Codex forces `core.fsmonitor=false` on internal Git commands so a
repository cannot select an executable fsmonitor helper. This also
disables Git's built-in daemon for `status`, `diff`, and `ls-files`,
turning those worktree reads into full scans in large repositories.
Read the raw effective `core.fsmonitor` value and preserve it only when
Git interprets it as true and advertises built-in daemon support through
`git version --build-options`. Query uncommon boolean spellings back
through Git using the exact effective value. Unset, false, helper paths,
malformed values, probe failures, and unsupported Git builds continue to
force `core.fsmonitor=false`.
Centralize this policy in `git-utils` while keeping process execution in
the existing local and workspace-command adapters. Probe once per
worktree workflow and reuse the result for its Git commands, including
the TUI `/diff` path. Metadata-only commands and repository discovery
remain disabled without probing. Each probe and requested Git process
keeps its own existing timeout, and the decision is not cached because
layered and conditional Git configuration can change while Codex runs.
---------
Co-authored-by: Chris Bookholt <bookholt@openai.com>
## Why
`log_remote_compact_failure` was the only consumer of the
compact-request logging payload and most of the token-usage breakdown
fields. Once that failure log is removed, keeping the surrounding
carrier types leaves dead plumbing in the compaction path and context
manager.
## What changed
- Remove `log_remote_compact_failure`, `CompactRequestLogData`, and the
v2 wrapper that only fed that log.
- Let both remote compaction implementations return the original
compaction error directly.
- Replace `TotalTokenUsageBreakdown` with a narrow helper that returns
only the remaining value needed by compaction analytics.
- Keep `estimate_response_item_model_visible_bytes` private to the
context manager implementation.
## Validation
- `cargo check -p codex-core`
Fixes a TUI regression where thread transitions such as `/new` and
`/clear` could rebuild config without the cloud requirements loader,
allowing users to fall back to non-cloud-managed settings. The config
refresh path now preserves cloud requirements during thread
reinitialization, and config loading is moved off the deep TUI event
stack to avoid stack-overflow crashes during those reloads.
- Passes the cloud requirements loader through TUI config rebuild paths.
- Keeps cloud requirements applied for `/new`, `/clear`, `/fork`, side
conversations, and session picker transitions.
- Runs config building on a Tokio task so reloads do not occur on the
deep TUI caller stack.
- Adds regression coverage that cloud requirements survive
thread-transition config refreshes.
## Test/Repro:
- Start Codex with a cloud requirement applied.
- Use `/new` or `/clear`.
- The refreshed/fresh-session config should still include the cloud
requirements
This can be tested with any config item, at this moment for oai staff
the easiest item to test is the `mentions_v2` feature. This is currently
enabled in cloud requirements, but is not enabled by default. As a
result, prior to these changes that feature is disabled after `/new` or
`/clear`. Testing the same steps with a binary from this branch should
not drop the feature enablement.
## Summary
- Update the web search tool prompt to require Markdown links for cited
sources.
- Explicitly tell the model not to use `turnX`-style citations in
responses.
## Context
https://openai.slack.com/archives/C0AU83S0ZQU/p1780964147777649?thread_ts=1780352049.512299&cid=C0AU83S0ZQU
## Test plan
- `git diff --check`
- `python3 scripts/format.py --check` (fails only on Rust formatter
setup: rustup cannot create temp files under `/home/dev-user/.rustup`;
Just and Python formatter checks pass when using temp cache dirs)
## Summary
- Render `/debug-config`'s `allowed_sandbox_modes` from the finalized
permission constraints instead of the raw requirements list.
- Add regression coverage for configured full-access and external
sandbox modes being omitted when effective permissions reject them.
## Details
`allowed_sandbox_modes` comes from managed requirements, but the final
permissions can be further constrained by derived validation rules. For
example, `permissions.filesystem.deny_read` requires sandbox
enforcement, so modes that disable or externalize Codex's sandbox are
not actually usable even if they were present in the raw requirements
TOML.
The debug renderer now enumerates the configured sandbox-mode labels and
keeps only those accepted by `Config.permissions`. That makes
`/debug-config` reflect the same effective permission-profile constraint
path used by runtime config validation, while preserving the existing
source/provenance display.
## Validation
- Added a regression test for effective sandbox-mode filtering in
`/debug-config`.
## Background
Bare URLs containing `~` in their path are currently only clickable up
to the tilde in the interactive TUI. For example, Codex renders the
visible text for:
`https://www.cs.tufts.edu/~nr/cs257/archive/olin-shivers/dissertation.pdf`
but the OSC 8 destination stops at `https://www.cs.tufts.edu/`. This
makes Cmd-click open the wrong location even though the terminal
recognizes the complete URL outside Codex.
Fixes#26774.
## Root Cause
The URL scanner already accepts `~`. The truncation happens earlier:
with strikethrough parsing enabled, `pulldown-cmark` splits this URL
into adjacent decoded `Event::Text` values around the tilde. The
Markdown renderer annotated each text event independently, so only the
first event still looked like a complete URL with a supported scheme.
The renderer now merges adjacent decoded text events before URL
annotation. It preserves the combined source range while retaining
parser-decoded contents, which avoids regressing entities such as
`&`.
## Changes
- Add a small iterator that merges adjacent decoded Markdown text events
and their source ranges.
- Apply it at the Markdown renderer boundary before hyperlink detection.
- Add regression coverage for the reported URL in prose, wrapped table
output, and entity-decoded URLs.
## How to Test
1. Run Codex with `just c`.
2. Ask the assistant to output this exact bare URL with no Markdown link
syntax:
`https://www.cs.tufts.edu/~nr/cs257/archive/olin-shivers/dissertation.pdf`
3. Hold Cmd and hover or click the URL.
4. Confirm the complete URL, including the suffix after `~`, is one
destination.
5. Repeat with the URL inside a Markdown table and confirm wrapped
portions retain the same complete destination.
Targeted tests:
- `just test -p codex-tui url_with_tilde`
- `just test -p codex-tui merged_text_events_preserve_entity_decoding`
The full `codex-tui` test run was also executed. Its only failures were
the two existing Guardian feature-flag tests:
-
`app::tests::update_feature_flags_disabling_guardian_clears_review_policy_and_restores_default`
-
`app::tests::update_feature_flags_disabling_guardian_clears_manual_review_policy_without_history`
## Why
Codex needs stable `file:` URI identifiers that can cross process and
operating-system boundaries without eagerly interpreting them as native
paths. Existing fields also need to keep accepting absolute path strings
during migration.
## What changed
- Add `codex-utils-path-uri` with a validated, immutable `PathUri`
wrapper that currently accepts only `file:` URLs.
- Expose URI-level `basename`, `parent`, and `join` operations that
preserve authorities and percent encoding without guessing the source
operating system.
- Keep native conversion explicit through `AbsolutePathBuf` and the
current host rules.
- Serialize as canonical URI text while accepting both URI text and
legacy absolute native paths during deserialization.
- Add adversarial coverage for Windows-looking and POSIX paths, UNC
authorities, encoded metadata characters, non-UTF-8 POSIX paths, URI
hierarchy operations, and legacy serde round trips.
## Summary
Some customer MCP tools expose large input schemas that exceed Codex's
compact schema budget even after description stripping. Today, the final
compaction pass collapses complex schemas starting at depth 2, which can
erase important shallow call structure such as small `anyOf` branches,
required fields, and help-mode entry points. In one reported case, this
degraded a tool schema into `query: any | any`, leaving the model
without enough structure to discover the required help call.
This change raises the deep-schema collapse boundary from depth 2 to
depth 3. That preserves one additional layer of the tool contract while
still collapsing deeper expensive subtrees to `{}` when a schema remains
over budget.
## What Changed
- Increased `MAX_COMPACT_TOOL_SCHEMA_DEPTH` from `2` to `3`.
- Updated the schema compaction traversal test to assert the new
collapse boundary.
- The resulting compacted shape keeps useful shallow structure, for
example:
- top-level argument names
- shallow `anyOf` branches
- required object fields
- nested property names one level deeper than before
## Validation
- Ran `just test -p codex-tools`: 81 tests passed.
- Ran a golden schema corpus comparison over 214 discovered tool input
schemas under `golden_schemas/*/mcp_tools/*/input_schema.json`.
- Depth 2 and depth 3 had identical percentile token counts across the
corpus.
- Both ended with `0 / 214` schemas over 1k tokens.
- Both ended with `0 / 214` schemas over the 4,000-byte compact JSON
budget.
- Only one golden schema changed, increasing from 49 to 56 tokens, so
this does not appear to introduce a meaningful corpus-wide regression.
Corpus percentile results:
| Percentile | Depth 2 | Depth 3 |
|---|---:|---:|
| p0 | 9 | 9 |
| p10 | 31 | 31 |
| p25 | 54 | 54 |
| p50 | 81 | 81 |
| p75 | 143 | 143 |
| p90 | 290 | 290 |
| p95 | 431 | 431 |
| p99 | 600 | 600 |
| max | 832 | 832 |
## Background
This was prompted by
[#26858](https://github.com/openai/codex/issues/26858), where the
attached doctor report did not include the editor selection and I had to
[ask which editor was in
use](https://github.com/openai/codex/issues/26858#issuecomment-4653829891)
before investigating the external-editor newline issue. Capturing these
variables in doctor makes that context available up front in future
reports.
`codex doctor` is intended to capture enough local context to diagnose
startup and terminal behavior, but it did not report the environment
variables that select an external editor or configure command pagers.
The TUI [prefers `VISUAL` over
`EDITOR`](https://github.com/openai/codex/blob/56554904babcaacf4444a2cc90716880837dff7c/codex-rs/tui/src/external_editor.rs#L31-L38),
so missing or unexpected values can explain why the external-editor
shortcut fails or launches the wrong command. Pager values are also
useful inherited-shell context even though [unified exec normalizes its
effective pager variables to
`cat`](https://github.com/openai/codex/blob/56554904babcaacf4444a2cc90716880837dff7c/codex-rs/core/src/unified_exec/process_manager.rs#L60-L70).
These variables can contain arbitrary command arguments or inline
environment assignments. The human report is local, but `codex doctor
--json` may be attached to feedback, so the machine-readable report
should not include their raw contents.
## What Changed
- Report `VISUAL` and `EDITOR` in the system environment details, using
`not set` when either variable is absent.
- Report inherited `PAGER`, `GIT_PAGER`, `GH_PAGER`, and `LESS` values
when present.
- Preserve full values in local human output while reducing these fields
to `set` or `not set` in redacted JSON output.
- Add structured check, JSON-redaction, rendered-output, and snapshot
coverage.
## How to Test
1. From `codex-rs`, run Codex with explicit editor and pager variables:
```sh
env VISUAL='code --wait' EDITOR=vim PAGER='less -R' GIT_PAGER=delta
GH_PAGER=less LESS=-FRX \
cargo run -p codex-cli --bin codex -- doctor --no-color
```
2. Confirm the `system` details show the full values for all six
variables.
3. Unset the pager variables and rerun the command. Confirm pager rows
are omitted while missing editor variables are shown as `not set`.
4. Run the same configured environment with `doctor --json`. Confirm
each configured editor or pager field is reported as `set` and none of
the raw commands or arguments appear in the JSON.
Targeted tests:
- `just test -p codex-cli` (279 tests passed)
## Why
Metric descriptions should be declared with reusable OTEL instruments
instead of being coupled to individual consumers. Counter descriptions
are the smallest API primitive needed by the exec-server observability
work.
## What changed
- Adds `counter_with_description` while preserving the existing counter
API.
- Caches counters by name and description so instrument metadata remains
part of the declaration identity.
- Covers the exported description together with the existing value and
attribute contract.
This PR only adds counter descriptions. It does not add gauges,
second-based durations, or exec-server adoption.
## Stack
1. **#26091: counter descriptions**
2. #27057: gauge instruments
3. #27058: second-based duration histograms
Related independent coverage: #27059 tests OTLP HTTP log and trace event
export.
The `codex-exec-server` bounded service tag now stays with the
exec-server adoption change instead of this reusable infrastructure
stack.
## Validation
- `just test -p codex-otel`
- `just fix -p codex-otel`
- `just fmt`
## Summary
This changes the default remote plugin marketplace listing to use the
cached global remote catalog when it is already present on disk. The
foreground `plugin/list` response can then return from the local catalog
cache instead of waiting on `/ps/plugins/list`.
When a cached global catalog was present at the start of the request,
`plugin/list` still schedules a background refresh through the existing
plugin-list background task path so the disk cache is updated for future
requests. Cache misses keep the existing synchronous remote fetch path
and write the cache, and they do not schedule an extra duplicate
background `/ps/plugins/list` refresh.
Installed/enabled state continues to come from the existing remote
installed overlay path. This change only affects the global remote
catalog directory data used by `plugin/list`.
## Testing
- `just fmt`
- `just test -p codex-app-server
plugin_list_uses_cached_global_remote_catalog_and_refreshes_it`
- `just test -p codex-core-plugins`
- `git diff --check`
Curated plugin startup refresh now removes cached plugins whose names no
longer appear in the raw openai-curated marketplace. This prevents users
with the old standalone Google Sheets plugin selected locally from
continuing to load its stale cache after the curated repo drops it.
Existing config is left untouched, and plugins still present in the
marketplace continue to refresh from local curated sources.
Validation:
- `just fmt`
- `just test -p codex-core-plugins`
- `git diff --check`
## Why
Some connector golden schemas use JSON Schema composition keywords
beyond `anyOf`, specifically top-level or nested `oneOf` and `allOf`.
Codex currently needs to preserve those shapes when parsing MCP tool
input schemas so connector tools do not lose valid schema structure
during normalization.
To prevent an increased Responses API error rate, this PR will be merged
after the Responses API supports top-level `oneOf`/`allOf`.
## What Changed
- Adds `oneOf` and `allOf` support to `JsonSchema`, matching the
existing `anyOf` handling.
- Traverses `oneOf` and `allOf` anywhere schema children are visited,
including sanitization, definition reachability, description stripping,
and deep schema compaction.
- Adds a final large-schema compaction pass that prunes schema objects
containing `anyOf`, `oneOf`, or `allOf` to `{}` if earlier compaction
passes still leave the schema over budget.
## Validation
Golden schema token validation over `2,025` schemas under
`golden_schemas`, all parsed successfully. Token count is `o200k_base`
over compact JSON from `parse_tool_input_schema`.
| Percentile | Before PR | After oneOf/allOf | After pruning |
|---|---:|---:|---:|
| p0 | 9 | 9 | 9 |
| p10 | 63 | 64 | 64 |
| p25 | 86 | 87 | 87 |
| p50 | 125 | 128 | 128 |
| p75 | 203 | 206 | 206 |
| p90 | 327 | 333 | 333 |
| p95 | 460 | 473 | 473 |
| p99 | 763 | 779 | 779 |
| max | 891 | 955 | 955 |
Totals:
| Parser state | Total tokens |
|---|---:|
| Before PR | 345,713 |
| After oneOf/allOf | 352,686 |
| After pruning | 352,686 |
The pruning column matches the oneOf/allOf column for this corpus
because no parsed compact golden schema remains over the `4,000`
compact-byte budget after the earlier compaction passes.
## Summary
- require the main agent to read selected `SKILL.md` files completely,
continuing truncated or paginated reads through EOF
- require the main agent to personally read task-required instruction
references instead of delegating their interpretation
- clarify that progressive disclosure selects relevant files without
permitting partial reads
- preserve subagent use for task work when the selected skill allows it
- cover both absolute-path and aliased-root prompt variants
## Why
Partial reads can skip routing and verification requirements later in
skill instructions. Delegated summaries can also omit constraints the
main agent needs to follow. The existing "Read only enough" wording made
both behaviors appear acceptable.
## Impact
Agents should follow complete selected skill instructions while
continuing to avoid unrelated references, scripts, and assets. Subagents
remain available for task execution where permitted.
## Test plan
- `just test -p codex-core-skills` (101 passed)
- `just fmt`
- `git diff --check`
## Summary
- stop emitting `codex_error_subreason` on `codex_turn_event`
- remove the transient analytics fact plumbing that copied
`CodexErr::InvalidRequest(String)` into the event
- update analytics serialization coverage accordingly
## Why
`codex_error_subreason` is a free-form copy of `InvalidRequest(String)`,
including raw provider 400 bodies in some paths. That makes it unsafe as
an analytics field because it can carry user-derived or sensitive text.
## Validation
- `just fmt`
- `just test -p codex-analytics`
## Why
Image edits should use the exact images selected by the model instead of
inferring edit inputs from conversation history.
## What changed
- Replaced the image tool's `action` argument with optional
`referenced_image_paths`.
- Treats omitted or empty references as generation and populated
references as editing.
- Reads referenced absolute image paths and packages them as image data
URLs for the edit request.
- Removed the previous history-selection and image-count heuristics.
- Updated direct and code-mode tool instructions and calls.
- Added an app-server integration test covering an attached image routed
to the image edit endpoint.
## Validation
- Tested end-to-end on local `just codex` with copy pasted image,
attached image, etc.
- `just test -p codex-image-generation-extension`
- `just test -p codex-app-server
standalone_image_edit_uses_attached_model_visible_image`
- `just fix -p codex-image-generation-extension`
- `just bazel-lock-check`
## Why
`codex sandbox` can start a network proxy from a configured permission
profile. Previously, sandbox-level containment was tied to managed
network requirements rather than whether a proxy was actually active.
This meant config-driven proxy policies were not consistently enforced
as the sandbox's only network path.
## What changed
- Enable proxy-only network containment whenever `codex sandbox` starts
a network proxy.
- Apply the same active-proxy check to the macOS and Linux sandbox
paths.
- Add a Linux regression test that verifies a sandboxed command cannot
establish a direct connection while the configured proxy is active.
## Test plan
- `just test -p codex-cli debug_sandbox::tests`
- `sandbox_with_network_proxy_blocks_direct_loopback_access` runs on
Linux to cover the config-driven proxy path end to end.
## Why
`codex sandbox --permissions-profile` is useful when running commands
under a named permissions profile, but the long option is cumbersome for
a debugging-oriented command. `-p` is already used for the config
profile selector, so `-P` gives the permissions profile selector a
compact, non-conflicting alias.
## What Changed
- Added `short = 'P'` to the `permissions_profile` option for the macOS,
Linux, and Windows sandbox command structs in
[`codex-rs/cli/src/lib.rs`](https://github.com/openai/codex/blob/6d9f9c5cdcaa0a156aa2dabbde259ae5e9e8bc0b/codex-rs/cli/src/lib.rs#L29-L112).
- Added parser coverage for `codex sandbox -P :workspace -- echo` in
[`codex-rs/cli/src/main.rs`](https://github.com/openai/codex/blob/6d9f9c5cdcaa0a156aa2dabbde259ae5e9e8bc0b/codex-rs/cli/src/main.rs#L2883-L2896).
## Verification
- `just test -p codex-cli` passed, including the new
`sandbox_parses_permissions_profile_short_alias` parser test.
## Why
Thread cwd and environment selections are a single logical setting in
core: updating one without the other can silently desynchronize the
next-turn execution context. This change makes that relationship
explicit in the internal thread settings flow while preserving the
existing app-server public API shape.
## What changed
- Moved the cwd/environment pair through internal
`ThreadSettingsOverrides.environment_settings` instead of a top-level
internal `cwd` field.
- Kept `thread/settings/update` public params unchanged, with app-server
translating top-level `cwd` into the paired internal settings shape.
- Moved `Op::UserInput` environment overrides into thread settings so
user turns and settings updates use the same core path.
- Updated core, app-server, MCP, memories, sample, and test callsites to
construct the paired settings shape.
## Verification
- `git diff --check`
- Local test run starting after PR creation.
## Summary
- tighten the default multi-agent v2 root and subagent usage hints to
bias toward local work
- add a pre-call gate to the v2 spawn_agent description for independent,
bounded, parallelizable subtasks
## Validation
- just fmt
- started just test -p codex-core, but it was interrupted before
completion per follow-up request to commit and push immediately
## Why
Auto Review should remain the effective approval reviewer when settings
cross runtime boundaries. A config or app-server round trip must not
change the reviewer identity, and delegated work must not silently fall
back to user review.
This requires both a stable canonical serialized value and propagation
of the effective setting. `auto_review` is the canonical value across
protocol and app-server output, while `guardian_subagent` remains
accepted as backward-compatible input.
## What changed
- serialize `ApprovalsReviewer::AutoReview` consistently as
`auto_review` across core protocol and app-server v2
- continue accepting `guardian_subagent` when reading existing config or
client requests
- carry the active turn's approval reviewer into spawned agents
- update config/debug expectations and add delegated-task regression
coverage
## Scope
This does not change Guardian policy or remove compatibility with
existing `guardian_subagent` inputs. It preserves the selected reviewer
across serialization, config reloads, app-server settings, and delegated
task setup.
Related Guardian changes are split independently:
- #26231 adds denials and soft denials
- #26334 retries transient reviewer failures
- #26333 reuses narrowly scoped low-risk approvals
- #26232 adds TUI denial recovery
## Validation
- `just test -p codex-app-server-protocol` (224 passed)
- regression coverage for delegated task reviewer propagation
- serialization coverage for canonical `auto_review` output and legacy
`guardian_subagent` input
---------
Co-authored-by: saud-oai <saud@openai.com>
## Why
Importing large external-agent session histories currently starts a full
live Codex thread for every imported session. This initializes unrelated
runtime systems and repeats expensive transcript, metadata, hashing, and
ledger work.
On a 50-session, 238 MiB fixture, the existing path took roughly 70
seconds to complete the import and 77 seconds end to end.
## What changed
- Persist imported sessions directly through `ThreadStore` instead of
starting full live threads.
- Process imports through a bounded five-session pipeline.
- Parse, extract, and hash each source file in one pass.
- Move blocking source preparation onto the blocking thread pool.
- Reuse prepared content hashes and update the import ledger once per
batch.
- Avoid metadata readback for newly written rollouts.
- Preserve imported conversation history and visible thread metadata.
- Keep the implementation out of `codex-core` and avoid changes to the
public `ThreadStore` trait.
## Performance
For the same 50-session, 238 MiB fixture:
| Path | Import completion | End to end |
| --- | ---: | ---: |
| Existing import | 69.61s | 76.62s |
| This change | 5.95s | 6.58s |
All 50 sessions imported successfully with no warnings or contention
signals.
## Validation
- `just test -p codex-external-agent-sessions`
- `just test -p codex-app-server external_agent_config_import`
- Verified imports do not initialize unrelated required MCP servers.
- Verified previously imported source versions are skipped and changed
sources can be imported again.
- Verified imported rollouts remain readable through thread listing and
history APIs.
## Why
Compaction analytics adds retained image count and compaction summary
output tokens for v1.5 specifically.
## What changed
- Add nullable `retained_image_count` and `compaction_summary_tokens`
fields to `codex_compaction_event`.
- Populate them only for `responses_compaction_v2`: retained images come
from the retained v2 compacted history, and summary tokens come from
`response.completed.token_usage.output_tokens`.
- Leave local and legacy remote compaction events as `null` for these
detail fields.
## Verification
- `just fmt`
- `just fix -p codex-core`
- `just test -p codex-core
build_v2_compacted_history_counts_retained_input_images`
- `git diff --check`
## Summary
- Keep the existing `x-codex-window-id` HTTP header unchanged.
- Also send the same window ID in Responses `client_metadata`, allowing
supported backend paths to surface it as
`x-client-meta-x-codex-window-id`.
- Cover normal HTTP Responses and remote compaction v2 requests without
changing window generation or compaction behavior.
## Why
In the `2026-06-06T23` production hour, all 28,729 HTTP compaction
requests had `window_id` in `x-codex-turn-metadata`, but only 73
retained the direct `x-codex-window-id` header. The request-body
`client_metadata` path is already used for installation ID and is
preserved through supported Responses API paths.
This is additive metadata only. It does not change the direct header,
request count, model input, compaction routing, window generation, or
user response behavior.
Legacy `/v1/responses/compact` is intentionally unchanged. Its current
server-side `CompressBody` schema does not accept `client_metadata` and
rejects unknown fields, so supporting that path requires a backend
schema change before the Codex client can safely send this field.
## Validation
- Current head: `219baef3c`, rebased onto `origin/main` at `26d932983`.
- The post-rebase diff remains limited to the original five files (`22`
insertions, `6` deletions); the legacy experiment remains fully
reverted.
- `just test -p codex-core
responses_stream_includes_subagent_header_on_review`: passed; validates
normal HTTP Responses metadata.
- `just test -p codex-core
remote_compact_v2_reuses_compaction_trigger_for_followups`: passed;
validates remote compaction v2.
- `just test -p codex-core
remote_manual_compact_chatgpt_auth_reuses_service_tier_and_prompt_cache_key`:
passed; validates that legacy compact keeps its accepted payload shape.
- `just test -p codex-core
remote_manual_compact_api_auth_omits_service_tier_and_reuses_prompt_cache_key`:
passed; validates the legacy API-key payload as well.
- `just fmt`: passed; an unrelated root `justfile` rewrite produced by
the formatter was discarded.
- `git diff --check origin/main...HEAD`: passed.
The focused server pytest could not start in the local monorepo
environment because test setup is missing the `dotenv` module. Server
source and tests explicitly show that `CompressBody` omits
`client_metadata` and `/v1/responses/compact` returns HTTP 400 for
unknown body fields.
## Why
Remote-control app-server sessions can reconnect every 5-7 seconds when
the shared transport-event queue fills. The queue's consumer handled
`ConnectionClosed` by awaiting all in-flight RPCs for the disconnected
connection. A stuck RPC therefore blocked processing of replacement
connection and initialize events until remote-control forwarding hit its
five-second timeout and reconnected again.
Related issue: N/A (internal remote-control incident investigation).
## What Changed
- Split fast RPC admission closure from draining:
`ConnectionRpcGate::close()` rejects queued and future RPCs, while
`shutdown()` continues waiting for RPCs that already started.
- Close a disconnected connection's RPC gate before spawning the
existing RPC drain and resource cleanup in a tracked background task, so
the transport-event consumer remains available without waiting for
active RPCs.
- Reap completed cleanup tasks during normal operation, drain them
during graceful shutdown, and abort them during forced shutdown.
- Add regression coverage for closing with an active RPC, rejecting
post-close requests without polling them, and preserving the existing
shutdown wait behavior.
## Verification
`just test -p codex-app-server --lib connection_rpc_gate` passes all 6
tests, including the new close-versus-drain regression coverage.
## Summary
- Restore separate release symbol archives for macOS, Linux, and Windows
binaries.
- Build release binaries with `line-tables-only` debuginfo instead of
full debuginfo.
- Strip Unix distribution binaries after extracting symbols, preserve
Windows PDBs, and keep symbol archives available to the release job.
- Strip the packaged Linux `bwrap` binary before hashing it so the
embedded digest matches the distributed bytes.
## Root cause
The first symbol-artifact implementation enabled
`CARGO_PROFILE_RELEASE_DEBUG=full`. In the June 2 release runs, macOS
ARM primary builds reached the 90-minute timeout while still inside
`Cargo build`. After the symbol changes were reverted, the same primary
build completed in about 22 minutes. The archive step itself completed
in tens of seconds when reached.
Rust's `line-tables-only` debuginfo level preserves function names and
source locations for symbolication without emitting the heavier variable
and type information from full debuginfo.
## Validation
- Ran `just fmt` from `codex-rs`.
- Ran `just test-github-scripts` from the repository root: 23 tests
passed.
- Ran `bash -n` and `shellcheck` on
`.github/scripts/archive-release-symbols-and-strip-binaries.sh`.
- Parsed both modified workflows as YAML and ran `git diff --check`.
- Built a macOS release smoke binary with `line-tables-only`, archived
its dSYM through the restored script, stripped the production binary,
and verified that `atos` resolves `symbol_smoke_function` to
`main.rs:2`.
- Ran Linux archive-script control-flow coverage with stubbed `objcopy`
and `strip` commands.
- Ran Windows PDB archive staging coverage and verified
underscore-emitted Rust PDB names are staged under shipped hyphenated
binary names.
## Follow-up
The release workflow only runs for tags or manual dispatches, so CI
cannot dry-run the full release matrix on this PR. The next release run
will verify runner time and memory behavior under `line-tables-only`.
## Summary
- add contains_external_context() to tool output so other tools can be
opted out of influencing memory when disable_on_external_context=true
- Classify standalone web-search output as external context (to match
behavior as hosted web search)
- Verify with integration test
## Why
Multi-agent v2 residency is intended to keep only the threads that need
to be live. The existing rollout resume path still walked persisted open
descendants and reopened the entire descendant tree when resuming a v2
root, which turns resume into an eager reload of work that should stay
unloaded until it is explicitly needed.
The interrupted-agent path has a related residency issue. Interrupted
agents remain open by design, so an idle interrupted resident should be
eligible for eviction just like an idle completed or errored resident.
Otherwise a resident set full of interrupted agents can consume every v2
slot and block later spawns or reloads with `AgentLimitReached`.
## What Changed
- Return early from `resume_agent_from_rollout` after resuming a v2
thread so persisted v2 descendants are not reopened eagerly.
- Treat idle `Interrupted` v2 residents as unloadable in the LRU
residency path.
- Add focused coverage for v2 root resume leaving descendants unloaded
and for eviction of an idle interrupted v2 resident when a new slot is
needed.
## Verification
Added targeted `codex-core` tests covering:
- v2 root resume with persisted descendants, verifying only the root is
loaded after resume.
- residency eviction of an idle interrupted v2 agent when the resident
set is full.
## Why
`close_agent` is the wrong model-facing name for the v2 operation after
the residency changes. V2 agents remain reusable by task name, and
residency/unloading owns capacity management; the exposed tool should
describe the action it actually performs: interrupt the target agent's
current turn without making the agent unavailable for future messages or
follow-up tasks.
## What changed
- Rename the multi-agent v2 tool from `close_agent` to
`interrupt_agent`.
- Keep the v1 `close_agent` surface unchanged.
- Update the v2 handler to send `Op::Interrupt`, keep interrupted agents
registered, and reject root/self targets with interrupt-specific errors.
- Route interrupt delivery through the existing dead-thread cleanup path
so stale resident entries do not keep consuming capacity.
- Update tool planning and handler tests for the new v2 surface and
semantics.
## Verification
Added focused coverage in:
- `core/src/tools/spec_plan_tests.rs`
- `core/src/tools/handlers/multi_agents_tests.rs`
## Why
Multi-Agent V2 concurrency should count active non-root turns, not
resident or durable agent threads. The limit is intentionally best
effort: admission checks are synchronous, but concurrent successful
checks may overshoot slightly.
## What changed
- Keep one root-derived execution limit on the shared `AgentControl`.
- Count active V2 subagent turns with an RAII guard owned by
`RunningTask`.
- Check capacity before spawning or starting an idle agent, including
direct app-server `turn/start` submissions.
- Preserve queued delivery for agents that are already running.
- Exempt automatic idle continuations so `/goal` work is not dropped
when capacity is temporarily full.
- Keep root and V1 turns outside this limiter.
## Test coverage
- `execution_guards_count_active_v2_subagent_turns`
- `execution_guards_ignore_root_and_v1_turns`
- `v2_nested_spawn_checks_shared_active_execution_capacity`
## Summary
- ignore RUSTSEC-2026-0173 in cargo-deny and cargo-audit config
- document that proc-macro-error2 is pulled in transitively via
i18n-embed-fl/age/codex-secrets
- leave the ignore temporary until codex-secrets moves off age or age
drops i18n-embed-fl
## Validation
- just fmt
- cargo deny check --hide-inclusion-graph
## Why
Multi-agent v2 treats agents as durable logical agents, not just live
entries in `ThreadManager`. After the reload-on-delivery change, a v2
agent can be addressed even if its thread is not currently loaded.
This PR adds the next layer: loaded v2 subagents can be paged out of
`ThreadManager` when the session has too many resident agents. That
keeps residency separate from logical identity and prepares the stack
for making v2 concurrency count active execution instead of existing
agents.
## What Changed
- Add an `AgentControl`-scoped LRU for resident v2 subagents.
- Reserve residency before spawning or reloading a v2 subagent.
- If resident capacity is full, unload the least-recently-used idle v2
subagent from `ThreadManager`.
- Keep `ThreadManager` as a primitive loaded-thread store; it does not
own the LRU policy.
- Keep unloaded agents registered and durable so they can be reloaded by
the delivery path.
- Preserve the existing v2 cap semantics by using the derived non-root
v2 cap for residency.
Eviction is intentionally conservative. A thread is unloadable only when
it is a v2 subagent, has completed or errored, has no active turn, and
has no pending mailbox work. Before removal, the rollout is materialized
and flushed.
## Assumptions And Non-Goals
- PR #26623 provides the reload-on-delivery path for unloaded v2 agents.
- `ThreadManager` membership means loaded/resident, not logical agent
existence.
- `AgentRegistry` remains the logical identity/metadata source for v2
agents that may be unloaded.
- `list_agents` remains a recent/resident view for now.
- This does not change active execution concurrency; that is the next
PR.
- This does not change `close_agent` semantics.
- This does not change or remove `resume_agent`.
- This does not add a new residency config knob.
## Stack
1. V2 durable lookup and reload on delivery (#26623) - reload unloaded
v2 agents before delivering follow-up/input.
2. V2 residency LRU (this PR) - unload idle resident v2 agents from
`ThreadManager` when resident capacity is full.
3. V2 active-execution concurrency - count running non-root v2 turns
instead of logical agents.
4. V2 close/interrupt semantics - make v2 close interrupt the current
turn without deleting durable identity.
5. V2 resume cleanup - remove the manual resume surface for v2 while
keeping internal reload support.
## Validation
- Added focused coverage for the residency LRU eviction path.
- Local clippy/check/tests were not run; CI will cover them.
## What
- Consume plaintext `output` from standalone search while retaining
optional `encrypted_output` parsing.
- Expose `web.run` to code mode and return search output to nested
JavaScript calls.
- Cover direct and code-mode standalone search paths with integration
tests.
## Why
`/v1/alpha/search` now returns plaintext output, which code mode needs
to consume standalone search results.
## Test plan
- `just test -p codex-api`
- `just test -p codex-web-search-extension`
- `just test -p codex-core code_mode_can_call_standalone_web_search`
- `just test -p codex-app-server
standalone_web_search_round_trips_output`
## Why
MCP startup failures from spawned subagents were rendered as global
notifications, so a child thread's failure could pollute the visible
parent transcript. Routing the notification to the child exposed two
related replay problems: session refresh could discard the buffered
event, and a newly created child `ChatWidget` did not know the expected
MCP server set, which could leave its startup spinner running after
every server had settled.
MCP startup diagnostics should remain visible in the thread that owns
the startup without affecting other transcripts. The protocol also needs
to support a future app-scoped MCP lifecycle where startup is not owned
by any thread.
## Reported Behavior
The [originating Slack
report](https://openai.slack.com/archives/C08JZTV654K/p1780604538859939)
called out that using subagents could turn MCP startup failures into a
wall of yellow CLI warnings because repeated failures were not
deduplicated. The intended behavior is for those diagnostics to remain
visible once in the thread that owns the startup, without polluting the
parent transcript.
## What Changed
- add nullable `threadId` ownership to `mcpServer/startupStatus/updated`
- populate it from the app-server conversation ID for the current
thread-scoped lifecycle and regenerate the protocol schema and
TypeScript artifacts
- treat a missing or null `threadId` as app-scoped without injecting it
into the active chat transcript
- route and buffer thread-owned MCP startup notifications by thread in
the TUI
- preserve buffered MCP startup events across child session refresh
- seed expected MCP servers before replaying a thread snapshot so
startup reaches its terminal state
- suppress an identical repeated failure warning for the same server
within one startup round
The owning thread still renders the detailed failure and final `MCP
startup incomplete (...)` summary.
## How to Test
1. Configure an optional MCP server named `smoke` that exits during
initialization.
2. Launch the TUI with multi-agent support enabled.
3. Confirm the main thread's own startup failure renders one detailed
`smoke` warning and one incomplete-startup summary.
4. Spawn exactly one subagent.
5. Confirm the parent transcript does not receive the subagent's MCP
startup failure.
6. Switch to the subagent thread and confirm it contains exactly one
detailed `smoke` failure and one incomplete-startup summary.
7. Confirm the subagent's MCP startup spinner disappears and the thread
remains usable.
8. Switch between the parent and subagent and confirm the warnings
neither move nor duplicate.
Targeted tests:
- `just test -p codex-app-server-protocol`
- `just test -p codex-app-server
thread_start_emits_mcp_server_status_updated_notifications`
- `just test -p codex-tui mcp_startup`
The parent/child behavior and spinner completion were also exercised
manually in tmux. `just argument-comment-lint` was attempted but blocked
by an unrelated local Bazel LLVM empty-glob failure; touched Rust
callsites were inspected manually.
## Why
Interactive `codex resume` and `codex fork` expose both a session ID
positional and an initial prompt positional. With `--last`, Clap still
assigns the first positional to the session ID, so a command such as
`codex fork --last "/compact focus on auth"` either fails parsing or
attempts to look up the prompt as a session ID instead of sending it to
the latest session.
This makes it impossible to select the latest session and immediately
provide a follow-up prompt, even though `codex exec resume --last`
already supports that workflow.
<img width="1746" height="1024" alt="CleanShot 2026-06-06 at 17 00
47@2x"
src="https://github.com/user-attachments/assets/86885c07-a23c-48ee-b0ee-47f2484f6eb7"
/>
## What Changed
- Reinterpret the first positional as the initial prompt when
interactive `resume --last` or `fork --last` is used and no explicit
second prompt was parsed.
- Preserve the existing `resume SESSION_ID PROMPT` and `fork SESSION_ID
PROMPT` behavior.
- Add parser-level regression coverage for latest-session and
explicit-session prompt forms.
## How to Test
1. Start an interactive session, exit it, then run `codex resume --last
"continue from the latest session"`.
2. Confirm Codex resumes the latest session and submits the supplied
prompt instead of treating it as a session ID.
3. Run `codex fork --last "take a different approach"`.
4. Confirm Codex forks the latest session and submits the supplied
prompt.
5. Also verify `codex resume SESSION_ID "continue here"` and `codex fork
SESSION_ID "branch here"` still target the explicit session and submit
the prompt.
Targeted tests:
- `just test -p codex-cli` (267 passed)
## Why
This PR fixes approval sandbox semantics in the unified-exec path. The
zsh-fork runtime exposed the bug because the shell can do meaningful
work before any intercepted child `execv(2)` exists: redirections,
builtins, globbing, and pipeline setup all happen in the launch process.
If the model requested `sandbox_permissions=require_escalated`, or an
exec-policy `allow` rule explicitly bypassed the sandbox, that approved
sandbox decision needs to be preserved for the launch path and for
intercepted execs that use the same approval machinery.
The behavior is not only about zsh fork. The production changes are in
shared approval/escalation code, so they also affect non-zsh-fork
intercepted exec paths that go through the same sandbox decision logic.
The narrow intent is to preserve the approval decision while still
keeping denied-read profiles and bounded additional-permission requests
sandboxed.
## Production Changes
- `codex-rs/core/src/tools/runtimes/unified_exec.rs`: derives a
`launch_sandbox_permissions` value from the requested sandbox
permissions and the runtime filesystem policy, then uses that value for
managed-network/env setup and launch sandbox selection. This keeps full
approval or policy-bypass decisions visible to the first unified-exec
attempt, while still preventing a full sandbox override from discarding
denied-read restrictions. Direct unified exec keeps the same decision
surface; the important difference is that zsh-fork launch setup no
longer accidentally loses the approved parent sandbox decision.
- `codex-rs/core/src/tools/runtimes/shell/unix_escalation.rs`: makes
intercepted-exec escalation selection explicit for the three sandbox
permission modes. `UseDefault` only escalates when an exec-policy
decision allows sandbox bypass, `RequireEscalated` escalates when
unsandboxed execution is allowed, and `WithAdditionalPermissions`
escalates through the bounded additional-permissions path instead of
being treated as a full unsandboxed override. Unsandboxed intercepted
execs now also rebuild the environment as `RequireEscalated`, which
strips managed-network proxy variables consistently with other
unsandboxed execution.
## Test Coverage
Most of the PR is tests. The new coverage verifies:
- unified exec preserves parent approval and exec-policy sandbox
decisions for zsh-fork launch selection;
- bounded `with_additional_permissions` remains sandboxed and
permission-profile based;
- denied-read profiles are not weakened by parent approval;
- explicit prompt rules still prompt for intercepted execs after the
parent command is approved;
- unsandboxed intercepted execs strip managed-network env vars.
No documentation update is needed; this is an internal approval/sandbox
correctness fix.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/24981).
* #24982
* __->__ #24981
## Why
A remote-control WebSocket handshake can receive a generic HTTP 404 when
an intermediary routes the request without preserving the WebSocket
upgrade. Treating every 404 as proof that the remote app server is gone
clears valid enrollment and causes repeated re-enrollment, new
environment and server IDs, Habitat churn, and noisy `/server/enroll`
traffic.
## What Changed
- Clear enrollment only when a 404 JSON response explicitly contains
`{"detail":"Remote app server not found"}`.
- Preserve enrollment for empty, plain-text, malformed, or otherwise
unrecognized 404 responses, return the transport error, and retry with
the existing reconnect backoff.
- Log the status, correlation headers (`request-id` or
`x-oai-request-id`, plus `cf-ray`), and bounded/redacted response body
for unrecognized 404s.
- Cover both explicit missing-server re-enrollment and generic 404
enrollment preservation/reconnect behavior.
## Verification
`just test -p codex-app-server-transport` passes all 114 tests on the
rebased branch, including the targeted explicit and generic WebSocket
404 scenarios.
Related issue: N/A
Skill reloads can get noisy when the watcher keeps triggering
`skills/list` and the same invalid `SKILL.md` error comes back each
time.
This keeps the first warning visible, then suppresses repeats while the
same `(path, message)` is still active. If the error clears and later
comes back, or if the message changes, it will show again.
Validation:
- `just fmt`
- `just test -p codex-tui skill_load_warning_state`
## Why
Permission profile allowlists are an enterprise security boundary, but
they also need to compose across the managed requirements layers added
in #24620.
A map representation lets each requirements layer add, allow, or revoke
individual profiles without replacing an entire array.
## Managed Contract
Administrators configure the mergeable allow map with
`allowed_permission_profiles`. A recommended enterprise configuration
explicitly lists every built-in and custom profile users should be able
to select:
```toml
default_permissions = "review_only"
[allowed_permission_profiles]
":read-only" = true
":workspace" = true
review_only = true
# ":danger-full-access" is intentionally omitted, so it is denied.
[permissions.review_only]
extends = ":read-only"
```
- Profiles whose effective merged value is `true` are allowed.
- Missing profiles and profiles set to `false` are denied.
- This is a closed allowlist: built-in profiles and profiles introduced
in future versions are denied unless explicitly allowed.
- Explicitly list each built-in profile the enterprise wants to make
available. Omit built-ins such as `:danger-full-access` when they should
remain unavailable.
- Set `default_permissions` explicitly to the allowed profile users
should receive when they have no local selection.
- Higher-precedence layers override only the profile keys they define.
- `false` is only needed when a higher-precedence layer must revoke a
`true` inherited from a lower layer.
- Explicit keys must refer to known built-in or managed profiles.
A custom or narrowed allowlist requires an allowed
`default_permissions`. For compatibility, if both `:workspace` and
`:read-only` are explicitly allowed, an omitted default resolves to
`:workspace`; customer configurations should still set the intended
default explicitly.
When `allowed_permission_profiles` is absent, existing implicit
permission and legacy `sandbox_mode` behavior is unchanged.
## What Changed
- Add `allowed_permission_profiles` as a `BTreeMap<String, bool>` that
merges per profile across requirements layers.
- Enforce managed defaults, strict denial of omitted profiles, and the
explicitly allowed standard-pair fallback.
- Expose `allowedPermissionProfiles` through `configRequirements/read`
and regenerate its schemas.
- Add regression coverage for map composition and revocation, managed
defaults, strict denial of omitted built-ins, and API output.
## Verification
- Focused `codex-config` coverage for layered map composition and
revocation
- Focused `codex-core` coverage for managed defaults, invalid defaults,
strict denial of omitted built-ins, and the standard built-in pair
- Focused `codex-app-server` coverage for requirements API output
- Scoped Clippy for `codex-config`, `codex-core`,
`codex-app-server-protocol`, and `codex-app-server`
## Documentation
The managed `requirements.toml` documentation should introduce
`allowed_permission_profiles` as a closed permission-profile allowlist
before this setting is published on developers.openai.com.
---------
Co-authored-by: Codex <noreply@openai.com>
## Summary
- send `X-OpenAI-Internal-Codex-Responses-Lite: true` on HTTP Responses
requests and WebSocket upgrade requests when model metadata enables
Responses Lite
- use client metadata when sending it over the websocket
This PR is stacked on #26490.
## Why
The Responses Lite marker is request-scoped for HTTP but
connection-scoped for Responses-over-WebSocket because it is carried on
the upgrade request. Reusing a cached socket opened for the opposite
mode would therefore send the wrong transport contract.
## Validation
- `just test -p codex-core responses_lite`
- `just test -p codex-core
responses_websocket_reconnects_when_responses_lite_mode_changes`
- `just fix -p codex-core`
- `just fmt`
## Summary
- add v2 personal access token support for `codex login
--with-access-token` and `CODEX_ACCESS_TOKEN`
- classify opaque `at-` tokens separately from legacy Agent Identity
JWTs
- hydrate required ChatGPT account metadata through AuthAPI
`/v1/user-auth-credential/whoami`
- use PATs directly as bearer tokens while preserving existing ChatGPT
account surfaces
- expose PAT-backed auth as the explicit `personalAccessToken`
app-server auth mode
## Implementation
PAT auth is intentionally small and stateless. Loading a PAT performs
one AuthAPI metadata request, stores the hydrated metadata in the
in-memory auth object, and redacts the secret from debug output. Legacy
Agent Identity JWT handling remains unchanged. The shared access-token
classifier lives in a private neutral module because it dispatches
between both credential types.
PAT hydration fails closed when AuthAPI omits any required metadata,
including email. Hydrated metadata is intentionally not persisted:
startup performs a live `whoami` preflight so revoked tokens or changed
account metadata are not accepted from a stale cache.
## Workspace restriction scope
This change intentionally does **not** apply
`forced_chatgpt_workspace_id` to PAT authentication. The setting is a
client-side config guardrail, not an authorization boundary, and PAT
does not currently require workspace-ID parity. The PAT login and
`CODEX_ACCESS_TOKEN` paths therefore validate through AuthAPI without
threading workspace-restriction state through access-token loading.
Existing workspace checks for non-PAT auth remain on their established
paths.
## App-server compatibility
The public app-server `AuthMode` is shared across v1 and v2, and
PAT-backed auth reports `personalAccessToken` through both APIs.
Following human review, this intentionally removes the temporary v1
compatibility mapping that reported PATs as `chatgpt`; the deprecated v1
API is kept in parity with v2 rather than maintaining a separate closed
enum. Clients with exhaustive auth-mode handling in either API version
must add the new case and should generally treat it as ChatGPT-backed
unless they need PAT-specific behavior.
The v1 auth-status response still omits the raw PAT when `includeToken`
is requested because that response cannot carry the account metadata
needed to reuse the credential safely. Persisted PAT auth also omits the
new enum value so older Codex builds can deserialize `auth.json` and
infer PAT auth from the credential field after a rollback.
## Validation
Latest review-fix validation:
- `CARGO_INCREMENTAL=0 just test -p codex-login` (126 passed)
- `CARGO_INCREMENTAL=0 just test -p codex-cli` (263 passed)
- `CARGO_INCREMENTAL=0 just test -p codex-cli
stored_auth_validation_handles_personal_access_token`
- `CARGO_INCREMENTAL=0 just test -p codex-app-server-protocol` (226
passed)
- `CARGO_INCREMENTAL=0 just test -p codex-models-manager
refresh_available_models_uses_remote_only_catalog_for_chatgpt_auth`
- `CARGO_INCREMENTAL=0 just test -p codex-tui
existing_non_oauth_chatgpt_login_counts_as_signed_in`
- `CARGO_INCREMENTAL=0 just fix -p codex-login -p
codex-app-server-protocol -p codex-models-manager -p codex-tui -p
codex-cli`
- `just fmt`
- `git diff --check`
The broader `codex-tui` suite previously compiled and ran 2,834 tests.
Three unrelated environment-sensitive guardian/IDE-socket tests failed
after retries; the PAT-relevant TUI coverage passed.
## Summary
- add `Feature::TerminalVisualizationInstructions` as
`UnderDevelopment`, disabled by default
- keep terminal visualization instructions inside the TUI package
- append them to existing developer instructions for TUI start, resume,
and fork flows only when enabled
- intentionally do not apply them to `codex exec`
## Rollout
Control behavior is unchanged. TUI dogfooders can enable
`terminal_visualization_instructions`; no default user receives the new
terminal-specific instructions.
The shared visualization-selection rule is supplied separately through
the `codex_proxy_model_3` Statsig layer for every target Codex model
slug in the gated cohort. This TUI feature determines how to render an
appropriate visualization on the terminal surface; the model-layer
treatment determines when to use one.
## Validation
- `cargo test -p codex-tui
terminal_visualization_instructions_are_gated_for_all_tui_thread_flows
--lib`
- `cargo test -p codex-features --lib`
- `cargo fmt --all -- --check`
- `git diff --check`
- GPT-5.4 and GPT-5.5 real prompt-pipeline smoke tests: both visualized
the positive mapping case, abstained on the negative route case, and
passed exact prompt-stack verification on CLI and App
- refreshed onto current `main` with a clean merge and reran the focused
validation
The full 53-probe all-model treatment comparison and requested
production coding evals remain rollout gates before broadening beyond
the initial employee cohort.
This PR remains open for normal human review.
## Summary
Responses Lite does not execute hosted Responses tools, so models using
it must route web search and image generation through Codex-owned
executors & standalone Response's API endpoints.
This PR is stacked on #26487.
## Validation
- `cargo test -p codex-core responses_lite_ --lib`
- `cargo test -p codex-core
standalone_executors_remain_hidden_without_flags_or_responses_lite
--lib`
- `cargo test -p codex-core
hosted_tools_follow_provider_auth_model_and_config_gates --lib`
- `cargo test -p codex-web-search-extension -p
codex-image-generation-extension`
- `cargo test -p codex-app-server --test all standalone_`
- `cargo fmt --all -- --check`
## Summary
- Remove the legacy startup remote plugin sync path that called
`/plugins/list` and reconciled curated plugin cache/config.
- Remove the `sync_plugins_from_remote` API, its result/error types,
startup marker task, and tests that expected the legacy request.
- Keep the current remote installed bundle sync and remote catalog flows
(`/ps/plugins/installed` and `/ps/plugins/list`) intact.
## Validation
- `just fmt`
- `git diff --check`
- `env HOME=/private/tmp/codex-xin-build-home
USERPROFILE=/private/tmp/codex-xin-build-home just test -p
codex-core-plugins`
- Searched for legacy `/plugins/list` sync references; remaining matches
are `/ps/plugins/list` catalog tests/code.
## Notes
- `just test -p codex-app-server plugin_list` is currently blocked
before running filtered tests by an unrelated compile error in
`app-server/tests/suite/v2/image_generation.rs`:
`app_test_support::McpProcess` is not exported.
## Why
Terminal turn errors can leave a goal active. Automatic goal
continuation may then repeatedly hit a permanent failure, including
compaction requests rejected with HTTP 400, and consume excessive
tokens.
This PR changes the goal extension to treat all turn-ending errors
(including non-retryable errors and retryable errors that have exceeded
their retry count) as "blocking" for the goal. The downside to this
change is that there are some errors that may eventually succeed (e.g. a
429 due to a service outage), and previously the goal runtime would have
kept the agent going in these situations.
## What changed
- Block the current active goal when a turn ends with an error other
than a usage-limit error.
- Preserve the existing `usage_limited` transition for usage-limit
errors.
- Share progress accounting, guarded state updates, metrics, and event
emission in the goal runtime.
pakrym-oaiandGitHub
canvrno-oaiandGitHub
yuning-oaiandGitHub
Boyang NiuandGitHub
Felipe CouryandGitHub
Adam Perry @ OpenAIandGitHub
Celia ChenandGitHub
richardopenaiandGitHub
xl-openaiandGitHub
fchen-oaiandGitHub
rhan-oaiandGitHub
Won ParkandGitHub
viyatb-oaiandGitHub
Michael BolinandGitHub
jifandGitHub
mpc-oaiandGitHub
stefanstokic-oaiandGitHub
ningyi-oaiandGitHub
Anton PanasenkoandGitHub
Jeremy RoseandGitHub
rka-oaiandGitHub
Channing CongerandGitHub
Eric NingandGitHub
cooper-oaiandGitHub
vie-oaiandGitHub
Eric TrautandGitHub