Merged
Conversation
- Let typed user messages submit while realtime is active and mirror accepted text into the realtime text stream. - Add integration coverage and snapshot for outbound realtime text.
## Problem The TUI had shell-style Up/Down history recall, but `Ctrl+R` did not provide the reverse incremental search workflow users expect from shells. Users needed a way to search older prompts without immediately replacing the current draft, and the interaction needed to handle async persistent history, repeated navigation keys, duplicate prompt text, footer hints, and preview highlighting without making the main composer file even harder to review. https://github.com/user-attachments/assets/5165affd-4c9a-46e9-adbd-89088f5f7b6b <img width="1227" height="722" alt="image" src="https://github.com/user-attachments/assets/8bc83289-eeca-47c7-b0c3-8975101901af" /> ## Mental model `Ctrl+R` opens a temporary search session owned by the composer. The footer line becomes the search input, the composer body previews the current match only after the query has text, and `Enter` accepts that preview as an editable draft while `Esc` restores the draft that existed before search started. The history layer provides a combined offset space over persistent and local history, but search navigation exposes unique prompt text rather than every physical history row. ## Non-goals This change does not rewrite stored history, change normal Up/Down browsing semantics, add fuzzy matching, or add persistent metadata for attachments in cross-session history. Search deduplication is deliberately scoped to the active Ctrl+R search session and uses exact prompt text, so case, whitespace, punctuation, and attachment-only differences are not normalized. ## Tradeoffs The implementation keeps search state in the existing composer and history state machines instead of adding a new cross-module controller. That keeps ownership local and testable, but it means the composer still coordinates visible search status, draft restoration, footer rendering, cursor placement, and match highlighting while `ChatComposerHistory` owns traversal, async fetch continuation, boundary clamping, and unique-result caching. Unique-result caching stores cloned `HistoryEntry` values so known matches can be revisited without cache lookups; this is simple and robust for interactive search sizes, but it is not a global history index. ## Architecture `ChatComposer` detects `Ctrl+R`, snapshots the current draft, switches the footer to `FooterMode::HistorySearch`, and routes search-mode keys before normal editing. Query edits call `ChatComposerHistory::search` with `restart = true`, which starts from the newest combined-history offset. Repeated `Ctrl+R` or Up searches older; Down searches newer through already discovered unique matches or continues the scan. Persistent history entries still arrive asynchronously through `on_entry_response`, where a pending search either accepts the response, skips a duplicate, or requests the next offset. The composer-facing pieces now live in `codex-rs/tui/src/bottom_pane/chat_composer/history_search.rs`, leaving `chat_composer.rs` responsible for routing and rendering integration instead of owning every search helper inline. `codex-rs/tui/src/bottom_pane/chat_composer_history.rs` remains the owner of stored history, combined offsets, async fetch state, boundary semantics, and duplicate suppression. Match highlighting is computed from the current composer text while search is active and disappears when the match is accepted. ## Observability There are no new logs or telemetry. The practical debug path is state inspection: `ChatComposer.history_search` tells whether the footer query is idle, searching, matched, or unmatched; `ChatComposerHistory.search` tracks selected raw offsets, pending persistent fetches, exhausted directions, and unique match cache state. If a user reports skipped or repeated results, first inspect the exact stored prompt text, the selected offset, whether an async persistent response is still pending, and whether a query edit restarted the search session. ## Tests The change is covered by focused `codex-tui` unit tests for opening search without previewing the latest entry, accepting and canceling search, no-match restoration, boundary clamping, footer hints, case-insensitive highlighting, local duplicate skipping, and persistent duplicate skipping through async responses. Snapshot coverage captures the footer-mode visual changes. Local verification used `just fmt`, `cargo test -p codex-tui history_search`, `cargo test -p codex-tui`, and `just fix -p codex-tui`.
Addresses openai#17313 Problem: The visual context meter in the status line was confusing and continued to draw negative feedback, and context reporting should remain an explicit opt-in rather than part of the default footer. Solution: Remove the visual meter, restore opt-in context remaining/used percentage items that explicitly say "Context", keep existing context-usage configs working as a hidden alias, and update the setup text and snapshots.
Addresses openai#17498 Problem: The TUI derived /status instruction source paths from the local client environment, which could show stale <none> output or incorrect paths when connected to a remote app server. Solution: Add an app-server v2 instructionSources snapshot to thread start/resume/fork responses, default it to an empty list when older servers omit it, and render TUI /status from that server-provided session data. Additional context: The app-server field is intentionally named instructionSources rather than AGENTS.md-specific terminology because the loaded instruction sources can include global instructions, project AGENTS.md files, AGENTS.override.md, user-defined instruction files, and future dynamic sources.
## Summary Stop counting elicitation time towards mcp tool call time. There are some tradeoffs here, but in general I don't think time spent waiting for elicitations should count towards tool call time, or at least not directly towards timeouts. Elicitations are not exactly like exec_command escalation requests, but I would argue it's ~roughly equivalent. ## Testing - [x] Added unit tests - [x] Tested locally
Include MCP wall time in the output so the model is aware of how long it's calls are taking.
## Summary - run exec-server filesystem RPCs requiring sandboxing through a `codex-fs` arg0 helper over stdin/stdout - keep direct local filesystem execution for `DangerFullAccess` and external sandbox policies - remove the standalone exec-server binary path in favor of top-level arg0 dispatch/runtime paths - add sandbox escape regression coverage for local and remote filesystem paths ## Validation - `just fmt` - `git diff --check` - remote devbox: `cd codex-rs && bazel test --bes_backend= --bes_results_url= //codex-rs/exec-server:all` (6/6 passed) --------- Co-authored-by: Codex <noreply@openai.com>
Problem: After openai#17294 switched exec-server tests to launch the top-level `codex exec-server` command, parallel remote exec-process cases can flake while waiting for the child server's listen URL or transport shutdown. Solution: Serialize remote exec-server-backed process tests and harden the harness so spawned servers are killed on drop and shutdown waits for the child process to exit.
To prevent the spammy: <img width="424" height="172" alt="Screenshot 2026-04-09 at 13 36 16" src="https://github.com/user-attachments/assets/b5ece9e3-c561-422f-87ec-041e7bd6813d" />
## Summary - add an exec-server `envPolicy` field; when present, the server starts from its own process env and applies the shell environment policy there - keep `env` as the exact environment for local/embedded starts, but make it an overlay for remote unified-exec starts - move the shell-environment-policy builder into `codex-config` so Core and exec-server share the inherit/filter/set/include behavior - overlay only runtime/sandbox/network deltas from Core onto the exec-server-derived env ## Why Remote unified exec was materializing the shell env inside Core and forwarding the whole map to exec-server, so remote processes could inherit the orchestrator machine's `HOME`, `PATH`, etc. This keeps the base env on the executor while preserving Core-owned runtime additions like `CODEX_THREAD_ID`, unified-exec defaults, network proxy env, and sandbox marker env. ## Validation - `just fmt` - `git diff --check` - `cargo test -p codex-exec-server --lib` - `cargo test -p codex-core --lib unified_exec::process_manager::tests` - `cargo test -p codex-core --lib exec_env::tests` - `cargo test -p codex-core --lib exec_env_tests` (compile-only; filter matched 0 tests) - `cargo test -p codex-config --lib shell_environment` (compile-only; filter matched 0 tests) - `just bazel-lock-update` ## Known local validation issue - `just bazel-lock-check` is not runnable in this checkout: it invokes `./scripts/check-module-bazel-lock.sh`, which is missing. --------- Co-authored-by: Codex <noreply@openai.com> Co-authored-by: pakrym-oai <pakrym@openai.com>
## Summary When a `spawn_agent` call does a full-history fork, keep the parent's effective agent type and model configuration instead of applying child role/model overrides. This is the minimal config-inheritance slice of openai#16055. Prompt-cache key inheritance and MCP tool-surface stability are split into follow-up PRs. ## Design - Reject `agent_type`, `model`, and `reasoning_effort` for v1 `fork_context` spawns. - Reject `agent_type`, `model`, and `reasoning_effort` for v2 `fork_turns = "all"` spawns. - Keep v2 partial-history forks (`fork_turns = "N"`) configurable; requested model/reasoning overrides and role config still apply there. - Keep non-forked spawn behavior unchanged. ## Tests - `cargo +1.93.1 test -p codex-core spawn_agent_fork_context --lib` - `cargo +1.93.1 test -p codex-core multi_agent_v2_spawn_fork_turns --lib` - `cargo +1.93.1 test -p codex-core multi_agent_v2_spawn_partial_fork_turns_allows_agent_type_override --lib`
Addresses openai#16255 Problem: Incomplete Responses streams could leave completed custom tool outputs out of cleanup and retry prompts, making persisted history inconsistent and retries stale. Solution: Route stream and output-item errors through shared cleanup, and rebuild retry prompts from fresh session history after the first attempt.
Addresses openai#17252 Problem: Plan-mode clarification questionnaires used the generic user-input notification type, so configs listening for plan-mode-prompt did not fire when request_user_input waited for an answer. Solution: Map request_user_input prompts to the plan-mode-prompt notification and remove the obsolete user-input TUI notification variant.
Addresses openai#17453 Problem: /status rate-limit reset timestamps can be truncated in narrow layouts, leaving users with partial times or dates. Solution: Let narrow rate-limit rows drop the fixed progress bar to preserve the percent summary, and wrap reset timestamps onto continuation lines instead of truncating them.
Addresses openai#17514 Problem: PR openai#16966 made the TUI render the deprecated context-compaction notification, while v2 could also receive legacy unified-exec interaction items alongside terminal-interaction notifications, causing duplicate "Context compacted" and "Waited for background terminal" messages. Solution: Suppress deprecated context-compaction notifications and legacy unified-exec interaction command items from the app-server v2 projection, and render canonical context-compaction items through the existing TUI info-event path.
Problem: PR openai#17601 updated context-compaction replay to call a new ChatWidget handler, but the handler was never implemented, breaking codex-tui compilation on main. Solution: Render context-compaction replay through the existing info-message path, preserving the intended `Context compacted` UI marker without adding a one-off handler.
Addresses openai#17593 Problem: A regression introduced in openai#16492 made thread/start fail when Codex could not persist trusted project state, which crashes startup for users with read-only config.toml. Solution: Treat trusted project persistence as best effort and keep the current thread's config trusted in memory when writing config.toml fails.
Helps with FS migration later
…7365) ## Summary This updates the Windows elevated sandbox setup/refresh path to include the legacy `compute_allow_paths(...).deny` protected children in the same deny-write payload pipe added for split filesystem carveouts. Concretely, elevated setup and elevated refresh now both build deny-write payload paths from: - explicit split-policy deny-write paths, preserving missing paths so setup can materialize them before applying ACLs - legacy `compute_allow_paths(...).deny`, which includes existing `.git`, `.codex`, and `.agents` children under writable roots This lets the elevated backend protect `.git` consistently with the unelevated/restricted-token path, and removes the old janky hard-coded `.codex` / `.agents` elevated setup helpers in favor of the shared payload path. ## Root Cause The landed split-carveout PR threaded a `deny_write_paths` pipe through elevated setup/refresh, but the legacy workspace-write deny set from `compute_allow_paths(...).deny` was not included in that payload. As a result, elevated workspace-write did not apply the intended deny-write ACLs for existing protected children like `<cwd>/.git`. ## Notes The legacy protected children still only enter the deny set if they already exist, because `compute_allow_paths` filters `.git`, `.codex`, and `.agents` with `exists()`. Missing explicit split-policy deny paths are preserved separately because setup intentionally materializes those before applying ACLs. ## Validation - `cargo fmt --check -p codex-windows-sandbox` - `cargo test -p codex-windows-sandbox` - `cargo build -p codex-cli -p codex-windows-sandbox --bins` - Elevated `codex exec` smoke with `windows.sandbox='elevated'`: fresh git repo, attempted append to `.git/config`, observed `Access is denied`, marker not written, Deny ACE present on `.git` - Unelevated `codex exec` smoke with `windows.sandbox='unelevated'`: fresh git repo, attempted append to `.git/config`, observed `Access is denied`, marker not written, Deny ACE present on `.git`
openai#17638) - stop `list_tool_suggest_discoverable_plugins()` from reloading the curated marketplace for each discoverable plugin - reuse a direct plugin-detail loader against the already-resolved marketplace entry The trigger was to stop those logs spamming: ``` d=019d81cf-6f69-7230-98aa-74294ff2dc5a}:submission_dispatch{otel.name="op.dispatch.user_input" submission.id="019d86c8-0a8e-7013-b442-109aabbf75c9" codex.op="user_input"}:turn{otel.name="session_task.turn" thread.id=019d81cf-6f69-7230-98aa-74294ff2dc5a turn.id=019d86c8-0a8e-7013-b442-109aabbf75c9 model=gpt-5.4}: ignoring interface.defaultPrompt: prompt must be at most 128 characters path=/Users/jif/.codex/.tmp/plugins/plugins/life-science-research/.codex-plugin/plugin.json 2026-04-13T12:27:30.402Z WARN [019d81cf-6f69-7230-98aa-74294ff2dc5a] codex_core::plugins::manifest - session_loop{thread_id=019d81cf-6f69-7230-98aa-74294ff2dc5a}:submission_dispatch{otel.name="op.dispatch.user_input" submission.id="019d86c8-0a8e-7013-b442-109aabbf75c9" codex.op="user_input"}:turn{otel.name="session_task.turn" thread.id=019d81cf-6f69-7230-98aa-74294ff2dc5a turn.id=019d86c8-0a8e-7013-b442-109aabbf75c9 model=gpt-5.4}: ignoring interface.defaultPrompt: prompt must be at most 128 characters path=/Users/jif/.codex/.tmp/plugins/plugins/build-ios-apps/.codex-plugin/plugin.json 2026-04-13T12:27:30.402Z WARN [019d81cf-6f69-7230-98aa-74294ff2dc5a] codex_core::plugins::manifest - session_loop{thread_id=019d81cf-6f69-7230-98aa-74294ff2dc5a}:submission_dispatch{otel.name="op.dispatch.user_input" submission.id="019d86c8-0a8e-7013-b442-109aabbf75c9" codex.op="user_input"}:turn{otel.name="session_task.turn" thread.id=019d81cf-6f69-7230-98aa-74294ff2dc5a turn.id=019d86c8-0a8e-7013-b442-109aabbf75c9 model=gpt-5.4}: ignoring interface.defaultPrompt: prompt must be at most 128 characters path=/Users/jif/.codex/.tmp/plugins/plugins/life-science-research/.codex-plugin/plugin.json 2026-04-13T12:27:30.405Z WARN [019d81cf-6f69-7230-98aa-74294ff2dc5a] codex_core::plugins::manifest - session_loop{thread_id=019d81cf-6f69-7230-98aa-74294ff2dc5a}:submission_dispatch{otel.name="op.dispatch.user_input" submission.id="019d86c8-0a8e-7013-b442-109aabbf75c9" codex.op="user_input"}:turn{otel.name="session_task.turn" thread.id=019d81cf-6f69-7230-98aa-74294ff2dc5a turn.id=019d86c8-0a8e-7013-b442-109aabbf75c9 model=gpt-5.4}: ignoring interface.defaultPrompt: prompt must be at most 128 characters path=/Users/jif/.codex/.tmp/plugins/plugins/build-ios-apps/.codex-plugin/plugin.json 2026-04-13T12:27:30.406Z WARN [019d81cf-6f69-7230-98aa-74294ff2dc5a] codex_core::plugins::manifest - session_loop{thread_id=019d81cf-6f69-7230-98aa-74294ff2dc5a}:submission_dispatch{otel.name="op.dispatch.user_input" submission.id="019d86c8-0a8e-7013-b442-109aabbf75c9" codex.op="user_input"}:turn{otel.name="session_task.turn" thread.id=019d81cf-6f69-7230-98aa-74294ff2dc5a turn.id=019d86c8-0a8e-7013-b442-109aabbf75c9 model=gpt-5.4}: ignoring interface.defaultPrompt: prompt must be at most 128 characters path=/Users/jif/.codex/.tmp/plugins/plugins/life-science-research/.codex-plugin/plugin.json 2026-04-13T12:27:30.408Z WARN [019d81cf-6f69-7230-98aa-74294ff2dc5a] codex_core::plugins::manifest - session_loop{thread_id=019d81cf-6f69-7230-98aa-74294ff2dc5a}:submission_dispatch{otel.name="op.dispatch.user_input" submission.id="019d86c8-0a8e-7013-b442-109aabbf75c9" codex.op="user_input"}:turn{otel.name="session_task.turn" thread.id=019d81cf-6f69-7230-98aa-74294ff2dc5a turn.id=019d86c8-0a8e-7013-b442-109aabbf75c9 model=gpt-5.4}: ignoring interface.defaultPrompt: prompt must be at most 128 characters path=/Users/jif/.codex/.tmp/plugins/plugins/build-ios-apps/.codex-plugin/plugin.json ```
…ai#17398) Currently app-server may unload actively running threads once the last connection disconnects, which is not expected. Instead track when was the last active turn & when there were any subscribers the last time, also add 30 minute idleness/no subscribers timer to reduce the churn.
Windows gives an error when you combine `protocol = ANY` with `SetRemotePorts` This fixes that
The recent release broke, codex suggested this as the fix Source failure: https://github.com/openai/codex/actions/runs/24362949066/job/71147202092 Probably from openai@ac82443 For why it got in: ``` The relevant setup: .github/workflows/rust-ci.yml (line 1) runs on PRs, but for codex-rs it only does: cargo fmt --check cargo shear argument-comment lint via Bazel no cargo check, no cargo clippy over the workspace, no cargo test over codex-tui .github/workflows/rust-ci-full.yml (line 1) runs on pushes to main and branches matching **full-ci**. That one does compile TUI because: codex-rs/Cargo.toml includes "tui" as a workspace member lint_build runs cargo clippy --target ... --tests --profile ... the matrix includes both dev and release profiles tests runs cargo nextest run ..., but only dev-profile tests Release CI also compiles it indirectly. .github/workflows/rust-release.yml (line 235) builds --bin codex, and cli/Cargo.toml (line 46) depends on codex-tui. ``` Codex tested locally with `cargo check -p codex-tui --release` and was able to repro, and verified that this fixed it
### Motivation - Switch the default model used for memory Phase 2 (consolidation) to the newer `gpt-5.4` model. ### Description - Change the Phase 2 model constant from `"gpt-5.3-codex"` to `"gpt-5.4"` in `codex-rs/core/src/memories/mod.rs`. ### Testing - Ran `just fmt`, which completed successfully. - Attempted `cargo test -p codex-core`, but the build failed in this environment because the `codex-linux-sandbox` crate requires the system `libcap` pkg-config entry and the required system packages could not be installed, so the test run was blocked. ------ [Codex Task](https://chatgpt.com/codex/cloud/tasks/task_i_69d977693b48832a967e78d73c66dc8e)
# External (non-OpenAI) Pull Request Requirements Before opening this Pull Request, please read the dedicated "Contributing" markdown file or your PR may be closed: https://github.com/openai/codex/blob/main/docs/contributing.md If your PR conforms to our contribution guidelines, replace this text with a detailed and high quality description of your changes. Include a link to a bug report or enhancement request.
Cap mirrored user text sent to realtime with the existing 300-token turn budget while preserving the full model turn. Adds integration coverage for capped realtime mirror payloads. --------- Co-authored-by: Codex <noreply@openai.com>
# External (non-OpenAI) Pull Request Requirements Before opening this Pull Request, please read the dedicated "Contributing" markdown file or your PR may be closed: https://github.com/openai/codex/blob/main/docs/contributing.md If your PR conforms to our contribution guidelines, replace this text with a detailed and high quality description of your changes. Include a link to a bug report or enhancement request.
## Why
For more advanced MCP usage, we want the model to be able to emit
parallel MCP tool calls and have Codex execute eligible ones
concurrently, instead of forcing all MCP calls through the serial block.
The main design choice was where to thread the config. I made this
server-level because parallel safety depends on the MCP server
implementation. Codex reads the flag from `mcp_servers`, threads the
opted-in server names into `ToolRouter`, and checks the parsed
`ToolPayload::Mcp { server, .. }` at execution time. That avoids relying
on model-visible tool names, which can be incomplete in
deferred/search-tool paths or ambiguous for similarly named
servers/tools.
## What was added
Added `supports_parallel_tool_calls` for MCP servers.
Before:
```toml
[mcp_servers.docs]
command = "docs-server"
```
After:
```toml
[mcp_servers.docs]
command = "docs-server"
supports_parallel_tool_calls = true
```
MCP calls remain serial by default. Only tools from opted-in servers are
eligible to run in parallel. Docs also now warn to enable this only when
the server’s tools are safe to run concurrently, especially around
shared state or read/write races.
## Testing
Tested with a local stdio MCP server exposing real delay tools. The
model/Responses side was mocked only to deterministically emit two MCP
calls in the same turn.
Each test called `query_with_delay` and `query_with_delay_2` with `{
"seconds": 25 }`.
| Build/config | Observed | Wall time |
| --- | --- | --- |
| main with flag enabled | serial | `58.79s` |
| PR with flag enabled | parallel | `31.73s` |
| PR without flag | serial | `56.70s` |
PR with flag enabled showed both tools start before either completed;
main and PR-without-flag completed the first delay before starting the
second.
Also added an integration test.
Additional checks:
- `cargo test -p codex-tools` passed
- `cargo test -p codex-core
mcp_parallel_support_uses_exact_payload_server` passed
- `git diff --check` passed
# Conflicts: # codex-rs/app-server/tests/suite/v2/realtime_conversation.rs # codex-rs/core/src/codex.rs # codex-rs/core/src/codex_tests.rs # codex-rs/core/src/memories/mod.rs # codex-rs/core/src/memories/tests.rs # codex-rs/core/src/project_doc.rs # codex-rs/core/src/unified_exec/process_manager.rs # codex-rs/core/tests/suite/realtime_conversation.rs # codex-rs/core/tests/suite/rmcp_client.rs # codex-rs/exec-server/tests/common/exec_server.rs
There was a problem hiding this comment.
Pull request overview
Syncs upstream/main into the fork and resolves conflicts by aligning fork-specific behavior with upstream changes (notably AbsolutePathBuf, realtime request shaping, MCP parallel-call support, and app-server thread lifecycle semantics).
Changes:
- Add
supports_parallel_tool_callsto MCP server config and route parallel eligibility via exact MCP payload server name. - Migrate many CODEX_HOME / skills paths to
AbsolutePathBufand update related tests + schemas. - Update app-server behavior around thread unsubscribe/idle unload and add experimental
thread/memoryMode/set.
Reviewed changes
Copilot reviewed 142 out of 144 changed files in this pull request and generated no comments.
Show a summary per file
| File | Description |
|---|---|
| docs/config.md | Document MCP parallel tool-call opt-in (supports_parallel_tool_calls). |
| codex-rs/windows-sandbox-rs/src/workspace_acl.rs | Remove legacy workspace .codex/.agents ACL helpers; keep is_command_cwd_root. |
| codex-rs/windows-sandbox-rs/src/setup_orchestrator.rs | Merge explicit deny-write paths with computed protected children; add test. |
| codex-rs/windows-sandbox-rs/src/setup_main_win.rs | Treat deny-write carveouts uniformly; remove best-effort .codex/.agents protection step. |
| codex-rs/windows-sandbox-rs/src/lib.rs | Stop re-exporting removed workspace ACL helpers; stop calling them in impl. |
| codex-rs/windows-sandbox-rs/src/firewall.rs | Refactor firewall rule network-scope configuration + add COM acceptance test. |
| codex-rs/utils/home-dir/src/lib.rs | Return AbsolutePathBuf from find_codex_home; adjust tests. |
| codex-rs/utils/home-dir/Cargo.toml | Add dependency on codex-utils-absolute-path. |
| codex-rs/utils/absolute-path/src/lib.rs | Add ordering traits + helpers (from_absolute_path_checked, canonicalize, ancestors, test_path_buf) and tests. |
| codex-rs/tui/src/updates.rs | Adapt CODEX_HOME path join to AbsolutePathBuf conversions. |
| codex-rs/tui/src/test_support.rs | Centralize platform-absolute test paths via test_path_buf. |
| codex-rs/tui/src/status/tests.rs | Normalize status tests to use platform-absolute test paths. |
| codex-rs/tui/src/status/card.rs | Improve narrow-terminal rendering: keep percentage visible and wrap reset timestamp. |
| codex-rs/tui/src/onboarding/onboarding_screen.rs | Convert codex_home handling from clone to to_path_buf(). |
| codex-rs/tui/src/lib.rs | Convert codex_home to PathBuf at API boundaries; map find_codex_home output. |
| codex-rs/tui/src/history_cell.rs | Pass codex_home to plugin manager as PathBuf; update tests to platform paths. |
| codex-rs/tui/src/chatwidget/tests/plan_mode.rs | Align notifications tests to new Plan Mode prompt notification shape. |
| codex-rs/tui/src/chatwidget/tests/permissions.rs | Use platform-absolute test paths for workspace-write roots. |
| codex-rs/tui/src/chatwidget/tests/history_replay.rs | Update tests for AbsolutePathBuf codex_home and platform-absolute paths. |
| codex-rs/tui/src/chatwidget/tests/helpers.rs | Set config.codex_home as absolute; fix skill path construction. |
| codex-rs/tui/src/chatwidget/tests/composer_submission.rs | Use AbsolutePathBuf in skill path tests; adjust assertions. |
| codex-rs/tui/src/chatwidget/tests.rs | Re-export test_path_buf for chatwidget tests. |
| codex-rs/tui/src/chatwidget/skills.rs | Represent skill paths as AbsolutePathBuf; remove canonicalization helper. |
| codex-rs/tui/src/chatwidget.rs | Store skill initial state by AbsolutePathBuf; rework user-input notification to PlanModePrompt; suppress deprecated context-compacted event handling for v2. |
| codex-rs/tui/src/bottom_pane/skills_toggle_view.rs | Switch skill toggle items to AbsolutePathBuf; update tests. |
| codex-rs/tui/src/bottom_pane/mod.rs | Update tests to use platform-absolute skill paths. |
| codex-rs/tui/src/bottom_pane/chat_composer.rs | Use platform-absolute skill paths in mention-item tests. |
| codex-rs/tui/src/app_event.rs | Change SetSkillEnabled.path to AbsolutePathBuf. |
| codex-rs/skills/src/lib.rs | Require absolute CODEX_HOME for system skills cache operations. |
| codex-rs/rmcp-client/src/oauth.rs | Use AbsolutePathBuf.join(...).to_path_buf() for fallback file. |
| codex-rs/rmcp-client/src/bin/test_stdio_server.rs | Add sync tool for deterministic concurrency tests (barrier + sleeps). |
| codex-rs/protocol/src/protocol.rs | Add Op::SetThreadMemoryMode and ThreadMemoryMode; skill metadata path becomes AbsolutePathBuf. |
| codex-rs/plugin/src/load_outcome.rs | Represent plugin skill roots/disabled paths as AbsolutePathBuf. |
| codex-rs/network-proxy/src/certs.rs | Convert managed CA paths from AbsolutePathBuf to PathBuf where needed. |
| codex-rs/exec/src/lib.rs | Convert codex_home to PathBuf for auth/cloud requirements APIs. |
| codex-rs/exec-server/tests/common/exec_server.rs | Run exec-server tests with isolated CODEX_HOME tempdir. |
| codex-rs/core/tests/suite/truncation.rs | Update MCP server config fixtures to include supports_parallel_tool_calls. |
| codex-rs/core/tests/suite/subagent_notifications.rs | Adapt role config file fields to PathBuf conversion. |
| codex-rs/core/tests/suite/sqlite_state.rs | Adjust rollout path comparisons for AbsolutePathBuf conversions; add MCP server flag. |
| codex-rs/core/tests/suite/snapshots/all__suite__realtime_conversation__conversation_user_text_turn_is_capped_when_mirrored_to_realtime.snap | New snapshot for capped realtime-mirrored user text. |
| codex-rs/core/tests/suite/skills.rs | Make skills test robust to path canonicalization differences (match by name). |
| codex-rs/core/tests/suite/search_tool.rs | Update MCP server config fixture with supports_parallel_tool_calls. |
| codex-rs/core/tests/suite/realtime_conversation.rs | Add test verifying realtime-mirrored user text is capped while model request preserves full text. |
| codex-rs/core/tests/suite/code_mode.rs | Update MCP server config fixture with supports_parallel_tool_calls. |
| codex-rs/core/tests/common/test_codex.rs | Convert codex_home to PathBuf when building thread manager for tests. |
| codex-rs/core/src/tools/spec_tests.rs | Initialize new ToolRouterParams.parallel_mcp_server_names. |
| codex-rs/core/src/tools/router_tests.rs | Update tests for new tool_supports_parallel(&ToolCall) API and MCP server-name exact match semantics. |
| codex-rs/core/src/tools/router.rs | Track parallel MCP eligibility by exact MCP payload server name; update API accordingly. |
| codex-rs/core/src/tools/parallel.rs | Use new router API when deciding parallel scheduling. |
| codex-rs/core/src/tools/js_repl/mod.rs | Ensure JS REPL nested routing disables parallel scheduling. |
| codex-rs/core/src/tools/handlers/multi_agents_v2/spawn.rs | Reject model/role overrides for full-history forks; preserve inherited settings. |
| codex-rs/core/src/tools/handlers/multi_agents_common.rs | Apply default reasoning level fallback; add helper to reject full-fork overrides. |
| codex-rs/core/src/tools/handlers/multi_agents/spawn.rs | Enforce no overrides when using fork_context/full-history behavior. |
| codex-rs/core/src/tools/code_mode/mod.rs | Propagate configured parallel MCP servers to nested tool router. |
| codex-rs/core/src/thread_manager_tests.rs | Update tests for AbsolutePathBuf CODEX_HOME and required conversions. |
| codex-rs/core/src/thread_manager.rs | Convert plugin/models managers to accept PathBuf; normalize skills CODEX_HOME to AbsolutePathBuf in tests. |
| codex-rs/core/src/skills_watcher.rs | Convert skill root paths to PathBuf watch paths. |
| codex-rs/core/src/skills.rs | Use AbsolutePathBuf for CWD + effective skill roots; convert skill invocation path to PathBuf at boundary. |
| codex-rs/core/src/realtime_context.rs | Extract realtime turn token budget constant; factor truncation loop into helper. |
| codex-rs/core/src/prompt_debug.rs | Use AbsolutePathBuf for codex_home in tests. |
| codex-rs/core/src/project_doc_tests.rs | Convert codex_home to PathBuf for helper APIs. |
| codex-rs/core/src/project_doc.rs | Simplify project-root resolution using AbsolutePathBuf joins/clones. |
| codex-rs/core/src/plugins/manager_tests.rs | Update plugin skill roots and MCP server config fixtures for new types/flags. |
| codex-rs/core/src/plugins/discoverable_tests.rs | Add regression test ensuring curated marketplace isn’t reloaded per plugin; wire tracing capture. |
| codex-rs/core/src/plugins/discoverable.rs | Switch curated plugin reading API to avoid per-plugin reload; convert codex_home to PathBuf. |
| codex-rs/core/src/otel_init.rs | Convert codex_home to PathBuf for otel settings. |
| codex-rs/core/src/message_history.rs | Build history file path via AbsolutePathBuf.join(...).to_path_buf(). |
| codex-rs/core/src/memories/tests.rs | Update tests for AbsolutePathBuf codex_home/cwd and rollout path conversions. |
| codex-rs/core/src/memories/prompts_tests.rs | Remove consolidation prompt tests that no longer match updated prompt behavior. |
| codex-rs/core/src/mcp_tool_call_tests.rs | Convert codex_home to PathBuf when building models manager. |
| codex-rs/core/src/mcp_tool_call.rs | Convert config folder path to PathBuf for config edits builder. |
| codex-rs/core/src/mcp_skill_dependencies.rs | Add supports_parallel_tool_calls to derived MCP server configs. |
| codex-rs/core/src/guardian/tests.rs | Use platform-absolute helper paths; convert codex_home for models manager. |
| codex-rs/core/src/connectors.rs | Convert codex_home to PathBuf at plugin/mcp manager boundaries. |
| codex-rs/core/src/config/permissions_tests.rs | Update signature usage to pass AbsolutePathBuf CODEX_HOME. |
| codex-rs/core/src/config/mod.rs | Make Config.codex_home an AbsolutePathBuf; adjust loaders and API adapters accordingly. |
| codex-rs/core/src/config/edit_tests.rs | Add/round-trip supports_parallel_tool_calls in MCP server serialization tests. |
| codex-rs/core/src/config/edit.rs | Serialize supports_parallel_tool_calls when true. |
| codex-rs/core/src/codex_thread.rs | Add set_thread_memory_mode wrapper method. |
| codex-rs/core/src/codex_tests_guardian.rs | Convert codex_home to PathBuf for models/plugins managers. |
| codex-rs/core/src/codex_tests.rs | Thread manager/router construction updated for new path types and router params. |
| codex-rs/core/src/agent/role_tests.rs | Update SkillsManager construction to accept AbsolutePathBuf. |
| codex-rs/core/src/agent/control_tests.rs | Convert codex_home to PathBuf for thread manager tests. |
| codex-rs/core/config.schema.json | Add supports_parallel_tool_calls to MCP server schema. |
| codex-rs/core-skills/src/system.rs | Require absolute CODEX_HOME for uninstall path computation. |
| codex-rs/core-skills/src/model.rs | Use AbsolutePathBuf for skill paths and disabled sets/indexes. |
| codex-rs/core-skills/src/mention_counts.rs | Use AbsolutePathBuf for disabled-path set. |
| codex-rs/core-skills/src/manager.rs | Use AbsolutePathBuf for cwd, roots, caches; canonicalize via AbsolutePathBuf::canonicalize. |
| codex-rs/core-skills/src/loader_tests.rs | Update tests to use AbsolutePathBuf and platform-absolute test helpers. |
| codex-rs/core-skills/src/loader.rs | Use AbsolutePathBuf throughout root discovery, project-root detection, and parse resolution. |
| codex-rs/core-skills/src/invocation_utils_tests.rs | Update implicit invocation tests to AbsolutePathBuf + platform-absolute helpers. |
| codex-rs/core-skills/src/invocation_utils.rs | Use AbsolutePathBuf for canonicalization/joins and implicit invocation detection. |
| codex-rs/core-skills/src/injection_tests.rs | Update explicit mention tests to AbsolutePathBuf and platform-absolute display. |
| codex-rs/core-skills/src/injection.rs | Track disabled/seen skill paths as AbsolutePathBuf; convert to PathBuf at invocation boundary. |
| codex-rs/core-skills/src/config_rules.rs | Store rule selectors as AbsolutePathBuf; resolve disabled paths accordingly. |
| codex-rs/config/src/mcp_types_tests.rs | Add (de)serialization tests for supports_parallel_tool_calls. |
| codex-rs/config/src/mcp_types.rs | Add supports_parallel_tool_calls to MCP server config and raw config. |
| codex-rs/config/src/mcp_edit_tests.rs | Ensure supports_parallel_tool_calls is serialized in edits output. |
| codex-rs/config/src/mcp_edit.rs | Serialize supports_parallel_tool_calls when true. |
| codex-rs/codex-mcp/src/mcp_connection_manager_tests.rs | Update MCP config fixtures with supports_parallel_tool_calls. |
| codex-rs/codex-mcp/src/mcp/skill_dependencies_tests.rs | Update skill path and MCP config fixtures for new types/flags. |
| codex-rs/codex-mcp/src/mcp/skill_dependencies.rs | Update derived MCP server configs with supports_parallel_tool_calls. |
| codex-rs/codex-mcp/src/mcp/mod_tests.rs | Update effective server fixtures with supports_parallel_tool_calls. |
| codex-rs/codex-mcp/src/mcp/mod.rs | Ensure Codex Apps MCP server sets supports_parallel_tool_calls: false. |
| codex-rs/codex-mcp/Cargo.toml | Add dev-dependency on codex-utils-absolute-path. |
| codex-rs/codex-api/src/endpoint/realtime_websocket/methods_v2.rs | Strengthen background agent tool description to preserve user wording. |
| codex-rs/cloud-tasks/src/util.rs | Convert codex_home to PathBuf for AuthManager creation. |
| codex-rs/cli/src/mcp_cmd.rs | Default new MCP servers to supports_parallel_tool_calls: false; convert codex_home for plugin manager. |
| codex-rs/cli/src/login.rs | Convert codex_home to PathBuf for login flows. |
| codex-rs/chatgpt/src/connectors.rs | Convert codex_home to PathBuf at auth/plugins boundaries. |
| codex-rs/app-server/tests/suite/v2/thread_unsubscribe.rs | Update expectations: unsubscribe does not unload immediately; adjust status behaviors. |
| codex-rs/app-server/tests/suite/v2/thread_memory_mode_set.rs | Add tests for experimental thread memory mode setter (loaded + stored). |
| codex-rs/app-server/tests/suite/v2/skills_list.rs | Add test ensuring relative CWDs are accepted for skills list requests. |
| codex-rs/app-server/tests/suite/v2/realtime_conversation.rs | Update expected background agent tool description in WebRTC start test. |
| codex-rs/app-server/tests/suite/v2/mod.rs | Register new thread memory mode set test module. |
| codex-rs/app-server/tests/suite/v2/experimental_api.rs | Ensure thread/memoryMode/set requires experimental capability. |
| codex-rs/app-server/tests/suite/v2/connection_handling_websocket.rs | Update expectation: disconnect does not immediately unload last thread. |
| codex-rs/app-server/tests/common/mcp_process.rs | Add helper to send thread/memoryMode/set request. |
| codex-rs/app-server/src/thread_status.rs | Add per-thread watch subscriptions and watcher updates; add unit test. |
| codex-rs/app-server/src/thread_state.rs | Track “has connections” via watch channel; expose subscription API for unload logic. |
| codex-rs/app-server/src/message_processor.rs | Convert codex_home to PathBuf for config/external-agent APIs; simplify initialize response codex_home handling. |
| codex-rs/app-server/src/lib.rs | Convert codex_home to PathBuf when calling cloud requirements loader. |
| codex-rs/app-server/src/bespoke_event_handling.rs | Suppress deprecated events/items for v2 clients to avoid duplicates; update tests config plumbing. |
| codex-rs/app-server/README.md | Document new thread/memoryMode/set and updated unsubscribe idle-unload behavior. |
| codex-rs/app-server-protocol/src/protocol/v2.rs | Add ThreadMemoryMode types + request/response; change skill paths to AbsolutePathBuf. |
| codex-rs/app-server-protocol/src/protocol/common.rs | Register experimental thread/memoryMode/set request. |
| codex-rs/app-server-protocol/schema/typescript/v2/SkillSummary.ts | Update skill path type to AbsolutePathBuf. |
| codex-rs/app-server-protocol/schema/typescript/v2/SkillMetadata.ts | Update skill path type to AbsolutePathBuf. |
| codex-rs/app-server-protocol/schema/typescript/index.ts | Export ThreadMemoryMode. |
| codex-rs/app-server-protocol/schema/typescript/ThreadMemoryMode.ts | Add generated TS type for thread memory mode. |
| codex-rs/app-server-protocol/schema/json/v2/SkillsListResponse.json | Update skill path schema ref to AbsolutePathBuf. |
| codex-rs/app-server-protocol/schema/json/v2/PluginReadResponse.json | Update skill path schema ref to AbsolutePathBuf. |
| codex-rs/app-server-protocol/schema/json/codex_app_server_protocol.v2.schemas.json | Add ThreadMemoryMode + update skill path schemas to AbsolutePathBuf. |
| codex-rs/app-server-protocol/schema/json/codex_app_server_protocol.schemas.json | Add ThreadMemoryMode + update skill path schemas to AbsolutePathBuf. |
| codex-rs/app-server-protocol/schema/json/ClientRequest.json | Add ThreadMemoryMode schema. |
| codex-rs/Cargo.lock | Add lockfile entries for new absolute-path dependency edges. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
upstream/mainfromopenai/codexintoElectivus/codex:mainAbsolutePathBufand realtime/request-shape changes introduced upstreamTest Plan
just fmtcargo test -p codex-core conversation_user_text_turn_is_capped_when_mirrored_to_realtimecargo build -p codex-rmcp-client --bin test_stdio_servercargo test -p codex-core stdio_mcp_parallel_tool_calls_default_false_runs_seriallycargo test -p codex-core stdio_mcp_parallel_tool_calls_opt_in_runs_concurrentlycargo test -p codex-app-server realtime_conversation_stop_emits_closed_notificationcargo test -p codex-app-server webrtc_v1_start_posts_offer_returns_sdp_and_joins_sidebandcargo test -p codex-exec-server exec_server_accepts_initialize