Commit Graph
18 Commits
Author SHA1 Message Date
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
jackz d04b0561d3 Preserve account network policy for ChatGPT backend requests (#47703)
## Why

ChatGPT backend requests could bypass the configured network policy by using a default HTTP client. Requests using captured credentials must also retain the corresponding account policy so revocation continues to block them.

## What changed

- Use the configured HTTP client factory for ChatGPT GET and POST requests, enforcing managed network policy while retaining cookies.
- Capture authentication and network policy together for app reads and plugin reads and installs, preserving that policy across the post-install configuration reload.
- Bind GET requests to the current account policy before loading credentials.

## Testing

Add regression tests for revoked account policies, blocked connector destinations, and network policy enforcement after configuration reload with a cached app client.

GitOrigin-RevId: 5298842eec9664af49df70e89624653d1452fb33
2026-09-24 00:50:02 +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
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
Alex Daley 2cfee7de25 Refresh live thread tools through app/installed (#43039)
## Why

Calling `app/installed` with `threadId` and `forceRefresh: true` refreshed a separate runtime snapshot without updating the thread's tools for subsequent turns.

## What changed

Use the thread's current configuration and refresh its live app tools when a thread is specified. Account for the refreshed snapshot's model-visible tools when reporting `callable`. Requests without `threadId` continue to use a separate runtime for refreshes.

## Testing

Add integration coverage verifying that refreshed tools replace previous tools in subsequent model requests and can be called, and that a failed refresh preserves the last working tools. Extend thread configuration coverage to include forced refreshes.

GitOrigin-RevId: fc13e28a59da00af470cf25c0cde356504e1575b
2026-09-05 15:30:18 +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
Alex Zamoshchin 3666a46ea3 Remove the workspace settings gate for apps and plugins (#38994)
## What changed

- Stop fetching the ChatGPT workspace `enable_plugins` setting.
- Let the effective Codex feature configuration control app and plugin APIs,
  plugin-provided skills and hooks, and experimental feature reporting.

GitOrigin-RevId: 46aebf0f07cd47e093e48663e41207cdf9a38c9f
2026-08-17 12:26:59 +00:00
Matthew Zeng 7f928f6ddc Use thread configuration for app/read (#37891)
## What changed

- Add an optional `threadId` parameter to `app/read`.
- When provided, load the thread's effective configuration before applying app feature gating, workspace policy, and plugin attribution.
- Share the thread-aware configuration loader with `app/list`.

## Testing

- Add coverage showing that `app/read` honors a thread-level connector feature override.

GitOrigin-RevId: 161e910a2d7435ecf4acd0ba9f5f5069d1631f12
2026-08-10 22:39:29 +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
stevenlee-oai 4123bf6189 Track app/read request duration (#35048)
## What changed

- Record `codex.apps.read.duration_ms` when `app/read` returns a response.
- Tag the duration by the request's `include_tools` value.
- Move the `app/read` handler into its own request-processor module.

GitOrigin-RevId: e1563cd41c72ad03e7f5d5d33cd8a3b35e27984b
2026-07-23 23:55:05 +00:00
Matthew Zeng ceb2ffb793 Align installed app duration metrics with the legacy baseline (#35015)
## Why

The snapshot-backed `apps/installed` duration metric needs dimensions that can
be compared with the legacy `app/list` baseline.

## What changed

- Label snapshot-backed duration samples with `path=installed` and add the
  legacy-compatible `reload` dimension alongside the detailed refresh fields.
- Record duration samples only for successful responses so failed requests do
  not enter the success latency distribution.

## Testing

Added unit coverage for the duration metric dimensions on refreshed and
non-refreshed requests, and for omitting samples on failed requests.

GitOrigin-RevId: 0755dcaaa94f1d973adfc62a27ea97e3e01edc8b
2026-07-23 21:31:30 +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 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
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
Matthew Zeng a238b753af Add an API for reading installed app runtime state (#33843)
## What changed

- Add `app/installed` to return each connector observed in the committed runtime tool snapshot, including its runtime name and effective `enabled` and `callable` state.
- Support evaluating thread-specific configuration with `threadId` and refreshing the hosted connector tool snapshot with `forceRefresh`.
- Preserve observed connector identities as disabled when global or workspace policy disables Apps, and retain the previous snapshot when a refresh fails.

## Testing

- Cover cached and forced reads, policy and configuration filtering, thread-specific configuration, snapshot refresh failures, and protocol serialization.

GitOrigin-RevId: f697b6fb501b7d329a169e947a1c1607806222fe
2026-07-17 15:23:35 +00:00