docs(mcp): explain indexing status semantics

[Nottlespike]

Summary

• document that get_indexing_status reports coarse phase-based progress rather than a live file-count ratio
• explain why completed entries can sometimes show stale 0 files, 0 chunks snapshot metadata
• clarify that indexed codebases are keyed by absolute path, so the same repository under different paths is tracked separately

Docs updated

• packages/mcp/README.md
• docs/dive-deep/asynchronous-indexing-workflow.md
• docs/troubleshooting/faq.md

Verification

• pnpm install
• pnpm build

Both commands completed successfully in the local fork clone before opening this PR.

[Copilot]

Pull request overview

This PR clarifies how MCP indexing status should be interpreted by documenting that get_indexing_status reports coarse, phase-based progress (not a live file-count ratio), explaining why completed entries can show stale 0 files, 0 chunks, and noting that indexed codebases are tracked by absolute path (so the same repo under different paths is treated separately).

Changes:

• Documented phase-based progress semantics for get_indexing_status (including why progress can appear “jumpy”).
• Explained snapshot-based (potentially stale) file/chunk counts and how to refresh them via clear + re-index.
• Clarified absolute-path identity behavior for codebases across README, workflow guide, and FAQ.

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated no comments.

File	Description
packages/mcp/README.md	Adds a concise explanation of indexing status semantics and links to deeper docs.
docs/dive-deep/asynchronous-indexing-workflow.md	Adds detailed breakdown of progress phases, snapshot persistence, and path-based codebase identity.
docs/troubleshooting/faq.md	Adds targeted FAQ entries covering coarse progress and stale 0 files, 0 chunks, plus path identity note.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.