feat(comparisons): add code-sandbox and session-policy rows

[waleedlatif1]

Summary

• Add two comparison rows — codeSandboxRuntime (configurable code sandboxes) and sessionPolicy (custom session policy) — populated for Sim and all 20 competitor profiles
• Source Sim's facts from docs.sim.ai rather than the codebase, and repoint the execution-limits row at the Run Time Limits table (Enterprise async configurable up to 7 days)
• Add configurable-workspace-sandboxes and org-session-policies to the feature catalog, and refresh the stale sandboxed-code-execution entry (E2B or Daytona, Function base image)

Type of Change

• New feature

Testing

Type-check and biome clean. Every fact was researched against live vendor documentation, then independently re-verified by a second pass that fetched each cited URL, confirmed it substantiates the specific claim, and searched for contradicting evidence in both directions.

Notable corrections caught by that second pass:

• CrewAI's sandbox claim rested on CodeInterpreterTool, which was removed from crewai-tools (PR improvement(emails): align transactional emails with the platform neutral design system #5309, 2026-04-07; CERT/CC VU#221883)
• LangChain cited the private-preview announcement for a feature that went GA in May 2026
• Retool's detail listed preloaded Python packages that the cited page never enumerates, and rested a de-gating claim on a community forum post
• Vellum quoted marketing copy as documentation
• Three of Sim's own claims were overstated: prebuilt-image install cost is sim.ai-scoped (self-hosted Daytona installs per run), SANDBOXES_ENABLED alone does not enable sandboxes, and import-free JavaScript ignores the sandbox selection entirely. A 10 MB request-body cap not supported by either cited page was removed from the execution-limits row.

Notes for review

Facts whose value begins Yes:/No: render as a bare icon and discard shortValue. Conditional capabilities (self-hosted only, package-layer only, tier-gated, delegated to another product layer) therefore use the dataset's existing Partial: convention so the qualifier survives into the rendered table, and negatives established only by absence use Not publicly documented:. This removes unearned checkmarks and unearned crosses alike.

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)

[vercel]

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

1 Skipped Deployment

Project	Deployment	Actions	Updated (UTC)
docs	Skipped		Aug 11, 2026 1:24am

[cursor]

PR Summary

Low Risk
Changes are static comparison and catalog content only; no application execution or auth logic is modified in this diff.

Overview
Expands the landing comparisons dataset with two new dimensions: Configurable code sandboxes (codeSandboxRuntime) under Integrations and Custom session policy (sessionPolicy) under Security & compliance, wired through comparison-sections.ts and the compare types.

Each of Sim’s 20 competitor profiles (plus sim.ts) now carries sourced Fact entries for both keys, using Partial: / not publicly documented phrasing where capabilities are tier-gated, self-hosted-only, or absent so the UI keeps qualifiers instead of bare checkmarks.

The feature catalog adds org session policies and configurable workspace sandboxes, and refreshes sandboxed code execution (E2B or Daytona, Function base image). Sim’s own compare facts for sandboxes and session policies are aligned to docs.sim.ai; execution time limits cite the Run time limits docs (Enterprise async up to 7 days). Several competitors get corrected or expanded custom code step facts (e.g. Retool, Tines, Workato).

^{Reviewed by Cursor Bugbot for commit a3a39f4. Configure here.}

[greptile-apps]

Greptile Summary

This PR extends the comparison dataset with configurable code-sandbox and session-policy coverage for Sim and all supported competitors.

• Registers the two new rows in the typed comparison sections and profile schema.
• Adds corresponding facts and sources across Sim and 20 competitor profiles.
• Adds related feature-catalog entries and refreshes Sim’s sandbox and execution-limit claims.

Confidence Score: 5/5

The PR appears safe to merge because no blocking failure remains.

No blocking failure remains.

Important Files Changed

Filename	Overview
apps/sim/lib/compare/data/types.ts	Adds required typed facts for configurable sandbox runtimes and session policies.
apps/sim/app/(landing)/comparisons/comparison-sections.ts	Registers both new fact keys in their matching security and integrations sections.
apps/sim/lib/compare/data/sim.ts	Adds sourced Sim facts for sandbox configuration and organization session policies while updating execution-limit sourcing.
apps/sim/lib/compare/data/feature-catalog.ts	Adds the corresponding feature-catalog records and refreshes the sandboxed-execution entry.
apps/sim/lib/compare/data/competitors/crewai.ts	Adds sourced CrewAI assessments for sandbox-runtime configuration and session-policy support.
apps/sim/lib/compare/data/competitors/langchain.ts	Adds sourced LangChain assessments covering LangSmith sandboxes and self-hosted session controls.

_{Reviews (2): Last reviewed commit: "fix(comparisons): resolve customCodeStep..." | Re-trigger Greptile}

[waleedlatif1]

@greptile

[waleedlatif1]

@cursor review

[cursor]

✅ Bugbot reviewed your changes and found no new issues!

Comment @cursor review or bugbot run to trigger another review on this PR

^{Reviewed by Cursor Bugbot for commit a3a39f4. Configure here.}