feat(copilot): show model-authored tool activity

[waleedlatif1]

Summary

• Show model-authored action descriptions consistently in workspace, organization, browser, and subagent activity.
• Preserve descriptions across saved history, reconnects, and stopped runs. Keep existing fallback labels, icons, controls, animation, and deterministic group summaries.
• Let actual tool outcomes determine failure, cancellation, and completion wording.

Companion: simstudioai/mothership#497

The optional metadata supports a rolling deployment; Sim can land first and continues to render older calls with existing labels.

Type of Change

• Feature

Testing

1,729 tests passed across 84 suites. Type-checking, lint, all 46 audits, and generated-contract parity passed. Checked the production activity components in the local preview for live replacement and expanded history in light and dark mode. Provider inference is covered with mocked streams; no live model run was performed.

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
docs	Skipped		Sep 13, 2026 3:36am UTC

[github-actions]

⚠️ 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#497 — OPEN, not merged (targets staging) — feat(activity): describe tool actions with the calling model

[waleedlatif1]

@greptile

[waleedlatif1]

@cubic-dev-ai review this PR

[cubic-dev-ai]

@cubic-dev-ai review this PR

@waleedlatif1 I have started the AI code review. It will take a few minutes to complete.

[greptile-apps]

Confidence Score: 5/5

The PR appears safe to merge; the previous outcome-wording issues are resolved and no new actionable failure remains.

Summary

• Adds optional activity-description metadata to generated stream and persisted-message contracts.
• Normalizes and preserves descriptions across live calls, snapshots, reconnects, stopped runs, and subagent activity.
• Uses shared status formatting across activity rows, group headers, summaries, permission cards, and the landing-page demonstration.
• Adds regression coverage for normalization, persistence, replay, status projection, invalid metadata, and repeated formatting.
• The changes since the previous review resolve both prior wording findings without introducing a distinct actionable issue.

Diagram

%%{init: {'theme': 'neutral'}}%%
flowchart LR
  A[Model tool-call event] --> B[Normalize activity description]
  B --> C[Tool-call state]
  C --> D[Turn and transcript serialization]
  D --> E[Persisted chat history]
  C --> F[Live activity components]
  E --> G[History and reconnect replay]
  F --> H[Outcome-aware display formatter]
  G --> H
  H --> I[Workspace, organization, browser, and subagent activity]

Loading

_{Reviews (3) · Last reviewed commit: "fix(copilot): keep model activity outcom..."}

[waleedlatif1]

@greptile

[waleedlatif1]

@cubic-dev-ai review this PR

[cubic-dev-ai]

@cubic-dev-ai review this PR

@waleedlatif1 I have started the AI code review. It will take a few minutes to complete.