Commit Graph
85 Commits
Author SHA1 Message Date
cooper-oai 219ab4043e Use runtime authentication for OpenAI MCP and app requests (#59749)
## What changed

- Select fresh authentication for each HTTP operation on eligible OpenAI MCP connections while preserving the connection's credential source and account network policy. Stop redirects when requests carry runtime assertions.
- Pass the owning thread's authentication and runtime context through app discovery, connector metadata, and trusted-access requests. Include the runtime authentication mode in MCP connection and tool-cache identities.
- Give resumed actors analytics clients bound to their own authentication context, and serialize stored-credential reloads with token refresh while preserving host-provided credentials.

## Testing

Add coverage for fresh request assertions, revoked account policies, redirect handling, resumed-actor isolation, and MCP uploads in dual-header and assertion-only modes.

GitOrigin-RevId: f06900a6db61cd6cf53c3aa8075afeec4d5706d9
2026-11-05 22:03:29 +00:00
Joe Savona aa1399cbcd Forward caller metadata on MCP resource reads (#59509)
## What changed

Accept an optional `_meta` object on `mcpServer/resource/read` and forward it to MCP `resources/read`, including reads bound to an originating tool call. Update the protocol schemas and generated TypeScript and Python types.

Reject caller metadata containing host-owned `threadId`, `x-codex-turn-metadata`, or `codex/connectionLease` keys. For `codex_apps`, also reserve `connector_id`, `link_id`, and `_codex_apps.resource_uri` to preserve app and account routing.

## Testing

Add integration coverage for metadata forwarding through stdio, hosted app reads with and without a thread, and origin-bound widget reads. Cover rejection of reserved keys and non-object metadata.

GitOrigin-RevId: 227ee0fb5fe15fa2ff2ec66d4d5ae16de8935a8c
2026-11-04 22:55:22 +00:00
yitaoh-oai 3c074bb44a Add model Search discovery to MCP bindings (#59034)
## What changed

Add `McpBinding` APIs to discover the model's Search tool profile through an already authorized, host-owned Apps connection. Discovery sends turn metadata, paginates `tools/list`, and returns a scoped binding with the refreshed declaration and connector-provided invocation context.

Require a visible Search tool and an object-valued invocation context. Preserve the context only for calls using the same client, while allowing normal dispatch to recheck visibility, account selection, and approval policy.

Bound discovery to five seconds and distinguish critical timeout, transport, and server errors from unavailability. Expose the existing retryable transport error classifier for this distinction.

## Testing

Add coverage for opaque invocation context extraction and extend transport error classification coverage to HTTP 503 and 403 responses, exercising the exported classifier through a contextual error.

GitOrigin-RevId: 9848d4adb91e3fb2b9406349c31d1fd5c5c47a33
2026-11-03 01:59:24 +00:00
sayan-oai 0585dcb5db Preserve sandbox context in prepared MCP calls (#59020)
## Why

MCP permission profiles need the directory context used to interpret them. Prepared calls must retain that context alongside their captured permissions across runtime refreshes.

## What changed

- Store each server's permission source as thread permissions or a captured environment `FileSystemSandboxContext`.
- Capture environment working directories, home and temporary directories, and materialized workspace roots. Retain the host working directory for thread permissions.
- Expose the captured source through `PreparedMcpCall::permission_source()`, while keeping hosted Apps on thread permissions even when a local environment is attached.

## Testing

Extend binding tests to verify that prepared calls retain environment sandbox paths across refreshes and expose the host working directory for thread permissions. Update elicitation coverage to include hosted Apps with an attached local environment.

GitOrigin-RevId: 87e94605daece324786eebc07b62a507d35e5ced
2026-11-03 01:08:08 +00:00
rhan-oai 5be57bedd0 Add scoped host metadata hooks for MCP tool requests (#58395)
## What changed

Expose `McpToolRequestMetaHook` and `McpToolRequestMetaProvider` so hosts can supply a per-invocation `_meta` value using the thread, turn, and call IDs. Apply the hook before dispatch only when the tool, server name, source, and full transport configuration match the selected local MCP registration.

Reject metadata key collisions and propagate provider errors to the tool caller without dispatching the call.

## Testing

Add integration coverage for matching registrations, different contributors and routing headers, unrelated tools and servers, provider failures, and existing metadata keys.

GitOrigin-RevId: 2bf51c375a04617d61b24ca1cbbcaa810fb06720
2026-10-30 17:32:09 +00:00
Charlie Marsh 5e3496e0ad Share eligible local stdio MCP connections across chats (#57211)
## What changed

Extend `mcp_connection_sharing` to pool compatible local stdio connections that negotiate MCP `2026-07-28`. Keep legacy servers and servers that request input during startup private.

Preserve each chat's tool catalog and route input requests to the calling chat. Release connections independently for each chat, shutting down the shared server after the final release, and retire pooled connections on forced refresh without interrupting other chats.

## Testing

Add pool, runtime, app-server, and core scenario tests covering protocol gating, startup cancellation, refresh, final-release shutdown, and separate tool visibility and simultaneous input responses across chats sharing one process.

GitOrigin-RevId: 896b107267a20ec1bffccdefca6c40fe2945a022
2026-10-26 19:37:32 +00:00
viyatb-oai d124fe9de1 Add negotiated network policy metadata support for MCP calls (#56278)
## What changed

Add an optional `NetworkPolicyMetadataProvider` to the MCP runtime. Advertise `codex/network-policy-meta` only to trusted ChatGPT origins when a provider is available, and attach policy metadata only when the sending session also advertises support.

Strip caller-supplied policy metadata and derive restrictions from the call's captured permission profile and server environment. Resolve metadata against each session's capabilities, including after recovery, while retaining one policy snapshot per call. Fail the call before sending if policy resolution fails. Existing runtime callers leave the provider unset.

## Testing

Add tests for capability negotiation, trusted-origin restrictions, forged metadata removal, both tool dispatch paths, and policy snapshot reuse. Add HTTP session-recovery coverage for changing capabilities and policy-resolution failures while preserving caller metadata and read-only restrictions.

GitOrigin-RevId: 4b978f986abc0475fc67659be98fc01a2d6ce7cd
2026-10-22 22:33:07 +00:00
jif c419fd01a7 Fix enterprise MCP credential selection and reauthentication (#55859)
## What changed

- Prefer an eligible account grant over saved enterprise credentials, with a fallback to saved enterprise sign-in during initial connection if the account grant is rejected.
- Remember rejected account grants per enterprise MCP registration across threads and report authentication failures as requiring reauthentication. Keep administrator configuration errors distinct from sign-in failures.
- Compare account grants independently of access and ID token rotation, recheck the latest identity eligibility after exchange, and retry once when the refresh grant changes.
- Make MCP authentication status reflect usable account grants, saved enterprise credentials, and completed connection failures.

## Testing

Extend regression coverage for enterprise sign-in failures and recovery, MCP authentication status, account grant identity across token refreshes, and retries after transient credential failures.

GitOrigin-RevId: eeac65f668d5d2d55e9d8bf4547fbcbdd6a6c42d
2026-10-21 10:40:59 +00:00
jif 6b13dffc5e Reuse Codex account grants for enterprise MCP authentication (#55698)
## What changed

- Prefer stored enterprise credentials when available; otherwise use a validated Codex account OAuth grant whose issuer matches the enterprise MCP configuration.
- Pin each connection to its credential source and OAuth client, reject stale account grants, and hold the account refresh lease only during the IdP exchange.
- Report actionable sign-in and issuer configuration errors, and classify token failures by credential source.

GitOrigin-RevId: 26673f276a31e4ca5290f6b120f0ac44c77d7239
2026-10-20 23:27:33 +00:00
Anthony Tafoya f7a135ec61 Reconcile V2 executor plugins with cloud catalogs (#55301)
## What changed

- Use V2 discovery inventories for plugin MCP contributions when supplied, including empty or failed inventories; retain legacy discovery when no V2 snapshot is supplied.
- Merge plugins by canonical identity, using cloud metadata and enablement for remote plugins and attaching executor installations only when versions match. Preserve configured executor-local plugins and executor enablement when cloud data is unavailable.
- Keep installation order stable across refreshes and run merged MCP declarations on the first retained executor installation while preserving attribution for the others.
- Carry local and remote identities through selected-plugin snapshots, skill attribution, and active-plugin telemetry. Track disabled plugin IDs alongside disabled roots.
- Preserve a complete cloud catalog when a partial refresh arrives, and cap tool-description plugin attribution at 1,024 bytes while retaining all plugin associations.

## Testing

Add coverage for catalog parsing and reconciliation, enablement and discovery-mode selection, installation refresh ordering, executor-specific MCP normalization, selected-plugin snapshots, and bounded UTF-8 attribution text.

GitOrigin-RevId: a8ad352de6a2b8dc4bfd1ff6a5c62ee8ed1d1664
2026-10-19 15:15:17 +00:00
tongzhou wang 1b6e0d8145 Track content provenance through prompt assembly and compaction (#53831)
## Why

Message roles and content classifications do not identify who supplied each context part. Source attribution needs to survive prompt assembly and history truncation, including messages that combine text from different producers.

## What changed

- Add per-part `ContentItemMetadata` for user input, developer instructions, `AGENTS.md`, skills, harness context, command hooks, and tool context with optional callable namespaces.
- Carry attribution alongside content and classifications through contextual fragments, extension prompts, hook output, and agent messages. Keep tool-provided context-window hints separate from harness text.
- Preserve the source of retained text slices during compaction and attribute generated truncation notices to the harness. Default missing historical attribution to unknown.
- Attribute host MCP calls using cached tool namespaces only when catalog revisions remain stable, without starting servers or refreshing catalogs for attribution.
- Send the new metadata to Responses Lite and strip it from requests to endpoints that do not support it.

## Testing

Extend compaction tests to cover mixed sources, missing or extra metadata entries, and discarded media. Update Responses Lite request assertions to verify endpoint-specific attribution handling.

GitOrigin-RevId: b0ebc929b7c60f3ec49d1affbf897312d63edcc8
2026-10-14 02:01:49 +00:00
Michael Bolin 7d0b91d5d6 Separate MCP sandbox policy from launcher metadata (#53709)
## Why

MCP servers must forward sandbox policy unchanged to `codex sandbox --sandbox-state-json`, while interpreting launcher information to find the Codex CLI. Keep those contracts separate so consumers can preserve unknown policy fields.

## What changed

- Accept the experimental `codex/sandbox-state` capability alongside the deprecated `codex/sandbox-state-meta` capability, and send identical policy values under both `_meta` keys.
- Move `codexExecutable` out of the policy into `codex/sandbox-launcher`, supplied only when a verified CLI path is available for a local stdio server.
- Replace stale sandbox metadata while retaining unrelated entries, and remove stale launcher metadata when no launcher is available.
- Document the metadata contract and how servers should forward policy and retain authority for long-lived subprocesses.

## Testing

Update unit and integration coverage for policy serialization, identical state aliases, launcher availability across execution environments, and stale metadata replacement.

GitOrigin-RevId: e544c06e6e023953b1fc8069b7b1affa065262d1
2026-10-13 16:23:44 +00:00
Adam Perry @ OpenAI 806d2d1cc1 Remove per-content source attribution metadata (#52329)
## What changed

- Remove `ContentItemMetadata`, provenance and namespace types, and the `content_item_metadata` protocol field while retaining `content_item_kinds` classifications.
- Simplify context fragments, extension contributions, and hook output to carry content without source attribution. Return MCP tool results directly without an attribution wrapper.
- Render context-window hints together in a single text fragment.

## Testing

Update Responses and Responses Lite request assertions to expect content-kind classifications without per-content attribution, and adapt context, hook, and extension tests to the simplified types.

GitOrigin-RevId: 201894cd4c93c6d4b4c41c845e7a9af1dd3c95ca
2026-10-08 23:57:36 +00:00
tongzhou wang ad54b75574 Track source attribution for individual context parts (#52195)
## What changed

- Add `ContentItemMetadata` to distinguish user input, developer instructions, `AGENTS.md`, skills, harness context, and tool-supplied context independently of message role and content classification.
- Keep attribution attached to content through prompt assembly, history processing, and hook-output spilling. Distinguish command hooks from MCP hooks and retain tool namespaces when known.
- Treat missing historical attribution as unknown and send per-content metadata only to Responses Lite.

## Testing

Update request and history assertions to cover attribution persistence and Responses Lite metadata handling.

GitOrigin-RevId: 24e56005f5bdb98bf82f2b3943f29c4c81f3d587
2026-10-08 17:56:54 +00:00
Michael Bolin 78a19f5ab5 Expose a verified sandbox launcher to local MCP servers (#52182)
## Why

MCP servers receiving sandbox state need a usable Codex executable to launch commands with the issuing call's policy. HTTP and remote servers cannot assume access to the host's filesystem.

## What changed

- Include optional `codexExecutable` metadata for local stdio servers when the host supplies an absolute, UTF-8 path to a CLI supporting `sandbox --sandbox-state-json`. Cache capability probes by executable path and bound them to five seconds.
- Document forwarding the sandbox state unchanged and requiring an explicit opt-out rather than silently falling back to PATH lookup or unsandboxed execution when the launcher is absent.
- Honor `useMxc` from forwarded sandbox state when selecting the Windows sandbox backend and network proxy policies, preserving a parent's selection made through CLI overrides.

## Testing

Add coverage for launcher eligibility across local, remote, and HTTP servers, invalid or missing executable paths, and binaries without sandbox-state support. Extend metadata integration and serialization tests to cover the optional launcher field, legacy state, and unknown future fields.

GitOrigin-RevId: ea8cd3770616e5a620b423a01052a7bc828bceb9
2026-10-08 17:25:09 +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
Rennie c45ea25ffb Allow subagents to request MCP elicitation input (#46877)
## Why

MCP requests requiring user input previously failed in subagents with guidance to ask the parent agent, blocking browser sign-in, form input, and interactive tool approval in the child thread.

## What changed

Remove the root-only MCP elicitation guard and `allow_user_interaction` plumbing so subagents can surface prompts and wait for responses under the existing approval policy and automatic review rules. Connector authentication can now return retry guidance after acceptance or preserve the original failure when declined.

Keep legacy tool approvals through `request_user_input` restricted to the root thread.

## Testing

Update unit and integration coverage for subagent prompt resolution, form responses, connector authentication acceptance and decline, automatic approval, strict review, and approval-policy updates on reused connections. Update the browser sign-in scenario snapshot to show the subagent continuing after an accepted response.

GitOrigin-RevId: c226fc6dfde724ed22b91dc04dd32bbc15245bee
2026-09-20 19:42:18 +00:00
Anthony Tafoya 394dadb93d Add turn-start cloud plugin discovery to the MCP extension (#46572)
## What changed

- Support an optional cloud provider alongside executor plugins, refreshing its thread-scoped catalog at each regular turn when plugins are enabled.
- Use cloud connector metadata for app attribution without starting cloud-declared MCP servers.
- Scope cached catalogs to authentication and Apps availability. Retain the previous catalog on discovery failure within the same scope, clear stale catalogs on auth changes, and reject results completed under outdated credentials.
- Add a cancellable regular-task startup phase that reconciles MCP before discovery and reapplies contributor state afterward without invalidating resource caches.

## Testing

Add regression coverage for per-turn refresh, empty catalogs, discovery failures, plugin disabling, auth changes during discovery, MCP reconciliation and cancellation, and cloud app attribution alongside executor MCP tools.

GitOrigin-RevId: 8469eb109ea316e21cbc4122c52ad8000caeef03
2026-09-19 02:07:58 +00:00
Rennie 40584fad87 Keep MCP user interaction on the root thread (#46066)
## Why

MCP requests that need human input, including browser sign-in, must be handled by the root thread. Subagents need guidance to hand these blockers to their parent without prompting the user or automatically accepting requests that require input.

## What changed

- Reject interactive MCP elicitations and tool approval prompts in subagents with guidance to ask the parent and wait before retrying.
- Recognize browser authentication and `codex_requires_user_input` metadata even when the form schema is empty, while preserving automatic permission approvals and review decisions.
- Carry user-interaction eligibility through MCP runtime creation and connection reuse, and guard prompt registration.
- Preserve connector authentication diagnostics alongside handoff guidance, subject to normal tool-output limits.

## Testing

Add unit and integration coverage for blocked subagent prompts, root browser authentication, automatic approval and review, connection reuse, and authentication diagnostic preservation and truncation. Add a request-history snapshot for browser-auth handoff guidance.

GitOrigin-RevId: 83e146b6e5c1a2a22a34681ad45615f504b3c96c
2026-09-17 01:18:37 +00:00
Henry Levy 29e6bc814e Preserve orchestrator skill caches across MCP runtime updates (#46033)
## Why

Orchestrator skill caches were tied to the entire MCP connection set, so runtime updates could discard cached catalogs and contents even when the Apps connection was reused. Plugin changes still need to refresh those resources without requiring a reconnect.

## What changed

Key orchestrator skill caches by the Apps server connection and an explicit invalidation generation. Preserve cached resources while that identity stays unchanged, and invalidate them on MCP runtime refresh requests or configuration refreshes. Replacing the connection also changes the cache identity.

## Testing

Extend the production-turn integration test to verify cache reuse across ordinary turns and approval-policy changes, refreshed skill contents after plugin invalidation without reconnecting, and fresh resource requests after a forced reconnect.

GitOrigin-RevId: 43ce059972369c4c735742e8224b60a692244b02
2026-09-16 21:41:23 +00:00
priyanshusingh-de 2e572378f4 Add connector auth failure detection without an install URL (#44938)
## Why

`connector_auth_failure_from_tool_result` requires an install URL to return an auth failure, even when the tool result contains valid auth failure metadata.

## What changed

Export `is_connector_auth_failure_from_tool_result` from `codex-mcp` to detect auth failures independently of an install URL. Share metadata validation with the existing parser, requiring an error result, an explicit auth failure flag, and a nonempty connector ID that does not conflict with the metadata.

## Testing

Add unit tests for detection without an install URL, rejection of missing or mismatched connector identities and non-auth errors or successful results, and detection for all three supported auth reasons.

GitOrigin-RevId: 6e4e177f26d9a34c56874b0360bae63f6c89107e
2026-09-11 23:36:17 +00:00
Matthew Zeng 8570091e14 Honor thread-level plugin exclusions across runtime capabilities (#44655)
## What changed

- Apply `disabled_plugin_ids` to plugin skills, recommendations, hooks, and MCP servers without modifying shared plugin state.
- Activate selection changes when the next task starts, keeping pending settings from changing the active runtime.
- Hide app tools contributed only by disabled plugins from model tool catalogs and search. Preserve connectors shared with enabled plugins and existing direct Apps RPC behavior.
- Include plugin identity in MCP approval keys and use that identity when persisting plugin tool approvals.

## Testing

Add regression coverage for disabling and re-enabling plugin skills and tools, deferred activation of settings, shared connector ownership, selected plugin servers, executor hooks, and plugin-specific approval keys and persistence.

GitOrigin-RevId: 1153ff6aa7ab6953d50e838da05203904ecd2956
2026-09-10 21:51:34 +00:00
Alex Zamoshchin 94697375cb Add MIME-filtered resource listing for Codex Apps (#44548)
## Why

Codex Apps applies resource MIME filters to each request separately, so continuation requests must include the filter as well as the cursor.

## What changed

Add `McpResourceClient::list_codex_apps_resources` with a required `mime_type` and optional cursor. Send the filter as a top-level `mimeType` parameter in `resources/list` requests and return resources with the next cursor.

Require a host-owned `codex_apps` registration before sending filtered requests, rejecting extension servers that use the same name.

## Testing

Add integration tests covering MIME filters on both pagination requests, returned resource pages, and rejection of extension name collisions without sending a resource request.

GitOrigin-RevId: 4fb33da56c6ef99286564ead7f74b77d8b337335
2026-09-10 14:22:21 +00:00
jif 0df39752cb Notify opted-in stdio MCP servers of auth changes (#43428)
## What changed

Advertise the experimental `codex/auth-change` capability for stdio MCP connections with an auth manager. When the server opts in, send `notifications/codex/authChanged` after initialization and on subsequent auth changes, with credential and owner generation counters and no credentials.

Track owner changes separately from credential refreshes so consumers can detect login, logout, or user, workspace, and auth-mode changes even when notifications coalesce. Treat credential changes with incomplete owner identity as owner changes as well.

Tie the notification watcher to the managed client's lifetime, limit each send to five seconds, and close the connection if a subsequent notification fails.

## Testing

Add tests for credential refreshes versus owner changes, coalesced logout and account switches, capability opt-in, notification payloads, and watcher cleanup.

GitOrigin-RevId: 35a99f5252bd48ca60a71fbdd1f708a8158e812c
2026-09-07 10:37:46 +00:00
Alex Daley 32351a7b1a Keep refreshed MCP tool catalogs with their clients (#43031)
## Why

Refreshed Apps catalogs need to survive connection reuse. Catalog revisions scoped to the connection set can lose refreshed tools during reconciliation and invalidate prepared calls for unrelated servers.

## What changed

- Store tools, revisions, and refresh coordination on each MCP client, and key cached bindings by client identity and revision.
- Preserve existing binding snapshots while rejecting stale calls before preparation. Wait for active calls to finish before publishing a refreshed catalog.
- Add `CodexThread::refresh_codex_apps_tools` to reconcile the runtime and return the refreshed client's raw Apps inventory alongside tool names eligible under that runtime's generic MCP policy. Keep hidden and disabled tools in the inventory for callers to apply app-specific policy.

## Testing

Add regression coverage for refreshed catalogs surviving client reuse, unrelated calls remaining valid, binding cache invalidation, and refresh snapshots retaining the client's own inventory when another client wins the shared-cache race. Update stale-call and preparation tests to use client-owned catalogs.

GitOrigin-RevId: f2308c81f7474eb31f3380c091c977030123cda2
2026-09-05 15:04:46 +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
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
soyeon-oai a98b94625e Add trusted access context for MCP metadata (#40992)
## What changed

- Add `TrustedAccessContext` to fetch account-bound cyber verified-access grants and attach them as host-owned `openai/entitlementContext` metadata.
- Replace caller-supplied entitlement metadata and return an `unknown` status when authentication, identity consistency, response validation, size limits, or the lookup deadline cannot be verified.
- Add `HttpResponseBodyStream::from_chunks` for lightweight in-memory streaming clients.

## Testing

- Cover grant mapping, unsupported authentication, account and workspace changes, malformed or oversized responses, duplicate programs, and lookup timeouts.

GitOrigin-RevId: 343b6a6608c98c45a34939ef507c2183516a11c1
2026-08-26 22:54:10 +00:00
stevenlee-oai 9be8d6e1c3 Harden MCP OAuth callback handling (#40691)
## Why

MCP servers can share an OAuth callback URL. Without a validated issuer or a
server-specific callback path, an authorization response could be associated
with the wrong server.

## What changed

- Use stable callbacks when authorization metadata advertises issuer-bound
  responses, and validate the returned issuer before exchanging the code.
- Retain server-specific callback IDs for providers without issuer support,
  including fallback to the global or default callback for legacy registered
  clients.
- Persist registered callback URLs for MCP servers and plugins, and insert the
  active listener port into portless loopback redirects.

## Testing

Add coverage for issuer validation, callback-mode discovery, registered and
legacy clients, plugin OAuth, CLI persistence, and loopback listener ports.

GitOrigin-RevId: 2878c92e237fc17fd3def0bd2e1cce3e104a3db8
2026-08-25 20:26:23 +00:00
jif 93c54bca38 Resolve HTTP MCP bearer tokens in executor environments (#39926)
## Why

Executor-owned HTTP MCP servers need to read their bearer credentials from the
selected executor environment instead of the host process.

## What changed

- Preserve `bearer_token_env_var` for executor-owned HTTP MCP configurations and
  resolve it when the executor sends each request.
- Extend delegated HTTP headers with executor-local environment references while
  rejecting missing, empty, or protected credential variables.
- Keep transport-provided bearer authentication compatible with MCP redirect and
  OAuth handling without sending a placeholder authorization value.

## Testing

- Cover authenticated executor-owned MCP requests end to end.
- Cover delegated header resolution and rejection of protected variables.
- Cover parsing executor-owned bearer configuration and transport-provided bearer
  behavior.

GitOrigin-RevId: 442bf7382198ffb69eba797eb36d4c74faabda88
2026-08-21 12:50:15 +00:00
sayan-oai fde2156057 Enforce environment MCP policies (#39335)
## What changed

- Add environment-provided MCP restrictions for configured and plugin-provided servers.
- Disable attachment-scoped servers while their environment configuration is pending, failed, or unselected, while preserving selected-plugin access and the controller-owned Apps server.
- Apply the resolved policy to runtime startup, model tool exposure, telemetry, OAuth flows, and skill dependency installation.

## Testing

- Cover policy filtering for configured and plugin servers, environment state transitions, Apps ownership, and managed OAuth rejection.

GitOrigin-RevId: 7ca5d4dda14068e758497f88835d5cba685e159e
2026-08-19 01:26:16 +00:00
victor-openai a1dc95d5af Scope MCP resource reads by connector (#39244)
## What changed

- Add an optional `connectorId` to `mcpServer/resource/read`.
- Forward the selected connector through `x-codex-turn-metadata` for threaded and threadless resource reads, restricting hosted app resources to that connector.
- Update the generated protocol schemas and app-server documentation.

GitOrigin-RevId: 5cc94d703abbbb6086665910c1c9ed5dc7075210
2026-08-18 18:01:39 +00:00
jif 880f1135ea Scope MCP app resource reads to their originating call (#39187)
## Why

App widgets need to read resources using the app and account context of the
tool call that produced them, including after a thread is restored.

## What changed

- Add an optional `originCallId` to `mcpServer/resource/read` requests and
  return it on successful scoped reads.
- Track bounded provenance for successful app tool calls in thread history and
  use the current tool binding, account link, and app policy when reading the
  associated widget resource.
- Reject missing, mismatched, failed, or ambiguous origins, while keeping
  app-only tools available for widget reads without exposing them to the model.

## Testing

Add app-server coverage for scoped widget reads across both history modes,
ephemeral and persistent threads, server restarts, app-only visibility, and
invalid origin cases.

GitOrigin-RevId: 11eaefc066b2a3b639599e4cbdef680233d150a2
2026-08-18 11:51:21 +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
Evan Fannin 41014b11bd Add MCP event discovery and subscriptions (#37494)
## What changed

- Expose hosted Plugin Runtime event definitions through `McpResourceClient::list_events`.
- Add cancellable `events/stream` subscriptions that route lifecycle notifications to the matching request and cancel when the stream is dropped.
- Bound event notification and queue sizes, time out stalled response headers, and close streamable HTTP responses locally on cancellation.

## Testing

- Add streamable HTTP integration coverage for isolated concurrent subscriptions, local cancellation, and stalled response-header timeouts.

GitOrigin-RevId: 98c6fffa8f004eb2638c1b0705f659222cbbdfdb
2026-08-07 19:36:52 +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
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
jacobzhou-oai bd12b3a9ec Add Agent Plugins MCP config parsing (#36796)
## What changed

- Add `parse_agent_plugin_mcp_config` to translate Agent Plugins v1 `mcp.json` files into Codex MCP server configuration.
- Normalize `stdio` and streamable HTTP transports, including `PLUGIN_ROOT` and `PLUGIN_DATA` expansion, contained plugin paths, secure endpoint validation, and filtering of client-owned HTTP headers.
- Keep valid sibling servers when another server is invalid, while returning per-server parse errors.
- Preserve UTF-8 HTTP header values when forwarding streamable HTTP protocol headers.

## Testing

- Cover transport mapping, placeholder expansion, path containment, schema and field validation, per-server errors, platform-specific environment handling, and UTF-8 headers.

GitOrigin-RevId: ed4ab0fcf495afbb381ce48beb93989629444c56
2026-08-03 20:36:59 +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 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
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 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 f6aad1f363 Extract MCP binding clients from the connection manager (#34561)
## What changed

- Add `McpBindingClients` to hold the ready MCP clients captured for a model step.
- Move concurrent, paginated resource and resource-template listing into the new helper.
- Keep server filtering in `McpConnectionManager` while preserving per-client timeouts, duplicate-cursor detection, and warning behavior.

GitOrigin-RevId: 0e3f8f135126b17d73058ca84e98493a27543ca0
2026-07-21 15:04:43 +00:00
jif f24e695470 Centralize thread MCP connections in McpRuntime (#33889)
## What changed

- Add a thread-owned `McpRuntime` that atomically publishes connection-set
  replacements and owns shutdown.
- Route `McpResourceClient` snapshots and cache keys through that runtime so
  extension clients observe refreshed MCP servers.
- Keep model-step configuration snapshots separate from ownership of live MCP
  connections.

## Testing

- Add coverage that captures an extension's session resource client, refreshes
  the MCP server configuration, and verifies that the existing client sees the
  newly published server.

GitOrigin-RevId: 351b2e25594b8eb6b91e50ff8d06b7d49768ae1c
2026-07-17 18:43:14 +00:00
Konstantine Kahadze 2b486b4676 Attribute OpenAI docs MCP requests to Codex (#33424)
## What changed

- Add `source=codex` to requests sent to the OpenAI developer docs MCP endpoint.
- Preserve OAuth discovery URLs and leave clients for other MCP servers unchanged.

## Testing

- Add unit coverage for regular and streaming HTTP requests, OAuth discovery, and non-docs MCP clients.

GitOrigin-RevId: d04e19fe6fc2db0b5cd7bfb429f0cb821c49b28a
2026-07-15 20:54:54 +00:00
jif 42c5d3c80d Reuse MCP tool catalogs across sessions (#33184)
## Why

Starting a new session should not have to wait for an unchanged stdio MCP
server to initialize before its tools can be presented to the model.

## What changed

- Cache recent tool catalogs for matching stdio MCP server configurations and
  use them while a new live connection starts in the background.
- Bound the process-wide cache to 32 entries with a 30-minute TTL, and key
  entries by the server configuration, environment, working directory, and
  elicitation capabilities that affect the catalog.
- Keep connection-specific instructions and tool annotations out of cached
  catalogs. Resolve tool calls against the live connection so tools that are
  unavailable or hidden in the new session cannot be invoked from stale data.
- Publish only the newest completed catalog fetch and do not cache HTTP servers
  or stdio configurations that depend on remotely sourced environment values.

## Testing

- Add coverage for cache expiration, environment changes, catalog sanitization,
  and out-of-order refreshes.
- Add an end-to-end test that starts inference from cached definitions while a
  replacement MCP process initializes, then verifies calls and visibility
  against the live process.

GitOrigin-RevId: 2ed0f29ba53ace12532730f951b175c588aa3ae7
2026-07-14 22:25:39 +00:00
Matthew Zeng 2f7d89b141 Extract connector runtime snapshot management (#32698)
## What changed

- Move the Codex Apps tool cache into a reusable `codex-connectors` runtime manager keyed by account and workspace.
- Represent cached tools as atomically published snapshots with refresh timestamps while preserving the newest accepted fetch generation.
- Harden disk persistence with bounded reads, atomic file replacement, and serialized writes so an older fetch cannot overwrite newer state.

## Testing

Add coverage for identity isolation, snapshot timestamps, oversized cache files, atomic replacement, and concurrent persistence ordering.

GitOrigin-RevId: 5ea2234469daae3abf54b030244c3251de62ca5a
2026-07-13 05:02:52 +00:00
thomas 8347b8de21 [codex-apps] Filter optional file fields by tool schema (#31686)
## Summary

Codex Apps file parameters are exposed to the model as local paths,
uploaded at execution time, and rewritten into provided-file payloads
before the MCP tool call.

The rewrite currently includes the documented optional fields
`mime_type` and `file_name` for every file parameter. Apps with strict
schemas can reject those fields when they are not declared.

## Changes

- Derive the supported optional file fields from each
`openai/fileParams` parameter's raw input schema before replacing it
with the model-visible local-path schema.
- Always include `download_url` and `file_id`.
- Include `mime_type` and `file_name` only when that specific file
parameter's schema accepts them, including schemas that allow additional
properties.
- Handle scalar and array file parameters, including items-only arrays,
composed schemas, and local JSON Schema references.
- Preserve the existing restriction that only the host-owned Codex Apps
MCP server can use this upload path.

This supports tools with different file contracts in the same app: one
parameter can accept the optional fields while another remains strict.

## Validation

- `just test -p codex-mcp`
- `just test -p codex-core mcp_openai_file`
- `just test -p codex-core codex_apps_file_params_`
- `just fix -p codex-mcp`
- `just fix -p codex-core`
- `just fmt`
- `git diff --check`
- Manually verified in the Codex Electron app that:
  - a strict file schema receives only `download_url` and `file_id`
  - a rich file schema also receives `mime_type` and `file_name`

Related: #31330
2026-07-09 14:32:23 -07:00
Channing Conger 84fe70c30e elicitations: Move to shared ElicitationService (#30627)
## Why

Code-mode tool results could return to the model while an MCP
elicitation was still waiting for user input. This differed from
parallel tool calling and could let the model continue before the user
resolved the request.

We need one session-level view of outstanding elicitations so tool
runtimes can consistently hold results until every pending elicitation
is resolved.

  ## What changed

- Added a counted, session-owned ElicitationService with RAII
registrations.
- Registered both core-originated and server-originated MCP elicitations
with the service.
- Migrated out-of-band elicitation tracking and unified exec timeout
pausing to the shared service.
- Made code-mode functions.exec and functions.wait capture their runtime
result normally, then hold it before returning while an elicitation is
outstanding.
  - Kept terminate: true immediate; only its result is held.
  - Preserved model-visible wall time across the elicitation hold.
- Kept the behavior session-scoped, with concurrent elicitations holding
the pause until all registrations are released.
2026-07-06 11:20:32 -07:00