Gate Search Assistant integration lookups with AppConfig by Sg312 · Pull Request #8301 · simstudioai/sim

Sg312 · 2026-09-25T17:31:00Z

Summary

Search Assistant can resolve people/resource IDs and read structured details through 39 existing read-only integration operations. The AppConfig flag mothership-search-integration-tools controls gateway discovery, calls, and the corresponding worker prompt instructions. It defaults off and has no environment-variable fallback.

When disabled, new Search requests omit the integration capability; discovery and execution also recheck the flag so an existing conversation cannot keep using it after the updated configuration is observed. The flag uses the shared AppConfig polling/cache behavior, including last-known-good values during AppConfig outages; it is a rollout toggle, while credential and authorization checks remain independent. Build and Plan retain their current integration tools. When enabled, Search uses the person's existing connected account and credential/visibility rules. Native results return normally; no OAuth scopes or additional Search result filtering are introduced. Writes and arbitrary MCP calls remain unavailable.

Sources: Slack, Gmail, Calendar, Drive, Sheets, Jira, Confluence, GitHub, GitLab, and Coda. GitLab personal-token operations retain the existing workspace-only restriction. Gmail labels and GitHub review threads are exposed through their existing shared tool catalogs. Generated-doc discovery now handles inherited version-mapped lists with appended operations.

Type of Change

Testing

492 focused and CI-regression tests passed after rebasing onto dev; includes on/off/on capability changes, revoked discovery/calls, and unchanged Build/Plan behavior.
New flag regressions failed before the guards were implemented, then passed.
Preserved dev's existing test-runner configuration; removing the inherited global mock-clearing override fixed the eight CI failures in older dev suites.
Sim typecheck, all 49 repository audits (including generated docs), lint, and diff checks passed.
Existing durable worker coverage verifies both catalog-free Search prompts and native integration call/checkpoint handling.
Live provider accounts have not been exercised; this rollout enables that testing in dev.

Checklist

Code follows project style guidelines
Self-reviewed my changes
Tests added/updated and passing
No new warnings introduced
I confirm that I have read and agree to the terms outlined in the Contributor License Agreement (CLA)

Companion PR

Companion: https://github.com/simstudioai/mothership/pull/530

vercel · 2026-09-25T17:31:07Z

The latest updates on your projects. Learn more about Vercel for GitHub.

1 Skipped Deployment

Project	Deployment	Actions	Updated
docs	Skipped		Sep 25, 2026 6:23pm UTC

github-actions · 2026-09-25T17:31:25Z

⚠️ Cross-repo companion check

One or more companion PRs aren't merged into staging yet. Merging this without them will leave copilot and sim out of sync — merge them in lockstep.

❌ simstudioai/mothership#530 — OPEN, not merged (targets staging) — Enable Search Assistant integration lookups

cubic-dev-ai

No issues found across 13 files

Confidence score: 5/5

Automated review surfaced no issues in the provided summaries.
No files require special attention.

_{Re-trigger cubic}

greptile-apps · 2026-09-25T17:37:09Z

Confidence Score: 3/5

[Medium risk] Gates Search Assistant integration lookups with a feature flag.

The PR is not yet safe to merge because Search integration access may remain available after flag revocation during an AppConfig outage.

Findings

Revoked access can persist ▶

Summary

The PR makes selected read-only integration lookups available to Search Assistant behind an AppConfig-only flag, with separate payload, discovery, and execution checks. It also updates shared tool exposure and generated integration documentation.

Search sends the integration capability only while the flag is enabled; Build and Plan keep their existing catalog behavior.
Discovery and execution apply the Search allowlist and connected-account restrictions, but their flag checks can retain an enabled AppConfig value after revocation during refresh failures.

Diagram

%%{init: {'theme': 'neutral'}}%%
flowchart LR
  A[Search request] --> B{AppConfig flag}
  B -->|enabled| C[Integration capability in payload]
  B -->|disabled| D[No integration capability]
  C --> E[Catalog discovery checks flag]
  E --> F[Allowed read-only operation]
  F --> G[Executor checks flag]
  G --> H[Connected-account tool call]

_{Reviews (2) · Last reviewed commit: "Gate Search integration tools with AppCo..."}

Sg312 · 2026-09-25T18:20:23Z

@greptile-apps please re-review the latest head d8a7eeb. Search integration capability is now gated by an AppConfig-only flag, with runtime discovery/execution revocation and regression coverage. The PR now targets dev; prior resolved findings and credential-scope limitations are documented in the description.

* Enable read-only integration lookups for Search Assistant * Preserve inherited tool versions in generated integration docs * Align provider tests with Search read-only operations * Gate Search integration tools with AppConfig * Preserve dev test runner isolation during promotion

…th benchmark tooling (#8637) * feat(mothership): authorize private cross-workspace memory scopes * feat(desktop): add gated macOS computer use * fix(desktop): preserve generated computer-use contracts * fix(desktop): cancel computer use when its renderer exits * fix(desktop): complete native computer tool lifecycle * fix(desktop): support rich editors and verified Mac input batches * fix: preserve desktop observations through recovery and report app focus * Gate Search Assistant integration lookups with AppConfig (#8301) * Enable read-only integration lookups for Search Assistant * Preserve inherited tool versions in generated integration docs * Align provider tests with Search read-only operations * Gate Search integration tools with AppConfig * Preserve dev test runner isolation during promotion * Default Plan chats to independently saved Opus 5.5 Medium preferences * Remove default Mship execution cutoff and expose Slack agent prerequisites * fix(catalog): preserve credential gates for automation discovery * Add workspace specification benchmarks with isolated Plan evaluation * Add private knowledge graph selection in settings * Retain benchmark run history with comparisons and human review * chore: redeploy Sim after benchmark configuration update * Add superuser benchmark console with selected-user execution * Inspect benchmark workspaces incrementally and search generated specs * Remove benchmark cutoffs and renew active stage leases * Generate benchmark redactions from exact passages * Create owned conversations for every benchmark execution * Preserve partial benchmark answers for human review * Grade benchmark mechanics with verified reference resolution * Reconcile Plan feature with staging contracts and validation gates * Expose the Graphiti rollout gate through authorized memory scope * Share benchmark super-user eligibility with Plan and knowledge graphs * fix(plan): address eligibility, benchmark state and desktop review findings * feat: compare benchmark planner models with saved scores * test: align Plan composer and desktop fixtures with staging * fix(desktop): keep disabled computer use dormant * fix(plan): enforce benchmark and native action admission * fix(plan): preserve secret metadata during benchmark reads * fix(plan): isolate embedded CLI and checkpoint benchmark stages * fix(desktop): bound native requests and completion images * fix(plan): revalidate access and retain benchmark state * fix(plan): qualify persisted effort integration fixtures * fix(db): reconcile benchmark migrations with staging retirement * fix(db): preserve table change log in benchmark migration chain * fix(benchmarks): delete artifacts with their execution target * fix(mothership): isolate benchmark state and preserve tool completions * fix(desktop): preserve action evidence in unload completions * fix(desktop): keep projected parent references valid * fix(computer): preserve uncertainty and label permission controls * test(mothership): await actual tool cancellation completion * fix(plan): resolve review findings and trigger initialization * docs(triggers): point Linq guidance at the builder module * fix(plan): preserve fork scope and benchmark redaction boundaries * fix(plan): retry retained completions and guard benchmark drafts * fix(computer): stop completion delivery at identity reset --------- Co-authored-by: Vikhyath Mondreti <vikhyath@simstudio.ai>

vercel Bot temporarily deployed to Preview September 25, 2026 17:31 Inactive

github-actions Bot added the requires-mothership-merge Has a companion PR on the mothership/copilot side — merge in lockstep label Sep 25, 2026

cubic-dev-ai Bot reviewed Sep 25, 2026

View reviewed changes

greptile-apps Bot reviewed Sep 25, 2026

View reviewed changes

Comment thread apps/sim/lib/mothership/assistant/tool-policy.ts

Comment thread apps/sim/blocks/blocks/github.ts

vercel Bot deployed to Preview September 25, 2026 17:40

View deployment

vercel Bot temporarily deployed to Preview September 25, 2026 17:48 Inactive

Sg312 added 4 commits September 25, 2026 11:14

Enable read-only integration lookups for Search Assistant

5cf53a4

Preserve inherited tool versions in generated integration docs

0478814

Align provider tests with Search read-only operations

efce9f2

Gate Search integration tools with AppConfig

d8a7eeb

Sg312 changed the base branch from staging to dev September 25, 2026 18:17

Sg312 requested a review from a team as a code owner September 25, 2026 18:17

Sg312 force-pushed the feat/search-assistant-query-filters branch from 3c11b4d to d8a7eeb Compare September 25, 2026 18:17

Sg312 changed the title ~~Enable read-only integration lookups for Search Assistant~~ Gate Search Assistant integration lookups with AppConfig Sep 25, 2026

vercel Bot deployed to Preview September 25, 2026 18:20

View deployment

Preserve dev test runner isolation during promotion

fb7923c

vercel Bot temporarily deployed to Preview September 25, 2026 18:23 Inactive

greptile-apps Bot reviewed Sep 25, 2026

View reviewed changes

Comment thread apps/sim/lib/mothership/tool-executor/executor.ts

Sg312 merged commit d4f32d6 into dev Sep 25, 2026
31 checks passed

waleedlatif1 deleted the feat/search-assistant-query-filters branch September 25, 2026 23:06

Navigation Menu

Repository navigation

Gate Search Assistant integration lookups with AppConfig - #8301

Gate Search Assistant integration lookups with AppConfig#8301
Sg312 merged 5 commits into
devfrom
feat/search-assistant-query-filters

Sg312 commented Sep 25, 2026 •

edited

Loading

Uh oh!

vercel Bot commented Sep 25, 2026 •

edited

Loading

Uh oh!

github-actions Bot commented Sep 25, 2026

Uh oh!

cubic-dev-ai Bot left a comment

Uh oh!

greptile-apps Bot commented Sep 25, 2026 •

edited

Loading

Uh oh!

Uh oh!

Uh oh!

Sg312 commented Sep 25, 2026

Uh oh!

Uh oh!

Uh oh!

This branch was previously deployed

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Conversation

Sg312 commented Sep 25, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Type of Change

Testing

Checklist

Companion PR

Uh oh!

vercel Bot commented Sep 25, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

github-actions Bot commented Sep 25, 2026

⚠️ Cross-repo companion check

Uh oh!

cubic-dev-ai Bot left a comment

Choose a reason for hiding this comment

Uh oh!

greptile-apps Bot commented Sep 25, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Confidence Score: 3/5

Findings

Summary

Uh oh!

Uh oh!

Uh oh!

Sg312 commented Sep 25, 2026

Uh oh!

Uh oh!

Uh oh!

This branch was previously deployed

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Sg312 commented Sep 25, 2026 •

edited

Loading

vercel Bot commented Sep 25, 2026 •

edited

Loading

greptile-apps Bot commented Sep 25, 2026 •

edited

Loading