claude. Desktop sends it to the agent's goal command instead of refusing it: an objective sets the goal (replacing one the agent holds), and pause, resume, clear and show map to the agent's ops. The agent's goal_updated events fill the thread's goal row, so the existing goal UI shows status, tokens and time, with its Resume and Clear buttons. The agent works on an active goal in turns it starts itself. Desktop turns on goal continuation over RPC in the settings file it writes for the agent, and those turns arrive through the existing path for turns the agent began. A refused goal command (goal mode off, plan mode active) is answered in the conversation, not a failed turn. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A goal continuation is a turn the agent starts by itself. Desktop ended it as soon as the buffered wake events were replayed, so each goal turn showed "Worked for 40ms" and its reply was split across turns. The turn now stays open until the agent's own end event. The event schemas also kept dropping the goal, so the goal row never showed. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
yaacovcorcos
force-pushed
the
claude/goal-mode-20261113
branch
from
November 14, 2026 18:34
afc527c to
6f588b9
Compare
yaacovcorcos
enabled auto-merge
November 14, 2026 18:35
92a8b80
github-merge-queue
Bot
removed this pull request from the merge queue due to it being already merged
Nov 14, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Platforms: the same server code on macOS, Windows and Linux; no platform-specific parts. Tested live on macOS only.
What
/goalnow works with Scient Agent as it does with Codex and Claude./goalto the agent'sgoalRPC command instead of refusing it (provider/omp/OmpGoal.ts). An objective sets the goal, replacing one the agent holds; pause, resume, clear and show map to the agent's ops.goal_updatedevents fill the thread's goal row, so the existing goal UI shows status, tokens and time, with Resume and Clear.goal.continuationModes: [interactive, rpc]in thescient-host.ymlit writes, and those turns arrive through the existing path for agent-started turns.nativeTurnOpeninNativeSessionAdapterV2.ts; only the OMP adapter sendscontinuation-started, so other providers are unaffected).effect-omp-rpcevent schemas keep the newgoalfield; before this they dropped it.Agents: needs no agent change. Today's published agent (0.1.10) has the
goalcommand.T3 files change only inside SCIENT-FORK seams.
Merge order: #923 → #924 → #925 → #926, all based on
mainand queued in that order; each branch sits on the one before it, so its diff shrinks to its own change as they merge.Tests
OmpGoal.test.ts: a new objective replaces the held goal (get, drop, create) and ends as a local-command turn; refusals and show/clear answers land in the conversation;goal_updatedmaps to the thread's goal.NativeSessionAdapterV2.test.ts"keeps a turn the agent started open until the agent ends it": fails without the fix ("Created notes" instead of "Created notes.txt").pnpm run typecheck,vp fmt --check,vp lint, seam check and provenance./goal Create a file named goal-check.txt ...ran as one turn ("Worked for 9.5s"), the reply in one piece, and the goal row read "Goal complete · 49k tokens". Record and screenshots:reviews/scient-agent-next-20261111/build-all-20261113/agentmodes-RECORD.mdin the ScientFactory workspace.🤖 Generated with Claude Code