## Summary
- resolve or inject the installation ID before core startup and pass it
through `ThreadManager`, `CodexSpawnArgs`, and `Session` as a plain
`String`
- keep child sessions on the parent installation ID instead of
rediscovering it inside core
- propagate installation ID startup failures in `mcp-server` instead of
panicking
## Why
Core was still touching the filesystem on the session startup path to
discover `installation_id`. This moves that work to the outer host
boundary so core no longer depends on `codex_home` reads during session
construction.
---------
Co-authored-by: Codex <noreply@openai.com>
## Why
`/responses/compact` should preserve the request-affinity fields that
apply to the active auth mode. ChatGPT-auth compact requests need the
effective `service_tier`, and compact requests for every auth mode need
the stable `prompt_cache_key`, so compaction does not quietly lose
routing or cache behavior that normal sampling already has.
This follows the request-parity direction from #20719, but keeps the net
change focused on the compact payload fields needed here.
## What changed
- Add `service_tier` and `prompt_cache_key` to the compact endpoint
input payload.
- Build the remote compact payload from the existing responses request
builder output so `Fast` still maps to `priority` when compact sends a
service tier.
- Pass the turn service tier into remote compaction, but only include it
in compact payloads for ChatGPT-backed auth.
- Keep `prompt_cache_key` on compact payloads for all auth modes.
- Add request-body diff snapshot coverage in
`core/tests/suite/compact_remote.rs` for:
- API-key auth reusing `prompt_cache_key` while omitting `service_tier`
even when `Fast` is configured.
- ChatGPT auth reusing both `service_tier` and `prompt_cache_key`.
- Drive the snapshot coverage through five varied turns: plain text,
multi-part text, tool-call continuation, image+text input, local-shell
continuation, and final-turn reasoning output.
## Verification
- Added insta snapshots for compact request-body parity against the last
normal `/responses` request after five varied turns.
- Not run locally per repo guidance; relying on GitHub CI for test
execution.
---------
Co-authored-by: Codex <noreply@openai.com>
## Why
MCP tool calls already include `session_id` in `x-codex-turn-metadata`,
but descendant threads intentionally share that value with the root
thread. Consumers that need to correlate work at the concrete thread
level also need the current `thread_id`.
## What changed
- add `thread_id` to `x-codex-turn-metadata` while preserving
`session_id` as the shared session identity
- thread the two identities separately through normal turns and spawned
review threads
- add regression coverage for resumed sessions, reserved metadata
fields, and deferred MCP tool calls
## Verification
- added focused coverage in `core/src/session/tests.rs`,
`core/src/turn_metadata_tests.rs`, and `core/tests/suite/search_tool.rs`
## Summary
Related to
https://openai.slack.com/archives/C095U48JNL9/p1777537279707449
TLDR:
We update the meaning of session ids and thread ids:
* thread_id stays as now
* session_id become a shared id between every thread under a /root
thread (i.e. every sub-agent share the same session id)
This PR introduces an explicit `SessionId` and threads it through the
protocol/client boundary so `session_id` and `thread_id` can diverge
when they need to, while preserving compatibility for older serialized
`session_configured` events.
---------
Co-authored-by: Codex <noreply@openai.com>
# Overview
MCP refreshes were rebuilding active threads from fresh disk-backed
config only, which dropped thread-start session overlays such as
app-injected MCP servers. This keeps refreshes current with disk config
while preserving the thread-local config that only the active thread
knows about.
# Changes
- Rebuild refreshed config per active thread using that thread's current
`cwd`, rather than fanning out one app-server config to every thread.
- Preserve each thread's `SessionFlags` layer while replacing reloadable
config layers with freshly loaded config, then derive the MCP refresh
payload from the rebuilt result.
- Move MCP refresh orchestration into app-server so manual refreshes
fail loudly while background refreshes remain best-effort, and route
plugin-triggered refreshes through the same per-thread reload path.
- Add regression coverage for session overlays, fresh project config,
plugin-derived MCP config, current requirements, and strict vs
best-effort refresh behavior.
# Verification
- Passed focused Rust coverage for the thread-config rebuild behavior
and deferred MCP refresh flow, plus `cargo test -p codex-app-server
--lib`.
- Verified end to end in the Codex dev app against the locally built
CLI: registered an MCP via thread config, verified that it could be used
successfully before refresh, manually triggered MCP refresh, and
verified that it continued to be available afterward.
## Summary
- make `thread_source` an explicit optional thread-level field on
`thread/start`, `thread/fork`, and returned thread payloads
- persist `thread_source` in rollout/session metadata so resumed live
threads retain the original value
- replace the old best-effort `session_source` -> `thread_source`
mapping with an explicit caller-supplied analytics classification
## Why
Before this change, analytics `thread_source` was populated by a
best-effort mapping from `session_source`. `session_source` describes
the runtime/client surface, not the actual thread-level origin, so that
projection was not accurate enough to distinguish cases such as `user`,
`subagent`, `memory_consolidation`, and future thread origins reliably.
Making `thread_source` explicit keeps one thread-level analytics field
while letting callers provide the real classification directly instead
of recovering it indirectly from `session_source`.
## Impact
For new analytics events, `thread_source` now reflects the explicit
thread-level classification supplied by the caller rather than an
inferred value derived from `session_source`. Existing protocol fields
remain optional; callers that omit `threadSource` now produce `null`
instead of a best-effort inferred value.
## Validation
- `just write-app-server-schema`
- `cargo test -p codex-analytics -p codex-core -p
codex-app-server-protocol --no-run`
- `cargo test -p codex-app-server-protocol
generated_ts_optional_nullable_fields_only_in_params`
- `cargo test -p codex-analytics
thread_initialized_event_serializes_expected_shape`
- `cargo test -p codex-core
resume_stopped_thread_from_rollout_preserves_thread_source`
## Why
`skills/list` is already exposed through app-server v2 and covered by
the app-server test suite. Keeping the separate core `Op::ListSkills`
path leaves a duplicate legacy protocol surface that no longer needs to
be maintained.
## What Changed
- Removed `Op::ListSkills` and `EventMsg::ListSkillsResponse` from the
core protocol.
- Deleted the corresponding core session handler and stale core
integration tests.
- Removed rollout/MCP ignore branches and protocol v1 docs references
for the deleted event/op.
- Left app-server `skills/list` and its existing coverage intact.
## Validation
- `cargo test -p codex-protocol`
- `cargo test -p codex-core --test all suite::skills`
- `cargo check -p codex-mcp-server -p codex-rollout -p
codex-rollout-trace`
- `just fix -p codex-core`
## Why
- Similar change as https://github.com/openai/codex/pull/19473.
- Without change: MCP tool calls receive
`_meta["x-codex-turn-metadata"]` with `session_id`, `turn_id`, and
`turn_started_at_unix_ms`.
- Issue: MCP servers may want the model and reasoning effort to better
understand tool-call behavior and latency relative to turn start.
## What Changed
- With change: MCP turn metadata now includes `model` and
`reasoning_effort`, propagated in `_meta["x-codex-turn-metadata"]`.
- Normal `/responses` turn metadata headers are unchanged.
## Verification
- `codex-rs/core/src/mcp_tool_call_tests.rs`
- `codex-rs/core/src/turn_metadata_tests.rs`
- `codex-rs/core/tests/suite/search_tool.rs`
## Why
Thread names are app-server metadata now, backed by the thread store and
sqlite state database. Keeping a core `SetThreadName` op plus a rollout
`thread_name_updated` event made rename persistence live in the wrong
layer and required historical replay support for an event that new
app-server flows should not write.
## What changed
- Removed `Op::SetThreadName` and `EventMsg::ThreadNameUpdated` from the
core protocol and deleted the core handler path that appended rename
events to rollouts.
- Updated app-server `thread/name/set` so both loaded and unloaded
threads write through thread-store metadata and app-server emits
`thread/name/updated` notifications.
- Updated local thread-store name metadata updates to write sqlite title
metadata and the legacy thread-name index without appending rollout
events.
- Removed state extraction and rollout handling for the deleted
thread-name event.
## Validation
- `cargo test -p codex-app-server thread_name_updated_broadcasts`
- `cargo test -p codex-app-server
thread_name_set_is_reflected_in_read_list_and_resume`
- `cargo test -p codex-thread-store
update_thread_metadata_sets_name_on_active_rollout_and_indexes_name`
- `cargo test -p codex-state`
- `cargo check -p codex-mcp-server -p codex-rollout-trace`
- `just fix -p codex-app-server -p codex-thread-store -p codex-state -p
codex-mcp-server -p codex-rollout-trace`
## Docs
No external documentation update is expected for this internal ownership
change.
**Summary**
- Add `codex-bwrap`, a standalone `bwrap` binary built from the existing
vendored bubblewrap sources.
- Remove the linked vendored bwrap path from `codex-linux-sandbox`;
runtime now prefers system `bwrap` and falls back to bundled
`codex-resources/bwrap`.
- Add bundled SHA-256 verification with missing/all-zero digest as the
dev-mode skip value, then exec the verified file through
`/proc/self/fd`.
- Keep `launcher.rs` focused on choosing and dispatching the preferred
launcher. Bundled lookup, digest verification, and bundled exec now live
in `linux-sandbox/src/bundled_bwrap.rs`; Bazel runfiles lookup lives in
`linux-sandbox/src/bazel_bwrap.rs`; shared argv/fd exec helpers live in
`linux-sandbox/src/exec_util.rs`.
- Teach Bazel tests to surface the Bazel-built `//codex-rs/bwrap:bwrap`
through `CARGO_BIN_EXE_bwrap`; `codex-linux-sandbox` only honors that
fallback in debug Bazel runfiles environments so release/user runtime
lookup stays tied to `codex-resources/bwrap`.
- Allow `codex-exec-server` filesystem helpers to preserve just the
Bazel bwrap/runfiles variables they need in debug Bazel builds, since
those helpers intentionally rebuild a small environment before spawning
`codex-linux-sandbox`.
- Verify the Bazel bwrap target in Linux release CI with a build-only
check. Running `bwrap --version` is too strong for GitHub runners
because bubblewrap still attempts namespace setup there.
**Verification**
- Latest update: `cargo test -p codex-linux-sandbox`
- Latest update: `just fix -p codex-linux-sandbox`
- `cargo check --target x86_64-unknown-linux-gnu -p codex-linux-sandbox`
could not run locally because this macOS machine does not have
`x86_64-linux-gnu-gcc`; GitHub Linux Bazel CI is expected to cover the
Linux-only modules.
- Earlier in this PR: `cargo test -p codex-bwrap`
- Earlier in this PR: `cargo test -p codex-exec-server`
- Earlier in this PR: `cargo check --release -p codex-exec-server`
- Earlier in this PR: `just fix -p codex-linux-sandbox -p
codex-exec-server`
- Earlier in this PR: `bazel test --nobuild
//codex-rs/linux-sandbox:linux-sandbox-all-test
//codex-rs/core:core-all-test
//codex-rs/exec-server:exec-server-file_system-test
//codex-rs/app-server:app-server-all-test` (analysis completed; Bazel
then refuses to run tests under `--nobuild`)
- Earlier in this PR: `bazel build --nobuild //codex-rs/bwrap:bwrap`
- Prior to this update: `just bazel-lock-update`, `just
bazel-lock-check`, and YAML parse check for
`.github/workflows/bazel.yml`
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/21255).
* #21257
* #21256
* __->__ #21255
- fork loaded parent threads from `ThreadStore` history in core agent
control paths
- migrate guardian review fork history to loaded session history instead
of rereading rollout files
## Verification
- `cargo test -p codex-core spawn_agent_fork`
## Why
We want the agent graph store to be passed down the stack as a real
dependency, the same way we already treat the thread store.
This will let us inject the agent graph store as a real dependency and
support implementations other than the local SQLite-backed one. Right
now most code instantiates a state DB and an agent graph store
just-in-time. Ideally, we would not depend on the state DB directly but
only read through the higher-level interfaces.
This change makes the dependency boundaries explicit and moves state DB
initialization to process bootstrap instead of hiding it inside local
store implementations.
## What changed
- `ThreadManager` now requires a `StateDbHandle` and an
`AgentGraphStore` at construction time instead of treating them as
optional internals.
- The local store constructors no longer lazily initialize SQLite.
Callers now initialize the state DB once per process and use that shared
handle to build:
- `LocalThreadStore`
- `LocalAgentGraphStore`
- App bootstraps (`app-server`, `mcp-server`, `prompt_debug`, and the
thread-manager sample) now initialize the state DB up front and inject
the resulting handle down the stack.
- `app-server` now consistently uses its process-scoped state DB handle
instead of reopening SQLite or trying to recover it from loaded threads.
- Device-key storage now reuses the shared state DB handle instead of
maintaining its own lazy opener.
- The thread archive / descendant traversal paths now use the injected
`AgentGraphStore` instead of reaching through local
thread-store-specific state.
## Verification
- `cargo check -p codex-core -p codex-thread-store -p codex-app-server
-p codex-mcp-server -p codex-thread-manager-sample --tests`
- `cargo test -p codex-thread-store`
- `cargo test -p codex-core
thread_manager_accepts_separate_agent_graph_store_and_thread_store --
--nocapture`
- `cargo test -p codex-app-server
thread_archive_archives_spawned_descendants -- --nocapture`
## Summary
Xcode 26.4 was built against app-server behavior from before MCP
elicitation requests became client-visible in CLI 0.120.0 via #17043.
That client line does not expect the new events/messages, so this PR
restores the old behavior for exactly that client/version combination.
The compatibility handling stays in the app-server layer: when the
initialized client is `Xcode` and its version starts with `26.4`, the
app server marks the live Codex thread so MCP elicitations are
auto-denied. The flag is applied on thread start/resume/fork/turn
attachment, carried through `Codex`/`CodexThread`, and stored on
`McpConnectionManager` so refreshed MCP managers preserve the behavior.
## Notes
This is intentionally narrow and includes a TODO to remove the
compatibility path once Xcode 26.4 ages out.
## Why
Tool registration used to bind a tool name to a handler externally,
which left ownership split between the registry plan and the handler
implementation. Some built-in handlers also multiplexed multiple in-core
tools by switching on the invoked tool name internally.
This moves the registry identity onto the handler itself and makes
built-in multi-tool areas use separate concrete handlers, so each
registered handler instance owns exactly one tool name and one dispatch
path.
## What Changed
- Added `ToolHandler::tool_name()` and changed
`ToolRegistryBuilder::register_handler` to derive the registry key from
the handler.
- Split built-in multiplexed handlers into concrete per-tool handlers
for unified exec, shell/local shell/container exec, MCP resources, goal
tools, and agent job tools.
- Kept name-carrying handler instances only where the runtime target is
inherently external or dynamic, such as MCP tools, dynamic tools, and
unavailable placeholders.
- Updated `ToolHandlerKind` and registry-plan construction so plan
entries map directly to concrete handler registrations.
## Verification
- `cargo test -p codex-tools tool_registry_plan`
- `cargo test -p codex-core --lib tools::registry_tests`
- `just fix -p codex-tools`
- `just fix -p codex-core`
## Why
The resume/fork picker is becoming the main way users recover previous
work, but the old fixed table made sessions hard to scan once thread
names, branches, working directories, and timestamps all mattered. This
redesign makes the picker denser by default, easier to search, and safer
to inspect before resuming or forking.
<table>
<tr>
<td>
<img width="1660" height="1103" alt="CleanShot 2026-05-03 at 12 34 10"
src="https://github.com/user-attachments/assets/313ede1d-1da4-4863-acd2-56b3e27e9703"
/>
</td>
<td>
<img width="1662" height="1100" alt="CleanShot 2026-05-03 at 12 34 15"
src="https://github.com/user-attachments/assets/cfde7d5c-bab0-4994-a807-254e53f344ea"
/>
</td>
</tr>
<tr>
<td>
<img width="1664" height="1107" alt="CleanShot 2026-05-03 at 12 39 22"
src="https://github.com/user-attachments/assets/e1ee58ca-4dc5-4a35-ae0f-47562da3974c"
/>
</td>
<td>
<img width="1662" height="1100" alt="CleanShot 2026-05-03 at 12 35 09"
src="https://github.com/user-attachments/assets/9c888072-eedf-4f45-985c-0c14df28bcc7"
/>
</td>
</tr>
</table>
## What Changed
- Replaces the old session table with responsive session rows that
prioritize the session name or preview, then show timestamp, cwd, and
branch metadata.
- Makes dense view the default while keeping comfortable view available
through `Ctrl+O`.
- Persists the picker view preference in `[tui].session_picker_view`,
including active profile-scoped config.
- Adds sort/filter controls for updated time, created time, cwd, and all
sessions.
- Expands search matching across session name, preview, thread id,
branch, and cwd.
- Makes `Esc` safer in search mode: it clears an active query before
starting a new session.
- Adds lazy transcript inspection:
- `Space` expands recent transcript context inline.
- `Ctrl+T` opens a transcript overlay.
- raw reasoning visibility follows `show_raw_agent_reasoning`.
- Keeps remote cwd filtering server-side for remote app-server sessions
so local path normalization does not incorrectly hide remote results.
- Updates snapshots and config schema for the new picker states and
config option.
## How to Test
1. Start Codex in a repo with several saved sessions.
2. Press `Ctrl+R` / resume picker entry point.
3. Confirm the picker opens in dense mode and shows session name or
preview, timestamp, cwd, and branch metadata.
4. Press `Ctrl+O` and confirm it switches between dense and comfortable
views.
5. Restart Codex and confirm the selected view persists.
6. Type a query that matches a branch, cwd, thread id, or session name;
confirm matching sessions appear.
7. Press `Esc` while the query is non-empty and confirm it clears search
instead of starting a new session.
8. Select a session and press `Space`; confirm recent transcript context
expands inline.
9. Press `Ctrl+T`; confirm the transcript overlay opens and respects
raw-reasoning visibility settings.
Targeted tests:
- `cargo test -p codex-tui resume_picker --no-fail-fast`
- `cargo test -p codex-core
runtime_config_resolves_session_picker_view_default_and_override`
- `cargo test -p codex-core profile_tui_rejects_unsupported_settings`
- `cargo check -p codex-thread-manager-sample`
- `cargo insta pending-snapshots`
# Why
We want shared hook trust that both the app and the TUI can build on,
but the metadata is only useful if runtime behavior agrees with it. This
PR adds a single backend trust model for hooks so unmanaged hooks cannot
run until the current definition has been reviewed, while managed hooks
remain runnable and non-configurable.
# What
- persist `trusted_hash` alongside hook state in `config.toml`
- expose `currentHash` and derived `trustStatus` through `hooks/list`
- derive trust from normalized hook definitions so equivalent hooks from
`config.toml` and `hooks.json` share the same trust identity
- gate unmanaged hooks on trust before they enter the runnable handler
set
# Reviewer Notes
- key file to review is `codex-rs/hooks/src/engine/discovery.rs`
- the only **core** change is schema related
## Why
When a turn exposes multiple selected environments, shell-style tools
need a model-facing way to identify the intended target environment and
handlers need to resolve that target before parsing cwd-relative
permission fields or launching processes.
This PR scopes that rollout to process tools. Filesystem-oriented tools
such as `apply_patch`, `view_image`, and `list_dir` are intentionally
left for follow-up slices.
## What Changed
- Adds an `include_environment_id` option to shell-style tool schema
builders.
- Exposes optional `environment_id` on `shell`, `shell_command`, and
`exec_command` only when `ToolEnvironmentMode::Multiple` is active.
- Adds a shared handler helper that parses `environment_id` and
`workdir` from JSON function-call arguments and returns the selected
`Environment` plus effective absolute cwd.
- Uses that helper in `shell`, `shell_command`, and `exec_command`
handling so process execution uses the selected environment filesystem
and cwd.
- Changes `ExecCommandRequest` to carry a required resolved `cwd`,
removing the process-manager fallback to the primary turn cwd for new
exec commands.
- Leaves `write_stdin` unchanged because it targets an existing process
id, not a new environment.
## Testing
- Added unit coverage for process-tool schema exposure, selected
environment resolution, primary fallback, no-environment handling,
unknown environment ids, and resolving cwd-relative permission paths
against the selected environment cwd.
- Added a remote-suite e2e coverage case for `exec_command` routing
across explicit zero environments, one local environment, and
local+remote environments.
- Ran `just fmt` and `git diff --check`.
---------
Co-authored-by: Codex <noreply@openai.com>
## Why
Granular copy is particularly difficult with the current output. Part of
it was solved with the introduction of the `/copy` command but when you
only need to copy parts of a response, you still encounter some issues:
- When you copy a paragraph, the result is a sequence of separate lines
instead of one correctly joined paragraph.
- When a word wraps, part of it stays on the original line and the rest
appears at the start of the next line.
- When you copy a long command, extra line breaks are often inserted,
and command arguments can be split across multiple lines.
https://github.com/user-attachments/assets/0ef85c84-9363-4aad-b43a-15fce062a443
## Solution
Now that we own the scrollback and we re-create it when we resize, we
have the opportunity of toggling between the raw text and the rich text
we see today.
- Add TUI raw scrollback mode with `tui.raw_output_mode`, `/raw
[on|off]`, and the configurable `tui.keymap.global.toggle_raw_output`
action.
- Render transcript cells through rich/raw-aware paths so raw mode
preserves source text and lets the terminal soft-wrap selection-friendly
output.
- Bind raw-mode toggle to `alt-r` by default, with the keybinding path
toggling silently while `/raw` continues to emit confirmation messages.
## Related Issues
Likely addressed by raw mode:
- #12200: clean copy for multiline and soft-wrapped output. Raw mode
removes Codex-inserted wrapping/indentation and lets the terminal
soft-wrap logical lines.
- #9252: command suggestions gain unwanted leading spaces when copied.
Raw mode renders transcript text without the rich-mode left
padding/gutter.
- #8258: prompt output is hard to copy because of leading indentation.
Raw mode renders user/source-backed transcript text without that
decorative indentation.
Partially or conditionally addressed:
- #2880: copy/export message as Markdown. Raw mode exposes raw Markdown
for terminal selection, but this PR does not add a dedicated
export/copy-message command.
- #19820: mouse drag selection + copy in the TUI. Raw mode improves
terminal-native selection of output/history text, but this PR does not
implement in-TUI mouse selection, highlighting, auto-copy, or composer
selection.
- #18979: copied content is divided into two parts. This should improve
cases caused by Codex-inserted wraps/padding in rendered output; if the
report is about pasting into the composer/input path, that remains
outside this PR.
## Validation
- `just write-config-schema`
- `just fmt`
- `cargo test -p codex-config`
- `cargo test -p codex-tui`
- `just fix -p codex-tui`
- `just argument-comment-lint`
- `cargo test -p codex-tui
raw_output_mode_can_change_without_inserting_notice -- --nocapture`
- `cargo test -p codex-tui
raw_slash_command_toggles_and_accepts_on_off_args -- --nocapture`
- `cargo test -p codex-tui raw_output_toggle -- --nocapture`
- `git diff --check`
- `cargo insta pending-snapshots`
# Why
Revert #20524 for now because the computer use plugin has not migrated
off legacy `notify` yet. Keeping the deprecation in place today would
show users a warning before the plugin path is ready to move, so this
rolls the change back until that migration is complete.
# What
- revert the legacy `notify` deprecation change from #20524
- restore the prior `notify` behavior and remove the temporary
deprecation metrics/docs from that change
Once the computer use plugin has migrated, we can land the same
deprecation again.
# Why
`PreToolUse` already exposes `hookSpecificOutput.additionalContext` in
the generated hook schema, but the runtime still rejected it as
unsupported. That leaves `PreToolUse` out of step with the other
context-injecting hooks and prevents hook authors from attaching
model-visible guidance to a pending tool call before it runs.
# What
- Parse `PreToolUse.additionalContext` and carry it through the hook
event pipeline.
- Record `PreToolUse` context at the hook boundary so successful context
is preserved for both allowed and blocked calls without widening the
tool registry surface.
- Preserve existing deny behavior when context is combined with either
`permissionDecision: "deny"` or the legacy `decision: "block"` shape.
## Why
Adding goal metrics makes it possible to track how often goals are
created, completed, and stopped by budget limits, plus the final token
and wall-clock usage for terminal outcomes.
## What Changed
- Added OpenTelemetry metric constants for goal lifecycle tracking:
- `codex.goal.created`: increments each time a new persisted goal is
created or an existing goal is replaced with a new objective.
- `codex.goal.completed`: increments when a goal transitions to
`complete`.
- `codex.goal.budget_limited`: increments when a goal transitions to
`budget_limited` because its token budget has been reached.
- `codex.goal.token_count`: records the final persisted token count when
a goal transitions to `complete` or `budget_limited`.
- `codex.goal.duration_s`: records the final persisted elapsed
wall-clock time, in seconds, when a goal transitions to `complete` or
`budget_limited`.
- Emitted creation metrics when a goal is created or replaced.
- Emitted terminal outcome counters and final usage histograms when a
goal transitions to `complete` or `budget_limited`, avoiding
double-counting later in-flight accounting for already budget-limited
goals.
- Added focused `codex-core` tests for create/complete metrics and
one-time budget-limit metrics.
## Why
`list_dir` still carries a full spec/handler/test path, but nothing in
the current model catalog advertises it via
`experimental_supported_tools`. That leaves us maintaining an
environment-backed tool surface that is effectively unused.
## What changed
- delete the `list_dir` handler and its tests from `codex-core`
- remove the `list_dir` spec builder, handler kind, and registry wiring
from `codex-tools`
- clean up the remaining internal README and registry tests so they no
longer mention the removed tool
## Why
The model list needs to carry display-ready service tier metadata so
clients can render tier choices with stable IDs, names, and
descriptions. A raw speed-tier string list is not enough for richer UI
copy or future tier labels.
## What changed
- Added `ModelServiceTier` to shared model metadata with string `id`,
`name`, and `description` fields.
- Added `service_tiers` to `ModelInfo` and `ModelPreset`, preserving
empty defaults for older cached model payloads.
- Exposed `serviceTiers` on app-server v2 `Model` responses and threaded
it through TUI app-server model conversion.
- Marked legacy `additional_speed_tiers` / `additionalSpeedTiers`
metadata as deprecated in source and generated schema output.
- Regenerated app-server protocol JSON schema and TypeScript fixtures,
including `ModelServiceTier.ts`.
## Verification
- Ran `just write-app-server-schema`.
- Did not run local tests per repo instruction; relying on PR CI.
---------
Co-authored-by: Codex <noreply@openai.com>
## Why
Large hook outputs can enter model-visible context through hook-specific
paths such as `additionalContext` and `Stop` continuation prompts.
Without a dedicated cap, one hook can inject a large blob directly into
conversation history instead of leaving a bounded preview for the model
and preserving the full text elsewhere.
## What
- spill hook text once it exceeds a fixed `2_500`-token budget,
preserving the full output on disk and leaving a head/tail preview plus
saved path in context
- add shared hook-output spilling under
`CODEX_HOME/hook_outputs/<thread_id>/<uuid>.txt`
- apply the cap to both `additionalContext`, `feedback_message`, and
`Stop` continuation fragments
Migrate token usage replay, rollback responses, and detached review
setup (a special case of forking) to be served from ThreadStore reads
rather direct rollout files.
- replay restored token usage from already-loaded `RolloutItem` history
instead of reopening `Thread.path`
- rebuild rollback responses from loaded `ThreadStore` snapshots and
history
- start detached reviews from store-backed parent history and stored
review-thread metadata
- remove obsolete app-server rollout-summary helper code that became
dead after the store-backed migration
- preserve response/notification ordering for resume, fork, rollback,
and detached review flows
- add integration test coverage for the affected paths
- Route `thread/metadata/update` through
`ThreadStore::update_thread_metadata`.
- Add `LocalThreadStore` git metadata patch support for set, partial
update, and clear semantics.
- Add some unit tests for the new thread store code
- Remove a lot of dead code/tests!
## Why
Tool families already disagree on what their existing `duration` fields
mean, so lifecycle latency should live on the shared item envelope
instead of being inferred from per-tool execution fields. Carrying that
envelope through app-server notifications gives downstream consumers one
reusable timing signal without pretending every tool has the same
execution semantics.
## What changed
- Adds `started_at_ms` to core `ItemStartedEvent` values and
`completed_at_ms` to core `ItemCompletedEvent` values.
- Populates those timestamps in the shared session lifecycle emitters,
so protocol-native items get timing without each producer tracking its
own clock state.
- Exposes `startedAtMs` on app-server `item/started` notifications and
`completedAtMs` on `item/completed` notifications.
- Maps the lifecycle timestamps through the app-server boundary while
leaving legacy-converted notifications nullable when no lifecycle
timestamp exists.
- Regenerates the app-server JSON schema and TypeScript fixtures for the
notification-envelope change and updates downstream fixtures that
construct those notifications directly.
- Extends the existing web-search and image-generation integration flows
to assert the new lifecycle timestamps on the native item events.
## Verification
- `cargo check -p codex-protocol -p codex-core -p
codex-app-server-protocol -p codex-app-server -p codex-tui -p codex-exec
-p codex-app-server-client`
- `cargo test -p codex-core --test all web_search_item_is_emitted`
- `cargo test -p codex-core --test all
image_generation_call_event_is_emitted`
- `cargo test -p codex-app-server-protocol`
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/20514).
* #18748
* #18747
* #17090
* #17089
* __->__ #20514
## Summary
Moves the WebRTC realtime sideband websocket join out of the voice start
critical path. Call creation still posts the SDP offer and session
config synchronously so the client gets the SDP answer, but the sideband
websocket now connects in the input task async and doesn't block
conversation state installation.
This lets the normal realtime input channels buffer text, handoff
output, and audio while the WebRTC sideband websocket is connecting. If
the sideband join fails while the conversation is still active, the task
sends a RealtimeEvent::Error through the existing events_tx / fanout
path.
To rephrase this:
* No longer blocked on sideband: the client can receive the SDP answer
earlier, set up the WebRTC peer connection, and let the media leg
progress while the sideband websocket joins.
* Still blocked on sideband: queued text, handoff output, and sideband
server events cannot flow until connect_webrtc_sideband(...).await
finishes and then run_realtime_input_task(...) starts
## Validation
- `env CODEX_SKIP_VENDORED_BWRAP=1 cargo test --manifest-path
codex-rs/Cargo.toml -p codex-core --test all
conversation_webrtc_start_posts_generated_session`
`CODEX_SKIP_VENDORED_BWRAP=1` is needed in this local environment
because `libcap.pc` is not installed for the vendored bubblewrap build.
## Testing
I tested this locally by running `cargo run -p codex-cli --bin codex --
--enable realtime_conversation` and invoking `/realtime`. Then, we get
logs emitted in `~/.codex/log/codex-tui.log`.
### Before the Change
Logging commit
(https://github.com/openai/codex/commit/c0299e6edf1222fa0c43c1796e4811976c26fecd)
```
2026-05-04T16:06:09.251956Z INFO session_loop{thread_id=019df3b9-e3d8-7271-b13a-b880119aa4c2}:submission_dispatch{otel.name="op.dispatch.realtime_conversation_start" submission.id="019df3bd-65df-7ee2-8125-1d6701fe39d2" codex.op="realtime_conversation_start"}: codex_core::realtime_conversation: starting realtime conversation
2026-05-04T16:06:09.251980Z INFO session_loop{thread_id=019df3b9-e3d8-7271-b13a-b880119aa4c2}:submission_dispatch{otel.name="op.dispatch.realtime_conversation_start" submission.id="019df3bd-65df-7ee2-8125-1d6701fe39d2" codex.op="realtime_conversation_start"}: codex_core::realtime_conversation: creating realtime call transport="webrtc"
2026-05-04T16:06:10.365722Z INFO session_loop{thread_id=019df3b9-e3d8-7271-b13a-b880119aa4c2}:submission_dispatch{otel.name="op.dispatch.realtime_conversation_start" submission.id="019df3bd-65df-7ee2-8125-1d6701fe39d2" codex.op="realtime_conversation_start"}: codex_core::realtime_conversation: realtime call created; sdp answer ready transport="webrtc" call_id=rtc_u0_Dbq65nhak5eLjQZ73yhAy elapsed_ms=1113 total_elapsed_ms=1113
2026-05-04T16:06:10.365843Z INFO session_loop{thread_id=019df3b9-e3d8-7271-b13a-b880119aa4c2}:submission_dispatch{otel.name="op.dispatch.realtime_conversation_start" submission.id="019df3bd-65df-7ee2-8125-1d6701fe39d2" codex.op="realtime_conversation_start"}: codex_core::realtime_conversation: connecting realtime sideband websocket call_id=rtc_u0_Dbq65nhak5eLjQZ73yhAy
2026-05-04T16:06:10.784528Z INFO session_loop{thread_id=019df3b9-e3d8-7271-b13a-b880119aa4c2}:submission_dispatch{otel.name="op.dispatch.realtime_conversation_start" submission.id="019df3bd-65df-7ee2-8125-1d6701fe39d2" codex.op="realtime_conversation_start"}: codex_core::realtime_conversation: connected realtime sideband websocket call_id=rtc_u0_Dbq65nhak5eLjQZ73yhAy elapsed_ms=418 total_elapsed_ms=1532
2026-05-04T16:06:10.784665Z INFO session_loop{thread_id=019df3b9-e3d8-7271-b13a-b880119aa4c2}:submission_dispatch{otel.name="op.dispatch.realtime_conversation_start" submission.id="019df3bd-65df-7ee2-8125-1d6701fe39d2" codex.op="realtime_conversation_start"}: codex_core::realtime_conversation: realtime conversation started
```
### After the Change
Logging commit
(https://github.com/openai/codex/commit/c8b00ac21adf4f8dd1fe3a81403a2bb6183fe13b)
```
2026-05-04T15:41:24.080363Z INFO ... codex_core::realtime_conversation: starting realtime conversation
2026-05-04T15:41:24.080434Z INFO ... codex_core::realtime_conversation: creating realtime call transport="webrtc"
2026-05-04T15:41:25.106906Z INFO ... codex_core::realtime_conversation: realtime call created; sdp answer ready transport="webrtc" call_id=rtc_u0_Dbpi8nhak5eLjQZ73yhAy elapsed_ms=1026 total_elapsed_ms=1026
2026-05-04T15:41:25.107067Z INFO ... codex_core::realtime_conversation: spawned realtime sideband connection task transport="webrtc" total_elapsed_ms=1026
2026-05-04T15:41:25.107160Z INFO ... codex_core::realtime_conversation: realtime conversation started
2026-05-04T15:41:25.107185Z INFO codex_core::realtime_conversation: connecting realtime sideband websocket call_id=rtc_u0_Dbpi8nhak5eLjQZ73yhAy
2026-05-04T15:41:25.107352Z INFO ... codex_core::realtime_conversation: sent realtime sdp answer to client
2026-05-04T15:41:26.076685Z INFO codex_core::realtime_conversation: connected realtime sideband websocket call_id=rtc_u0_Dbpi8nhak5eLjQZ73yhAy elapsed_ms=969 total_elapsed_ms=1996
2026-05-04T15:41:26.573893Z INFO codex_core::realtime_conversation: realtime session updated realtime_session_id=sess_u0_Dbpi8nhak5eLjQZ73yhAy
2026-05-04T15:41:26.573970Z INFO codex_core::realtime_conversation: received realtime conversation event event=SessionUpdated { ... }
```
### Conclusion
Here we see that we saved about a half a second in conversation startup
(1532ms -> 969ms). This also checks out with my sanity tests; I was
seeing at most a second of saving.
---------
Co-authored-by: Codex <noreply@openai.com>
## Why
The Bazel test coverage change exposed
`approved_folder_write_request_permissions_unblocks_later_apply_patch`,
and `rust-ci-full.yml` showed the same test failing on `main` on macOS.
There were two separate classes of problems here.
### Clean CI failure
The test emits an `apply_patch` tool call, but its config did not enable
the `apply_patch` tool, so the mocked response completed without an
`apply-patch-call` output. After enabling the tool, the same path also
needs the aggregate `codex-core` test binary to dispatch
`--codex-run-as-fs-helper`; sandboxed `apply_patch` uses that helper
under macOS Seatbelt.
The test now also canonicalizes the temporary patch target before
building the patch payload so the path matches normalized grants on
macOS, where `/var` paths often normalize to `/private/var`.
### Local/enterprise config isolation
The core test harness now builds its default test config with managed
config disabled, so host-managed enterprise config cannot alter these
tests. The request-permissions turns in this test also explicitly use
the user reviewer path, keeping the assertions focused on
`request_permissions` behavior rather than reviewer defaults from the
host.
## What Changed
- Enable `apply_patch` in
`approved_folder_write_request_permissions_unblocks_later_apply_patch`.
- Teach the core integration test binary to dispatch
`CODEX_FS_HELPER_ARG1`, matching the existing apply-patch and
linux-sandbox dispatch paths.
- Canonicalize the tempdir-backed patch target before creating the
patch.
- Ignore managed config in default core test configs and explicitly pin
this test to `ApprovalsReviewer::User`.
## Verification
Run outside the Codex app sandbox because these macOS tests
intentionally spawn Seatbelt:
- `cargo test -p codex-core
approved_folder_write_request_permissions_unblocks_later_apply_patch`
- `cargo test -p codex-core
approved_folder_write_request_permissions_unblocks_later_exec_without_sandbox_args`
## Why
Feedback reports do not currently surface a direct pointer to the last
model call, so investigations may require searching through many
requests in a session to find the bad response. Preserve the last
model-side IDs at response-stream time so immediate feedback reports
carry that breadcrumb.
## What changed
- Record `last_model_request_id` when a Responses stream exposes an
upstream request ID.
- Record `last_model_response_id` when the model response completes.
- Add unit coverage for the emitted feedback tags.
## Verification
- `cargo test -p codex-core
client::tests::response_stream_records_last_model_feedback_ids`
## Why
MCP servers can provide `instructions` that explain what their tools are
for. Directly exposed MCP namespaces already use those instructions when
a connector description is not available, but deferred `tool_search`
results did not preserve that fallback. The direct path falls back from
connector metadata to server instructions, while the deferred path only
carried `connector_description` and otherwise fell back to generic
namespace text.
That meant a plain MCP server could provide useful model-facing guidance
and still appear as `Tools in the X namespace.` whenever it was
discovered lazily through `tool_search`.
## What changed
- Store one model-facing `namespace_description` on `ToolInfo`, using
connector descriptions for connector-backed tools and server
instructions for plain MCP servers.
- Thread that namespace description through the `tool_search` source
list, search indexing, and returned namespace metadata.
- Add an end-to-end regression test for deferred non-app MCP search
results exposing server instructions as the namespace description.
## Verification
- `cargo test -p codex-tools
search_tool_description_lists_each_mcp_source_once --lib`
- `cargo test -p codex-core --test all
tool_search_uses_non_app_mcp_server_instructions_as_namespace_description`
## Summary
- normalize terminal-emitted C0 control characters through configurable
editor keymaps, covering raw control-key fallbacks like
Shift+Enter-as-LF in terminals from #20555 and #20898, plus part of the
modified-Enter behavior in #20580
- add default-unbound keymap actions for toggling Fast mode and killing
the current composer line, giving #20698 users a configurable zsh-style
Ctrl+U option without changing the existing default Ctrl+U behavior
- wire the new actions through gated /keymap picker entries, schema
generation, and snapshot coverage
Fixes#20555.
Fixes#20898.
## Testing
- just write-config-schema
- just fmt
- cargo test -p codex-config
- cargo test -p codex-tui keymap::tests
- cargo test -p codex-tui bottom_pane::textarea::tests
- cargo test -p codex-tui keymap_setup::tests
- cargo insta pending-snapshots
- just fix -p codex-tui
- git diff --check
- just argument-comment-lint
## Why
SQLite state was still being opened from consumer paths, including lazy
`OnceCell`-backed thread-store call sites. That let one process
construct multiple state DB connections for the same Codex home, which
makes SQLite lock contention and `database is locked` failures much
easier to hit.
State DB lifetime should be chosen by main-like entrypoints and tests,
then passed through explicitly. Consumers should use the supplied
`Option<StateDbHandle>` or `StateDbHandle` and keep their existing
filesystem fallback or error behavior when no handle is available.
The startup path also needs to keep the rollout crate in charge of
SQLite state initialization. Opening `codex_state::StateRuntime`
directly bypasses rollout metadata backfill, so entrypoints should
initialize through `codex_rollout::state_db` and receive a handle only
after required rollout backfills have completed.
## What Changed
- Initialize the state DB in main-like entrypoints for CLI, TUI,
app-server, exec, MCP server, and the thread-manager sample.
- Pass `Option<StateDbHandle>` through `ThreadManager`,
`LocalThreadStore`, app-server processors, TUI app wiring, rollout
listing/recording, personality migration, shell snapshot cleanup,
session-name lookup, and memory/device-key consumers.
- Remove the lazy local state DB wrapper from the thread store so
non-test consumers use only the supplied handle or their existing
fallback path.
- Make `codex_rollout::state_db::init` the local state startup path: it
opens/migrates SQLite, runs rollout metadata backfill when needed, waits
for concurrent backfill workers up to a bounded timeout, verifies
completion, and then returns the initialized handle.
- Keep optional/non-owning SQLite helpers, such as remote TUI local
reads, as open-only paths that do not run startup backfill.
- Switch app-server startup from direct
`codex_state::StateRuntime::init` to the rollout state initializer so
app-server cannot skip rollout backfill.
- Collapse split rollout lookup/list APIs so callers use the normal
methods with an optional state handle instead of `_with_state_db`
variants.
- Restore `getConversationSummary(ThreadId)` to delegate through
`ThreadStore::read_thread` instead of a LocalThreadStore-specific
rollout path special case.
- Keep DB-backed rollout path lookup keyed on the DB row and file
existence, without imposing the filesystem filename convention on
existing DB rows.
- Verify readable DB-backed rollout paths against `session_meta.id`
before returning them, so a stale SQLite row that points at another
thread's JSONL falls back to filesystem search and read-repairs the DB
row.
- Keep `debug prompt-input` filesystem-only so a one-off debug command
does not initialize or backfill SQLite state just to print prompt input.
- Keep goal-session test Codex homes alive only in the goal-specific
helper, rather than leaking tempdirs from the shared session test
helper.
- Update tests and call sites to pass explicit state handles where DB
behavior is expected and explicit `None` where filesystem-only behavior
is intended.
## Validation
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo check -p
codex-rollout -p codex-thread-store -p codex-app-server -p codex-core -p
codex-tui -p codex-exec -p codex-cli --tests`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-rollout state_db_`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-rollout find_thread_path`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-rollout find_thread_path -- --nocapture`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-rollout try_init_ -- --nocapture`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-rollout`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo clippy -p
codex-rollout --lib -- -D warnings`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-thread-store
read_thread_falls_back_when_sqlite_path_points_to_another_thread --
--nocapture`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-thread-store`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p codex-core
shell_snapshot`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p codex-core
--test all personality_migration`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p codex-core
--test all rollout_list_find`
- `RUST_MIN_STACK=8388608 CODEX_SKIP_VENDORED_BWRAP=1
CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p codex-core
--test all rollout_list_find::find_prefers_sqlite_path_by_id --
--nocapture`
- `RUST_MIN_STACK=8388608 CODEX_SKIP_VENDORED_BWRAP=1
CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p codex-core
--test all rollout_list_find -- --nocapture`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p codex-core
interrupt_accounts_active_goal_before_pausing`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-app-server get_auth_status -- --test-threads=1`
- `CODEX_SKIP_VENDORED_BWRAP=1
CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-app-server --lib`
- `CODEX_SKIP_VENDORED_BWRAP=1
CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo check -p codex-rollout
-p codex-app-server --tests`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db just fix -p codex-rollout
-p codex-thread-store -p codex-core -p codex-app-server -p codex-tui -p
codex-exec -p codex-cli`
- `CODEX_SKIP_VENDORED_BWRAP=1
CARGO_TARGET_DIR=/tmp/codex-target-state-db just fix -p codex-rollout -p
codex-app-server`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db just fix -p
codex-rollout`
- `CODEX_SKIP_VENDORED_BWRAP=1
CARGO_TARGET_DIR=/tmp/codex-target-state-db just fix -p codex-core`
- `just argument-comment-lint -p codex-core`
- `just argument-comment-lint -p codex-rollout`
Focused coverage added in `codex-rollout`:
- `recorder::tests::state_db_init_backfills_before_returning` verifies
the rollout metadata row exists before startup init returns.
- `state_db::tests::try_init_waits_for_concurrent_startup_backfill`
verifies startup waits for another worker to finish backfill instead of
disabling the handle for the process.
-
`state_db::tests::try_init_times_out_waiting_for_stuck_startup_backfill`
verifies startup does not hang indefinitely on a stuck backfill lease.
-
`tests::find_thread_path_accepts_existing_state_db_path_without_canonical_filename`
verifies DB-backed lookup accepts valid existing rollout paths even when
the filename does not include the thread UUID.
-
`tests::find_thread_path_falls_back_when_db_path_points_to_another_thread`
verifies DB-backed lookup ignores a stale row whose existing path
belongs to another thread and read-repairs the row after filesystem
fallback.
Focused coverage updated in `codex-core`:
- `rollout_list_find::find_prefers_sqlite_path_by_id` now uses a
DB-preferred rollout file with matching `session_meta.id`, so it still
verifies that valid SQLite paths win without depending on stale/empty
rollout contents.
`cargo test -p codex-app-server thread_list_respects_search_term_filter
-- --test-threads=1 --nocapture` was attempted locally but timed out
waiting for the app-server test harness `initialize` response before
reaching the changed thread-list code path.
`bazel test //codex-rs/thread-store:thread-store-unit-tests
--test_output=errors` was attempted locally after the thread-store fix,
but this container failed before target analysis while fetching `v8+`
through BuildBuddy/direct GitHub. The equivalent local crate coverage,
including `cargo test -p codex-thread-store`, passes.
A plain local `cargo check -p codex-rollout -p codex-app-server --tests`
also requires system `libcap.pc` for `codex-linux-sandbox`; the
follow-up app-server check above used `CODEX_SKIP_VENDORED_BWRAP=1` in
this container.
## Why
This is a prep PR in the multi-environment process-tool stack. It
separates ownership/config cleanup from the behavior change that teaches
process tools to route by selected environment, so the follow-up PR can
focus on model-facing `environment_id` behavior.
## Stack
1. https://github.com/openai/codex/pull/20646 - `EnvironmentContext`
rendering for selected environments
2. https://github.com/openai/codex/pull/20669 - selected-environment
ownership and tool config prep (this PR)
3. https://github.com/openai/codex/pull/20647 - process-tool
`environment_id` routing
## What Changed
- keep the resolved turn environment list wrapped in
`ResolvedTurnEnvironments` through `TurnContext` instead of unwrapping
it back to a raw `Vec`
- add `TurnContext::resolve_path_against` so cwd-relative path
resolution has one shared helper
- replace the old tool config boolean with `ToolEnvironmentMode::{None,
Single, Multiple}`
## Testing
- Tests not run locally; this prep refactor is covered by GitHub CI for
the stack.
Co-authored-by: Codex <noreply@openai.com>
## Summary
- Treat `approval_mode = "approve"` as skip-review across all permission
modes.
- Remove the mode-specific split in the MCP auto-approval gate so
approved tools bypass review consistently.
- Expand regression coverage in the shared MCP helper and the core
tool-call flow.
## Testing
- `just fmt`
- `cargo test -p codex-mcp`
- `cargo test -p codex-core
approve_mode_skips_arc_and_guardian_in_every_permission_mode`
- `git diff --check`
- Full `cargo test -p codex-core` was also attempted, but the suite hit
an unrelated pre-existing stack overflow in an existing multi-agent test
## Why
`ModelClientSession` and `compact_conversation_history()` were still
rebuilding the same `ResponsesApiRequest` fields separately. That
duplication makes it easy for normal `/responses` turns and compact
requests to drift when request-shape changes land later, which is
exactly the kind of cache-affecting divergence we want to avoid.
This follow-up keeps the scope small by extracting the shared
request-construction logic into one helper and using it from both paths.
## What changed
- move `ResponsesApiRequest` construction into a shared
`ModelClient::build_responses_request(...)` helper in
`core/src/client.rs`
- update the normal `/responses` streaming path to call that helper
instead of the old `ModelClientSession`-local implementation
- update `compact_conversation_history()` to derive its compact payload
from the same helper so `model`, `instructions`, `input`, `tools`,
`parallel_tool_calls`, `reasoning`, and `text` stay aligned with normal
request building
- add a unit test covering the shared helper's prompt cache key,
installation metadata, and `service_tier` behavior
## Verification
- `cargo test -p codex-core
build_responses_request_sets_shared_cache_and_metadata_fields`
- `cargo test -p codex-core --test all
remote_compact_v2_reuses_context_compaction_for_followups`
## Docs
No docs update needed.
## Summary
Early adopters of the `/goal` feature have provided feedback that they
expect a goal they explicitly paused to remain paused when they resume a
thread. Previously, resuming a thread would reactivate a paused goal.
This PR keeps persisted goal status unchanged during thread resume. This
honors the user feedback while also simplifying the core goal logic.
Rather than have the core logic automatically resume a paused goal, that
responsibility is transferred to the client. The TUI now detects a
resumed thread with a paused goal and asks the user whether to `Resume
goal` or `Leave paused`. The prompt appears only for quiet resume flows,
so users who resume with an immediate prompt are not interrupted.
<img width="544" height="111" alt="image"
src="https://github.com/user-attachments/assets/0ac9de1c-6ee6-47ba-b223-c03c8eb4c192"
/>
## Why
This adds the `remote_compaction_v2` client path so remote compaction
can run through the normal Responses stream and install a
`context_compaction` item that trigger a compaction.
The goal is to migrate some of the compaction logic on the client side
We keeps the v2 transport behind a feature flag while letting follow-up
requests reuse the compacted context instead of falling back to the
legacy compaction item shape.
## What changed
- add `ResponseItem::ContextCompaction` and refresh the generated
app-server / schema / TypeScript fixtures that expose response items on
the wire
- add `core/src/compact_remote_v2.rs` to send compaction through the
standard streamed Responses client, require exactly one
`context_compaction` output item, and install that item into compacted
history
- route manual compact and auto-compaction through the v2 path when
`remote_compaction_v2` is enabled, while keeping the existing remote
compaction path as the fallback
- preserve the new item type across history retention, follow-up request
construction, telemetry, rollout persistence, and rollout-trace
normalization
- add targeted coverage for the feature flag, `context_compaction`
serialization, rollout-trace normalization, and remote-compaction
follow-up behavior
## Verification
- added protocol tests for `context_compaction`
serialization/deserialization in `protocol/src/models.rs`
- added rollout-trace coverage for `context_compaction` normalization in
`rollout-trace/src/reducer/conversation_tests.rs`
- added remote compaction integration coverage for v2 follow-up reuse
and mixed compaction output streams in
`core/tests/suite/compact_remote.rs`
---------
Co-authored-by: Codex <noreply@openai.com>
## Why
`multi_agent_v2` usage hints sometimes need to reference resolved config
values such as the effective thread limit. Those values only exist after
config layering, defaulting, and feature materialization, so the raw
TOML alone was not enough to render them.
## What changed
- allow
`features.multi_agent_v2.{usage_hint_text,root_agent_usage_hint_text,subagent_usage_hint_text}`
to use `{{ ... }}` placeholders backed by the materialized effective
config
- fail config loading with a targeted error when a referenced
placeholder does not exist or does not resolve to a scalar value
- move resolved-config materialization into a shared helper so config
interpolation and config-lock export/replay both serialize the same
resolved feature, memory, and agent settings
## Example
```
[features.multi_agent_v2]
enabled = true
usage_hint_text = "lorem {{ features.multi_agent_v2.max_concurrent_threads_per_session }} ipsum"
```
gets rendered as
```
"description": String("... \lorem 4 ipsum"),
```
## Why
`McpToolCall` was still an app-server item synthesized from deprecated
legacy begin/end events. Recent item migrations moved this ownership
into core `TurnItem`s, so MCP tool calls now follow the same canonical
lifecycle and leave legacy events as compatibility fanout.
Keeping the core item close to the v2 `ThreadItem::McpToolCall` shape
also avoids spreading MCP result semantics across app-server conversion
code. Core now owns whether a completed call is `completed` or `failed`,
and whether the payload is a tool result or an error.
## What changed
- Added core `TurnItem::McpToolCall` with flattened `server`, `tool`,
`arguments`, `status`, `result`, and `error` fields.
- Updated MCP tool call emitters, including MCP resource tools, to emit
`ItemStarted`/`ItemCompleted` around directly constructed core MCP
items.
- Updated app-server v2 conversion to project the core MCP item into
`ThreadItem::McpToolCall` without deriving status or splitting `Result`
locally.
- Ignored live deprecated MCP legacy fanout in app-server v2 to avoid
duplicate item notifications, while keeping thread history replay on the
legacy event path.
## Verification
- `cargo test -p codex-protocol`
- `cargo test -p codex-app-server-protocol`
- `cargo test -p codex-core --lib mcp_tool_call`
- `cargo check -p codex-app-server`
- `cargo test -p codex-app-server
mcp_tool_call_completion_notification_contains_truncated_large_result`
Tool suggest still misfires when model needs tool_search, updating the
prompts to further disambiguate it:
- [x] rename it from `tool_suggest` to `request_plugin_install`
- [x] rephrase "suggestion" to "install" in the tool descriptions.
- [x] disambiguate "the tool" vs "the plugin/connector".
Tested with the Codex App and verified it still works.
## Why
The model needs a way to see which environments are available during a
multi-environment turn without changing the legacy single-environment
prompt surface or pulling replay/persistence changes into the same
review.
## Stack
1. https://github.com/openai/codex/pull/20646 - `EnvironmentContext`
rendering for selected environments (this PR)
2. https://github.com/openai/codex/pull/20669 - selected-environment
ownership and tool config prep
3. https://github.com/openai/codex/pull/20647 - process-tool
`environment_id` routing
## What Changed
- extend `environment_context` so multi-environment turns render an
`<environments>` block with the selected environment ids and cwd values
- keep zero- and single-environment turns on the existing cwd-only
render path
- keep replay and persistence paths on the legacy surface for now so
this PR stays scoped to live prompt rendering
- add focused coverage in
`codex-rs/core/src/context/environment_context_tests.rs`
## Testing
- CI
---------
Co-authored-by: Codex <noreply@openai.com>
Ahmed Ibrahim ·
jif-oai ·
Matthew Zeng ·
aaronl-openai ·
rhan-oai ·
pakrym-oai ·
mchen-oai ·
Michael Bolin ·
Tom ·
Rasmus Rygaard ·
Eric Traut ·
Felipe Coury ·
Abhinav ·
starr-openai ·
alexsong-oai ·
kmeelu-oai ·
charley-openai ·
sayan-oai ·
Ruslan Nigmatullin ·
Channing Conger ·