## Summary
If a subagent requests approval, and the user persists that approval to
the execpolicy, it should (by default) propagate. We'll need to rethink
this a bit in light of coming Permissions changes, though I think this
is closer to the end state that we'd want, which is that execpolicy
changes to one permissions profile should be synced across threads.
## Testing
- [x] Added integration test
---------
Co-authored-by: Codex <noreply@openai.com>
- this allows blocking the user's prompts from executing, and also
prevents them from entering history
- handles the edge case where you can both prevent the user's prompt AND
add n amount of additionalContexts
- refactors some old code into common.rs where hooks overlap
functionality
- refactors additionalContext being previously added to user messages,
instead we use developer messages for them
- handles queued messages correctly
Sample hook for testing - if you write "[block-user-submit]" this hook
will stop the thread:
example run
```
› sup
• Running UserPromptSubmit hook: reading the observatory notes
UserPromptSubmit hook (completed)
warning: wizard-tower UserPromptSubmit demo inspected: sup
hook context: Wizard Tower UserPromptSubmit demo fired. For this reply only, include the exact
phrase 'observatory lanterns lit' exactly once near the end.
• Just riding the cosmic wave and ready to help, my friend. What are we building today? observatory
lanterns lit
› and [block-user-submit]
• Running UserPromptSubmit hook: reading the observatory notes
UserPromptSubmit hook (stopped)
warning: wizard-tower UserPromptSubmit demo blocked the prompt on purpose.
stop: Wizard Tower demo block: remove [block-user-submit] to continue.
```
.codex/config.toml
```
[features]
codex_hooks = true
```
.codex/hooks.json
```
{
"hooks": {
"UserPromptSubmit": [
{
"hooks": [
{
"type": "command",
"command": "/usr/bin/python3 .codex/hooks/user_prompt_submit_demo.py",
"timeoutSec": 10,
"statusMessage": "reading the observatory notes"
}
]
}
]
}
}
```
.codex/hooks/user_prompt_submit_demo.py
```
#!/usr/bin/env python3
import json
import sys
from pathlib import Path
def prompt_from_payload(payload: dict) -> str:
prompt = payload.get("prompt")
if isinstance(prompt, str) and prompt.strip():
return prompt.strip()
event = payload.get("event")
if isinstance(event, dict):
user_prompt = event.get("user_prompt")
if isinstance(user_prompt, str):
return user_prompt.strip()
return ""
def main() -> int:
payload = json.load(sys.stdin)
prompt = prompt_from_payload(payload)
cwd = Path(payload.get("cwd", ".")).name or "wizard-tower"
if "[block-user-submit]" in prompt:
print(
json.dumps(
{
"systemMessage": (
f"{cwd} UserPromptSubmit demo blocked the prompt on purpose."
),
"decision": "block",
"reason": (
"Wizard Tower demo block: remove [block-user-submit] to continue."
),
}
)
)
return 0
prompt_preview = prompt or "(empty prompt)"
if len(prompt_preview) > 80:
prompt_preview = f"{prompt_preview[:77]}..."
print(
json.dumps(
{
"systemMessage": (
f"{cwd} UserPromptSubmit demo inspected: {prompt_preview}"
),
"hookSpecificOutput": {
"hookEventName": "UserPromptSubmit",
"additionalContext": (
"Wizard Tower UserPromptSubmit demo fired. "
"For this reply only, include the exact phrase "
"'observatory lanterns lit' exactly once near the end."
),
},
}
)
)
return 0
if __name__ == "__main__":
raise SystemExit(main())
```
Adds an environment crate and environment + file system abstraction.
Environment is a combination of attributes and services specific to
environment the agent is connected to:
File system, process management, OS, default shell.
The goal is to move most of agent logic that assumes environment to work
through the environment abstraction.
## Description
This PR fixes a bad first-turn failure mode in app-server when the
startup websocket prewarm hangs. Before this change, `initialize ->
thread/start -> turn/start` could sit behind the prewarm for up to five
minutes, so the client would not see `turn/started`, and even
`turn/interrupt` would block because the turn had not actually started
yet.
Now, we:
- set a (configurable) timeout of 15s for websocket startup time,
exposed as `websocket_startup_timeout_ms` in config.toml
- `turn/started` is sent immediately on `turn/start` even if the
websocket is still connecting
- `turn/interrupt` can be used to cancel a turn that is still waiting on
the websocket warmup
- the turn task will wait for the full 15s websocket warming timeout
before falling back
## Why
The old behavior made app-server feel stuck at exactly the moment the
client expects turn lifecycle events to start flowing. That was
especially painful for external clients, because from their point of
view the server had accepted the request but then went silent for
minutes.
## Configuring the websocket startup timeout
Can set it in config.toml like this:
```
[model_providers.openai]
supports_websockets = true
websocket_connect_timeout_ms = 15000
```
## Why
PR #13783 moved the `codex.rs` unit tests into `codex_tests.rs`. This
applies the same extraction pattern across the rest of `codex-rs/core`
so the production modules stay focused on runtime code instead of large
inline test blocks.
Keeping the tests in sibling files also makes follow-up edits easier to
review because product changes no longer have to share a file with
hundreds or thousands of lines of test scaffolding.
## What changed
- replaced each inline `mod tests { ... }` in `codex-rs/core/src/**`
with a path-based module declaration
- moved each extracted unit test module into a sibling `*_tests.rs`
file, using `mod_tests.rs` for `mod.rs` modules
- preserved the existing `cfg(...)` guards and module-local structure so
the refactor remains structural rather than behavioral
## Testing
- `cargo test -p codex-core --lib` (`1653 passed; 0 failed; 5 ignored`)
- `just fix -p codex-core`
- `cargo fmt --check`
- `cargo shear`
## Summary
- persist the code mode runner process in the session-scoped code mode
store
- switch the runner protocol from `init` to `start` with explicit
session ids
- handle runner-side session processing without the init waiter queue
## Validation
- just fmt
- cargo check -p codex-core
- node --check codex-rs/core/src/tools/code_mode_runner.cjs
## Why
to support a new bring your own search tool in Responses
API(https://developers.openai.com/api/docs/guides/tools-tool-search#client-executed-tool-search)
we migrating our bm25 search tool to use official way to execute search
on client and communicate additional tools to the model.
## What
- replace the legacy `search_tool_bm25` flow with client-executed
`tool_search`
- add protocol, SSE, history, and normalization support for
`tool_search_call` and `tool_search_output`
- return namespaced Codex Apps search results and wire namespaced
follow-up tool calls back into MCP dispatch
(Experimental)
This PR adds a first MVP for hooks, with SessionStart and Stop
The core design is:
- hooks live in a dedicated engine under codex-rs/hooks
- each hook type has its own event-specific file
- hook execution is synchronous and blocks normal turn progression while
running
- matching hooks run in parallel, then their results are aggregated into
a normalized HookRunSummary
On the AppServer side, hooks are exposed as operational metadata rather
than transcript-native items:
- new live notifications: hook/started, hook/completed
- persisted/replayed hook results live on Turn.hookRuns
- we intentionally did not add hook-specific ThreadItem variants
Hooks messages are not persisted, they remain ephemeral. The context
changes they add are (they get appended to the user's prompt)
## Summary
request_permissions flows should support persisting results for the
session.
Open Question: Still deciding if we need within-turn approvals - this
adds complexity but I could see it being useful
## Testing
- [x] Updated unit tests
---------
Co-authored-by: Codex <noreply@openai.com>
Adds a built-in `request_permissions` tool and wires it through the
Codex core, protocol, and app-server layers so a running turn can ask
the client for additional permissions instead of relying on a static
session policy.
The new flow emits a `RequestPermissions` event from core, tracks the
pending request by call ID, forwards it through app-server v2 as an
`item/permissions/requestApproval` request, and resumes the tool call
once the client returns an approved subset of the requested permission
profile.
## Summary
This is a purely mechanical refactor of `OtelManager` ->
`SessionTelemetry` to better convey what the struct is doing. No
behavior change.
## Why
`OtelManager` ended up sounding much broader than what this type
actually does. It doesn't manage OTEL globally; it's the session-scoped
telemetry surface for emitting log/trace events and recording metrics
with consistent session metadata (`app_version`, `model`, `slug`,
`originator`, etc.).
`SessionTelemetry` is a more accurate name, and updating the call sites
makes that boundary a lot easier to follow.
## Validation
- `just fmt`
- `cargo test -p codex-otel`
- `cargo test -p codex-core`
## Summary
- record a realtime close developer message when a new realtime session
replaces an active one
- assert the replacement marker through the mocked responses request
path
---------
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Charles Cunningham <ccunningham@openai.com>
Support loading plugins.
Plugins can now be enabled via [plugins.<name>] in config.toml. They are
loaded as first-class entities through PluginsManager, and their default
skills/ and .mcp.json contributions are integrated into the existing
skills and MCP flows.
This reverts commit https://github.com/openai/codex/pull/12633. We no
longer need this PR, because we favor sending normal exec command
approval server request with `additional_permissions` of skill
permissions instead
Previous to this change, `determine_action()` would
1. check if `program` is associated with a skill
2. if so, check if `program` is in `execve_session_approvals` to see
whether the user needs to be prompted
This PR flips the order of these checks to try to set us up so that
"session approvals" are always consulted first (which should soon extend
to include session approvals derived from `prefix_rule()`s, as well).
Though to make the new ordering work, we need to record any relevant
metadata to associate with the approval, which in the case of a
skill-based approval is the `SkillMetadata` so that we can derive the
`PermissionProfile` to include with the escalation. (Though as noted by
the `TODO`, this `PermissionProfile` is not honored yet.)
The new `ExecveSessionApproval` struct is used to retain the necessary
metadata.
## What Changed
- Replace the `execve_session_approvals` `HashSet` with a map that
stores an `ExecveSessionApproval` alongside each approved `program`.
- When a user chooses `ApprovedForSession` for a skill script, capture
the matched `SkillMetadata` in the session approval entry.
- Consult that cache before re-running `find_skill()`, and reuse the
originally approved skill metadata and permission profile when allowing
later execve callbacks in the same session.
## Why
`unix_escalation.rs` checks a session-scoped approval cache before
prompting again for an execve-intercepted skill script. Without also
recording `ReviewDecision::ApprovedForSession`, that cache never gets
populated, so the same skill script can still trigger repeated approval
prompts within one session.
## What Changed
- Add `execve_session_approvals` to `SessionServices` so the session can
track approved skill script paths.
- Record the script path when a skill-script prompt returns
`ReviewDecision::ApprovedForSession`, but only for the skill-script path
rather than broader prefix-rule approvals.
- Reuse the cached approval on later execve callbacks by treating an
already-approved skill script as `Decision::Allow`.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/12756).
* #12758
* __->__ #12756
## Why
`codex-rs/core/src/tools/runtimes/shell/unix_escalation.rs` previously
located `codex-execve-wrapper` by scanning `PATH` and sibling
directories. That lookup is brittle and can select the wrong binary when
the runtime environment differs from startup assumptions.
We already pass `codex-linux-sandbox` from `codex-arg0`;
`codex-execve-wrapper` should use the same startup-driven path plumbing.
## What changed
- Introduced `Arg0DispatchPaths` in `codex-arg0` to carry both helper
executable paths:
- `codex_linux_sandbox_exe`
- `main_execve_wrapper_exe`
- Updated `arg0_dispatch_or_else()` to pass `Arg0DispatchPaths` to
top-level binaries and preserve helper paths created in
`prepend_path_entry_for_codex_aliases()`.
- Threaded `Arg0DispatchPaths` through entrypoints in `cli`, `exec`,
`tui`, `app-server`, and `mcp-server`.
- Added `main_execve_wrapper_exe` to core configuration plumbing
(`Config`, `ConfigOverrides`, and `SessionServices`).
- Updated zsh-fork shell escalation to consume the configured
`main_execve_wrapper_exe` and removed path-sniffing fallback logic.
- Updated app-server config reload paths so reloaded configs keep the
same startup-provided helper executable paths.
## References
- [`Arg0DispatchPaths`
definition](e355b43d5c/codex-rs/arg0/src/lib.rs (L20-L24))
- [`arg0_dispatch_or_else()` forwarding both
paths](e355b43d5c/codex-rs/arg0/src/lib.rs (L145-L176))
- [zsh-fork escalation using configured wrapper
path](e355b43d5c/codex-rs/core/src/tools/runtimes/shell/unix_escalation.rs (L109-L150))
## Testing
- `cargo check -p codex-arg0 -p codex-core -p codex-exec -p codex-tui -p
codex-mcp-server -p codex-app-server`
- `cargo test -p codex-arg0`
- `cargo test -p codex-core tools::runtimes::shell::unix_escalation:: --
--nocapture`
## Why
This PR switches the `shell_command` zsh-fork path over to
`codex-shell-escalation` so the new shell tool can use the shared
exec-wrapper/escalation protocol instead of the `zsh_exec_bridge`
implementation that was introduced in
https://github.com/openai/codex/pull/12052. `zsh_exec_bridge` relied on
UNIX domain sockets, which is not as tamper-proof as the FD-based
approach in `codex-shell-escalation`.
## What Changed
- Added a Unix zsh-fork runtime adapter in `core`
(`core/src/tools/runtimes/shell/unix_escalation.rs`) that:
- runs zsh-fork commands through
`codex_shell_escalation::run_escalate_server`
- bridges exec-policy / approval decisions into `ShellActionProvider`
- executes escalated commands via a `ShellCommandExecutor` that calls
`process_exec_tool_call`
- Updated `ShellRuntime` / `ShellCommandHandler` / tool spec wiring to
select a `shell_command` backend (`classic` vs `zsh-fork`) while leaving
the generic `shell` tool path unchanged.
- Removed the `zsh_exec_bridge`-based session service and deleted
`core/src/zsh_exec_bridge/mod.rs`.
- Moved exec-wrapper entrypoint dispatch to `arg0` by handling the
`codex-execve-wrapper` arg0 alias there, and removed the old
`codex_core::maybe_run_zsh_exec_wrapper_mode()` hooks from `cli` and
`app-server` mains.
- Added the needed `codex-shell-escalation` dependencies for `core` and
`arg0`.
## Tests
- `cargo test -p codex-core
shell_zsh_fork_prefers_shell_command_over_unified_exec`
- `cargo test -p codex-app-server turn_start_shell_zsh_fork --
--nocapture`
- verifies zsh-fork command execution and approval flows through the new
backend
- includes subcommand approve/decline coverage using the shared zsh
DotSlash fixture in `app-server/tests/suite/zsh`
- To test manually, I added the following to `~/.codex/config.toml`:
```toml
zsh_path = "/Users/mbolin/code/codex3/codex-rs/app-server/tests/suite/zsh"
[features]
shell_zsh_fork = true
```
Then I ran `just c` to run the dev build of Codex with these changes and
sent it the message:
```
run `echo $0`
```
And it replied with:
```
echo $0 printed:
/Users/mbolin/code/codex3/codex-rs/app-server/tests/suite/zsh
In this tool context, $0 reflects the script path used to invoke the shell, not just zsh.
```
so the tool appears to be wired up correctly.
## Notes
- The zsh subcommand-decline integration test now uses `rm` under a
`WorkspaceWrite` sandbox. The previous `/usr/bin/true` scenario is
auto-allowed by the new `shell-escalation` policy path, which no longer
produces subcommand approval prompts.
Send a request with `generate: falls` but a full set of tools and
instructions to pre-warm inference.
---------
Co-authored-by: Codex <noreply@openai.com>
## Summary
- move regular-turn context diff/full-context persistence into
`run_turn` so pre-turn compaction runs before incoming context updates
are recorded
- after successful pre-turn compaction, rely on a cleared
`reference_context_item` to trigger full context reinjection on the
follow-up regular turn (manual `/compact` keeps replacement history
summary-only and also clears the baseline)
- preserve `<model_switch>` when full context is reinjected, and inject
it *before* the rest of the full-context items
- scope `reference_context_item` and `previous_model` to regular user
turns only so standalone tasks (`/compact`, shell, review, undo) cannot
suppress future reinjection or `<model_switch>` behavior
- make context-diff persistence + `reference_context_item` updates
explicit in the regular-turn path, with clearer docs/comments around the
invariant
- stop persisting local `/compact` `RolloutItem::TurnContext` snapshots
(only regular turns persist `TurnContextItem` now)
- simplify resume/fork previous-model/reference-baseline hydration by
looking up the last surviving turn context from rollout lifecycle
events, including rollback and compaction-crossing handling
- remove the legacy fallback that guessed from bare `TurnContext`
rollouts without lifecycle events
- update compaction/remote-compaction/model-visible snapshots and
compact test assertions (including remote compaction mock response
shape)
## Why
We were persisting incoming context items before spawning the regular
turn task, which let pre-turn compaction requests accidentally include
incoming context diffs without the new user message. Fixing that exposed
follow-on baseline issues around `/compact`, resume/fork, and standalone
tasks that could cause duplicate context injection or suppress
`<model_switch>` instructions.
This PR re-centers the invariants around regular turns:
- regular turns persist model-visible context diffs/full reinjection and
update the `reference_context_item`
- standalone tasks do not advance those regular-turn baselines
- compaction clears the baseline when replacement history may have
stripped the referenced context diffs
## Follow-ups (TODOs left in code)
- `TODO(ccunningham)`: fix rollback/backtracking baseline handling more
comprehensively
- `TODO(ccunningham)`: include pending incoming context items in
pre-turn compaction threshold estimation
- `TODO(ccunningham)`: inject updated personality spec alongside
`<model_switch>` so some model-switch paths can avoid forced full
reinjection
- `TODO(ccunningham)`: review task turn lifecycle
(`TurnStarted`/`TurnComplete`) behavior and emit task-start context
diffs for task types that should have them (excluding `/compact`)
## Validation
- `just fmt`
- CI should cover the updated compaction/resume/model-visible snapshot
expectations and rollout-hydration behavior
- I did **not** rerun the full local test suite after the latest
resume-lookup / rollout-persistence simplifications
## Summary
- add `previous_context_item: Option<TurnContextItem>` to
`ContextManager`
- expose session/state accessors for reading and updating the stored
previous context item
- switch settings diffing to use `TurnContextItem` instead of
`TurnContext`
- remove submission-loop local `previous_context` and persist the
previous context item in history
## Testing
- `just fmt`
- `just fix -p codex-core`
- `cargo test -p codex-core --test all model_switching::`
- `cargo test -p codex-core --test all collaboration_instructions::`
- `cargo test -p codex-core --test all personality::`
- `cargo test -p codex-core --test all
permissions_messages::permissions_message_not_added_when_no_change`
zsh fork PR stack:
- https://github.com/openai/codex/pull/12051
- https://github.com/openai/codex/pull/12052👈
### Summary
This PR introduces a feature-gated native shell runtime path that routes
shell execution through a patched zsh exec bridge, removing MCP-specific
behavior from the shell hot path while preserving existing
CommandExecution lifecycle semantics.
When shell_zsh_fork is enabled, shell commands run via patched zsh with
per-`execve` interception through EXEC_WRAPPER. Core receives wrapper
IPC requests over a Unix socket, applies existing approval policy, and
returns allow/deny before the subcommand executes.
### What’s included
**1) New zsh exec bridge runtime in core**
- Wrapper-mode entrypoint (maybe_run_zsh_exec_wrapper_mode) for
EXEC_WRAPPER invocations.
- Per-execution Unix-socket IPC handling for wrapper requests/responses.
- Approval callback integration using existing core approval
orchestration.
- Streaming stdout/stderr deltas to existing command output event
pipeline.
- Error handling for malformed IPC, denial/abort, and execution
failures.
**2) Session lifecycle integration**
SessionServices now owns a `ZshExecBridge`.
Session startup initializes bridge state; shutdown tears it down
cleanly.
**3) Shell runtime routing (feature-gated)**
When `shell_zsh_fork` is enabled:
- Build execution env/spec as usual.
- Add wrapper socket env wiring.
- Execute via `zsh_exec_bridge.execute_shell_request(...)` instead of
the regular shell path.
- Non-zsh-fork behavior remains unchanged.
**4) Config + feature wiring**
- Added `Feature::ShellZshFork` (under development).
- Added config support for `zsh_path` (optional absolute path to patched
zsh):
- `Config`, `ConfigToml`, `ConfigProfile`, overrides, and schema.
- Session startup validates that `zsh_path` exists/usable when zsh-fork
is enabled.
- Added startup test for missing `zsh_path` failure mode.
**5) Seatbelt/sandbox updates for wrapper IPC**
- Extended seatbelt policy generation to optionally allow outbound
connection to explicitly permitted Unix sockets.
- Wired sandboxing path to pass wrapper socket path through to seatbelt
policy generation.
- Added/updated seatbelt tests for explicit socket allow rule and
argument emission.
**6) Runtime entrypoint hooks**
- This allows the same binary to act as the zsh wrapper subprocess when
invoked via `EXEC_WRAPPER`.
**7) Tool selection behavior**
- ToolsConfig now prefers ShellCommand type when shell_zsh_fork is
enabled.
- Added test coverage for precedence with unified-exec enabled.
### What changed
1. Removed per-turn MCP selection reset in `core/src/tasks/mod.rs`.
2. Added `SessionState::set_mcp_tool_selection(Vec<String>)` in
`core/src/state/session.rs` for authoritative restore behavior (deduped,
order-preserving, empty clears).
3. Added rollout parsing in `core/src/codex.rs` to recover
`active_selected_tools` from prior `search_tool_bm25` outputs:
- tracks matching `call_id`s
- parses function output text JSON
- extracts `active_selected_tools`
- latest valid payload wins
- malformed/non-matching payloads are ignored
4. Applied restore logic to resumed and forked startup paths in
`core/src/codex.rs`.
5. Updated instruction text to session/thread scope in
`core/templates/search_tool/tool_description.md`.
6. Expanded tests in `core/tests/suite/search_tool.rs`, plus unit
coverage in:
- `core/src/codex.rs`
- `core/src/state/session.rs`
### Behavior after change
1. Search activates matched tools.
2. Additional searches union into active selection.
3. Selection survives new turns in the same thread.
4. Resume/fork restores selection from rollout history.
5. Separate threads do not inherit selection unless forked.
### Description
#### Summary
Introduces the core plumbing required for structured network approvals
#### What changed
- Added structured network policy decision modeling in core.
- Added approval payload/context types needed for network approval
semantics.
- Wired shell/unified-exec runtime plumbing to consume structured
decisions.
- Updated related core error/event surfaces for structured handling.
- Updated protocol plumbing used by core approval flow.
- Included small CLI debug sandbox compatibility updates needed by this
layer.
#### Why
establishes the minimal backend foundation for network approvals without
yet changing high-level orchestration or TUI behavior.
#### Notes
- Behavior remains constrained by existing requirements/config gating.
- Follow-up PRs in the stack handle orchestration, UX, and app-server
integration.
---------
Co-authored-by: Codex <199175422+chatgpt-codex-connector[bot]@users.noreply.github.com>
This PR introduces a skill-expansion mechanism for mentions so nested or
skill or connection mentions are expanded if present in skills invoked
by the user. This keeps behavior aligned with existing mention handling
while extending coverage to deeper scenarios. With these changes, users
can create skills that invoke connectors, and skills that invoke other
skills.
Replaces #10863, which is not needed with the addition of
[search_tool_bm25](https://github.com/openai/codex/issues/10657)
Added multi-limit support end-to-end by carrying limit_name in
rate-limit snapshots and handling multiple buckets instead of only
codex.
Extended /usage client parsing to consume additional_rate_limits
Updated TUI /status and in-memory state to store/render per-limit
snapshots
Extended app-server rate-limit read response: kept rate_limits and added
rate_limits_by_name.
Adjusted usage-limit error messaging for non-default codex limit buckets
Summary
- move `core/src/hooks` implementation into a new `codex-hooks` crate
with its own manifest
- update `codex-rs` workspace and `codex-core` crate to depend on the
extracted `hooks` crate and wire up the shared APIs
- ensure references, modules, and lockfile reflect the new crate layout
Testing
- Not run (not requested)
As of this PR, `SessionServices` retains a
`Option<StartedNetworkProxy>`, if appropriate.
Now the `network` field on `Config` is `Option<NetworkProxySpec>`
instead of `Option<NetworkProxy>`.
Over in `Session::new()`, we invoke `NetworkProxySpec::start_proxy()` to
create the `StartedNetworkProxy`, which is a new struct that retains the
`NetworkProxy` as well as the `NetworkProxyHandle`. (Note that `Drop` is
implemented for `NetworkProxyHandle` to ensure the proxies are shutdown
when it is dropped.)
The `NetworkProxy` from the `StartedNetworkProxy` is threaded through to
the appropriate places.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/11207).
* #11285
* __->__ #11207
**Why We Did This**
- The goal is to reduce MCP tool context pollution by not exposing the
full MCP tool list up front
- It forces an explicit discovery step (`search_tool_bm25`) so the model
narrows tool scope before making MCP calls, which helps relevance and
lowers prompt/tool clutter.
**What It Changed**
- Added a new experimental feature flag `search_tool` in
`core/src/features.rs:90` and `core/src/features.rs:430`.
- Added config/schema support for that flag in
`core/config.schema.json:214` and `core/config.schema.json:1235`.
- Added BM25 dependency (`bm25`) in `Cargo.toml:129` and
`core/Cargo.toml:23`.
- Added new tool handler `search_tool_bm25` in
`core/src/tools/handlers/search_tool_bm25.rs:18`.
- Registered the handler and tool spec in
`core/src/tools/handlers/mod.rs:11` and `core/src/tools/spec.rs:780` and
`core/src/tools/spec.rs:1344`.
- Extended `ToolsConfig` to carry `search_tool` enablement in
`core/src/tools/spec.rs:32` and `core/src/tools/spec.rs:56`.
- Injected dedicated developer instructions for tool-discovery workflow
in `core/src/codex.rs:483` and `core/src/codex.rs:1976`, using
`core/templates/search_tool/developer_instructions.md:1`.
- Added session state to store one-shot selected MCP tools in
`core/src/state/session.rs:27` and `core/src/state/session.rs:131`.
- Added filtering so when feature is enabled, only selected MCP tools
are exposed on the next request (then consumed) in
`core/src/codex.rs:3800` and `core/src/codex.rs:3843`.
- Added E2E suite coverage for
enablement/instructions/hide-until-search/one-turn-selection in
`core/tests/suite/search_tool.rs:72`,
`core/tests/suite/search_tool.rs:109`,
`core/tests/suite/search_tool.rs:147`, and
`core/tests/suite/search_tool.rs:218`.
- Refactored test helper utilities to support config-driven tool
collection in `core/tests/suite/tools.rs:281`.
**Net Behavioral Effect**
- With `search_tool` **off**: existing MCP behavior (tools exposed
normally).
- With `search_tool` **on**: MCP tools start hidden, model must call
`search_tool_bm25`, and only returned `selected_tools` are available for
the next model call.
Instead of storing a special connection on the client level make the
regular task responsible for establishing a normal client session and
open a connection on it.
Then when the turn is started we pass in a pre-established session.
This introduces a `Hooks` service. It registers hooks from config and
dispatches hook events at runtime.
N.B. The hook config is not wired up to this yet. But for legacy
reasons, we wire up `notify` from config and power it using hooks now.
Nothing about the `notify` interface has changed.
I'd start by reviewing `hooks/types.rs`
Some things to note:
- hook names subject to change
- no hook result yet
- stopping semantics yet to be introduced
- additional hooks yet to be introduced
## Summary
When resuming with a different model, we should also append a developer
message with the model instructions
## Testing
- [x] Added unit tests
Make ModelClient a session-scoped object.
Move state that is session level onto the client, and make state that is
per-turn explicit on corresponding methods.
Stop taking a huge Config object, instead only pass in values that are
actually needed.
---------
Co-authored-by: Josh McKinney <joshka@openai.com>
Add a centralized FileWatcher in codex-core (using notify) that watches
skill roots from the config layer stack (recursive)
Send `SkillsChanged` events when relevant file system changes are
detected
On `SkillsChanged`:
* Invalidate the skills cache immediately in ThreadManager
* Emit EventMsg::SkillsUpdateAvailable to active sessions
~~* Broadcast a new app-server notification:
SkillsListUpdatedNotification~~
This change does not inject new items into the event stream. That means
the agent will not know about new skills, so it won't be able to
implicitly invoke new skills. It also won't know about changes to
existing skills, so if it has already read the contents of a modified
skill, it will not honor the new behavior.
This change also does not detect modifications to AGENTS.md.
I plan to address these limitations in a follow-on PR modeled after
#9985. Injection of new skills and AGENTS was deemed to risky, hence the
need to split the feature into two stages. The changes in this PR were
designed to easily accommodate the second stage once we have some other
foundational changes in place.
Testing: In addition to automated tests, I did manual testing to confirm
that newly-created skills, deleted skills, and renamed skills are
reflected in the TUI skill picker menu. Also confirmed that
modifications to behaviors for explicitly-invoked skills are honored.
---------
Co-authored-by: Xin Lin <xl@openai.com>
An experimental flow for env var skill dependencies. Skills can now
declare required env vars in SKILL.md; if missing, the CLI prompts the
user to get the value, and Core will store it in memory (eventually to a
local persistent store)
<img width="790" height="169" alt="image"
src="https://github.com/user-attachments/assets/cd928918-9403-43cb-a7e7-b8d59bcccd9a"
/>
Add a `.sqlite` database to be used to store rollout metatdata (and
later logs)
This PR is phase 1:
* Add the database and the required infrastructure
* Add a backfill of the database
* Persist the newly created rollout both in files and in the DB
* When we need to get metadata or a rollout, consider the `JSONL` as the
source of truth but compare the results with the DB and show any errors
