Commit Graph
97 Commits
Author SHA1 Message Date
Matthew Zeng bd89ce67cc Prepare MCP connections for coordinated OAuth refresh (#42128)
## What changed

- Add the under-development `mcp_oauth_refresh_coordination` feature and pin its selected refresh mode to each MCP connection.
- Treat the refresh mode as part of OAuth connection identity so runtime and MCP configuration refreshes reconnect when the mode changes.
- Keep legacy refresh behavior in builds where coordination is unavailable and emit a warning when coordinated mode is selected.

## Testing

- Cover connection replacement when the feature is toggled through both runtime and MCP configuration refresh paths.

GitOrigin-RevId: 89596150f0338e6ede0e712badecea4450831766
2026-09-01 20:26:57 +00:00
Evan Fannin 53691bad98 Keep MCP event subscriptions alive after task unloading (#41899)
## Why

Event subscriptions may need to outlive the MCP runtime associated with a task.

## What changed

- Add `McpEventStreamOpener`, which retains the hosted Apps MCP connection settings and opens each event stream with an independent client.
- Keep subscription cancellation tied to account changes and removal of the task's event server, including when cancellation ownership is forwarded across runtime replacement.
- Expose the opener and cancellation forwarding through `McpResourceClient`.

## Testing

Add an HTTP transport test that shuts down the runtime, refreshes credentials for the same account, and verifies that a new event stream connects with the current authorization and receives notifications.

GitOrigin-RevId: e102aa382e63121661ff0567f7523515e459922d
2026-08-31 19:18:18 +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
pakrym-oai f742dabc6f Support per-tool MCP output limits (#41421)
## What changed

- Add a positive `output_token_limit` setting to each entry under an MCP server's `tools` configuration.
- Apply the most restrictive limit when plugin and user policies overlap, while keeping approval policy independent.
- Carry the effective MCP output budget in conversation history so tool output, post-tool hook responses, and resumed sessions use the same truncation limit.

## Testing

- Cover configuration parsing, serialization, schema validation, and plugin policy merging.
- Cover MCP output below and above the configured limit, post-tool hook responses, and session resume.

GitOrigin-RevId: d0beb4fca9ba6055d9e1d31c137373b465d50d61
2026-08-28 21:40:23 +00:00
jif 92f887ec35 Use refreshed MCP tool caches during binding capture (#41344)
## Why

An MCP binding can wait for one server while another connection updates a
shared tool catalog. Preferring the catalog captured before that wait can omit
newly available tools from the first model request.

## What changed

- Recheck the current MCP tool catalog before using the captured fallback.
- Keep the captured catalog when it expires during the wait, while honoring a
  server that disables catalog caching.

## Testing

- Cover a shared Apps cache populated by a peer while binding capture waits.
- Cover cache opt-out while capture waits for another server.

GitOrigin-RevId: e4389c7ba23e4d8397dbae0930c9e36ba0a172fb
2026-08-28 14:53:53 +00:00
jif 7625343977 Preserve cached MCP tools during binding capture (#41336)
## Why

Binding capture can wait for multiple MCP servers concurrently. During that wait, a tool catalog may be published by another connection or expire after it has already allowed a server to remain dormant. Re-reading only the current cache could omit those tools or trigger unnecessary startup.

## What changed

- Retain the cached catalog that permits lazy startup for the duration of binding capture.
- Recheck the cache after the optional startup grace so catalogs published while waiting are included.
- Add regression coverage for catalogs published during startup and catalogs that expire while another server is resolving.

GitOrigin-RevId: b5c66831db8f9ebecc79ff25c5b4b0182ad68a2f
2026-08-28 13:42:37 +00:00
trolle-oai 124e560b93 Make the optional MCP startup grace configurable (#41199)
## What changed

- Add `mcp_optional_startup_grace_ms` with a default of 1,000 ms to control how long tool catalog capture waits for optional MCP servers.
- Treat a value of `0` as disabling the shared grace, so optional servers use their configured `startup_timeout_sec` instead.
- Apply updated grace values during runtime and MCP configuration refreshes, and reset cached startup deadlines when the configured duration changes.

## Testing

- Cover custom, disabled, refreshed, and shared startup grace behavior in MCP connection and core integration tests.

GitOrigin-RevId: 936196215ed6e0a29c9ec72cfee17663978df8ef
2026-08-27 20:31:40 +00:00
felixxia-oai aa89cf62bb Freeze plugin roots in MCP tool attribution (#41117)
## Why

Plugin MCP trust decisions must describe the exact host-discovered server
registration. Looking up a plugin again by ID can resolve a different root.

## What changed

- Retain the host plugin root in MCP catalog attribution and connection identity.
- Reconnect an MCP server when its attributed plugin root changes.
- Pass the retained root through tool lifecycle attribution and use it directly
  when building trusted tool context.

## Testing

Add coverage for catalog identity, connection reconciliation, lifecycle
attribution, and rejecting a different root associated with the same plugin ID.

GitOrigin-RevId: bc92743dd40ab44065a07c3ea972b4956ef8351f
2026-08-27 11:27:50 +00:00
soyeon-oai ae357e7250 Attach verified access context to eligible plugin MCP calls (#41005)
## What changed

- Fetch ChatGPT account access and attach `cyber_trusted_access` under
  `openai/entitlementContext` when an installed or selected plugin explicitly
  requests it from a local, read-only stdio tool with no arguments.
- Reject caller-supplied entitlement context on direct MCP calls, and fall back
  to an `unknown` status when access cannot be verified or the account changes
  during the lookup.
- Count entitlement lookup time against the MCP tool-call timeout.

## Testing

- Cover eligible calls plus unowned, remote, HTTP, mutable, argument-bearing,
  API-key, undeclared, direct, and account-switch cases in core and app-server
  integration tests.

GitOrigin-RevId: 303b61585ef4530276c373d914a2d0ccef1f4ac2
2026-08-27 00:02:26 +00:00
sayan-oai 4213b38f3c Honor attachment-owned permissions for MCP servers (#40728)
## Why

MCP servers attached to executor environments must retain their owner's
permission profile instead of inheriting the thread-wide sandbox authority.

## What changed

- Resolve and capture a permission profile for each enabled MCP server when
  publishing the runtime, and reject calls or elicitations when that authority
  is unavailable.
- Use the captured server profile for tool approval decisions, elicitation, and
  sandbox metadata, including after runtime refreshes.
- Materialize `:workspace_roots` from `PathUri` values so permissions preserve
  the path convention of remote executor environments.
- Give threadless app discovery and resource reads an explicit default
  permission profile.

## Testing

Added coverage for per-server elicitation authority, unresolved attachments,
runtime refreshes, restricted tool calls, and foreign-platform workspace roots.

GitOrigin-RevId: 6b188d4b08b29e9971ff7aa68a7785a0cdf9e394
2026-08-25 22:50:49 +00:00
Tamir Duberstein 20c3f9733f Restart pending MCP connections when startup timeout changes (#40636)
## Why

Reusing an MCP connection that is still starting after its
`startup_timeout_sec` changes leaves the old startup budget in effect.

## What changed

- Track the effective startup timeout on each MCP connection.
- Reuse a pending startup only when its timeout still matches the current
  configuration.
- Continue reusing ready connections when only the startup timeout changes.

## Testing

Added integration coverage that refreshes the timeout while one server is
still initializing and another is ready, verifying that only the pending
startup is replaced.

GitOrigin-RevId: 5ed71a57d3bf0dd6e227aacd16acd3a35bc37ecf
2026-08-25 16:20:38 +00:00
Tamir Duberstein f5853cbe90 Reconnect MCP servers when authentication mode changes (#40634)
## What changed

- Include the configured authentication mode in the MCP connection identity so
  runtime reconciliation replaces connections instead of reusing them after an
  authentication-mode change.
- Add a regression test covering a switch from OAuth to ChatGPT authentication
  for an executor-owned MCP server.

GitOrigin-RevId: 18cd9df62a9a5ee44594dcde6a844ad7d5e67ee2
2026-08-25 16:14:26 +00:00
Eric Traut 343074d420 Report runtime MCP connection status (#40068)
## Why

MCP inventory can be cached or collected separately from a thread's live
connections, so tool availability alone does not describe the current runtime
state.

## What changed

- Add a nullable `runtimeStatus` to `mcpServerStatus/list` for thread-scoped
  requests, covering not-started, starting, connected, authentication-required,
  failed, cancelled, and disabled connections.
- Observe published connection state without starting or reconnecting servers,
  and return an unknown status when no thread is supplied or the active
  configuration no longer matches the published registration.
- Show connection state and tool counts in the compact `/mcp` view while
  retaining the detailed inventory in `/mcp verbose` and compatibility with
  servers that omit `runtimeStatus`.

## Testing

- Cover runtime status transitions, deferred and disabled servers, closed
  transports, configuration changes, protocol compatibility, and TUI rendering.

GitOrigin-RevId: e3bb6efe652f0fa8b3c97d5c53e4729b3a87cd91
2026-08-22 05:54:43 +00:00
Krish Chainani ab8768306f Preserve executor context for MCP stop hooks (#40012)
## What changed

- Scope executor-provided stop-hook calls to the MCP server environment that registered the hook, and reject calls when that environment does not match.
- Forward turn metadata with executor stop-hook requests while retaining the hook call's `threadId` metadata.

## Testing

- Cover environment matching for MCP tool calls and verify executor stop hooks receive their environment ID and request metadata.

GitOrigin-RevId: b544ea3a6ca1f61389fb4597978ed7aac27d529a
2026-08-21 21:17:42 +00:00
Angad Singh 1bfabb21fe Raise the MCP tool name limit to 128 bytes (#39594)
## Why

The Responses API accepts tool names up to 128 bytes, but MCP tool name
normalization limited model-visible names to 64 bytes.

## What changed

- Preserve MCP tool names up to the 128-byte Responses API limit.
- Continue shortening and hashing names that exceed the limit so generated
  names remain bounded and unique.

## Testing

- Cover names at the 128-byte boundary and immediately above it.
- Verify distinct long names remain 128 bytes and code-mode compatible.

GitOrigin-RevId: 75544d00e75dd0e9328b3e2ac763d26f9cc99a48
2026-08-20 05:21:09 +00:00
Abhinav d35e5495f9 Route hook MCP calls through current connections (#39331)
## What changed

- Execute hook-triggered MCP calls through the runtime's latest connection set instead of preparing a separate catalog-bound call.
- Keep hook calls from waiting for server startup or reconnecting, and reject disconnected servers immediately.
- Apply the shorter of the hook-requested timeout and the server's configured tool timeout.

## Testing

- Update connection manager tests to cover non-waiting calls and disabled tool filters.

GitOrigin-RevId: 3166b2d1e26d9ae2b8b3a648b4d0897cc260eb93
2026-08-19 01:15:10 +00:00
Abhinav 87070a7792 Enable MCP tool hooks in Codex sessions (#39296)
## What changed

- Execute `mcp_tool` hook handlers through the session's shared MCP runtime, including managed hook configurations.
- Restrict hook calls to already-connected, cataloged, and policy-allowed tools. Unavailable servers fail immediately without starting or reconnecting them.
- Pass session metadata to hook tools, cap hook timeouts by the server timeout, and invoke hooks without model-tool approval or recursive hook dispatch.
- Record handler type and execution mode in hook telemetry, and mark memory as externally influenced after successful or blocking MCP hooks when configured.

## Testing

- Added end-to-end coverage for prompt interpolation, hidden tools, blocking decisions, unavailable servers, thread metadata, approval bypass, and memory-mode handling.
- Added MCP runtime coverage for startup readiness, tool filters, catalog revisions, and managed connector policy.

GitOrigin-RevId: 1647cb801ebc5fa385c7bda9d9c266a389c611b8
2026-08-18 22:10:43 +00:00
Matthew Zeng 45c9c74e29 Reuse pending MCP startups during reconciliation (#38493)
## Why

MCP runtime reconciliation can occur while an unchanged server is still
starting, such as when capability roots become available. Reconciliation
should neither wait for that startup nor initialize the same server again.

## What changed

- Reuse an active, uncancelled pending MCP connection when its identity,
  catalog limit, and protocol mode still match.
- Publish the shared startup result through the reconciled server view while
  applying its updated tool filter.
- Preserve cancellation when a reused pending server is subsequently removed.

## Testing

Added coverage for filtered-tool publication, disabling a reused pending
server, and capability-root reconciliation during Codex Apps startup.

GitOrigin-RevId: 690cf8695e75b341d097d7d22b5da6993b24e787
2026-08-14 04:49:14 +00:00
Eric Traut f8a3db0b99 Clarify MCP OAuth reauthentication errors (#38418)
## Why

When an MCP server rejects existing OAuth credentials, reporting that the server
is merely not logged in obscures that the user needs to authenticate again.

## What changed

Pass the MCP startup failure reason into error formatting and report that the
server requires OAuth reauthentication when appropriate. Preserve the existing
recovery hint for either `codex mcp login` or the client's OAuth sign-in flow.

## Testing

Cover the reauthentication message for both login flows and verify it in the
streamable HTTP OAuth round-trip test.

GitOrigin-RevId: 6f6d5fe7519b1a476f8b70d976223b2ea1ec938e
2026-08-13 18:45:13 +00:00
xl-openai 379cb68444 Add dynamic HTTP header helpers for MCP servers (#38245)
## What changed

- Add `http_headers_helper` configuration for local streamable HTTP MCP servers. The configured shell command runs once per connection and returns a JSON object of headers that is cached across requests.
- Apply helper headers to MCP startup and OAuth flows while restricting them to the server origin, stopping redirects, rejecting reserved or duplicate headers, and enforcing output and execution limits.
- Reject helpers for remote or managed-disabled servers, use the local environment working directory, and redact helper commands from `codex mcp list` and `codex mcp get` output.

## Testing

- Cover configuration validation, helper lifecycle and output parsing, origin isolation, OAuth discovery and token refresh, managed requirements, environment selection, and CLI redaction.

GitOrigin-RevId: 84e0e26ce75520b0869d37c72b1678e033bd6818
2026-08-12 20:36:32 +00:00
jif 0ca439900e Cache tool catalogs for streamable HTTP MCP servers (#37970)
## Why

Subagents should be able to use known HTTP MCP tool definitions without opening a connection until a tool is actually called.

## What changed

- Add streamable HTTP configurations to the process-scoped MCP tool catalog cache when their authentication identity can be derived safely.
- Fingerprint transport settings, relevant environment variables, protocol mode, plugin status, and client capabilities so catalogs are reused only across equivalent connections.
- Keep OAuth and other dynamically resolved credential configurations out of the shared cache.

## Testing

- Add an integration test proving that a subagent receives cached HTTP tools without reinitializing the server, then starts its own connection when it calls one.

GitOrigin-RevId: bb2787e29e9b71993def31aafd1f0d8f1b728d26
2026-08-11 09:22:50 +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
mchen-oai 4b0e2a0bff Support MCP form input in full-access user threads (#37864)
## Why

Standard MCP forms can require user-entered values even when tool permissions are
otherwise auto-approved in full-access sessions.

## What changed

- Recognize the `openai/standard-form-input` client extension and surface
  non-approval forms in full-access, user-initiated root threads.
- Keep approval forms, automation and subagent threads, headless sessions, and
  clients without the capability on their existing decline or review paths.
- Treat the capability as client-only so it is not advertised to MCP servers,
  and enable it after session startup so required servers cannot block startup
  waiting for form input.

## Testing

Add unit and app-server coverage for accepted form round trips, declined cases,
approval metadata safeguards, resumed threads, and extension filtering.

GitOrigin-RevId: 053bfe397a5c79eceef90a81d13e2aca6353af43
2026-08-10 18:20:12 +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
jif 27e4a05cd3 Expose runtime activity in server diagnostics (#37486)
## What changed

- Add lifecycle-backed gauges for in-flight and queued app requests, pending server requests and mailbox messages, active turns, and live MCP connections.
- Register each gauge on first use and decrement it when the tracked work or resource is dropped.
- Document the new `server/diagnostics` gauge names and account for the diagnostics request itself in the response example and test.

GitOrigin-RevId: 4bb82a3918af0b502d149b5d761ad669b2083f39
2026-08-07 18:38:24 +00:00
jif b3ffe3d001 Recover MCP servers after OAuth reauthentication (#37337)
## Why

An OAuth-backed Streamable HTTP MCP server can fail startup when its stored credentials are rejected. If a client then completes OAuth sign-in and replaces those credentials, the failed server needs to become available without restarting the Codex session.

## What changed

- Track the credential store and OAuth tokens used for each MCP connection, and detect replacements after authentication failures.
- Refresh affected MCP servers before the next turn and include their recovered tools in the model request.
- Classify HTTP authentication challenges and rejected refresh tokens as requiring reauthentication, with sign-in guidance appropriate to local and client-managed environments.

## Testing

- Cover recovery from expired credentials through an externally written replacement token.
- Cover authentication-error classification, startup messaging, and `Auto` store migration from file credentials to the keyring.

GitOrigin-RevId: 9b090089d4e7a44ffc182f4e25da20a18e97b70f
2026-08-07 00:17:46 +00:00
jif 1151b23f01 Start cached MCP servers lazily for subagents (#37261)
## Why

Subagents can reuse cached MCP tool definitions without starting every optional
server before any of its tools are used.

## What changed

- Defer startup for subagent-owned, optional MCP servers when their cache has at
  least one visible, allowed tool, and trigger startup on the first operation
  that needs the live client.
- Keep root sessions, required servers, selected plugin servers, and explicit
  reconnects eager.
- Exclude empty catalogs from cache eligibility and keep dormant servers out of
  the initial startup summary.

## Testing

- Extend MCP tool-cache coverage for eager root startup, unused and filtered
  subagent servers, deferred startup status events, and startup that survives an
  interrupted first tool call.

GitOrigin-RevId: e7528ff08312583a6747cbc6550ea5b6eabda9a6
2026-08-06 11:18:24 +00:00
jif 952e87d3f2 Reuse stable MCP bindings across sampling steps (#37101)
## What changed

- Cache an `McpBinding` on each published MCP runtime once server startup has
  settled and the tool catalog revision is stable.
- Reuse the cached binding while the catalog revision remains unchanged, and
  rebuild it after a runtime publish or catalog change.
- Treat terminal failures from optional servers as stable, while continuing to
  wait for required servers and reconnecting Codex Apps servers.

## Testing

- Cover binding reuse within one published runtime and invalidation after a
  republish.
- Cover stability checks for pending, failed optional, required, and
  reconnected servers.

GitOrigin-RevId: 783a6b04897f6c484a6d56fd9cee542814041759
2026-08-05 14:04:39 +00:00
Martin Au-Yeung ee46c5ba0e Negotiate MCP extensions per app-server session (#36910)
## Why

App-server clients need to advertise structured MCP extension settings, including supported MCP App UI MIME types, rather than only opting into OpenAI form elicitation with a boolean.

## What changed

- Add an `extensions` map to initialize capabilities and preserve `mcpServerOpenaiFormElicitation` as a legacy alias for `openai/form`.
- Capture the declared extension profile when a thread is started, resumed, or forked, propagate it to subagents, and advertise it to downstream MCP servers during initialization.
- Keep the profile stable for the lifetime of the loaded session instead of changing it on later turns or direct tool calls.

## Testing

- Cover extension conversion, downstream MCP initialization, session isolation, legacy form support, and subagent inheritance.

GitOrigin-RevId: fbcedbb74ce788e574b0f884a4c45c4cedb9de54
2026-08-04 15:23:43 +00:00
tongzhou wang 51c9ed6d4f Add per-surface MCP tool exposure controls (#36781)
## Why

MCP tools can be exposed directly, discovered through tool search, or called
from Code Mode. Servers need to be able to opt out of any of these surfaces
without disabling their tools everywhere.

## What changed

- Add `omit_tools_from` to MCP server configuration, accepting any combination
  of `direct`, `deferred`, and `code_mode`.
- Apply the exclusions independently when building direct, deferred, and Code
  Mode tool surfaces while keeping omitted tools registered for permitted uses.
- Remove client-private `_meta` fields from MCP results returned to Code Mode.
- Include the new setting in the configuration schema and MCP config
  serialization.

## Testing

- Cover every exposure combination across Code Mode, Code-Mode-only sessions,
  tool search, direct-only namespaces, and prefixed and unprefixed MCP names.
- Verify direct and nested execution paths, parallel-call support, config
  round-tripping, and `_meta` filtering.

GitOrigin-RevId: 12dfcb78bb5c5ecf4d70f38a8b5022792463a27f
2026-08-03 18:51:46 +00:00
jif e4e040881a Raise the host-owned Codex Apps catalog limit (#36772)
## Why

Codex Apps tool catalogs can exceed the standard MCP limit of 2,048 items and
still need to remain available through tool search.

## What changed

- Allow up to 8,192 catalog items for host-owned `codex_apps` registrations.
- Keep the 2,048-item limit for other MCP servers, including extensions that
  register the `codex_apps` name.
- Restrict the shared Codex Apps tool cache to host-owned registrations.

## Testing

- Cover large catalogs for built-in and hosted-plugin registrations while
  verifying that another extension retains the standard limit.
- Verify that a same-named extension cannot read the host-owned Apps cache.

GitOrigin-RevId: 2265693a460e9be63c4c849169cba7324def4f49
2026-08-03 17:06:46 +00:00
jif bf4d3f51ea Restrict hosted MCP credentials to local environments (#36306)
## Why

Executor-owned MCP servers must not receive hosted ChatGPT actor credentials or credentials from the host's OAuth store.

## What changed

- Provide the ChatGPT auth provider and consult stored OAuth credentials only for MCP servers in the local environment.
- Require non-local servers configured with `auth = "chatgpt"` to supply a non-empty, valid static `Authorization` header. Reject environment-backed authorization so host secrets are not resolved for an executor-owned server.
- Report unsupported authentication and fail startup before connecting when an executor-owned server has no acceptable explicit authorization.

## Testing

Add coverage for local credential forwarding, non-local credential isolation, static header validation, auth status, OAuth lookup avoidance, and startup rejection.

GitOrigin-RevId: e18f1878f260c93d9babd390a5a7eac86172299b
2026-07-31 10:42:02 +00:00
jif 85c082cccc Share optional MCP startup grace across connection sets (#36011)
## Why

Each connection set could restart the one-second startup grace for the same
cacheable optional MCP server, repeatedly delaying catalog capture while that
server was still pending.

## What changed

- Store the optional startup deadline in the shared tool catalog cache entry.
- Reuse that deadline until a catalog is published, and allow a fresh grace
  period after the cached catalog expires.
- Preserve per-connection-set startup grace for servers that disable catalog
  caching.

## Testing

Added a paused-time test covering shared deadlines, immediate cached-tool reuse,
cache expiration, and disabled caching.

GitOrigin-RevId: 3494969ee7002c70ce9e4ffd370e46a22d38cc11
2026-07-29 18:53:15 +00:00
jif c550cb3e01 Clean up cancelled MCP elicitation requests (#35836)
## Why

Cancelling an in-flight MCP elicitation could leave its response handler registered in the shared router.

## What changed

- Remove an elicitation from the router when its pending request future is dropped.
- Keep cleanup scoped to the cancelled request so other pending elicitations remain routable.

## Testing

Added a test that cancels one of two pending elicitations, verifies the cancelled request can no longer be resolved, and confirms the other request still completes.

GitOrigin-RevId: 9a10360459f0b39552d9d29a6e1b867c1f09e97d
2026-07-28 22:16:42 +00:00
Charlie Marsh 84ccb2938b Resolve MCP tool catalogs concurrently (#35777)
## What changed

- Resolve per-server tool catalogs concurrently in `list_all_tools` and binding capture.
- After the shared startup wait, recheck servers that previously exposed cached tools so a newly ready client contributes its current catalog and callable client.

## Testing

- Add gated-client tests that verify multiple server catalogs start before any one server is released.
- Verify binding capture replaces cached Codex Apps tools with the ready client's tools when startup completes during capture.

GitOrigin-RevId: a30d1a535ed1588f2bba21f2741e8bbd9342e339
2026-07-28 14:13:03 +00:00
jif d9e1c9cd55 Avoid blocking turns on optional MCP startup (#35742)
## Why

A pending optional MCP server can delay the first model request even when the
turn does not need that server.

## What changed

- Give optional MCP servers a shared one-second startup grace, then omit servers
  that are still pending from the captured tool catalog.
- Continue waiting when the turn explicitly requires a server through a plugin,
  skill dependency, or `mcp://` mention, and preserve this behavior for input
  received between sampling steps.
- Route direct resource requests to the live connection set when a pending
  server was omitted from the binding, while keeping all-server resource
  discovery non-blocking.

## Testing

- Cover the shared grace period and resource behavior for pending optional
  servers.
- Verify plugin, plugin-skill, and direct MCP mentions wait for startup.
- Verify an Apps-enabled turn proceeds without tools from an unrelated pending
  optional server.

GitOrigin-RevId: b5f895c5a5362fe73f7d33250367662d4a217e4d
2026-07-28 09:32:48 +00:00
thomas be2e4afcd7 Add MCP 2026-07-28 discovery support (#35724)
## What changed

- Add an opt-in `mcp_2026_07_28` protocol mode while preserving the legacy
  lifecycle by default.
- Negotiate the new protocol over streamable HTTP with `server/discover`,
  including bounded responses, redirect protection, and fallback only when a
  response establishes that the endpoint is legacy-only.
- Require stdio servers to opt in with
  `CODEX_MCP_PROTOCOL_VERSION=2026-07-28`, and add a bounded local stdio
  transport for the modern lifecycle.
- Consume paginated tool, resource, and resource-template catalogs in modern
  mode, reject repeated cursors, and retain discovered server identity.
- Reconnect reusable MCP clients when their selected protocol mode changes.

## Testing

- Cover HTTP JSON and SSE discovery, legacy fallback and rejection cases,
  redirects, retries, response limits, and pagination.
- Cover local and executor stdio discovery, protocol markers, message limits,
  and legacy compatibility.

GitOrigin-RevId: f6a78816e127d2a482292d63b91c8384f1595903
2026-07-28 05:52:12 +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 3bbf1fe757 Expose cached MCP tools before server startup (#35590)
## Why

Cached MCP definitions can be supplied to inference without waiting for the
server to finish initializing.

## What changed

- Publish cached tools while startup is still in progress, clearing their
  potentially stale read-only hint.
- Wait for the selected server to start before executing a tool call, then
  prepare the call against the refreshed live binding.
- Keep cached tools visible in a binding even when no live client is available,
  while rejecting attempts to prepare those calls.

## Testing

- Cover cached-tool visibility before startup and replacement with live tool
  metadata afterward.
- Verify cached definitions reach inference before MCP initialization and that
  calls unavailable in the live catalog return the expected model-visible
  error.

GitOrigin-RevId: 3aae8f474c344ccdc5e08fe321bbad21d85bffd1
2026-07-27 10:25:32 +00:00
Celia Chen 265cd2e100 Initialize execution environments with the final HTTP policy (#34995)
## Why

The TUI must inspect the default execution environment before loading its final
configuration. Initializing the environment manager at that point can give
startup services the bootstrap HTTP policy instead of the effective policy after
managed requirements are applied.

## What changed

- Split environment discovery from manager construction so callers can inspect
  the default environment without starting remote connections.
- Build the environment manager after final configuration loading and pass its
  resolved `HttpClientFactory` through all construction paths.
- Add shared test support for managers that use the legacy default HTTP policy.

## Testing

- Cover connection-free environment discovery and explicit HTTP policy
  propagation.
- Verify TUI startup services use the final managed `respect_system_proxy` value.

GitOrigin-RevId: 928fa31e6b4bcfbe1a121cade2f351427fdfa0f4
2026-07-23 19:24:41 +00:00
sayan-oai 74e9d7efc4 Allow omitting MCP tool prefixes per server (#34991)
## What changed

- Accept a table form of `features.non_prefixed_mcp_tool_names` with an
  optional `server_names` list while preserving the existing boolean form.
- Omit the legacy `mcp__` namespace prefix only for tools from selected MCP
  servers. When no server list is provided, the enabled feature continues to
  omit the prefix for every server.
- Cover configuration resolution, tool normalization, and an MCP stdio
  round trip with selected servers.

GitOrigin-RevId: bdfb7ac54226de5051f06610e2c6b78b23912ef0
2026-07-23 18:54:55 +00:00
jif 9e1f43dc2d Move MCP connection helpers into the test module (#34962)
Keep the `McpConnectionSet` test constructors and accessors alongside the
connection manager tests instead of defining test-only helpers in the
production module.

GitOrigin-RevId: 925392f8b7d903b131ef1b49afd7e50f41226b1f
2026-07-23 15:40:03 +00:00
jif 34b935e3e5 Replace closed MCP connections during reconciliation (#34957)
## Why

MCP connection reconciliation can otherwise reuse a client after its service or
underlying transport has stopped.

## What changed

- Add `RmcpClient::is_closed` to report closed client, service, and transport
  states.
- Exclude closed clients when selecting a reusable MCP connection so
  reconciliation starts a replacement.

## Testing

- Add a reconciliation test that disconnects an in-process MCP transport and
  verifies that its connection is replaced.

GitOrigin-RevId: 366a85c9959dbe1763923d7e33a4ecf52d9c3c6a
2026-07-23 15:29:10 +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 e497325a6a Centralize thread MCP state in McpRuntime (#34930)
## What changed

- Make `McpRuntime` own the published MCP configuration, connections, elicitation routing, and selected capability roots for a thread.
- Capture immutable MCP bindings for model steps and tool calls so in-flight work keeps a consistent connection set and approval authority while refreshed state is published atomically.
- Mark MCP state dirty when relevant configuration, plugins, environments, authentication, or elicitation capabilities change, then rebuild it before the next sampling request or out-of-band MCP operation.
- Separate config reloads from server invalidation: `ReloadMcpConfig` applies resolved MCP inputs, while `RefreshMcpServers` requests reinitialization from the thread's latest state.

## Testing

- Cover refreshed state visibility for existing turns, stable step bindings, current approval authority, cancelled refresh retries, resource-client reconciliation, and Apps recovery between sampling requests.

GitOrigin-RevId: 59eabb1aa8dc083426bd18ef4d3630508f376401
2026-07-23 11:27:34 +00:00
jif 84d2b203ed Make MCP resource clients follow the latest runtime (#34733)
## What changed

- Make `McpResourceClient` resolve resource operations and cache identity from
  the latest `McpRuntime` connection snapshot.
- Remove step-bound resource clients from `McpBinding` and the associated
  per-binding client identity tracking.

GitOrigin-RevId: ee59f5867308c5a63e6e232384a50cf1e0c2a011
2026-07-22 11:13:09 +00:00
jif 516f1e2aff Rename the MCP connection manager to McpConnectionSet (#34708)
## What changed

- Use `McpConnectionSet` as the primary name for the collection of active MCP
  server connections throughout `codex-mcp` and its callers.
- Keep `McpConnectionManager` as a backward-compatible type alias.

GitOrigin-RevId: 9753838b4fd0a0b6429a9c4af0c077137616f388
2026-07-22 09:25:22 +00:00
jif 65f8bf6853 Bind MCP calls to captured catalog revisions (#34588)
## Why

An MCP connection or tool catalog can change after a model step captures its
available tools. Calls from that step must not be rerouted to a replacement
client or run against a catalog revision the model did not see.

## What changed

- Add `McpBinding` to capture the ready clients, visible tools, resources, and
  server metadata for one sampling request.
- Prepare calls against the captured client and reject them if the tool catalog
  changes before call preparation and execution finish.
- Keep resource access and cache identity tied to the binding's exact connection
  set, and omit servers that do not have a ready client.
- Preserve each client's unfiltered tool catalog so bindings can apply the
  current filter consistently.

## Testing

Add coverage for connection replacement, stale catalog rejection, serialized
call preparation and refresh, ready-client capture, and binding-scoped resource
identity.

GitOrigin-RevId: a25da4d2c7f5ed06c41caa0c6d15c464c1698314
2026-07-21 18:13:41 +00:00
jif 2d85e6d3a6 Split MCP connection manager into focused modules (#34522)
## What changed

- Move required-server startup validation into `connection_manager/required.rs`.
- Move tool listing, lookup, metadata attachment, and Codex Apps cache refresh into `connection_manager/tool_catalog.rs`.
- Keep the existing connection-manager API and behavior unchanged.

GitOrigin-RevId: 7249896699f756bdbb6e00bc2bbc4a98098741a9
2026-07-21 11:45:36 +00:00
stevenlee-oai 19940967bd Support threadless MCP connections without event channels (#34408)
## What changed

- Make the MCP connection manager's event sender optional.
- Skip startup notifications when a caller has no session event stream.
- Decline interactive MCP elicitations in that mode while allowing the
  underlying operation to continue.
- Update threadless resource reads, status snapshots, and connector discovery
  to use the channel-free path.

## Testing

- Extend the app-server MCP resource test to verify that a threadless resource
  read declines an elicitation and still returns the resource contents.

GitOrigin-RevId: 65fea152adbc02a78e09a40cae4134b6dccffd34
2026-07-20 20:43:36 +00:00