Report MCP OAuth Auto store drift

[stevenlee-oai]

Codex Thread 019edd6d-6f14-74e2-853c-345d1803d4a6

Stack

Review and merge in order. Every layer is independently correct and documents its safe stopping point.

1. openai/codex#30292 — aggregate File/Secrets store locking
2. openai/codex#30293 — resolve and lifecycle-pin the exact OAuth store
3. openai/codex#30416 — serialized authoritative refresh transaction
4. openai/codex#30294 — Codex-owned transport refresh and one-shot 401 recovery
5. openai/codex#30295 — login/logout transaction serialization
6. openai/codex#30296 — diagnostic-only Auto store drift reporting

This PR is layer 6.

Why

Auto is intentionally resolved once and pinned only for a client lifecycle in this stack. If keyring availability differs in a later process, Auto can resolve to a different store. We do not want to add a durable credential-authority selector or migration policy in this stack, but we do want evidence if this rare assumption fails in practice.

What this PR does

• Records a token-free, best-effort observation at $CODEX_HOME/.mcp-oauth-store-resolutions.json.
• Keys observations with the same compute_store_key(server_name, url) identity used by credential locking.
• Records configured mode, keyring backend, and resolved File/Keyring store.
• Emits a warning and codex.mcp.oauth.store_resolution_changed counter when repeated Auto resolution under the same backend changes stores.
• Uses a short independent aggregate lock and atomic writes.

Explicit decisions

• This sidecar is observational, never credential authority. It cannot choose a store, block OAuth, or trigger migration or reconciliation.
• Failures to read, lock, parse, or write it are logged and swallowed.
• Explicit mode or keyring-backend changes reset the comparison baseline.
• Auto with no credential records nothing; a successful Auto login records the selected store.
• The observation intentionally survives logout so a later login can reveal drift. It contains no token material.
• State is scoped to the active CODEX_HOME; different homes are intentionally independent.

Safe stopping point

This PR changes observability only. The five correctness layers below it are independently complete without this diagnostic.

Validation

• just test -p codex-rmcp-client (116 passed; expected environment skips)
• Resolution-change, intentional-mode-change, and no-credential diagnostics tests