Commit Graph

21 Commits

Author SHA1 Message Date
aphonpra-oai
a186f5484d Resolve local JSON Schema refs in Code Mode types (#38664)
## Why

Code Mode rendered document-local `$ref` values as `unknown`, hiding referenced
input and structured-output shapes from generated TypeScript declarations.

## What changed

- Resolve fragment-only JSON Pointer references against the root schema,
  including escaped and percent-encoded pointer segments.
- Preserve `$ref` siblings as intersections and parenthesize unions used in
  `allOf` intersections.
- Bound recursive and repeated expansion, intermediate rendering work, and
  final output size, falling back to `unknown` when a limit is reached or a
  reference cannot be resolved safely.

## Testing

Add unit coverage for recursive, escaped, nested-resource, dangling, and
oversized references, plus integration coverage for generated Code Mode tool
descriptions and MCP structured output types.

GitOrigin-RevId: 95c6aa32e25325b5be9359dfac3b3328e5e7a499
2026-08-14 22:40:19 +00:00
Adam Perry @ OpenAI
478215c5c1 Preserve large gRPC code-mode tool errors (#38621)
## Why

Code-mode tool failure messages larger than 64 KiB were truncated before they
reached the host.

## What changed

- Remove the tool error size limit from the gRPC protocol and host validation.
- Forward failed tool completion messages without truncation.

## Testing

- Verify that a multibyte error larger than 64 KiB is preserved exactly.

GitOrigin-RevId: 264ae4ba4adea5c19b669e4f41ccfd41a0c30fb5
2026-08-14 18:30:45 +00:00
Adam Perry @ OpenAI
27a98dde4d Use protobuf's built-in Bazel proto rule (#38280)
## What changed

- Load `proto_library` for the code-mode protocol directly from the
  `com_google_protobuf` repository.
- Remove the now-unneeded direct `rules_proto` module dependency.

GitOrigin-RevId: 5a01191b2c46c7fafd263ed93f153a878b09aaa8
2026-08-13 00:26:06 +00:00
Channing Conger
ba2fb48319 Forward gRPC code-mode callbacks to session delegates (#38072)
## What changed

- Subscribe each gRPC code-mode session to nested tool calls and forward tool and notification callbacks to its delegate.
- Complete tool calls through the host while bounding oversized results and errors.
- Track callback ownership and cancellation so completed cells drain notifications, terminated cells cancel them, and shutdown revokes outstanding work.
- Validate callback identifiers, cell ownership, enabled tools, and pending callback limits without serializing independent callbacks or sessions.

## Testing

- Add integration and state tests for callback forwarding, completion ordering, cancellation, malformed callbacks, delegate panics, oversized results, and concurrent work.

GitOrigin-RevId: 005afbb90eea0eb77d746b930a1a96ca6dfcd4e7
2026-08-11 20:40:26 +00:00
Channing Conger
1e557a554e Add gRPC-backed code-mode sessions (#38041)
## What changed

- Add `GrpcCodeModeSessionProvider` for opening code-mode sessions over HTTP/2 or an existing `tonic` channel.
- Support execution, waiting, termination, per-session limits, cell-closure callbacks, and graceful shutdown over the gRPC protocol.
- Bound transport waits and error messages, validate host identifiers and responses, and clean up abandoned executions and observers.

## Testing

- Add end-to-end TCP tests covering session persistence, cancellation, concurrent waits, shutdown, cell cleanup, and independent yield limits.
- Add unit coverage for protocol conversion, deadlines, and session lifecycle state.

GitOrigin-RevId: d4729ce608ad4b42a99744b07e1f230e46cb24ec
2026-08-11 17:31:11 +00:00
Channing Conger
8073dbb20b Define the code-mode host gRPC protocol (#37510)
## What changed

- Add the `codex.code_mode.v1` protobuf API for managing code-mode sessions, executions, waits, tool callbacks, notifications, and content results.
- Generate and export the Rust client/server bindings with `tonic` under Cargo.
- Add Bazel protobuf targets and a `prost` toolchain that uses the workspace's Rust runtime versions.

GitOrigin-RevId: 51d9d044e01dab2f4d25ab79aa7a52585485eee3
2026-08-07 23:27:39 +00:00
Curtis 'Fjord' Hawthorne
0a0ebb8535 Add a unified image budget (#37206)
## What changed

- Add the gated `unified_image_budget` feature for models that support original image detail or Responses Lite.
- Apply one 6,000-pixel, 10,000-patch preprocessing limit regardless of legacy image detail hints.
- Hide detail controls from `view_image` and code mode while continuing to accept existing hints for compatibility.
- Preserve detail-based resizing and tool contracts for unsupported models.

## Testing

- Cover unified resizing limits, Responses Lite, legacy detail hints, unsupported models, and `view_image` integration in code mode.

GitOrigin-RevId: cb07bff1669a96599fdfd076b3d9ec80f2b6fff7
2026-08-06 03:15:08 +00:00
Sean Huang
9d00bb01c0 Add per-session code-mode execution limits (#37114)
## What changed

- Add `create_session_with_limits` and session-scoped cell execution limits.
- Clamp execute and wait yield times to the session's `max_yield_time_ms`
  without terminating the running cell.
- Negotiate support with remote code-mode hosts and include non-default limits
  in `session/open`, while keeping unlimited sessions compatible with hosts and
  providers that do not support limits.

## Testing

- Cover yield-time clamping, zero-timeout behavior, and isolation between
  sessions.
- Cover wire serialization, capability negotiation, unsupported hosts, and
  shared process-host execution.

GitOrigin-RevId: 9517321cd605bb87f93eeaa6ba331cc2e346e582
2026-08-05 16:09:01 +00:00
Channing Conger
60c722e075 Add a dual-WebSocket transport for code mode (#36812)
## Why

Large nested-tool callbacks can occupy a WebSocket and delay unrelated session
operations on the same code-mode connection.

## What changed

- Negotiate the optional `dual-websocket-v1` capability and pair a second,
  token-scoped WebSocket with the control connection.
- Route nested-tool callbacks and their results over the bulk socket while
  keeping session operations, notifications, and execution responses on the
  control socket. Reject messages sent on the wrong lane.
- Preserve the single-connection transport when the capability is unavailable,
  and bound pairing, queued callbacks, and deferred cross-socket messages.
- Defer callbacks that arrive before their execution-started response, and
  return delegate errors without disconnecting the connection.

## Testing

Add protocol, transport, driver, and WebSocket integration coverage for
capability negotiation, lane routing, pairing failures, out-of-order messages,
and progress during large concurrent tool results.

GitOrigin-RevId: fa4504653e7cbf3c4ec930ae57aa0a41345bad66
2026-08-03 23:48:28 +00:00
Channing Conger
97576b1794 Run code mode exclusively through the standalone host (#36217)
## What changed

- Move the V8 implementation into a dedicated `codex-code-mode-runtime` crate used by `codex-code-mode-host`, removing the embedded runtime fallback from the Codex process.
- Resolve the host executable from the active installation layout and check its availability before selecting tools.
- Fall back to direct tools with a one-time warning when optional code mode is unavailable. Keep `code_mode_only` and `disable_in_process_fallback` configurations fail-closed.

## Testing

- Cover host discovery for standalone and package layouts, including missing hosts and symlinks.
- Verify direct-tool fallback, one-time warnings, and fail-closed code-mode-only behavior.

GitOrigin-RevId: 5aa3c6f1db148b2231fc24089a2ee0e2b00dbddb
2026-07-30 20:24:29 +00:00
Channing Conger
f61b51ddd9 Support remote code-mode hosts in app-server (#35098)
## What changed

- Add `--code-mode-host ws://...` and `wss://...` support to `codex app-server`, gated by the `code_mode_host` feature. When omitted, app-server continues to start a local host.
- Share one remote WebSocket connection across the process's threads, using the configured HTTP client's proxy and TLS policy and preserving the existing framed host protocol.
- Reject invalid host URLs, bound WebSocket frame sizes, close connections cleanly, and return an error when a connection exceeds 1,024 pending delegate calls without disconnecting it.

## Testing

- Cover CLI validation, WebSocket protocol execution and shutdown, connection sharing across app-server threads, and delegate-call capacity recovery.

GitOrigin-RevId: 715e82d4d9db1e7e2f91b754a777dcab504e2ae4
2026-07-24 04:37:01 +00:00
Channing Conger
0dfa778dae Add WebSocket transport to the code-mode host (#35078)
## What changed

- Add a `--listen` option that accepts `stdio`, `stdio://`, or a
  `ws://IP:PORT` endpoint, while retaining stdio as the default.
- Serve the existing length-prefixed protocol in binary WebSocket messages,
  with isolated connections, shared host limits, and a `/readyz` endpoint.
- Reject browser-origin handshakes and contain malformed frames to the affected
  connection.

## Testing

- Cover listen URL parsing and complete-frame encoding and decoding.
- Exercise readiness, cell execution, tool callbacks, large frames, concurrent
  connections, malformed frames, and origin rejection through the WebSocket
  listener.

GitOrigin-RevId: 01c8be4c6256b8ce4a3a0002440dcb3294e5f887
2026-07-24 02:40:11 +00:00
pakrym-oai
99efeef650 Add buffered code-mode exec yields (#34441)
## What changed

- Add the experimental `code_mode_buffered_exec` feature.
- When enabled, default code-mode `exec` calls without an explicit
  `yield_time_ms` to 30 seconds instead of 10 seconds.
- Report the effective default in the model-visible `exec` tool description.

## Testing

- Verify that the generated tool description advertises the 30-second default
  when the feature is enabled.

GitOrigin-RevId: 0eea4d0105137f09050ce31aad18c25c79df6b2a
2026-07-21 02:07:13 +00:00
nhamidi-oai
643de86a19 Add audio output support to dynamic tools and code mode (#34080)
## What changed

- Add `inputAudio` content items to dynamic tool responses, app-server events, thread history, and generated protocol schemas.
- Add an `audio()` code-mode helper that accepts inline data URLs, audio URL objects, and MCP audio blocks.
- Convert MCP audio blocks into model input when audio is supported, and replace unsupported audio with an explanatory text item.
- Reject non-data audio URLs and track audio item counts in dynamic tool analytics.

## Testing

- Cover audio serialization, protocol round trips, thread-history conversion, MCP modality filtering, code-mode helper inputs, and invalid URL handling.

GitOrigin-RevId: 1ed52a8f9c62d4840fb71c5ec736b4a3566243d6
2026-07-18 23:22:13 +00:00
sayan-oai
a6b99ee5c4 code-mode: retain shared MCP types for deferred tools (#31745)
## Why

When MCP tools are deferred behind `tool_search`, Code mode keeps them
callable but omits their individual declarations from the initial `exec`
description. The shared MCP `CallToolResult` types were derived only
from directly rendered tools, so deferring every MCP tool also removed
the common response contract that models need to interpret MCP results.

This restores that contract without undoing the context savings from
deferred tool definitions. This is a follow-up to #29486.

## What changed

- Track deferred Code-mode tool definitions separately from directly
rendered definitions.
- Render the shared MCP type preamble when either direct or deferred MCP
tools are available.
- Keep deferred tool declarations out of the initial prompt.
- Add unit and integration coverage for deferred MCP tools.

## Testing

- `just test -p codex-code-mode-protocol`
- `just test -p codex-core
code_mode_only_guides_all_tools_search_and_calls_deferred_app_tools`
2026-07-09 08:17:13 -07:00
Channing Conger
3b78f58fb2 [codex] extend code-mode host IPC transport (#30108)
## Summary

- add an `EncodedFrame` type so IPC payloads are serialized and
size-checked before entering bounded queues
- add the V1 `operation/cancel` client-to-host message
- pin the new wire shape with protocol tests

## Why

The process-owned code-mode host needs bounded, pre-encoded outbound
messages and a best-effort cancellation signal. Keeping these wire
primitives in a protocol-only change lets their compatibility contract
be reviewed independently from either endpoint.

## Stack

This is **1 of 4** in the process-owned code-mode session stack. The
next PR targets this branch.

## Validation

- `just test -p codex-code-mode-protocol` — 22 passed
- `just fix -p codex-code-mode-protocol`
- `just fmt`
2026-06-25 13:26:47 -07:00
Channing Conger
b3e1c33776 code-mode: define process host wire protocol (#29804)
## Why

The process-owned code mode implementation needs an explicit, bounded
wire contract before either side depends on it. Keeping framing and
message semantics in `codex-code-mode-protocol` gives the client and
sidecar one shared source of truth and makes compatibility failures
detectable during connection setup.

## What changed

- adds a versioned client/host handshake with required and optional
capabilities
- defines operation requests and responses for session lifecycle and
cell control
- defines reverse delegate request, response, cancellation, and
cell-closure messages
- adds a four-byte little-endian length-prefixed JSON codec with a hard
frame cap
- rejects malformed frames, unknown fields, invalid identifiers, and
unsupported protocol states
- locks the wire representation down with explicit JSON round-trip tests

## Testing

- `just test -p codex-code-mode-protocol`

## Stack

Part 1 of 6. Followed by
[#29805](https://github.com/openai/codex/pull/29805).
2026-06-24 20:03:22 -07:00
Channing Conger
db6e676afc code-mode: Remove Session::is_alive() (#29732)
Remove this unused API. This API is insidious in that it implies that
alive state should be determinable from the caller, and implies that a
preflight should indicate routing. Lets drop this, and handle errors
correctly from a failed session in the future.
2026-06-23 15:14:13 -07:00
Channing Conger
be0dfcfbea [codex] define code mode host handshake protocol (#29515)
## Summary

- add validated protocol-version, capability, and session identifier
types
- define explicit `ClientToHost` and `HostToClient` JSON envelopes for
connection negotiation and session open/close acknowledgements
- reject invalid states and unknown fields during decoding, with
explicit wire-format and round-trip coverage

## Why

This establishes the transport-neutral encoding shape needed to build
and test the new code-mode host incrementally. Cell, tool callback, and
failure-domain messages are intentionally deferred until their actors
and behavior tests establish the required semantics.

This is additive protocol scaffolding and does not change the current
production code-mode implementation.

## Validation
2026-06-23 14:57:44 -07:00
rka-oai
c09df9e353 [code-mode] Reject remote image URLs from output helpers (#27732)
## Summary

- reject HTTP(S) image URLs from the shared code-mode output-image
normalization path
- return a concise model-visible tool error so the model can recover on
its next turn
- apply the targeted rejection to both `image()` and `generatedImage()`
- leave other non-empty image URL values to existing downstream handling

The returned error is:

> Tool call failed: remote image URLs are not supported in tool outputs.
Pass a base64 data URI instead

## Why

Responses Lite cannot lower a remote image URL emitted from a structured
tool output. Rejecting HTTP(S) values in the Codex harness preserves the
tool-call metadata and gives the model a recoverable next turn instead
of invalidating the sample.

## Test coverage

The regression is covered primarily by a `test_codex()` agent
integration test that simulates the Responses API exchange and asserts
the failed model-visible exec output. A supplemental runtime test covers
both `http://` and `https://` inputs across both image output helpers.

## Test plan

- `cd codex-rs && just test -p codex-code-mode`
- `cd codex-rs && just test -p codex-code-mode-protocol`
- `cd codex-rs && just test -p codex-core
code_mode_image_helper_rejects_remote_url`
- `cd codex-rs && just fmt`
- `git diff --check origin/main...HEAD`

Related context: https://github.com/openai/openai/pull/1022346
2026-06-12 02:49:17 -07:00
Channing Conger
aa46f2debf code-mode standalone: extract protocol and add host crate (#27724)
This is phase 1 of a 4 phase stack:
1. **Add protocol and host crates for new IPC code mode implementation**
2. Create the new standalone binary
3. Create a new IPC `CodeModeSessionProvider` to use new binary
4. Remove v8 from core and only use IPC provider


## Add protocol and host crates for new IPC code mode implementation
Establish a clean process boundary without changing the existing
in-process behavior.

- Add the codex-code-mode-protocol crate for shared session, runtime,
response, and tool-definition types.
- Move protocol-facing code out of the V8-backed implementation.
- Add a buildable codex-code-mode-host crate as the foundation for the
standalone process.
- Keep the existing in-process runtime as the active implementation.
2026-06-11 22:37:26 -07:00