Commit Graph
29 Commits
Author SHA1 Message Date
jif 67fb9da4b6 Preserve safe enterprise MCP authentication error details (#56153)
## Why

Enterprise MCP token exchange and sign-in failures can collapse into generic errors, hiding useful diagnostics such as an OAuth `invalid_scope` rejection or a cancelled sign-in.

## What changed

Introduce `EmaErrorDetail` to carry static operation messages and sanitized SDK diagnostics through token-source errors and enterprise login completion. Exchange failures can report the stage, HTTP status, and allowlisted OAuth error code, such as `IdentityProvider: HTTP 400: invalid_scope`, without retaining arbitrary provider text or raw error chains.

Preserve specific discovery, credential storage, cancellation, and account/configuration mismatch errors instead of replacing them with generic failure messages.

## Testing

Extend tests to cover `invalid_scope` diagnostics, specific sign-in completion errors, and exclusion of credentials from diagnostics even when an outer error context contains sensitive text.

GitOrigin-RevId: e9280a5db3565ea91da0810bab528da5ee088d64
2026-10-22 11:51:23 +00:00
jif ec8edd576c Refine enterprise MCP auth errors and request authority checks (#55691)
## What changed

- Classify token-source failures by credential kind and exchange stage, with sign-in or administrator guidance that omits provider error text. Treat resource authorization failures separately from enterprise identity failures when deciding whether authentication is required.
- Add policy-bound request authority checks that return `RequestNotSent` when policy is updating or unavailable, while allowing admitted responses to finish. Support child authorities that isolate connection revocation and share response draining.
- Recheck account validity after acquiring the credential invalidation lock and check cancellation before deleting a rejected credential.

## Testing

Extend regression coverage for policy suspension during token renewal, completion of admitted requests, recovery with fresh authority, and transport retry classification. Expand provider-error tests to cover `unauthorized_client` and `invalid_client` while checking that credential text is not exposed.

GitOrigin-RevId: c0097adc35cb5fdffde1466e4bc2b5ec78114a4b
2026-10-20 22:33:14 +00:00
Matthew Zeng 4ae6016a93 Retire rejected MCP OAuth refresh tokens (#54079)
## Why

Coordinated MCP OAuth refresh must stop retrying a definitively rejected refresh token, including after the runtime is rebuilt.

## What changed

Remove the rejected refresh token while preserving the access token and credential record. Compare stored credentials under the appropriate locks before writing so a replacement login is preserved, and update file entries using their existing keys.

Keep rejection handling alive through caller cancellation and prevent reuse within the runtime even if persistence fails. For ordinary direct-keyring credentials shared across `CODEX_HOME` directories, retire the token only in the current runtime because locking does not span those directories. Report persistence failures without exposing backend diagnostics.

## Testing

Add coverage for reauthentication after runtime rebuild, legacy file keys, cancellation with a concurrent credential replacement, keyring scope, and persistence failures with diagnostic redaction.

GitOrigin-RevId: a6e602ca2e2893ed711d853becc45142d9575fab
2026-10-14 20:00:52 +00:00
zbarsky-openai 9dd798805f Prevent recursive Tokio tracing in telemetry and SQLite logs (#51775)
## Why

Tokio runtime tracing can cause SQLite log writes to enqueue more writes and exporter activity to generate further OTLP exports.

## What changed

- Exclude `tokio` and `runtime` spans from OTLP export alongside `h2` spans.
- Limit `tokio::` and `runtime::` targets to `INFO` in the default log filter, and reject their `TRACE` events directly in the SQLite sink even without an outer filter.
- Box and pin the session-loop future before spawning it.
- Reorder tracing and Tokio test attributes, restrict the skills concurrency test's subscriber to the catalog-refresh span, and use the default log filter in the SQLite formatter comparison test.

GitOrigin-RevId: f545013a2469088d7f9890c1f46bb93eb5446d2d
2026-10-07 17:28:32 +00:00
Matthew Zeng a20fe6335f Replace the Figma OAuth exception with Mercado Pago (#50189)
## What changed

Allow the issuer `https://mcp.mercadopago.com/mcp` to use authorization endpoints on `https://auth.mercadopago.com` and token endpoints on `https://mcp.mercadopago.com` without issuer-bound callbacks. Remove the previous Figma exception.

## Testing

Update the provider-exception test to accept the Mercado Pago combination and reject lookalike issuer hosts, unrelated token hosts, and HTTP issuer and token URLs.

GitOrigin-RevId: 3838c7e4c32d6a2022f0011d6020e383035fe67f
2026-10-02 05:25:51 +00:00
Nick Steele ecc78e4cf5 Add renewable EMA HTTP authentication and credential versioning (#49987)
## What changed

- Add `EmaAuthenticatedHttpClient` to cache and renew resource bearers, serialize concurrent renewals, and include authentication time in the request deadline. Confine bearers to the configured MCP endpoint and reject redirects.
- Return authentication-required errors for `401` responses without replaying MCP operations. Preserve a newer cached bearer when a delayed response rejects an older one.
- Add revocable request authority that cancels pending requests and ends response streams.
- Pin enterprise credentials to a persistent version advanced on save or deletion. Use short credential locks and invalidate rejected grants only when their record and version are still current, preserving newer logins.
- Hide keyring account identifiers from enterprise credential errors and traces while preserving authentication failure classification.

## Testing

Add tests for token expiry and renewal, endpoint confinement, redirects, request deadlines, revocation during renewal and streaming, delayed `401` responses, credential replacement and logout races, and credential error privacy.

GitOrigin-RevId: ee3e5cf7ecbba3d09e1ab29ed4fbb2a35eacc60d
2026-10-01 13:57:48 +00:00
Celia Chen 05ea5f757e Add attributed MCP OAuth credential storage telemetry (#49392)
## What changed

- Instrument MCP OAuth loads, saves, deletes, fallback cleanup, and refresh persistence with credential-free storage metrics, distinguishing configured policy from operations on a pinned store.
- Retain the originating client across background tasks, blocking storage operations, and session recovery, including recovery after startup found no credentials.
- Preserve typed keyring and lock error categories for metrics and remove raw error details from storage warnings.

## Testing

Add tests for policy and pinned-store outcomes, best-effort cleanup failures, wrapped lock errors, and successful or failed refresh persistence without duplicate observations. Add recovery tests that verify client attribution after anonymous startup and across threads with different originators.

GitOrigin-RevId: 5ea4528bcdcf500c8ffdf1d9c7008ea52112c726
2026-09-29 23:01:46 +00:00
Nick Steele 4994306e9f Enable enterprise MCP sign-in and account-scoped grant cleanup (#49276)
## Why

The app server previously rejected OAuth login for enterprise-managed MCP servers. These servers need an explicit sign-in flow that ties saved authorization to the active Codex user and workspace and prevents canceled or superseded attempts from saving credentials.

## What changed

- Enable enterprise sign-in through `mcpServer/oauth/login` for configured servers with a connected thread, trusted IdP registration, and `features.use_xaa` enabled. Scope shared enterprise credentials by user, workspace, issuer, and client ID.
- Add `loginId` to MCP OAuth login responses and completion notifications, preserving compatibility with older servers that omit it.
- Support enterprise login replacement and `account/login/cancel`, wait for callback listener shutdown before replacement, and recheck account and configuration before saving grants. Fence stale attempts across processes and account changes.
- Remove shared enterprise authorization during account logout and `codex mcp logout`, including when the feature is disabled. Continue account logout if enterprise cleanup fails, and invalidate MCP runtimes on account changes.

Start a fresh session after successful enterprise sign-in to use the saved grant.

## Testing

Add regression coverage for login replacement and cancellation, callback port reuse, account changes during setup, cross-process logout invalidation, persisted workspace policy selection, cleanup failures, and responses from older servers without `loginId`.

GitOrigin-RevId: 7ed4caaab4659ed1e67064262cf5cee48e3a26ac
2026-09-29 14:46:33 +00:00
willwang-openai 83b56bc5ad Support client secrets for pre-registered MCP OAuth clients (#47891)
## Why

MCP OAuth configuration supported a pre-registered client ID but could not supply a client secret for token exchange or refresh.

## What changed

- Add `oauth.client_secret` and `codex mcp add --oauth-client-secret`, requiring a nonempty secret and client ID. Persist the secret in server configuration and accept `clientSecret` in plugin configuration.
- Pass configured credentials through CLI, app-server, and plugin login flows and token refresh. Require a new login when a configured confidential client's ID differs from stored credentials.
- Redact secrets in debug output and keep them out of authorization URLs and persisted OAuth token records.
- Invalidate cached OAuth connections when the configured client ID or secret changes.

## Testing

Add coverage for configuration validation and round trips, CLI argument redaction and subsequent login, app-server login, connection invalidation, and refresh with `client_secret_basic` and `client_secret_post` in both refresh modes. Verify secret exclusion from token records and reject mismatched client IDs before contacting the provider.

GitOrigin-RevId: 85bb0e410e9e68e6cd68eb6359badfc7eac78147
2026-09-24 17:26:18 +00:00
viyatb-oai 2c2a42e65d Restrict MCP OAuth authorization endpoints to HTTP(S) (#47326)
## What changed

Reject authorization endpoints with schemes other than `http` or `https` before client registration or authorization URL return. Document this constraint for `mcpServer/oauth/login`.

## Testing

Make existing asynchronous tests wait for cleanup: wait for `ThreadIdle` before injecting user input in the guardian cached-score test, and poll for queue consumption before asserting that dispatched items are gone.

GitOrigin-RevId: e5f6b4c5556234c3cc2aa56910486e892c011116
2026-09-22 17:31:02 +00:00
Andrei Eternal 5ac0b8768d Surface MCP reconnect signals when expired OAuth tokens cannot refresh (#43947)
## Why

Refresh failures could leave expired MCP OAuth credentials reporting ordinary errors instead of signaling that authentication is required, preventing tool calls from offering a reconnect signal.

## What changed

- Classify provider failures and timeouts as `AuthorizationRequired` when the access token has expired. Keep proactive refresh failures as ordinary errors while the token remains valid.
- Reread stored credentials after a failed refresh and adopt a valid login completed during the request, enforcing the existing issuer binding for refresh tokens. Preserve stored credentials for later retries.
- Convert authentication-required tool-call errors into a reconnect message with `mcp/www_authenticate` metadata, without exposing provider or transport details.

## Testing

Add coverage for startup and runtime OAuth recovery, proactive refresh failures, concurrent login adoption, issuer mismatches, credential preservation, and successful retries. Verify failed local refreshes do not send tool calls and server-rejected calls are not replayed.

GitOrigin-RevId: 9cf64b0452685d2085df5dc0bcecee16ffe42e47
2026-09-09 00:03:41 +00:00
Nick Steele b090e901f8 Add staged enterprise OIDC login and coordinated logout (#43844)
## Why

Enterprise sign-in needs to keep browser completion separate from credential storage so callers can recheck the active account and configuration before saving a grant. Logout must also prevent an earlier sign-in from restoring credentials, including from another process sharing `CODEX_HOME`.

## What changed

- Add enterprise login APIs in `rmcp-client` that return an authorization URL and stage validated credentials for an explicit `commit_if` call. Store grants only in the keyring after rechecking caller authority under the credential lock.
- Require a registered client ID, published metadata matching the configured issuer, HTTP loopback callbacks, a refresh token, and a valid OIDC identity assertion. Request `openid` and `offline_access` with `prompt=consent`, and omit MCP resource indicators from authorization and code exchange.
- Persist a login generation under the credential lock so logout invalidates pending and staged sign-ins across processes, even when no grant is stored.
- Keep credentials and account identifiers out of enterprise error chains and logs, and avoid logging callback payloads when the receiver has closed.

## Testing

Add coverage for discovery validation, loopback callbacks, PKCE, staged keyring storage, cancellation, stale attempts, cross-process logout, and error/log privacy. Preserve ordinary MCP OAuth login without a refresh token, and adjust the terminal polling test deadline to include the minimum empty-poll wait.

GitOrigin-RevId: 2a27b9a26505a2f6fdecce8877f6e2c21e148f72
2026-09-08 16:07:38 +00:00
Matthew Zeng 88912c04cd Enable coordinated MCP OAuth refresh (#42413)
## What changed

- Honor `McpOAuthRefreshMode::Coordinated` for streamable HTTP MCP connections by letting RMCP refresh and persist credentials through the pinned credential store.
- Reread credentials while holding the refresh lock, persist refreshed tokens before retrying requests, and serialize login and logout writes with in-flight refreshes.
- Keep OAuth preparation outside MCP operation and handshake deadlines, and allow refresh persistence to finish if the initiating caller is cancelled.

## Testing

- Cover coordinated startup refresh, concurrent refreshes, `401` retries, credential mutation races, provider timeouts, and caller cancellation.

GitOrigin-RevId: 100ae788048087be23e26bb43f868b1fcebb007a
2026-09-03 02:00:12 +00:00
Matthew Zeng 312709252d Add an RMCP OAuth credential store adapter (#42384)
## What changed

- Add a test-only `CredentialStore` adapter that maps RMCP refreshes onto Codex's pinned OAuth credential backend.
- Require refresh transaction guards for mutations, preserve the pinned backend, and update the runtime credential snapshot only after persistence succeeds.
- Preserve scopes and token expiry metadata while rejecting credentials that no longer match the connection's client or issuer.

## Testing

- Cover guarded save and clear operations, persistence failures, pinned-store read failures, replacement and removal handling, and expiry round trips.

GitOrigin-RevId: eb1b98024322c03af94f5ab2e88c7dc4ae54893a
2026-09-02 23:19:11 +00:00
Eric Traut 94cbbddafc Support package-style MCP server names (#41700)
## What changed

- Allow MCP server names to contain `:`, `@`, `/`, and `.`, enabling names such as `npm:@modelcontextprotocol/server-sequential.thinking`.
- Preserve these names across `mcp add`, `get`, `list`, and `remove`, runtime tool namespaces, and OAuth credential lookup.
- Quote non-bare server names in generated `config.toml` recovery hints and keep similarly escaped OAuth credential names isolated.

## Testing

- Add CLI and runtime round-trip coverage for npm-style names.
- Add snapshot coverage for quoted recovery hints and a regression test for OAuth credential-name collisions.

GitOrigin-RevId: 97e9353cdbc544db4eb2377ddbfa1d2d539b1e04
2026-08-30 16:45:34 +00:00
Nick Steele 9b4a0f8a0a Add enterprise IdP identity resolution for MCP OAuth (#40739)
## What changed

- Resolve stored enterprise IdP sessions against discovered authorization
  metadata, requiring the configured issuer, public-client authentication, and
  supported ID-JAG token exchange capabilities.
- Bind OIDC identity claims and MCP resource indicators to their configured
  issuer, client, and server, and require reauthentication when pinned keyring
  credentials are removed or replaced.
- Hold the credential lock while rereading refresh tokens, and isolate
  enterprise credentials by reserved namespace and Codex home.

## Testing

- Cover metadata and claim validation, resource binding, credential replacement
  and keyring failures, refresh locking, expired ID tokens, and credential
  namespace isolation.

GitOrigin-RevId: edce3c6159f7d6831edf72e9608b3fc3f5823c83
2026-08-25 23:51:57 +00:00
jif 7f9832d0d0 Enforce issuer binding for MCP OAuth endpoints (#39935)
## Why

Interactive MCP OAuth must not trust authorization metadata that could route an
authorization code or PKCE verifier to an unrelated token endpoint.

## What changed

- Require an advertised issuer to match the origin that served authorization
  metadata.
- Validate authorization and token endpoint origins before starting both
  pre-registered and dynamically registered client flows.
- Allow delegated endpoint origins when the server advertises issuer-bound
  authorization responses, while retaining narrow compatibility exceptions for
  existing providers.

## Testing

Add coverage for rejected untrusted metadata, accepted issuer-bound delegation,
legacy provider exceptions, and both client registration paths.

GitOrigin-RevId: 43c9f94c9f6ba2d23d7e373576cf9fa26861cfc3
2026-08-21 13:28:28 +00:00
Jeremy Rose 250b5ea2bf Bind MCP OAuth refresh tokens to their issuer (#39615)
## Why

An authorization server discovered for an MCP server can change. A stored refresh token must not be sent to a different issuer than the one that originally granted it.

## What changed

- Persist the discovered authorization server issuer with new OAuth credentials and preserve it across refreshes.
- Validate that issuer against a single pinned metadata snapshot before refreshing or adopting stored refresh credentials.
- Require reauthentication when refresh credentials have no issuer or the issuer changed. An unexpired access token can still be used without exposing its refresh token.

## Testing

Add coverage for issuer persistence, missing and changed issuers, metadata changes during startup, and refresh-token preservation.

GitOrigin-RevId: 07e48ba892f627428a28bbed5cca4ad703e2a5fd
2026-08-20 06:25:17 +00:00
Eric Traut 02360b48d1 Isolate MCP resource headers during OAuth requests (#39019)
## Why

Headers configured for an MCP resource can contain credentials and must not be
forwarded to a different origin during OAuth discovery, registration, or token
exchange.

## What changed

- Apply configured resource headers only to OAuth requests on the MCP resource
  origin, while allowing OAuth-generated headers to take precedence.
- Follow credentialed OAuth redirects only when each destination remains on the
  resource origin. Preserve redirect method semantics, the overall timeout, the
  response size limit, and a maximum of 10 redirects.
- Use the Codex MCP user agent for requests to authorization-server origins.

## Testing

Add coverage for cross-origin header isolation, same-origin dynamic client
registration redirects, OAuth header precedence, token refresh, timeout
accounting, and response size limits.

GitOrigin-RevId: 609d06e2b065e4aa9ca5382b4ae60455f9e26db9
2026-08-17 16:29:47 +00:00
jif dd22460869 Add MCP OAuth credential contention regression tests (#37866)
## What changed

- Cover non-blocking credential probes when the file or secrets store is locked, including retaining only a matching prior credential snapshot and recovering after the lock is released.
- Extend the streamable HTTP OAuth round trip to verify that user turns continue during store contention, newly discovered servers recover after contention, and logged-out servers do not reuse authenticated connections.
- Cover reconciliation of authentication failures and effective `Authorization` headers.

GitOrigin-RevId: 8e377644001bd0be04dc9f79841080094d09d199
2026-08-10 18:40:02 +00:00
jif afcc95b431 Speed up MCP OAuth credential reads (#37860)
## Why

Refreshing MCP connection identities should not stall the async executor while another process holds the OAuth credential-store lock.

## What changed

- Probe file and secrets credential stores without waiting during runtime refreshes, retaining the last known credentials when the store is contended.
- Reuse unchanged authentication failures while credentials are temporarily unavailable instead of restarting the connection.
- Run blocking credential loads on a blocking worker during MCP client construction.
- Allow OAuth fallback when a configured authorization header is missing, empty, or invalid.

GitOrigin-RevId: 38dad5606da9a1ceb30fe945000ec9151a5058fa
2026-08-10 17:58:15 +00:00
iceweasel-oai 8b1b065719 Speed up MCP OAuth credential reads (#37842)
## Why

Concurrent MCP startup and status checks should not serialize when they only read the shared credential store. Repeated reads of the encrypted MCP OAuth store also needlessly decrypted unchanged contents.

## What changed

- Use shared locks for `File` and `Secrets` credential reads while keeping saves and deletes exclusive.
- Cache decrypted MCP OAuth secrets by store path, ciphertext, and passphrase, and invalidate the cache after writes.

## Testing

- Cover concurrent readers, reader/writer exclusion, shared credential loads, and cache invalidation after updates and deletes.

GitOrigin-RevId: f13512e6404d4919879ba5ba77a3e34e52b35640
2026-08-10 15:43:10 +00:00
Celia Chen 709283b432 Use configured HTTP clients for all MCP OAuth requests (#35814)
## What changed

- Require callers to provide an HTTP client for MCP OAuth discovery and login, removing the separate direct `reqwest` path.
- Use the shared `http` and `url` types throughout the MCP client and drop its direct `reqwest` dependency.
- Preserve configured MCP headers when routing OAuth discovery through the provided client.

## Testing

- Add coverage that routed OAuth discovery forwards configured headers.

GitOrigin-RevId: 1345f56bd794626533133447597a5908e57b9b48
2026-07-28 19:11:36 +00:00
thomas 61de0d8fe8 Upgrade rmcp to 3.0.0-beta.3 (#35720)
## What changed

- Update the `rmcp` model and transport integrations for `3.0.0-beta.3`.
- Preserve legacy `elicitation/create` form requests, schema defaults, metadata, and wire-format compatibility while adopting the new elicitation types.
- Harden OAuth discovery by using GET-first discovery without starting an MCP session, preventing cross-origin header redirects, validating authorization-server and callback issuers, and retaining compatibility with metadata that omits an issuer.
- Keep stored OAuth credentials readable and avoid requiring reauthorization after transient refresh failures.

## Testing

- Add coverage for legacy elicitation round trips, OAuth discovery variants, callback issuer validation, credential migration, and refresh failures.

GitOrigin-RevId: 756197d26f3fd347c28c400228f6b3d06ed493b7
2026-07-28 05:17:25 +00:00
jif e19e65317a Reuse MCP connections across runtime refreshes (#34952)
## Why

Refreshing MCP runtime state should not restart an unchanged, ready server or
relist its tools.

## What changed

- Reconcile refreshed MCP configuration against the published connection set
  and reuse connections whose transport, environment, authentication, OAuth
  credentials, and client capabilities are unchanged.
- Keep tool filters, timeouts, metadata, and plugin provenance in the published
  server view so those settings can change without reconnecting.
- Update elicitation authority in place for reused connections, and reconnect
  when connection-defining inputs or live OAuth credentials change.

## Testing

Added coverage for unchanged-server reuse, view-only and elicitation-policy
updates, connection identity changes, OAuth credential changes, and avoiding
redundant tool listing.

GitOrigin-RevId: f04f5db5fbdde127b6a14f6aa9673112c0b557e7
2026-07-23 14:55:31 +00:00
jif c7a4a7e136 Refactor OAuth store lock contention tests (#32801)
## What changed

- Extend the lock-contention test helper with a callback that runs while the
  aggregate store lock is held.
- Use a scoped worker thread and return its result directly after releasing the
  lock.
- Reuse the helper for concurrent update tests covering both file and secrets
  credential stores.

GitOrigin-RevId: 74b8b5370456e90ecd39fc2af2f0853594ca4f60
2026-07-13 13:56:34 +00:00
stevenlee-oai 6962a2ecae Serialize MCP OAuth credential refreshes (#32229)
## Why

Concurrent Codex processes can otherwise refresh the same rotating token, and a
cancelled or partially persisted refresh can leave durable and in-memory MCP
credentials out of sync.

## What changed

- Serialize each credential's read-refresh-write transaction across processes,
  reread the authoritative store after locking, and adopt credentials refreshed
  by another process.
- Keep refresh persistence running after caller cancellation, bound lock and
  provider waits independently, and preserve omitted refresh tokens and scopes.
- Fail MCP startup and operations when refresh or persistence fails instead of
  continuing with stale credentials, while requiring reauthorization for
  missing, unusable, or rejected refresh tokens.
- Exclude OAuth refresh time from the MCP initialization timeout.

## Testing

Add coverage for lock contention, concurrent refreshes, rejected and missing
credentials, storage failures, caller cancellation, and provider timeouts.

GitOrigin-RevId: 4d29b879bec646d2ceb922b526dc793b1a1f5423
2026-07-10 17:59:41 +00:00
stevenlee-oai cbdee7976b Resolve and pin MCP OAuth credential stores (#30293)
[Codex Thread
019edd6d-6f14-74e2-853c-345d1803d4a6](https://codex-thread-link.openai.chatgpt-team.site/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](https://github.com/openai/codex/pull/30292) —
aggregate File/Secrets store locking
2. [openai/codex#30293](https://github.com/openai/codex/pull/30293) —
resolve and lifecycle-pin the exact OAuth store
3. [openai/codex#30416](https://github.com/openai/codex/pull/30416) —
serialized authoritative refresh transaction
4. [openai/codex#30294](https://github.com/openai/codex/pull/30294) —
Codex-owned transport refresh and one-shot 401 recovery
5. [openai/codex#30295](https://github.com/openai/codex/pull/30295) —
login/logout transaction serialization
6. [openai/codex#30296](https://github.com/openai/codex/pull/30296) —
diagnostic-only Auto store drift reporting

**This PR is layer 2.**

## Why

`Auto` is keyring-first with a File fallback, but re-evaluating that
policy during transport reconstruction or persistence can make one MCP
client read from one store and later write to another. With rotating
refresh tokens, the second store may contain an older token. This layer
makes the source selected at client startup explicit and keeps that
authority stable for the client lifecycle.

## What this PR does

- Keeps `resolve_oauth_tokens_from_store_policy` as the single
configured-policy entry point and returns both credentials and the
concrete File or Keyring source that supplied them.
- Puts exact `load`, `save`, and `delete` operations on
`ResolvedOAuthCredentialStore`, making “resolve configured policy” and
“use the selected authority” distinct at call sites.
- Pins the first concrete source in `pinned_credential_store` in the
transport recipe, so initialization retries and session reconstruction
cannot re-evaluate `Auto` and adopt another store.
- Gives `OAuthPersistor` the resolved store and keeps subsequent
persistence and removal on that authority.
- Uses a typed keyring-load error to distinguish aggregate-store
coordination failures from ordinary backend failures; a coordination
failure is surfaced instead of triggering File fallback.
- Keeps login-time `Auto` behavior unchanged: prefer Keyring, fall back
to File when unavailable, and clean up legacy File state after a
successful keyring save.
- Adds structured server/backend context when fallback cleanup fails.

## Explicit decisions and non-goals

- The selection is lifecycle-local and in memory. This PR does not add a
durable backend selector, migration, reconciliation registry, or global
source of truth outside `CODEX_HOME`.
- `Auto` may choose File at the start of a later process if keyring
availability changes. Once this client resolves, a selected-store
failure is returned instead of hot-switching.
- Different `CODEX_HOME` instances remain independent even when they can
access the same Direct keyring credential.
- Cross-process refresh serialization is intentionally not part of this
layer.

## Safe stopping point

This PR can merge alone. A single MCP client no longer hot-switches
credential stores across transport rebuilds or persistence. Two
processes can still refresh the same selected credential concurrently
until layer 3.

## Review size

The net layer is 9 files, +668/−144. The production change remains
focused on store resolution and lifecycle pinning; the largest follow-up
is integration coverage that drives real session recovery.

## Validation

- `just test -p codex-rmcp-client` (99 passed; 5 expected skips)
- Real-client 404 recovery coverage with different Keyring and File
tokens; captured bearer headers prove the stale File token is never sent
- Mutation check: removing the lifecycle pin makes that integration
regression fail by observing the stale File token
2026-07-09 18:46:29 -04:00
stevenlee-oai 6cf42cf165 Serialize shared MCP OAuth credential stores (#30292)
[Codex Thread
019edd6d-6f14-74e2-853c-345d1803d4a6](https://codex-thread-link.openai.chatgpt-team.site/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](https://github.com/openai/codex/pull/30292) —
aggregate File/Secrets store locking
2. [openai/codex#30293](https://github.com/openai/codex/pull/30293) —
resolve and lifecycle-pin the exact OAuth store
3. [openai/codex#30416](https://github.com/openai/codex/pull/30416) —
serialized authoritative refresh transaction
4. [openai/codex#30294](https://github.com/openai/codex/pull/30294) —
Codex-owned transport refresh and one-shot 401 recovery
5. [openai/codex#30295](https://github.com/openai/codex/pull/30295) —
login/logout transaction serialization
6. [openai/codex#30296](https://github.com/openai/codex/pull/30296) —
diagnostic-only Auto store drift reporting

**This PR is layer 1.**

## Why

MCP OAuth credentials stored in File or Secrets share one aggregate map.
Concurrent read-modify-write operations for different MCP servers can
both read the same snapshot and let the later write discard the earlier
update. That is a correctness problem independent of refresh-token
rotation.

## What this PR does

- Adds a bounded cross-process lock around aggregate File and Secrets
loads, saves, and deletes.
- Distinguishes aggregate-lock failures from Secrets backend
unavailability, so Auto can fall back only for the latter and cannot
bypass serialization by reading or writing File.
- Keeps Direct keyring operations outside this lock because they are
already per credential.
- Releases the Secrets aggregate lock before legacy File cleanup so
cross-store cleanup cannot create nested aggregate-lock ordering.
- Tests actual contention by waiting for an observed `WouldBlock`,
rather than assuming a sleeping worker reached the lock.
- Tests load and save with only the Secrets lock path broken while
fallback File remains readable and writable.

## Decisions and non-goals

- This lock protects aggregate-store read-modify-write integrity only.
It does not choose a credential authority or serialize an OAuth refresh
transaction.
- The lock is scoped to the active `CODEX_HOME`, matching the aggregate
files it protects.
- Lock waits are bounded, and coordination failures are surfaced rather
than treated as evidence that Secrets is unavailable.

## Safe stopping point

This PR can merge alone. It prevents lost updates and partial aggregate
reads. Auto can still resolve again during a client lifecycle until
layer 2, and concurrent refreshes remain possible until layer 3.

## Validation

- `just test -p codex-rmcp-client` (96 passed; expected environment
skips)
- Focused aggregate File/Secrets lock contention and Auto fallback tests
2026-07-07 04:03:27 +00:00