Compare commits

..

133 Commits

Author SHA1 Message Date
friel-openai
9d9a2d451f Merge branch 'main' into codex/fix-plan-mode-task-complete-main 2026-04-28 12:06:37 -07:00
viyatb-oai
3377afd84a fix(network-proxy): harden linux proxy bridge helpers (#20001)
## Why
The Linux managed-proxy bridge helpers are long-lived child processes in
the sandbox networking path. Before this change they stayed dumpable and
the network seccomp profile did not block cross-process memory syscalls,
so another same-user process could potentially inspect or modify bridge
memory instead of interacting only through the intended proxy interface.

## What changed
- reuse the shared `codex-process-hardening` helper to mark bridge
helper children non-dumpable before they begin serving
- deny `process_vm_readv` and `process_vm_writev` in the existing
network seccomp filter

## Security impact
Bridge helpers are less exposed to same-user cross-process inspection or
memory writes, which reduces the chance that sandboxed code can
interfere with proxy support processes outside the intended IPC path.

## Verification
- `cargo test -p codex-process-hardening`
- `cargo test -p codex-linux-sandbox`
- attempted `cargo check -p codex-linux-sandbox --target
x86_64-unknown-linux-gnu`; blocked on missing `x86_64-linux-gnu-gcc` on
this macOS host

---------

Co-authored-by: Codex <noreply@openai.com>
2026-04-28 11:52:50 -07:00
charley-openai
de2ccf9473 [codex] Add token usage to turn tracing spans (#19432)
## Why

Slow Codex turns are easier to debug when token usage is visible in the
trace itself, without joining against separate analytics. This adds
token usage to existing turn-handling spans for regular user turns only.

[Example
turn](https://openai.datadoghq.com/apm/trace/9d353efa2cb5de1f4c5b93dc33c3df04?colorBy=service&graphType=flamegraph&shouldShowLegend=true&sort=time&spanID=3555541504891512675&spanViewType=metadata&traceQuery=)
<img width="1447" height="967" alt="Screenshot 2026-04-24 at 3 03 07 PM"
src="https://github.com/user-attachments/assets/ab7bb187-e7fc-41f0-a366-6c44610b2b2c"
/>

## What Changed

Added response-level token fields on completed handle_responses spans:

gen_ai.usage.input_tokens
gen_ai.usage.cache_read.input_tokens
gen_ai.usage.output_tokens
codex.usage.reasoning_output_tokens
codex.usage.total_tokens
Added aggregate token fields on regular turn spans:

codex.turn.token_usage.*
Added an explicit regular-turn opt-in via
SessionTask::records_turn_token_usage_on_span() so this is not coupled
to span-name strings.

## Testing

- `cargo test -p codex-otel`
- `cargo test -p codex-core
turn_and_completed_response_spans_record_token_usage`
- `just fmt`
- `just fix -p codex-core`
- `just fix -p codex-otel`
- Manual local Electron/app-server smoke test: regular user turn emits
the new span fields

Known status: `cargo test -p codex-core` was attempted and failed in
unrelated existing areas: config approvals, request-permissions,
git-info ordering, and subagent metadata persistence.
2026-04-28 11:41:32 -07:00
canvrno-oai
640a1b23ea Fix plan mode nudge test after task completion signature change (#20045)
Updates the plan mode nudge test to pass the new `duration_ms` argument
to task completion.

Co-authored-by: Codex <noreply@openai.com>
2026-04-28 11:24:22 -07:00
Michael Bolin
9e26613657 permissions: add built-in default profiles (#19900)
## Why

The migration away from `SandboxPolicy` needs new configs to start from
permissions profiles instead of deriving profiles from legacy sandbox
modes. Existing users can have empty `config.toml` files, and we should
not rewrite user-owned config files that may live in shared
repositories.

This PR introduces built-in profile names so an empty config can resolve
to a canonical `PermissionProfile`, while explicit named `[permissions]`
profiles still behave predictably.

## What changed

- Adds built-in `default_permissions` profile names:
  - `:read-only` maps to `PermissionProfile::read_only()`.
- `:workspace` maps to the workspace-write profile, including
project-root metadata carveouts.
- `:danger-no-sandbox` maps to `PermissionProfile::Disabled`, preserving
the distinction between no sandbox and a broad managed sandbox.
- Reserves the `:` prefix for built-in profiles so user-defined
`[permissions]` profiles cannot collide with future built-ins.
- Allows `default_permissions` to reference a built-in profile without
requiring a `[permissions]` table.
- Makes an otherwise empty config choose a built-in profile by
trust/platform context: trusted or untrusted project roots use
`:workspace` when the platform supports that sandbox, while roots
without a trust decision use `:read-only`.
- Keeps legacy `sandbox_mode` configs on the legacy path, and still
rejects user-defined `[permissions]` profiles that omit
`default_permissions` so we do not silently guess among custom profiles.
- Preserves compatibility behavior for implicit defaults: bare
`network.enabled = true` allows runtime network without starting the
managed proxy, explicit profile proxy policy still starts the proxy, and
implicit workspace/add-dir roots keep legacy metadata carveouts.

## Verification

- `cargo test -p codex-core builtin --lib`
- `cargo test -p codex-core profile_network_proxy_config`
- `cargo test -p codex-core
implicit_builtin_workspace_profile_preserves_add_dir_metadata_carveouts`
- `cargo test -p codex-core
permissions_profiles_network_enabled_allows_runtime_network_without_proxy`
- `cargo test -p codex-core
permissions_profiles_proxy_policy_starts_managed_network_proxy`

## Documentation

Public Codex config docs should mention these built-in names when the
`[permissions]` config format is ready to document as stable.









---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/19900).
* #20041
* #20040
* #20037
* #20035
* #20034
* #20033
* #20032
* #20030
* #20028
* #20027
* #20026
* #20024
* #20021
* #20018
* #20016
* #20015
* #20013
* #20011
* #20010
* #20008
* __->__ #19900
2026-04-28 11:21:39 -07:00
Friel
480ef646aa fix(tui): update plan mode task completion test 2026-04-28 18:11:31 +00:00
viyatb-oai
3afb185a4f fix(network-proxy): tighten network proxy bypass defaults (#20002)
## Why
Managed sessions use `NO_PROXY` to keep a small set of destinations on
the direct path by default. The old default also bypassed all IPv4
link-local addresses in `169.254.0.0/16`, which includes metadata
endpoints such as `169.254.169.254`. Because `NO_PROXY` is evaluated by
the client before the request reaches the managed proxy, requests to
that range could skip proxy-side allowlist and local-binding checks
entirely. On hosts where a link-local metadata service is reachable,
that creates a path to sensitive environment metadata or credentials
outside the intended enforcement point.

## What changed
- remove the default IPv4 link-local `169.254.0.0/16` bypass from the
managed proxy environment
- keep the existing loopback and private-network defaults unchanged
- update the regression assertion to lock in the narrower default

## Security impact
Link-local requests now stay on the managed-proxy path by default, so
the proxy can apply configured policy before they reach metadata-style
endpoints or other link-local services.

## Verification
- `cargo test -p codex-network-proxy`

Co-authored-by: Codex <noreply@openai.com>
2026-04-28 10:51:43 -07:00
stefanstokic-oai
4c68bd728f External agent session support (#19895)
## Summary

This extends external agent detection/import beyond config artifacts so
Codex can detect recent sessions files from the external agent home and
import them into Codex rollout history.

## What changed

- Added a focused `external_agent_sessions` module for:
  - session discovery
  - source-record parsing
  - rollout construction
  - import ledger tracking
- Wired session detection/import into the app-server external agent
config API.
- Added compaction handling so large imported sessions can be resumed
safely before the first follow-up turn.

## Testing

Added coverage for:
- recent-session detection
- custom-title handling
- recency filtering
- dedupe and re-detect-after-source-change behavior
- visible imported turn construction
- backward-compatible import payload deserialization
- end-to-end RPC import flow
- rejection of undetected session paths
- repeat-import behavior
- large-session compaction before first follow-up

Ran:
- `cargo test -p codex-app-server external_agent_config_import_ --test
all`
2026-04-28 17:42:36 +00:00
Felipe Coury
a036584104 fix(tui): let esc exit empty shell mode (#19986)
## Summary

- exit shell mode when `Esc` is pressed while the absorbed `!` is the
only input
- add direct regression coverage plus a composer snapshot for the
restored normal prompt state

## Root cause

Shell mode stores the leading `!` outside the editable textarea. After
typing only `!`, the textarea is empty but the composer is still in bash
mode, so the existing empty-composer `Esc` handling never runs.

## Validation

- `just fmt`
- `cargo test -p codex-tui
bottom_pane::chat_composer::tests::esc_exits_empty_shell_mode`
- `cargo test -p codex-tui
bottom_pane::chat_composer::tests::footer_mode_snapshots`
- `cargo insta pending-snapshots`

`cargo test -p codex-tui` still reports unrelated existing `/status`
snapshot drift in this local environment because the rendered
permissions text is `workspace-write with network access` instead of the
older `read-only` fixture text.
2026-04-28 14:35:24 -03:00
canvrno-oai
bc5a1b961e Move local /resume cwd filtering into thread/list (#19931)
Move local resume and fork cwd filtering to `thread/list` instead of
filtering in the TUI. This makes the `/resume` menu feel slightly faster
to load when working in repos with many historical threads, and
centralizes the cwd filtering in app-server.

**Affected:**
- /resume from inside the TUI.
- codex resume with no session ID and without --last
- codex resume --all
- codex fork with no session ID and without --last
- codex fork --all

**Not affected:**
- codex resume <id>
- codex fork <id>
- codex resume --last
- codex fork --last

Steps to test performance improvement in a real Codex environment:
- Launch `codex resume` using compiled binary in a directory that has
seen many threads.
- Launch `codex resume` using release binary in same directory.
- Observe difference in time-to-full-page as threads load.
2026-04-28 10:35:10 -07:00
Felipe Coury
c6bcd27832 feat(tui): suggest plan mode from composer drafts (#19901)
## Summary

- suggest Plan mode when the current composer draft contains the
standalone word `plan`
- shares the Codex App heuristics for detection
- excludes things line `/plan` and the word plan in shell mode
- reuse the existing `Shift+Tab` mode cycle and add thread-scoped
dismissal with `Esc`
- replace the normal footer hint while the reminder is visible so the
statusline stays anchored


https://github.com/user-attachments/assets/01123ae8-cee6-4e95-b563-44655c071cde

## Why

The desktop app already nudges users toward Plan mode when their draft
clearly signals planning intent. The TUI had the underlying `/plan` and
`Shift+Tab` flows, but no equivalent reminder at the moment the user was
most likely to benefit from them.

## Details

The reminder is shown only when Plan mode is available, the draft
contains standalone `plan`, the user is not already in Plan mode, the
composer is actionable, and the current thread has not dismissed the
reminder. Slash-command and shell-command drafts are excluded.

The first implementation used an extra composer row, but that moved the
statusline whenever the heuristic fired. This version keeps the layout
stable by rendering the reminder in the existing footer row instead.

## Validation

- `INSTA_UPDATE=always cargo test -p codex-tui
chatwidget::tests::plan_mode::plan_mode_nudge -- --nocapture`
- `just fmt`
- `just fix -p codex-tui`
- `./tools/argument-comment-lint/run.py -p codex-tui`
- `cargo insta pending-snapshots`
- `git diff --check`
2026-04-28 14:34:10 -03:00
maja-openai
273c2e21a9 Clarify network approval auto-review prompts (#19907)
## Why

Network access approval prompts were showing the generic retry reason,
which made auto-review focus on the blocked connection instead of the
command that caused it. This makes network approvals easier to assess by
telling the reviewer to evaluate whether the triggering command was
authorised by the user and within policy, and to treat the network call
as acceptable when it is a reasonable consequence of that command.

## What changed

- Split guardian approval request prompt rendering so `NetworkAccess`
has a dedicated branch.
- For network requests, show `Network approval context` and `Network
access JSON` instead of `Retry reason` / `Planned action JSON`.
- Added regression coverage for the network approval prompt wording and
for omitting retry reason in this case.

## Verification

- `cargo test -p codex-core
guardian::tests::build_guardian_prompt_items_explains_network_access_review_scope`
2026-04-28 10:25:37 -07:00
mchen-oai
01de13b7e6 Record MCP result telemetry on mcp.tools.call spans (#19509)
## Why
- Without change: MCP tool call spans include request-side details such
as server, tool, call ID, connector, session, and turn.
- Issue: Some useful telemetry is only known by the MCP server after it
handles the tool call, such as target identity or whether the call
triggered a user-facing flow.

## What Changed
- With change: Codex reads allowlisted telemetry from
`_meta["codex/telemetry"]["span"]` and records it on the
`mcp.tools.call` span.
- Adds span fields for `codex.mcp.target.id` and
`codex.mcp.user_flow.triggered`, with strict type checks and bounded
target ID length.


## Verification
`codex-rs/core/src/mcp_tool_call_tests.rs`
2026-04-28 17:20:38 +00:00
evawong-oai
0670d8971a Enforce workspace metadata protections in Seatbelt (#19847)
## Summary

Translate FileSystemSandboxPolicy project root metadata carveouts into
macOS Seatbelt rules.

## Scope

1. Thread protected metadata names into Seatbelt access roots.
2. Ask FileSystemSandboxPolicy whether each metadata carveout is
writable.
3. Emit Seatbelt deny rules that block creating or replacing protected
metadata names under writable roots.
4. Add coverage for first time metadata creation and read only
carveouts.

## Reviewer Focus

1. This PR only covers the macOS sandbox adapter.
2. The policy decision comes from FileSystemSandboxPolicy.
3. Read only subpath carveouts and metadata protection checks should
compose cleanly.

## Stack

1. Policy primitive: #19846
2. macOS Seatbelt adapter: this PR
3. Shell preflight UX: #19848
4. Runtime profile propagation: #19849
5. Linux bubblewrap adapter: #19852

## Validation

1. formatting for codex sandboxing
2. codex sandboxing package tests
2026-04-28 10:13:00 -07:00
efrazer-oai
f6797c3ac6 feat: verify agent identity JWTs with JWKS (#19764) 2026-04-28 09:56:20 -07:00
colby-oai
6138063656 Strip connector provenance metadata from custom MCP tools (#19875)
# Summary 
This prevents non-codex_apps MCP servers from spoofing connector
provenance metadata.
2026-04-28 12:43:26 -04:00
mchen-oai
ccec84b148 Add turn start timestamp to turn metadata (#19473)
## Why
- Without change: MCP tool calls receive
`_meta["x-codex-turn-metadata"]` with `session_id` and `turn_id`.
- Issue: MCP servers may want the turn start timestamp to measure
internal latency relative to turn start.

## What Changed
- With change: turn metadata now includes `turn_started_at_unix_ms`,
which is propagated to MCP tool calls in
`_meta["x-codex-turn-metadata"]`.

## Verification
- `codex-rs/core/src/mcp_tool_call_tests.rs`
- `codex-rs/core/src/turn_metadata_tests.rs`
- `codex-rs/core/src/turn_timing_tests.rs`
- `codex-rs/core/tests/responses_headers.rs`
- `codex-rs/core/tests/suite/search_tool.rs`
2026-04-28 16:36:59 +00:00
Eric Traut
4e0cf945b7 Terminate stdio MCP servers on shutdown to avoid process leaks (#19753)
## Why

Several bug reports describe thread shutdown (including subagent
threads) leaving stdio MCP server processes behind. These reports all
point at the same lifecycle gap: Codex launches stdio MCP servers, but
the session-level shutdown path does not explicitly close MCP clients or
terminate the server process tree.

Fixes #12491
Fixes #12976
Fixes #18881
Fixes #19469

## History

This is best understood as a regression/coverage gap in MCP session
lifecycle management, not as stdio MCP cleanup being absent all along.
#10710 added process-group cleanup for stdio MCP servers, but that
cleanup only runs when the `RmcpClient`/transport is dropped. The older
reports (#12491 and #12976) came after that cleanup existed, which
suggests the remaining problem was that some higher-level shutdown paths
kept the MCP manager alive or replaced it without explicitly draining
clients. The newer reports (#18881 and #19469) exposed the same family
around manager replacement and shutdown.

## What changed

- Added an explicit stdio MCP process handle in `codex-rmcp-client` so
local MCP servers terminate their process group and executor-backed MCP
servers call the executor process terminator.
- Added `RmcpClient::shutdown()` and manager-level MCP shutdown draining
so session shutdown, channel-close fallback, MCP refresh, and connector
probing stop owned MCP clients.
- Added regression coverage that starts a stdio MCP server, begins an
in-flight blocking tool call, shuts down the client, and asserts the
server process exits.

## Verification

- `cargo test -p codex-rmcp-client`
- `cargo test -p codex-mcp`
- `just fix -p codex-rmcp-client`
- `just fix -p codex-mcp`
- `just fix -p codex-core`

- Manual before/after validation with a temporary repro script:
- Pre-fix binary from `HEAD^` (`fed0a8f4fa`): reproduced the leak with
surviving MCP server and child PIDs, `survivors=[77583, 77592]`,
`leaked=true`.
- Post-fix binary from this branch (`67e318148b`): verified both MCP
processes were gone after interrupting `codex exec`, `survivors=[]`,
`leaked=false`.
2026-04-28 09:29:57 -07:00
Eric Traut
087c9c1f1f TUI: use cumulative turn duration for worked-for separator (#19929)
## Why

Fixes #19814.

The TUI's current `Worked for ...` timing behavior is a leftover from
#9599. At that point, models could emit multiple assistant messages in
one turn for preambles/commentary, but the TUI did not yet have a
reliable signal that an assistant message was the final answer when it
started streaming. To avoid showing an ever-growing elapsed time on each
preamble separator, #9599 made the separator timer incremental by
tracking elapsed time since the previous separator.

That workaround is no longer the right model for the final
completed-turn display. Since then, #16638 added protocol-native turn
timing, including `duration_ms` on turn completion. With that cumulative
duration available at the point where the TUI renders the completed-turn
separator, the UI can show the actual turn duration directly instead of
carrying per-separator timing state.

## What Changed

- Thread `duration_ms` into `ChatWidget::on_task_complete` from both
legacy `TurnCompleteEvent` handling and app-server `TurnCompleted`
notifications.
- Use `duration_ms` for the final `Worked for ...` separator, falling
back to the status indicator timer only when the protocol duration is
unavailable.
- Keep mid-turn separators before later assistant text as plain visual
dividers instead of clocked `Worked for ...` separators.
- Remove the old incremental separator timer state and helper
(`last_separator_elapsed_secs` / `worked_elapsed_from`).
- Add a snapshot regression test for a turn that runs a command and then
completes with a final answer, verifying the final separator uses the
cumulative turn duration.

## Verification

- `cargo test -p codex-tui
final_worked_for_uses_cumulative_turn_duration_snapshot`
- `just fix -p codex-tui`

Manual repro prompt:

```text
Manual timing repro. First send a short preamble/commentary sentence before using tools. Then run exactly this shell command: sleep 75; echo MANUAL_TIMING_DONE. After the command finishes, give a final answer that says "done". Do not skip the preamble.
```

After this change, the mid-turn break before the final answer should be
a plain divider, and the final completed-turn separator should show
`Worked for ...` using the cumulative turn duration.

Before:
<img width="414" height="102" alt="Screenshot 2026-04-27 at 10 09 01 PM"
src="https://github.com/user-attachments/assets/b9e2ce01-2460-40e4-a5c4-c9ba8add2557"
/>


After:
<img width="485" height="149" alt="Screenshot 2026-04-27 at 10 09 07 PM"
src="https://github.com/user-attachments/assets/d24089ae-d4e2-41b6-b966-07c98706ead4"
/>
2026-04-28 09:24:29 -07:00
jif-oai
5b7d6f5c4f feat: house-keeping memories 3 (#20005)
Move stuff in memories, no behavioural change expected
2026-04-28 18:13:35 +02:00
evawong-oai
0156b1e61f [sandbox] Enforce protected workspace metadata paths (#19846)
## Summary

Make FileSystemSandboxPolicy the semantic source of truth for project
root metadata protection. Under writable roots, `.git`, `.codex`, and
`.agents` stay protected unless user policy grants an explicit write
rule for that metadata path.

## Scope

1. Add `protected_metadata_names` to `WritableRoot`.
2. Teach `FileSystemSandboxPolicy::can_write_path_with_cwd` to reject
protected metadata writes under writable roots unless explicitly
allowed.
3. Default workspace write profiles to protect `.git`, `.codex`, and
`.agents`.
4. Add the Linux fallback setup needed before Linux enforcement lands
later in the stack.

## Reviewer Focus

1. The policy decision belongs in FileSystemSandboxPolicy, not shell
command parsing.
2. Legacy SandboxPolicy remains a compatibility projection, not the
source of the new rule.
3. Explicit user write rules can still opt into these metadata paths.

## Stack

1. Policy primitive: this PR
2. macOS Seatbelt adapter: #19847
3. Shell preflight UX: #19848
4. Runtime profile propagation: #19849
5. Linux bubblewrap adapter: #19852

## Validation

1. codex protocol permissions tests
2. formatting for codex protocol and codex linux sandbox
3. diff whitespace check
2026-04-28 09:10:41 -07:00
Felipe Coury
5e737372ee feat(tui): add configurable keymap support (#18593)
## Why

The TUI currently handles keyboard shortcuts as hard-coded event matches
spread across app, composer, pager, list, approval, and navigation code.
That makes shortcuts hard to customize, makes displayed hints easy to
drift from actual behavior, and makes future keymap work riskier because
there is no central action inventory.

This PR adds the foundation for configurable, action-based keymaps
without adding the interactive remapping UI yet. Onboarding
intentionally stays on fixed startup shortcuts because users cannot
reasonably configure keymaps before completing onboarding.

This is PR1 in the keymap stack:

- PR1: #18593: configurable keymap foundation
- PR2: #18594: `/keymap` picker and guided remapping UI
- PR3: #18595: Vim composer mode and the remap option

## Design Notes

The new model resolves named actions into concrete runtime bindings once
from config, then passes those bindings to the UI surfaces that handle
input or render shortcut hints.

The main concepts are:

- **Context**: a scope where an action is active, such as `global`,
`chat`, `composer`, `editor`, `pager`, `list`, or `approval`.
- **Action**: a named operation inside a context, such as
`global.open_transcript`, `composer.submit`, or `pager.close`.
- **Binding**: one or more single-key shortcuts assigned to an action,
written as config strings such as `ctrl-t`, `alt-backspace`, or
`page-down`. Multi-step sequences such as `ctrl-x ctrl-s`, `g g`, or
leader-key flows are not part of this PR.
- **Resolution order**: context-specific config wins first, supported
global fallbacks come next, and built-in defaults fill in anything
unset.
- **Explicit unbinding**: an empty array removes an action binding in
that scope and does not fall through to a fallback binding.
- **Conflict validation**: a resolved keymap rejects duplicate active
bindings inside the same scope so one keypress cannot dispatch two
actions.

## What Changed

- Added `TuiKeymap` config support under `[tui.keymap]`, including typed
contexts/actions, key alias normalization, generated schema coverage,
and user-facing config errors.
- Added `RuntimeKeymap` resolution in `codex-rs/tui/src/keymap.rs`,
including fallback precedence, built-in defaults, explicit unbinding,
and per-context conflict validation.
- Rewired existing TUI handlers to consume resolved keymap actions
instead of directly matching hard-coded keys in each component.
- Updated key hint rendering and footer/pager/list surfaces so displayed
shortcuts follow the resolved keymap.
- Kept onboarding shortcuts fixed in
`codex-rs/tui/src/onboarding/keys.rs` instead of exposing them through
`[tui.keymap]`.

## Validation

The branch includes focused coverage for config parsing, key
normalization, runtime fallback resolution, explicit unbinding,
duplicate-key conflict validation, default keymap consistency,
onboarding startup key behavior, and UI hint snapshots affected by
resolved key bindings.
2026-04-28 12:52:25 -03:00
Eric Traut
a61c785040 Reset TUI keyboard reporting on exit (#19625)
## Why

Codex enables enhanced keyboard reporting while the TUI owns the
terminal. In iTerm2, exiting the TUI with Ctrl+C can intermittently
leave the parent shell receiving raw CSI-u / `modifyOtherKeys` fragments
instead of normal key input.

Final terminal cleanup should put the parent shell back into normal
keyboard reporting even if the terminal misses the usual stack pop.

Fixes #19553.

## What Changed

- Move TUI keyboard enhancement setup and detection into
`tui/src/tui/keyboard_modes.rs`.
- Add an exit-only `restore_after_exit()` path that performs the normal
keyboard enhancement pop plus unconditional keyboard enhancement and
`modifyOtherKeys` resets.
- Keep temporary restore paths, such as external-editor handoff, using
the balanced stack pop behavior.

## Confidence

Medium. This is a speculative fix: I was not able to reproduce the
reported iTerm2 behavior manually, but the symptoms line up with
terminal keyboard reporting state surviving Codex exit. The added reset
sequences are scoped to final TUI shutdown and should be harmless when
the terminal is already clean.
2026-04-28 08:51:44 -07:00
friel-openai
598bbcdb58 Preserve assistant phase for replayed messages (#19832) 2026-04-28 08:46:13 -07:00
jif-oai
21e19912e0 feat: house-keeping memories 2 (#20000)
Just move metrics in a dedicated file
2026-04-28 17:26:44 +02:00
jif-oai
5a79dfab7c feat: house-keeping memories 1 (#19998)
Just move metrics in a dedicated file
2026-04-28 17:11:49 +02:00
jif-oai
1b74360365 feat: skip memory startup when Codex rate limits are low (#19990)
## Why

Memory startup runs in the background after an eligible turn, but it can
consume Codex backend quota at exactly the wrong time: when the user is
already near a rate-limit boundary. This PR adds a guard so the memory
pipeline backs off when the Codex rate-limit snapshot says the remaining
budget is too low.

## What Changed

- Added `memories.min_rate_limit_remaining_percent` with a default of
`25`, clamped to `0..=100`, and regenerated `core/config.schema.json`.
- Added `codex-rs/memories/write/src/guard.rs`, which fetches Codex
backend rate limits before memory startup and skips phase 1 / phase 2
when the Codex limit is reached or either tracked window is above the
configured usage ceiling.
- Keeps startup best-effort: non-Codex auth or rate-limit fetch/client
failures preserve the existing memory startup behavior.
- Records a `codex.memory.startup` counter with
`status=skipped_rate_limit` when startup is skipped.
- Added config parsing/clamping coverage and guard unit tests.

## Verification

- Added `codex-rs/memories/write/src/guard_tests.rs` for threshold,
primary/secondary window, and reached-limit behavior.
- Added config tests for TOML parsing and clamping.
2026-04-28 17:07:16 +02:00
efrazer-oai
0e8d6b8765 fix: configure AgentIdentity AuthAPI base URL (#19904)
## Summary

AgentIdentity runtime loading currently registers tasks against a single
hardcoded AuthAPI base URL. That works for production, but local and
staging validation may need registration to target a different
authapi-login-provider without baking internal staging service URLs into
the OSS binary.

This PR adds a small config surface for
`agent_identity_authapi_base_url` and threads it through the existing
auth-loading path as a direct argument. Explicit config wins. Without
config, task registration keeps using the production AuthAPI URL,
matching the current default behavior.

## Stack

1. openai/codex#19762 - `refactor: make auth loading async` (merged)
2. openai/codex#19763 - `refactor: load agent identity runtime eagerly`
3. This PR - `fix: configure AgentIdentity AuthAPI base URL`
4. openai/codex#19764 - `feat: verify agent identity JWTs with JWKS`

## Design decisions

- Keep the existing auth-loading shape and pass the new value as an
argument. This avoids another wrapper loader and keeps the call path
readable.
- Add config instead of embedding internal staging URLs. Environments
that need a non-production AuthAPI can configure it explicitly.
- Keep the default AuthAPI registration URL as production.
`chatgpt_base_url` remains separate and is used by the follow-up JWKS
verification PR for fetching public keys from the ChatGPT backend route.
- Resolve the AuthAPI base URL inside AgentIdentity loading, because
task registration is the only consumer of this value.

## Testing

Tests: targeted Rust checks, AgentIdentity auth tests, config schema
regeneration, formatter/fix pass, and whitespace diff check.
2026-04-28 08:06:45 -07:00
jif-oai
a9e5c34083 feat: trigger memories from user turns with cooldown (#19970)
## Why

Memory startup was tied to thread lifecycle events such as create, load,
and fork. That can run memory work before a thread receives real user
input, and it makes startup cost scale with thread management instead of
actual turns. Moving the trigger to `thread/sendInput` keeps memory
startup aligned with the first real user turn and lets it use the
current thread config at turn time.

The idea is to prevent ghost cost due to pre-warm triggered by the app

Turn-based startup can also make global phase-2 consolidation easier to
request repeatedly, so this adds a success cooldown and tightens the
default startup scan window.

## What Changed

- Start `codex_memories_write::start_memories_startup_task` after a
non-empty `thread/sendInput` turn is submitted, instead of from thread
create/load/fork paths:
d4a6885b78/codex-rs/app-server/src/codex_message_processor.rs (L6477-L6487)
- Expose `CodexThread::config()` so app-server can pass the live config
into memory startup at turn time.
- Add a six-hour successful-run cooldown for global phase-2
consolidation via `SkippedCooldown`:
d4a6885b78/codex-rs/state/src/runtime/memories.rs (L963-L966)
- Reduce memory startup defaults to at most 2 rollouts over 10 days:
d4a6885b78/codex-rs/config/src/types.rs (L31-L34)

## Verification

Updated the memory runtime coverage around phase-2 reclaim behavior,
including `phase2_global_lock_respects_success_cooldown`.

---------

Co-authored-by: Codex <noreply@openai.com>
2026-04-28 16:23:13 +02:00
jif-oai
fa127be25f Stabilize memory Phase 2 input ordering (#19967)
## Why

Phase 2 still needs to choose the most relevant stage-1 memory outputs
by usage and recency, but exposing that ranking as the rendered
`raw_memories.md` order creates unnecessary large diff. Usage-count or
timestamp changes can reshuffle otherwise unchanged memories, making the
workspace diff noisy and giving the consolidation prompt a misleading
recency signal from file position.
This fix will reduce token consumption

## What Changed

- Keep the existing top-N Phase 2 selection ranking by `usage_count`,
`last_usage`, `source_updated_at`, and `thread_id`.
- Return the selected rows in stable ascending `thread_id` order before
syncing Phase 2 filesystem inputs.
- Update the memory README, raw memories header, and consolidation
prompt so they describe the stable order and tell the prompt to use
metadata and workspace diffs instead of file order as the recency
signal.
- Adjust the memory runtime tests to use deterministic thread IDs and
assert the stable return order separately from the ranked selection
semantics.

## Test Coverage

- Existing memory runtime tests in
`codex-rs/state/src/runtime/memories.rs` now cover the stable returned
ordering for Phase 2 inputs.

---------

Co-authored-by: Codex <noreply@openai.com>
2026-04-28 13:32:05 +02:00
jif-oai
54d1401170 feat: fix hinting 3 (#19963)
Fix https://github.com/openai/codex/pull/19805#discussion_r3153265562
2026-04-28 13:12:51 +02:00
jif-oai
b7c0f26910 feat: fix hinting 2 (#19961)
Fix this:
https://github.com/openai/codex/pull/19805#discussion_r3153265562
2026-04-28 13:06:41 +02:00
jif-oai
431ebeaef7 feat: split memories part 2 (#19860)
Keep extracting memories out of core and moving the write trigger in the
app-server
This is temporary and it should move at the client level as a follow-up
This makes core fully independant from `codex-memories-write`

---------

Co-authored-by: Codex <noreply@openai.com>
2026-04-28 13:03:28 +02:00
jif-oai
fd36838cf3 Add MultiAgentV2 root and subagent context hints (#19805)
## Why

MultiAgentV2 sessions need startup guidance that matches the role of the
thread that is actually being created. Root agents and subagents have
different responsibilities, and forked subagents can inherit parent
rollout history. If the parent hint is carried into the child context,
the child can see stale or conflicting developer guidance before its own
session-specific context is added.

## What changed

- Added `features.multi_agent_v2.root_agent_usage_hint_text` and
`features.multi_agent_v2.subagent_usage_hint_text` config fields,
including schema/config parsing support.
- Injected the matching root or subagent hint into the initial context
as its own developer message when `multi_agent_v2` is enabled.
- Filtered configured MultiAgentV2 usage-hint developer messages out of
forked parent history so a child thread receives fresh guidance for its
own session source/config.
- Added targeted coverage for config parsing, initial-context rendering,
feature-config deserialization, and forked-history filtering.

## Context examples

With this config:

```toml
[features.multi_agent_v2]
enabled = true
root_agent_usage_hint_text = "Root guidance."
subagent_usage_hint_text = "Subagent guidance."
```

A root thread initial context renders the root hint as a standalone
developer message:

```text
[developer]
<existing developer context, when present>

[developer]
Root guidance.
```

A subagent thread initial context renders the subagent hint instead:

```text
[developer]
<existing developer context, when present>

[developer]
Subagent guidance.
```

When a subagent forks parent history, any parent developer message whose
text exactly matches the configured MultiAgentV2 root or subagent hint
is omitted from the forked history before the child receives its fresh
subagent hint.
2026-04-28 12:31:45 +02:00
xli-oai
803705f795 Add remote plugin uninstall API (#19456)
## Summary
- Adds the remote `plugin/uninstall` request form using required
`pluginId` plus optional `remoteMarketplaceName`, while preserving local
`pluginId` uninstall.
- Adds `codex_core_plugins::remote::uninstall_remote_plugin` for the
deployed ChatGPT plugin backend uninstall path and validates the backend
returns the same id with `enabled: false`.
- Routes app-server remote uninstall through feature checks, remote
plugin id validation, backend mutation, local downloaded cache deletion,
cache clearing, docs, and regenerated protocol schemas.

## Tests
- `just write-app-server-schema`
- `just fmt`
- `cargo test -p codex-app-server-protocol
plugin_uninstall_params_serialization_omits_force_remote_sync`
- `cargo test -p codex-app-server plugin_uninstall --test all`
- `cargo test -p codex-app-server plugin_uninstall`
- `cargo build -p codex-cli`
- `CODEX_BIN=/Users/xli/code/codex/codex-rs/target/debug/codex python3
/Users/xli/.codex/skills/xli-test-marketplace-api/scripts/run_marketplace_api_matrix.py`
(44 pass / 0 fail)
- `just fix -p codex-app-server-protocol -p codex-app-server -p
codex-tui`
- `just fix -p codex-app-server`
2026-04-28 03:27:53 -07:00
xl-openai
7d72fc8f53 feat: Cache remote plugin bundles on install (#19914)
Remote installs now fetch, validate, download, and cache the plugin
bundle locally
2026-04-28 00:53:27 -07:00
Eric Traut
b985768dc1 Add codex update command (#19933)
## Why

Addresses #9274

Running `codex update` currently starts an interactive Codex session
with `update` as the prompt. That is a rough edge for users who expect a
direct self-update command after seeing the existing update notice, and
it forces them to copy the suggested package-manager command manually.

## What changed

- Added a top-level `codex update` subcommand.
- Reused the existing install-channel detection and update command
runner that the TUI already uses for update prompts.
- Exposed the update-action lookup from `codex-tui` so the CLI can
invoke the same behavior.
- Added CLI coverage to ensure `codex update` is parsed as a subcommand
instead of becoming an interactive prompt.

## Verification

- `cargo test -p codex-cli`
- `cargo test -p codex-tui update_action::tests`
2026-04-27 23:33:59 -07:00
Michael Bolin
0a32c8b396 app-server-protocol: mark permission profiles experimental (#19899)
## Why

`PermissionProfile` is now the canonical internal permissions
representation, but the app-server wire shape is still intentionally
unstable while the migration continues. Stable app-server clients should
not see or generate code for these fields until the wire format settles.

## What changed

- Marks every app-server v2 field that sends `PermissionProfile` as
experimental, including `command/exec`, `thread/start`, `thread/resume`,
`thread/fork`, and `turn/start` request/response payloads.
- Enables per-field experimental inspection for `command/exec`, so
`permissionProfile` is gated without making the entire method
experimental.
- Fixes the generated TypeScript schema filter to be comment-aware. The
previous scanner treated apostrophes inside doc comments as string
delimiters, so some experimental fields leaked into stable TypeScript
even though stable JSON was filtered correctly.

## Verification

- `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/19899).
* #19900
* __->__ #19899
2026-04-28 06:08:34 +00:00
Michael Bolin
341550c275 permissions: store thread sessions as profiles (#19776)
## Why

After thread sessions have a required `PermissionProfile`, the TUI no
longer needs to cache a separate legacy `SandboxPolicy` in
`ThreadSessionState`. Keeping the legacy field would reintroduce two
permission authorities in the session cache and make later
replay/switching logic easier to get wrong.

This PR keeps legacy app-server compatibility at the ingestion boundary:
old `sandbox` response values are still accepted, but they are
immediately converted to a cwd-anchored profile.

## What Changed

- Removes `ThreadSessionState.sandbox_policy`.
- Updates active-session permission syncing to write only the current
`PermissionProfile`.
- Updates thread-read/replay/test fixtures to use profiles as the cached
session permission source.
- Leaves legacy `sandbox` fields in app-server request/response protocol
paths unchanged; those are compatibility boundaries and are converted
before entering cached TUI state.

## Verification

- `cargo test -p codex-tui thread_session_state::tests --lib`
- `cargo test -p codex-tui
inactive_thread_started_notification_initializes_replay_session --lib`
- `cargo test -p codex-tui thread_events --lib`
- `just fix -p codex-tui`




































---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/19776).
* #19900
* #19899
* __->__ #19776
2026-04-28 05:49:58 +00:00
Eric Traut
92fb848065 Allow large remote app-server resume responses (#19920)
## Why

Remote TUI resume uses the app-server websocket client. That client
inherited tungstenite's default `16 MiB` frame limit, so a large saved
session could make `thread/resume` return a single JSON-RPC response
frame that the client rejected before the TUI could deserialize or
render it.

Fixes #19837

## What Changed

- Configure the remote app-server websocket client with a bounded `128
MiB` max frame/message size.
- Preserve the concrete remote worker exit reason when completing
pending requests after a transport/read failure instead of replacing it
with a generic channel-closed error.
- Add a regression test that sends a single `>16 MiB` JSON-RPC response
frame and verifies the typed request succeeds.

Note: This isn't a perfect fix. It really just moves the limit to a much
larger value. I looked at a bunch of other potential fixes (both
server-side and client-side), and they all involved significant
complexity, had backward-compatibility impact, or impacted performance
of common use cases. This simple fix should address the vast majority of
remote use cases.

## Verification

I reproed the problem locally using a long rollout. Verified that fix
addresses connection drop.
2026-04-27 22:44:10 -07:00
Michael Bolin
fc2a69107c permissions: derive snapshot sandbox projections (#19775)
## Why

`ThreadConfigSnapshot` is used by app-server and thread metadata code as
a stable view of active runtime settings. Keeping both `sandbox_policy`
and `permission_profile` in the snapshot duplicates permission state and
makes it possible for the legacy projection to drift from the canonical
profile.

The legacy `sandbox` value is still needed at app-server compatibility
boundaries, so this PR derives it on demand from the snapshot profile
and cwd instead of storing it.

## What Changed

- Removes `ThreadConfigSnapshot.sandbox_policy`.
- Adds `ThreadConfigSnapshot::sandbox_policy()` as a compatibility
projection from `permission_profile` plus `cwd`.
- Updates app-server response/metadata code and tests to call the
projection only where legacy fields still exist.
- Keeps snapshot construction profile-only so split filesystem rules,
disabled enforcement, and external enforcement remain represented by the
canonical profile.

## Verification

- `cargo test -p codex-app-server
thread_response_permission_profile_preserves_enforcement --lib`
- `cargo test -p codex-core
dispatch_reclaims_stale_global_lock_and_starts_consolidation --lib`



































---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/19775).
* #19900
* #19899
* #19776
* __->__ #19775
2026-04-27 22:30:47 -07:00
Michael Bolin
bf38def44e permissions: make SessionConfigured profile-only (#19774)
## Why

`SessionConfiguredEvent` is the internal event that tells clients what
permissions are active for a session. Emitting both `sandbox_policy` and
`permission_profile` leaves two possible authorities and forces every
consumer to decide which one to honor. At this point in the migration,
the profile is expressive enough to represent managed, disabled, and
external sandbox enforcement, so the internal event can be profile-only.

The wire compatibility concern is older serialized events or rollout
data that only contain `sandbox_policy`; those still need to
deserialize.

## What Changed

- Removes `sandbox_policy` from `SessionConfiguredEvent` and makes
`permission_profile` required.
- Adds custom deserialization so old payloads with only `sandbox_policy`
are upgraded to a cwd-anchored `PermissionProfile`.
- Updates core event emission and TUI session handling to sync
permissions from the profile directly.
- Updates app-server response construction to derive the legacy
`sandbox` response field from the active thread snapshot instead of from
`SessionConfiguredEvent`.
- Updates yolo-mode display logic to treat both
`PermissionProfile::Disabled` and managed unrestricted filesystem plus
enabled network as full-access, while still preserving the distinction
between no sandbox and external sandboxing.

## Verification

- `cargo test -p codex-protocol session_configured_event --lib`
- `cargo test -p codex-protocol serialize_event --lib`
- `cargo test -p codex-exec session_configured --lib`
- `cargo test -p codex-app-server
thread_response_permission_profile_preserves_enforcement --lib`
- `cargo test -p codex-core
session_configured_reports_permission_profile_for_external_sandbox
--lib`
- `cargo test -p codex-tui session_configured --lib`
- `cargo test -p codex-tui
yolo_mode_includes_managed_full_access_profiles --lib`


































---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/19774).
* #19900
* #19899
* #19776
* #19775
* __->__ #19774
2026-04-27 22:06:47 -07:00
Eric Traut
5ba908d179 Avoid persisting ShutdownComplete after thread shutdown (#19630)
## Why

Fixes #19475.

`codex exec` can finish successfully and then emit an `ERROR` on stderr:

```text
failed to record rollout items: thread <id> not found
```

That happens because shutdown closes the live thread writer before
emitting `ShutdownComplete`. The terminal event was still using the
normal `send_event_raw` path, so it tried to append rollout items
through a recorder that had already been removed. The answer is correct,
but wrappers that treat stderr as failure can retry completed exec runs.

This looks like a likely recent regression from
[#18882](https://github.com/openai/codex/pull/18882), which routed live
thread writes through `ThreadStore` and added the shutdown-time live
writer close. I have not bisected this, so the PR treats #18882 as the
likely source based on the affected shutdown code path rather than a
proven first-bad commit.

## What Changed

`ShutdownComplete` now bypasses rollout persistence after thread
shutdown and is delivered directly to clients. The shutdown path still
records the protocol event in the rollout trace before delivery,
preserving trace visibility without attempting a post-shutdown
thread-store append.

The change also adds a regression test with the in-memory thread store
to assert that shutdown creates and shuts down the live thread without
appending another item after shutdown.
2026-04-27 22:02:08 -07:00
Eric Traut
b7e5588d18 Clarify PR template invitation requirement (#19912)
Addresses #19856

## Summary
- Clarifies that external code contributions are invitation only.
- Points contributors to `docs/contributing.md` for the full policy
instead of using the previous warning phrasing.
2026-04-27 21:45:15 -07:00
marksteinbrick-oai
6a8df2b61d [codex-analytics] include user agent in default headers (#17689)
## Summary
Adds the standard Codex `User-Agent` to shared default headers so the
responses-api WS handshake carries the same client OS and version
context as HTTP requests.

## Testing
- `cargo test -p codex-core
build_ws_client_metadata_includes_window_lineage_and_turn_metadata`
- `cargo test -p codex-core --test all responses_websocket`
2026-04-27 21:32:10 -07:00
efrazer-oai
c08177f7d0 refactor: load agent identity runtime eagerly (#19763)
## Summary

AgentIdentity auth previously registered the process task lazily behind
a `OnceCell`. That meant the auth object could be constructed before its
runtime task binding was known.

This PR makes AgentIdentity auth load the runtime task at auth load time
and stores the resulting process task id directly on the auth object.
The model-provider call path can then read a concrete task id instead of
handling a missing lazy value.

## Stack

1. [refactor: make auth loading
async](https://github.com/openai/codex/pull/19762) (merged)
2. **This PR:** [refactor: load AgentIdentity runtime
eagerly](https://github.com/openai/codex/pull/19763)
3. [fix: configure AgentIdentity AuthAPI base
URL](https://github.com/openai/codex/pull/19904)
4. [feat: verify AgentIdentity JWTs with
JWKS](https://github.com/openai/codex/pull/19764)

## Important call sites

| Area | Change |
| --- | --- |
| `AgentIdentityAuth::load` | Registers the process task during auth
loading and stores `process_task_id`. |
| `CodexAuth::from_agent_identity_jwt` | Awaits AgentIdentity auth
loading. |
| model-provider auth | Reads a concrete `process_task_id` instead of an
optional lazy value. |
| AgentIdentity auth tests | Mock task registration now covers eager
runtime allocation. |

## Design decisions

AgentIdentity auth now treats task registration as part of constructing
a usable auth object. That matches how callers use the value: once auth
is present, the model-provider path expects the task-scoped assertion
data to be ready.

## Testing

Tests: targeted Rust auth test compilation, formatter, scoped Clippy
fix, and Bazel lock check.
2026-04-27 21:09:26 -07:00
canvrno-oai
2307aa8d98 Allow /statusline and /title slash commands during active turns (#19917)
- Marks `/title` and `/statusline` as available during active tasks.
- Extends the existing slash-command availability test coverage to
include these commands alongside `/goal`.
2026-04-27 20:57:20 -07:00
Michael Bolin
af95662a70 permissions: require profiles in TUI thread state (#19773)
## Why

`ThreadSessionState` is the TUI's cached view of an app-server session.
To make `PermissionProfile` the canonical runtime permissions model,
cached thread sessions need to always have a profile instead of treating
the profile as an optional supplement to a legacy `sandbox` response
field.

The main compatibility concern is older app-server v2 lifecycle
responses that only include `sandbox` and omit `permissionProfile`:

- `thread/start` -> `ThreadStartResponse.sandbox`
- `thread/resume` -> `ThreadResumeResponse.sandbox`
- `thread/fork` -> `ThreadForkResponse.sandbox`

Those responses must still hydrate correctly when the TUI is pointed at
an older app-server. This PR converts the legacy `sandbox` value into a
`PermissionProfile` immediately at response ingestion time, using the
response `cwd`, so cached sessions do not carry an optional profile that
can later reinterpret cwd-bound grants against a different thread cwd.

This fallback is intentionally boundary compatibility. The follow-up PRs
in this stack continue the cleanup by making `SessionConfiguredEvent`
profile-only, deriving sandbox projections from snapshots only when an
API still needs them, and then removing `sandbox_policy` from
`ThreadSessionState`.

## What Changed

- Makes `ThreadSessionState.permission_profile` required.
- Converts legacy app-server response `sandbox` values into a
`PermissionProfile` at ingestion time using the response cwd.
- Ensures `thread/read` hydration does not reuse a primary session
profile that may be anchored to a different cwd; it uses the active
widget permission settings for the read thread fallback instead of
reusing cached primary-session permissions.
- Keeps the app-server request path unchanged: embedded sessions send
profiles, while remote sessions continue using legacy sandbox overrides
for compatibility.

## Verification

- `cargo test -p codex-tui thread_read --lib`
- `cargo test -p codex-tui
permission_settings_sync_preserves_active_profile_only_rules --lib`
- `cargo test -p codex-tui
resume_response_restores_turns_from_thread_items --lib`
- `cargo test -p codex-tui thread_session_state::tests --lib`




























---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/19773).
* #19900
* #19899
* #19776
* #19775
* #19774
* __->__ #19773
2026-04-27 20:39:06 -07:00
pakrym-oai
4e05f3053c Remove ghost snapshots (#19481)
## Summary
- Remove `ghost_snapshot` / `GhostCommit` from the Responses API surface
and generated SDK/schema artifacts.
- Keep legacy config loading compatible, but make undo a no-op that
reports the feature is unavailable.
- Clean up core history, compaction, telemetry, rollout, and tests to
stop carrying ghost snapshot items.

## Testing
- Unit tests passed for `codex-protocol`, `codex-core` targeted undo and
compaction flows, `codex-rollout`, and `codex-app-server-protocol`.
- Regenerated config and app-server schemas plus Python SDK artifacts
and verified they match the checked-in outputs.
2026-04-27 18:48:57 -07:00
Dylan Hurd
7e8594fc19 Stabilize plugin MCP fixture tests (#19452)
## Why

Recent `main` CI had repeated flakes in the plugin fixture tests:

- `codex-core::all
suite::plugins::explicit_plugin_mentions_inject_plugin_guidance` failed
in runs
[24909500958](https://github.com/openai/codex/actions/runs/24909500958),
[24908076251](https://github.com/openai/codex/actions/runs/24908076251),
[24906197645](https://github.com/openai/codex/actions/runs/24906197645),
and
[24898949647](https://github.com/openai/codex/actions/runs/24898949647).
- `codex-core::all suite::plugins::plugin_mcp_tools_are_listed` failed
in runs
[24909500958](https://github.com/openai/codex/actions/runs/24909500958),
[24908076251](https://github.com/openai/codex/actions/runs/24908076251),
and
[24898949647](https://github.com/openai/codex/actions/runs/24898949647).

The failures were in the same plugin/MCP fixture family: assertions
expected sample plugin guidance or tool inventory, but the test could
observe the session before the sample MCP server had finished startup.

## Root Cause

`explicit_plugin_mentions_inject_plugin_guidance` submitted the user
turn immediately after constructing the session. MCP startup is
asynchronous, so on a slower or busier CI runner the prompt could be
built before the sample plugin MCP server had reported its tools. That
made the test depend on scheduler timing rather than the fixture being
ready.

`plugin_mcp_tools_are_listed` already needed the same readiness
condition, but its wait logic was local to that test.

## What Changed

- Added a shared `wait_for_sample_mcp_ready` helper for the plugin
fixture tests.
- Wait for `McpStartupComplete` before submitting the explicit plugin
mention turn.
- Reuse the same readiness helper in the MCP tool-listing test.

## Why This Should Be Reliable

The tests now wait for the explicit readiness signal from the sample MCP
server before asserting guidance or tools derived from that server. This
removes the startup race while still exercising the real fixture path,
so the assertions should only run after the plugin inventory is
deterministic.

## Verification

- `cargo test -p codex-core --test all plugins::`
- GitHub CI for this PR is passing.
2026-04-28 01:14:44 +00:00
Michael Zeng
a3350de855 Refactor exec-server filesystem API into codex-file-system (#19892)
## Summary
- Extracted the shared filesystem types and `ExecutorFileSystem` trait
into a new `codex-file-system` crate
- Switched `codex-config` and `codex-git-utils` to depend on that crate
instead of `codex-exec-server`
- Kept `codex-exec-server` re-exporting the same API for existing
callers

## Testing
- Ran `cargo test -p codex-file-system`
- Ran `cargo test -p codex-git-utils`
- Ran `cargo test -p codex-config`
- Ran `cargo test -p codex-exec-server`
- Ran `just fix -p codex-file-system`, `just fix -p codex-git-utils`,
`just fix -p codex-config`, `just fix -p codex-exec-server`
- Ran `just fmt`
- Updated and verified the Bazel module lockfile
2026-04-27 17:43:15 -07:00
colby-oai
2f3b5ed81a disallow fileparams metadata for custom mcps (#19836)
## Summary
Disallow fileParams metadata for custom MCPs 

Restricts Codex openai/fileParams handling to the first-party codex_apps
MCP server. Custom MCP servers may still advertise the metadata, but
Codex now ignores it for upload rewriting, preventing non-Apps tools
from receiving signed OpenAI file refs for local paths. Added a
regression test for the allowed and denied cases.
2026-04-27 20:42:10 -04:00
Michael Bolin
755880ef9c permissions: derive config defaults as profiles (#19772)
## Why

This continues the permissions migration by making legacy config default
resolution produce the canonical `PermissionProfile` first. The legacy
`SandboxPolicy` projection should stay available at compatibility
boundaries, but config loading should not create a legacy policy just to
immediately convert it back into a profile.

Specifically, when `default_permissions` is not specified in
`config.toml`, instead of creating a `SandboxPolicy` in
`codex-rs/core/src/config/mod.rs` and then trying to derive a
`PermissionProfile` from it, we use `derive_permission_profile()` to
create a more faithful `PermissionProfile` using the values of
`ConfigToml` directly.

This also keeps the existing behavior of `sandbox_workspace_write` and
extra writable roots after #19841 replaced `:cwd` with `:project_roots`.
Legacy workspace-write defaults are represented as symbolic
`:project_roots` write access plus symbolic project-root metadata
carveouts. Extra absolute writable roots are still added directly and
continue to get concrete metadata protections for paths that exist under
those roots.

The platform sandboxes differ when a symbolic project-root subpath does
not exist yet.

* **Seatbelt** can encode literal/subpath exclusions directly, so macOS
emits project-root metadata subpath policies even if `.git`, `.agents`,
or `.codex` do not exist.
* **bwrap** has to materialize bind-mount targets. Binding `/dev/null`
to a missing `.git` can create a host-visible placeholder that changes
Git repo discovery. Binding missing `.agents` would not affect Git
discovery, but it would still create a host-visible project metadata
placeholder from an automatic compatibility carveout. Linux therefore
skips only missing automatic `.git` and `.agents` read-only metadata
masks; missing `.codex` remains protected so first-time project config
creation goes through the protected-path approval flow. User-authored
`read` and `none` subpath rules keep normal bwrap behavior, and `none`
can still mask the first missing component to prevent creation under
writable roots.

## What Changed

- Adds profile-native helpers for legacy workspace-write semantics,
including `PermissionProfile::workspace_write_with()`,
`FileSystemSandboxPolicy::workspace_write()`, and
`FileSystemSandboxPolicy::with_additional_legacy_workspace_writable_roots()`.
- Makes `FileSystemSandboxPolicy::workspace_write()` the single legacy
workspace-write constructor so both `from_legacy_sandbox_policy()` and
`From<&SandboxPolicy>` include the project-root metadata carveouts.
- Removes the no-carveout `legacy_workspace_write_base_policy()` path
and the `prune_read_entries_under_writable_roots()` cleanup that was
only needed by that split construction.
- Adds `ConfigToml::derive_permission_profile()` for legacy sandbox-mode
fallback resolution; named `default_permissions` profiles continue
through the permissions profile pipeline instead of being reconstructed
from `sandbox_mode`.
- Updates `Config::load()` to start from the derived profile, validate
that it still has a legacy compatibility projection, and apply
additional writable roots directly to managed workspace-write filesystem
policies.
- Updates Linux bwrap argument construction so missing automatic
`.git`/`.agents` symbolic project-root read-only carveouts are skipped
before emitting bind args; missing `.codex`, user-authored `read`/`none`
subpath rules, and existing missing writable-root behavior are
preserved.
- Adds coverage that legacy workspace-write config produces symbolic
project-root metadata carveouts, extra legacy workspace writable roots
still protect existing metadata paths such as `.git`, and bwrap skips
missing `.git`/`.agents` project-root carveouts while preserving missing
`.codex` and user-authored missing subpath rules.

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/19772).
* #19776
* #19775
* #19774
* #19773
* __->__ #19772
2026-04-27 16:50:10 -07:00
pakrym-oai
c5a495c2cd Streamline review and feedback handlers (#19498)
## Why

The remaining review, interrupt, fuzzy search, feedback, and git-diff
handlers still had local send-error branches that obscured otherwise
simple request handling. This final slice flattens those handlers
without changing the public protocol behavior.

## What Changed

- Streamlined review start, turn interrupt, fuzzy search session,
feedback upload, and git diff handlers in
`codex-rs/app-server/src/codex_message_processor.rs`.
- Converted validation and upload failures into returned JSON-RPC errors
where that avoids nested `send_error`/`return` blocks.
- Left unrelated sandbox setup and notification code untouched.

## Verification

- `cargo check -p codex-app-server`
- `cargo test -p codex-app-server --test all v2::review --
--test-threads=1`
2026-04-27 16:36:04 -07:00
Matthew Zeng
dcd139b7c4 Add MCP app feature flag (#19884)
## Summary
- Add the `enable_mcp_apps` feature flag to the `codex-features`
registry
- Keep it under development and disabled by default

## Testing
- Unit tests for `codex-features` passed
- Formatting passed
2026-04-27 16:28:49 -07:00
canvrno-oai
e64c765673 Show action required in terminal title (#18372)
Implements #18162

This updates the TUI terminal title to show an explicit action-required
state when Codex is blocked on user approval or input. The terminal
title now uses the activity title item to cover both active work and
blocked-on-user states, while still accepting the legacy spinner config
value.

Changes
- Rename the terminal title item from `spinner` to `activity` while
preserving legacy config compatibility
- Show `[ ! ] Action Required `while approval or input overlays are
active, with a blinking `[ . ]` alternate state
- Suppress the normal working spinner while Codex is blocked on user
action
- Add targeted coverage for action-required title behavior and legacy
title-item parsing

Testing
- Trigger an approval or input modal and confirm the tab title
alternates between `[ ! ] Action Required` and `[ . ] Action Required`
- Disable the activity title item and confirm the action-required title
does not appear
- Resolve the prompt and confirm the title returns to the normal
spinning/idel state


https://github.com/user-attachments/assets/e9ecc530-a6be-4fd7-b9a6-d550a790eb2c
2026-04-27 15:27:11 -07:00
pakrym-oai
e903d000b0 Streamline turn and realtime handlers (#19497)
## Why

Turn and realtime handlers had nested validation and send-error branches
that made the request path longer than the behavior warranted. This
slice keeps the same request semantics while letting the handlers return
errors from the failing step.

## What Changed

- Streamlined turn start, injected item, and turn steer request handling
in `codex-rs/app-server/src/codex_message_processor.rs`.
- Applied the same result-returning shape to realtime session response
handlers.
- Preserved existing request validation and thread-manager interactions.

## Verification

- `cargo check -p codex-app-server`
- `cargo test -p codex-app-server --test all v2::turn_start --
--test-threads=1`
- `cargo test -p codex-app-server --test all v2::turn_steer --
--test-threads=1`
- `cargo test -p codex-app-server --test all v2::thread_inject_items --
--test-threads=1`
2026-04-27 15:21:59 -07:00
pakrym-oai
739ab6bc51 Streamline thread resume and fork handlers (#19495)
## Why

Thread resume and fork had some of the deepest error-handling
indentation in this area because helpers emitted request errors
directly. Returning those failures gives the handlers a single request
boundary while preserving the async pending-resume behavior.

## What Changed

- Converted thread resume helpers in
`codex-rs/app-server/src/codex_message_processor.rs` to return `Result`
values for validation and view loading failures.
- Applied the same pattern to thread fork request handling.
- Simplified pending resume error construction by using the shared
JSON-RPC error helpers.

## Verification

- `cargo check -p codex-app-server`
- `cargo test -p codex-app-server --test all v2::thread_resume --
--test-threads=1`
- `cargo test -p codex-app-server --test all v2::thread_fork --
--test-threads=1`
2026-04-27 15:04:53 -07:00
cassirer-openai
30c5c768de [codex] Trace cancelled inference streams (#19839)
Records cancelled inference streams when Codex stops consuming a
provider response before `response.completed`, preserving complete
output items observed before cancellation.

Also closes still-running inference calls when the owning turn ends, so
reduced rollout traces do not leave stale `Running` inference nodes.

Covered by focused reducer coverage and a core stream-drop test for
partial output preservation.
2026-04-27 21:58:29 +00:00
pakrym-oai
2be9fd5a93 Streamline thread read handlers (#19494)
## Why

The thread read/list handlers mostly assemble views, but their error
handling was interleaved with response emission. Returning view-building
errors from the helper path keeps those handlers focused on data
assembly.

## What Changed

- Added a small mapper for `ThreadReadViewError` to JSON-RPC errors in
`codex-rs/app-server/src/codex_message_processor.rs`.
- Streamlined thread list, loaded-thread, read, turn-list, and summary
handlers to produce result values for the request boundary.
- Kept the existing invalid-request vs internal-error distinctions for
missing or unreadable thread data.

## Verification

- `cargo check -p codex-app-server`
- `cargo test -p codex-app-server --test all conversation_summary --
--test-threads=1`
2026-04-27 14:30:24 -07:00
Steve Coffey
0f40261e86 Publish Python SDK with Codex-pinned versioning (#18996)
**note**: a large chunk of this diff comes from regenerating Python
types after app-server schema changes on `main`.

This is PR 3 of 3 for the Python SDK PyPI publishing split. PR #18862
refreshed the generated SDK surface, and PR #18865 made the runtime
package publishable as `openai-codex-cli-bin`; this final PR makes the
SDK package publishable as `openai-codex-app-server-sdk` and pins both
packages to the same Codex runtime version.

The key idea is that the published SDK version is the Codex runtime
version. That one version now drives the SDK package version, the exact
runtime dependency, the client version reported by the SDK, and the
bootstrap runtime pin. This keeps release-time versioning in one lane
instead of scattering checked-in literals through the package.

## What changed

- Rename the SDK distribution from `codex-app-server-sdk` to
`openai-codex-app-server-sdk` for conflict-free PyPI publishing.
- Use `stage-sdk --codex-version ...` with one Codex version for both
the SDK package version and exact `openai-codex-cli-bin` dependency.
- Preserve hidden legacy `--runtime-version` / `--sdk-version` args only
to reject mismatched versions during staging.
- Map PEP 440 package versions back to Codex release tags for runtime
setup downloads, e.g. `0.116.0a1` -> `rust-v0.116.0-alpha.1`.
- Derive `codex_app_server.__version__`, the default
`AppServerConfig.client_version`, and
`_runtime_setup.pinned_runtime_version()` from the SDK package/project
version instead of hardcoding duplicate version strings.
- Carry the current generated SDK refresh from `main` so
`generate-types` stays clean after recent app-server schema changes.
- Update `sdk/python/uv.lock` for the renamed editable package.

## Validation

- `uv run --extra dev pytest` in `sdk/python` -> 59 passed, 37 skipped.
- Targeted `uv run ruff check` for the touched SDK files.
- `git diff --check`.
- Staged runtime with `--codex-version rust-v0.116.0-alpha.1
--platform-tag macosx_11_0_arm64`.
- Staged SDK with `--codex-version rust-v0.116.0-alpha.1`.
- Built runtime wheel, SDK wheel, and SDK sdist.
- `twine check /tmp/codex-python-pr3-build/dist/*` -> passed.
- Clean venv smoke installed `openai-codex-app-server-sdk==0.116.0a1`
from local dist and pulled `openai-codex-cli-bin==0.116.0a1`.
- Smoke imports passed for `Codex` and `bundled_codex_path()`.
2026-04-27 14:28:46 -07:00
starr-openai
4ded800374 [codex] Shard exec Bazel integration test (#19862)
## Summary

- shard `//codex-rs/exec:exec-all-test` into 8 Bazel shards
- keep the existing `no-sandbox` test tag unchanged

## Why

The Windows Bazel lane has been timing out this aggregated integration
test target at the default 300s test timeout. The target runs the
combined `codex-rs/exec/tests/all.rs` integration binary; sharding lets
Bazel split the Rust test cases across parallel test actions instead of
running the whole integration suite as one long action.

## Validation

Not run locally, per the Codex repo workflow for development-phase
changes.

Co-authored-by: Codex <noreply@openai.com>
2026-04-27 21:22:53 +00:00
pakrym-oai
5c30d79afb Streamline thread mutation handlers (#19493)
## Why

Thread mutation handlers had many short error branches whose only job
was to emit a JSON-RPC error and stop. This slice keeps those errors
visible, but lets each handler build a result and return early from
validation helpers instead of nesting the main path.

## What Changed

- Streamlined thread archive/unarchive, rename, memory, metadata,
rollback, compact, background terminal, shell, and guardian handlers in
`codex-rs/app-server/src/codex_message_processor.rs`.
- Reused shared JSON-RPC error constructors in
`codex-rs/app-server/src/bespoke_event_handling.rs` for rollback-related
request failures.
- Preserved direct `send_error` calls where they remain the simplest
boundary for pending async event responses.

## Verification

- `cargo check -p codex-app-server`
- `cargo test -p codex-app-server --test all v2::thread_rollback --
--test-threads=1`
2026-04-27 14:18:55 -07:00
joeytrasatti-openai
798de22637 [codex-backend] Prefer state git metadata in filtered thread lists (#19874)
### Summary

- `thread/list` filtered filesystem results already overlay state DB
metadata, but the existing merge only filled missing git fields.
- Prefer non-null SQLite git metadata over stale non-null rollout values
so persisted branch/SHA/origin updates are reflected in filtered thread
lists.
- Update the focused merge test to cover stale filesystem git metadata
being replaced by state-backed values.

### Testing

now getting expected icons
<img width="426" height="913" alt="Screenshot 2026-04-27 at 1 45 45 PM"
src="https://github.com/user-attachments/assets/027fb7e7-f54d-4353-8423-cb76f3c8f5ac"
/>
2026-04-27 21:02:40 +00:00
pakrym-oai
c5e2921e1d Streamline thread start handler (#19492)
## Why

The thread start handler mixed request validation, thread construction,
dynamic-tool validation, and JSON-RPC error emission in one nested flow.
Returning request errors from the helper path makes the successful setup
path easier to follow.

## What Changed

- Reworked `thread/start` handling in
`codex-rs/app-server/src/codex_message_processor.rs` so helper methods
return `Result` and the handler emits one result.
- Moved dynamic-tool validation failures into returned JSON-RPC errors
instead of local `send_error` branches.
- Preserved the existing thread creation and task-spawning behavior.

## Verification

- `cargo check -p codex-app-server`
- `cargo test -p codex-app-server --test all v2::dynamic_tools --
--test-threads=1`
- `cargo test -p codex-app-server --test all v2::turn_start --
--test-threads=1`
2026-04-27 13:56:20 -07:00
Michael Bolin
4b55979755 permissions: remove cwd special path (#19841)
## Why

The experimental `PermissionProfile` API had both `:cwd` and
`:project_roots` special filesystem paths, which made the permission
root ambiguous. This PR removes the unstable `current_working_directory`
special path before the permissions API is stabilized, so callers use
`:project_roots` for symbolic project-root access.

## What changed

- Removes `FileSystemSpecialPath::CurrentWorkingDirectory` from protocol
and app-server protocol models, plus regenerated app-server
JSON/TypeScript schemas.
- Replaces internal `:cwd` permission entries with `:project_roots`
entries.
- Keeps the existing cwd-update behavior for legacy-shaped
workspace-write profiles, while removing the deleted
`CurrentWorkingDirectory` case from that compatibility path.
- Keeps `PermissionProfile::workspace_write()` as the reusable symbolic
workspace-write helper, with docs noting that `:project_roots` entries
resolve at enforcement time.
- Updates app-server docs/examples and approval UI labeling to stop
advertising `:cwd` as a permission token.

## Compatibility

Persisted rollout items may contain the old
`{"kind":"current_working_directory"}` tag from earlier experimental
`permissionProfile` snapshots. This PR keeps that tag as a
deserialize-only alias for `ProjectRoots { subpath: None }`, while
continuing to serialize only the new `project_roots` tag.

## Follow-up

This PR intentionally does not introduce an explicit project-root set on
`SessionConfiguration` or runtime sandbox resolution. Today, the
resolver still uses the active cwd as the single implicit project root.
A follow-up should model project roots separately from tool cwd so
`:project_roots` entries can resolve against the configured project
roots, and resolve to no entries when there are no project roots.

## Verification

- `cargo test -p codex-protocol permissions:: --lib`
- `cargo test -p codex-app-server-protocol`
- `cargo test -p codex-sandboxing -p codex-exec-server --lib`
- `cargo test -p codex-core session_configuration_apply_ --lib`
- `cargo test -p codex-app-server
command_exec_permission_profile_project_roots_use_command_cwd --test
all`
- `cargo test -p codex-tui
thread_read_session_state_does_not_reuse_primary_permission_profile
--lib`
- `cargo test -p codex-tui
preset_matching_accepts_workspace_write_with_extra_roots --lib`
- `cargo test -p codex-config --lib`
2026-04-27 13:41:27 -07:00
Eric Traut
52c06b8759 Preserve TUI markdown list spacing after code blocks (#19706)
## Why

Fixes #19702.

The TUI markdown renderer could visually attach the next list marker to
a fenced code block inside the previous list item, even when the source
markdown included a blank line before the next item. That made
block-heavy loose lists harder to read, while the desired behavior is
still to keep simple lists compact.

## What changed

- Track whether the current rendered list item contains a code block.
- Preserve one blank separator before the following list marker only
when the previous item contained a code block.
- Add regression coverage for both paths: code-block list items keep the
separator, and simple loose list items stay compact.

## Verification

- `cargo test -p codex-tui markdown_render`

I also manually verified that the bug exists before and is fixed after.

## Before
<img width="437" height="240" alt="Screenshot 2026-04-26 at 1 19 01 PM"
src="https://github.com/user-attachments/assets/3bc9d64d-2dba-40d9-9d6b-a1d0b3c0f728"
/>

## After
<img width="410" height="269" alt="Screenshot 2026-04-26 at 1 18 54 PM"
src="https://github.com/user-attachments/assets/19c15bee-da32-455e-a7cb-e05eb85f4ea0"
/>
2026-04-27 13:40:46 -07:00
Eric Traut
0bd25ab374 Delay approval prompts while typing (#19513)
## Why

Fixes #7744. Approval modals can currently appear while the user is
typing ahead in the TUI composer, which lets plain letters like `y` or
`a` get consumed as approval shortcuts instead of staying in the draft
input.

## What changed

- Track recent composer typing activity in `bottom_pane/mod.rs`.
- Delay new approval overlays for 1 second while the composer is active,
keeping delayed requests queued until the user is idle.
- Preserve the existing active-overlay behavior so approvals that arrive
while an approval modal is already open are still queued into that
overlay.
- Prune delayed approvals when app-server resolution says the request
has already been handled.

## Verification

Added unit coverage for immediate approvals, delayed approvals, idle
deadline reset, typed shortcut letters staying in the composer, shortcut
handling after the delay, and resolved delayed-request pruning.

Focused `codex-tui` test groups pass locally. The full `cargo test -p
codex-tui` run currently aborts in
`app::tests::attach_live_thread_for_selection_rejects_unmaterialized_fallback_threads`;
that same test also fails when run alone with the same stack overflow.

Manual reviewer check:

1. Start the TUI from the repo root:

   ```bash
   RUST_LOG=trace just codex \
     -c log_dir=<temp-log-dir> \
     --ask-for-approval untrusted \
     --sandbox workspace-write
   ```

2. Submit this prompt:

   ```text
   create a file text.txt on my desktop
   ```

3. While the agent is preparing the approval request, immediately type
text such as `ya this should stay in the composer`.
4. Confirm the typed-ahead `y`/`a` remains in the composer instead of
approving the request.
5. Stop typing for about 1 second; the approval modal should then
appear.
6. Once the modal is visible, press `y` and confirm the approval
shortcut works normally.
2026-04-27 13:20:55 -07:00
Eric Traut
850f035b8c Fix filtered thread-list resume regression in TUI (#19591)
## Why

`codex resume` regressed after
[#18502](https://github.com/openai/codex/pull/18502) changed the default
`thread/list` scan-and-repair path for metadata-filtered listings. The
TUI resume picker uses `thread/list` with source/provider/cwd filters
and `useStateDbOnly: false`, which is the intended
correctness-preserving mode: it should still consult the filesystem so
healthy, missing, or stale SQLite state can be repaired.

The regression was that #18502 made that filtered, filesystem-backed
path call `reconcile_rollout` for every filesystem hit, and then call it
again for each SQLite hit. When `reconcile_rollout` does not already
have extracted rollout items, it falls back to loading the full JSONL
rollout. That changed the resume picker’s first page from a cheap
rollout-head scan plus SQLite read-repair into full-file reads for large
sessions, so a few long threads could dominate TUI startup/resume
latency.

This change addresses the regression by keeping `useStateDbOnly: false`
on the correctness-preserving path while avoiding unnecessary full JSONL
reads for rows the filesystem scan has already validated.
Source/provider/cwd filters can be decided from rollout-head metadata,
so non-search resume listings only need the lightweight read-repair path
for filesystem hits. Full reconciliation is still used for DB-only
filtered rows because those can be stale false positives, and for search
listings because search can depend on title metadata that may require
scanning the full rollout.

This fixes #19483.

## What changed

- For non-search filtered listings, repair filesystem hits with the
lightweight `read_repair_rollout_path` path instead of full
`reconcile_rollout`.
- Track thread IDs proven by the filesystem scan and only fully
reconcile SQLite-filtered hits that the filesystem scan did not return,
preserving stale-DB false-positive cleanup without full-reading every
healthy rollout.
- Leave search listings on full reconciliation, since search depends on
full title metadata rather than only source/provider/cwd metadata from
the rollout head.

## Verification

- `cargo test -p codex-rollout list_threads`
- `cargo test -p codex-app-server thread_list`
2026-04-27 13:02:39 -07:00
Curtis 'Fjord' Hawthorne
277186ec85 Cap original-detail image token estimates (#19865)
Clamp original-detail image patch estimates to the current 10k patch
budget so large images cannot inflate local context accounting without
bound. Add regression coverage for an over-budget image.

Fixes openai/codex#19806.
2026-04-27 12:39:24 -07:00
rhan-oai
215d5a8f7c [codex-analytics] remove ga flag (#19863) 2026-04-27 19:29:19 +00:00
sayan-oai
85c1500569 fix: filter dynamic deferred tools from model_visible_specs (#19771)
fixes #19486

### Problem
Right now dynamic deferred tools are filtered at normal-turn prompt
building time, rather than upstream while building the `ToolRouter`
itself. This causes issues because dynamic deferred tools are then
wrongly included in the router's `model_visible_specs`, which is what
the compaction request-building flow relies on.

### Fix
Move the dynamic deferred tool filtering to `ToolRouter` creation time
to solve this problem for every request that relies on `ToolRouter` for
`model_visible_specs`, which solves the issue generically.

### Tests
Added unit + integration tests to ensure dynamic deferred tools are
omitted from `model_visible_specs` and compaction request respectively.

Tested against live `/compact` endpoint; raw deferred dynamic tools
without `tool_search` returned `400` (current bug), while the filtered
payload (this fix) returns `200`.
2026-04-27 19:09:02 +00:00
pakrym-oai
e5709db6dc Streamline account and command handlers (#19491)
## Why

Account login/logout and command exec handlers were doing local error
sends in the middle of each handler. That made these request flows
branch heavily even though most of the logic is validate, perform the
operation, and return the response.

## What Changed

- Converted ChatGPT/API-key login, login cancel, logout, rate-limit, and
add-credit handlers in
`codex-rs/app-server/src/codex_message_processor.rs` to compute `Result`
values and send them once at the request boundary.
- Applied the same shape to command exec start/write/resize/terminate
handlers.
- Kept side-effect notifications in the same places after successful
request handling.

## Verification

- `cargo check -p codex-app-server`
- `cargo test -p codex-app-server --test all v2::account --
--test-threads=1`
- `cargo test -p codex-app-server --test all v2::command_exec --
--test-threads=1`
2026-04-27 12:03:49 -07:00
Michael Bolin
cafe717dca ci: migrate Bazel setup away from archived setup-bazelisk (#19851)
## Why

All Bazel CI jobs are currently blocked in the `setup-bazelisk` step
while trying to download Bazelisk.
[`bazelbuild/setup-bazelisk`](https://github.com/bazelbuild/setup-bazelisk)
is archived, and its README now recommends migrating to
[`bazel-contrib/setup-bazel`](https://github.com/bazel-contrib/setup-bazel),
so leaving our workflows on the archived action leaves CI exposed to
exactly this sort of outage.

Because `v8-canary` now consumes the shared local `setup-bazel-ci`
action, that workflow also needs to trigger when the action changes.
Without that follow-up, Bazel bootstrap regressions specific to the V8
canary path could be skipped by the workflow path filters.

## What Changed

- Switched `.github/actions/setup-bazel-ci/action.yml` from
`bazelbuild/setup-bazelisk` to `bazel-contrib/setup-bazel`, pinned to
`0.19.0`.
- Left `bazelisk-version` unset so GitHub-hosted runners can use their
preinstalled Bazelisk instead of downloading `1.x` at job start.
- Updated `.github/workflows/rusty-v8-release.yml` and
`.github/workflows/v8-canary.yml` to use the shared `setup-bazel-ci`
action instead of referencing `setup-bazelisk` directly.
- Added `.github/actions/setup-bazel-ci/**` to the `pull_request` and
`push` path filters in `.github/workflows/v8-canary.yml` so changes to
the shared Bazel setup action still run the canary workflow.
- Kept the existing repository-cache and Windows-specific Bazel setup
logic intact.

This keeps Bazel version selection anchored by `.bazelversion` while
removing the failing dependency on the archived setup action.

## Verification

- Searched `.github/` to confirm there are no remaining `setup-bazelisk`
references.
- Parsed the updated workflow and action YAML locally with Ruby's
`YAML.load_file`.
2026-04-27 11:37:30 -07:00
Michael Bolin
c2084552d9 ci: pin npm staging smoke test to a recent rust-release run (#19854)
## Why

The `build-test` workflow stages a representative `codex` npm tarball by
asking `scripts/stage_npm_packages.py` to look up a past `rust-release`
run for a hardcoded release version. That started failing in CI because
the representative version in `.github/workflows/ci.yml` was stale:

- the workflow was still using `0.115.0`
- `stage_npm_packages.py` resolves native artifacts by looking for a
`rust-release` run on the `rust-v<version>` branch
- that lookup no longer found a matching run for `rust-v0.115.0`, so the
smoke test failed before it could stage the package

This PR makes that smoke test depend on a known-good recent release run
instead of an older branch lookup that is no longer reliable.

## What Changed

- Updated the representative release version in
`.github/workflows/ci.yml` from `0.115.0` to `0.125.0`.
- Added an explicit `WORKFLOW_URL` pointing at a recent successful
`rust-release` run:
`https://github.com/openai/codex/actions/runs/24901475298`.
- Passed that URL to `scripts/stage_npm_packages.py` via
`--workflow-url` so the job can reuse the expected native artifacts
directly instead of relying on `gh run list --branch rust-v<version>` to
discover them.

That keeps the npm staging smoke test representative while making it
less sensitive to older release branch history disappearing from the
GitHub Actions lookup path.

## Verification

- Inspected the failing CI log from `build-test` and confirmed the
failure came from `scripts/stage_npm_packages.py` being unable to
resolve `rust-v0.115.0`.
- Confirmed that
`https://github.com/openai/codex/actions/runs/24901475298` is a
successful `rust-release` run for `rust-v0.125.0`.
2026-04-27 11:32:48 -07:00
efrazer-oai
2009f6e894 refactor: make auth loading async (#19762)
## Summary

Auth loading used to expose synchronous construction helpers in several
places even though some auth sources now need async work. This PR makes
the auth-loading surface async and updates the callers to await it.

This is intentionally only plumbing. It does not change how
AgentIdentity tokens are decoded, how task runtime ids are allocated, or
how JWT signatures are verified.

## Stack

1. **This PR:** [refactor: make auth loading
async](https://github.com/openai/codex/pull/19762)
2. [refactor: load AgentIdentity runtime
eagerly](https://github.com/openai/codex/pull/19763)
3. [feat: verify AgentIdentity JWTs with
JWKS](https://github.com/openai/codex/pull/19764)

## Important call sites

| Area | Change |
| --- | --- |
| `codex-login` auth loading | `CodexAuth` and `AuthManager`
construction paths now await auth loading. |
| app-server startup | Auth manager construction is awaited during
initialization. |
| CLI/TUI/exec/MCP/chatgpt callers | Existing auth-loading calls now
await the same behavior. |
| cloud requirements storage loader | The loader becomes async so it can
share the same auth construction path. |
| auth tests | Tests that load auth now run in async contexts. |

## Testing

Tests: targeted Rust auth test compilation, formatter, scoped Clippy
fix, and Bazel lock check.
2026-04-27 11:00:27 -07:00
pakrym-oai
4ed22fc7d2 Streamline plugin, apps, and skills handlers (#19490)
## Why

The plugin, app, and skills handlers had a lot of repeated
`send_error`/`return` branches that made the success path hard to scan.
This slice keeps behavior the same while moving fallible steps into
local response-producing helpers, so the request boundary can send one
result.

## What Changed

- Converted plugin list/install/uninstall handlers in
`codex-rs/app-server/src/codex_message_processor/plugins.rs` to return
`Result<*Response, JSONRPCErrorError>` from helper methods and call
`send_result` once.
- Added local error-mapping helpers for plugin install/uninstall and
marketplace failures.
- Applied the same mechanical shape to app list, skills list/config, and
marketplace add/remove/upgrade handlers in
`codex-rs/app-server/src/codex_message_processor.rs`.

## Verification

- `cargo check -p codex-app-server`
- `cargo test -p codex-app-server --test all v2::app_list --
--test-threads=1`
- `cargo test -p codex-app-server --test all v2::plugin_ --
--test-threads=1`
- `cargo test -p codex-app-server --test all v2::skills_list --
--test-threads=1`
2026-04-27 10:18:25 -07:00
Eric Traut
48dd7b58f0 Render delegated patch approval details (#19709)
## Why

Fixes #19632.

When a delegated agent requests approval for an in-progress file change,
the parent TUI handles that request from an inactive thread. The app
server already sent the `FileChange` item with the proposed diff, but
the inactive-thread approval path was not recovering and rendering it
the same way as the active-thread path.

The result was an inconsistent approval prompt: main-thread edits show a
normal patch preview history item before the approval modal, while
delegated edits did not show that preview in the transcript flow.

## What Changed

- Recover buffered or historical `FileChange` item changes when building
inactive-thread file-change approval requests.
- Reuse the app-server file-change conversion helper for both live
transcript rendering and inactive-thread approvals.
- Render recovered delegated patches as a normal patch preview history
cell before the approval modal.
- Keep apply-patch approval modals focused on the decision prompt and
optional metadata; they do not render a synthetic command line or embed
the diff body.

## Manual Repro And Verification

I manually reproduced the issue using a file under `~/Desktop` so the
write would require approval.

Before the fix:

1. Ask the main thread: `Use apply_patch, not shell redirection or
Python, to create ~/Desktop/bug1.txt with three short lines.`
2. Observe the expected TUI shape: the transcript shows a normal patch
preview such as `• Added ~/Desktop/bug1.txt (+N -0)` above the approval
modal, and the modal contains only the approval prompt/options without a
synthetic command line.
3. Ask for the delegated path: `Spawn a worker. Have it use apply_patch,
not shell redirection or Python, to create ~/Desktop/bug1.txt with four
short lines.`
4. Observe the delegated approval is inconsistent: the parent view does
not render the proposed patch as the normal transcript preview before
the modal, so the diff context is missing from the stream or appears
inside the modal instead of in the history flow.

After the fix:

1. Repeat the delegated worker prompt with `apply_patch`.
2. Confirm the parent view renders the same normal patch preview history
cell (`• Added ~/Desktop/bug1.txt (+N -0)` plus the diff) immediately
before the approval modal.
3. Confirm the approval modal remains focused on the decision prompt.
For delegated approvals it may show the worker thread label, but it
should not show a `$ apply_patch` command line or embed the diff body in
the modal.
2026-04-27 10:07:15 -07:00
Eric Traut
0e2300c02c Persist shell mode commands in prompt history (#19618)
## Why

`!` shell commands are currently surfaced as "Bash mode", which is
misleading for users running shells such as PowerShell or zsh. Those
commands also bypass the persistent prompt history path, so they cannot
be recalled after starting a new session.

Fixes #19613.

## What changed

- Rename the TUI footer label and related test wording from "Bash mode"
to "Shell mode".
- Persist accepted `!` shell commands to prompt history with the leading
`!`, so recall restores the composer into shell mode across sessions.
- Add coverage for immediate and queued shell-command submissions
emitting the prompt-history update.

## Verification

- `cargo test -p codex-tui bang_shell`
- `cargo test -p codex-tui shell_command_uses_shell_accent_style`
- `cargo test -p codex-tui footer_mode_snapshots`
- `cargo insta pending-snapshots --manifest-path tui/Cargo.toml`

Manually verified fix after confirming presence of bug prior to fix.
2026-04-27 09:54:25 -07:00
Eric Traut
6c51bf0c7c Hide rewind preview when no user message exists (#19510)
## Why

Fixes #19508.

In a fresh TUI session, pressing `Esc` twice entered the rewind
transcript overlay even though there was no user message to rewind to.
That produced an empty header-only transcript view and exposed a rewind
flow that could not select a valid target.

## What changed

The backtrack flow now checks whether a user-message rewind target
exists before opening the transcript preview. If no target exists, Codex
stays in the main TUI and shows `No previous message to edit.` instead
of opening an empty overlay.

The same guard applies when starting rewind preview from the transcript
overlay, and the first `Esc` no longer advertises the “edit previous
message” hint when there is no previous message available.

Snapshot coverage was added for the unavailable rewind info message,
along with a small target-detection test.
2026-04-27 09:51:12 -07:00
jif-oai
bb83eec825 chore: split memories part 1 (#19818)
Extract memories into 2 different crates
2026-04-27 16:01:05 +02:00
jif-oai
f431ec12c9 nit: one more fix (#19813)
Fix this:
https://github.com/openai/codex/pull/19812#discussion_r3147529230
2026-04-27 15:32:31 +02:00
jif-oai
79b4f691a6 Avoid rewriting Phase 2 selection on clean workspace (#19812)
## Why

Phase 2 can now claim the global consolidation lock on startup even when
the git-backed memory workspace is already clean. The clean-workspace
path still finalized through the normal Phase 2 success path, which
clears and re-marks `selected_for_phase2` rows. That made no-op startups
perform avoidable writes to `stage1_outputs`, creating unnecessary DB
I/O and contention when no memory files changed.

## What Changed

- Added a preserving-selection Phase 2 finalizer in `codex-state` that
only marks the global job row as succeeded.
- Kept the existing `mark_global_phase2_job_succeeded` behavior for real
consolidation runs, where the selected Phase 2 snapshot must be
rewritten.
- Switched the `succeeded_no_workspace_changes` branch in
`core/src/memories/phase2.rs` to use the preserving-selection finalizer.
- Added a regression test that installs a SQLite trigger on
`stage1_outputs` and verifies the clean finalizer performs zero updates
there.

## Testing

- `cargo test -p codex-state`
- `cargo test -p codex-core memories::tests::phase2`
2026-04-27 15:14:16 +02:00
jif-oai
5d314f324c Allow Phase 2 memory claims after retry exhaustion (#19809)
## Why

The Phase 2 memories job row is only the global lock for the git-backed
memory workspace. Manual memory edits do not enqueue new Stage 1 work,
so a Phase 2 row with `retry_remaining = 0` could be skipped before the
worker ever claimed the lock and generated `phase2_workspace_diff.md`.

That left workspace-only changes unconsolidated after repeated failures,
even when retry backoff had elapsed and the filesystem had real diffable
work.

## What Changed

- Allow `try_claim_global_phase2_job` to claim the Phase 2 lock after
the retry budget is exhausted, while still respecting active `retry_at`
backoff and fresh running leases.
- Treat `SkippedRetryUnavailable` for Phase 2 as backoff-only, and
update the outcome docs to match.
- Clamp Phase 2 retry bookkeeping at zero when failed attempts are
recorded.

## Verification

- Added
`phase2_global_lock_can_be_claimed_after_retry_budget_is_exhausted` to
cover the exhausted-budget lock claim path.
- Ran `cargo test -p codex-state`.
2026-04-27 14:58:11 +02:00
jif-oai
01ab25dbb5 feat: use git-backed workspace diffs for memory consolidation (#18982)
## Why

This PR make the `morpheus` agent (memory phase 2) use a git diff to
start it's consolidation. The workflow is the following:
1. The agent acquire a lock
2. If `.codex/memories` does not exist or is not a git root, initialize
everything (and make a first empty commit)
3. Update `raw_memories.md` and `rollout_summaries/` as before.
Basically we select max N phase 1 memories based on a given policy
4. We use git (`gix`) to get a diff between the current state of
`.codex/memories` and the last commit.
5. Dump the diff in `phase2_workspace_diff.md`
6. Spawn `morpheus` and point it to `phase2_workspace_diff.md`
7. Wait for `morpheus` to be done
8. Re-create a new `.git` and make one single commit on it. We do this
because we don't want to preserve history through `.git` and this is
cheap anyway
9. We release the lock
On top of this, we keep the retry policies etc etc

The goals of this new workflow are:
* Better support of any memory extensions such as `chronicle`
* Allow the user to manually edit memories and this will be considered
by the phase 2 agent
 
As a follow-up we will need to add support for user's edition while
`morpheus` is running

## What Changed

- Added memory workspace helpers that prepare the git baseline, compute
the diff, write `phase2_workspace_diff.md`, and reset the baseline after
successful consolidation.
- Updated Phase 2 to sync current inputs into `raw_memories.md` and
`rollout_summaries/`, prune old extension resources, skip clean
workspaces, and run the consolidation subagent only when the workspace
has changes.
- Tightened Phase 2 job ownership around long-running consolidation with
heartbeats and an ownership check before resetting the baseline.
- Simplified the prompt and state APIs so DB watermarks are bookkeeping,
while workspace dirtiness decides whether consolidation work exists.
- Updated the memory pipeline README and tests for workspace diffs,
extension-resource cleanup, pollution-driven forgetting, selection
ranking, and baseline persistence.

## Verification

- Added/updated coverage in `core/src/memories/tests.rs`,
`core/src/memories/workspace_tests.rs`, `state/src/runtime/memories.rs`,
and `core/tests/suite/memories.rs`.

---------

Co-authored-by: Codex <noreply@openai.com>
2026-04-27 14:32:44 +02:00
jif-oai
f8c527e529 multi_agent_v2: move thread cap into feature config (#19792)
## Why

`features.multi_agent_v2.max_concurrent_threads_per_session` is meant to
be the MultiAgentV2-specific session thread cap: it counts the root
thread and all open subagent threads. The previous implementation kept
this surface tied to `agents.max_threads`, which made it a global
subagent-only cap and allowed the legacy setting to coexist with
MultiAgentV2.

## What Changed

- Added `max_concurrent_threads_per_session` to
`[features.multi_agent_v2]` with default `4`.
- Removed the `[agents] max_concurrent_threads_per_session` alias to
`agents.max_threads`.
- When MultiAgentV2 is enabled, reject `agents.max_threads` and derive
the existing internal subagent slot limit as
`max_concurrent_threads_per_session - 1`.
- Regenerated `core/config.schema.json` and added coverage for the new
config semantics.

## Result
```
➜  codex git:(jif/clean-multi-agent-v2-config) codex -c features.multi_agent_v2.enabled=true -c features.multi_agent_v2.max_concurrent_threads_per_session=3
╭────────────────────────────────────────────────────╮
│ >_ OpenAI Codex (v0.0.0)                           │
│                                                    │
│ model:     gpt-5.5 xhigh   fast   /model to change │
│ directory: ~/code/codex                            │
╰────────────────────────────────────────────────────╯

  Tip: Update Required - This version will no longer be supported starting May 8th. Please upgrade to the latest version (https://github.com/openai/codex/releases/latest) using your preferred package manager.

› Can you try to spawn 4 agents


• I’ll try to start four lightweight agents at once and report exactly what the runtime accepts.

• Spawned Russell [no-apps] (gpt-5.5 xhigh)
  └ Spawn probe 1: reply briefly that you started, then wait for further instructions. Do not do any repo work.

• Spawned Descartes [no-apps] (gpt-5.5 xhigh)
  └ Spawn probe 2: reply briefly that you started, then wait for further instructions. Do not do any repo work.

• Agent spawn failed
  └ Spawn probe 3: reply briefly that you started, then wait for further instructions. Do not do any repo work.

• Agent spawn failed
  └ Spawn probe 4: reply briefly that you started, then wait for further instructions. Do not do any repo work.

• The runtime accepted the first two and rejected the next two with agent thread limit reached. I’m checking whether the two accepted probes have returned cleanly, then I’ll close them if needed.
```

---------

Co-authored-by: Codex <noreply@openai.com>
2026-04-27 13:31:56 +02:00
Eric Traut
4f1d5f00f0 Add Codex issue digest skill (#19779)
Problem: Maintainers need a shared way to run Codex GitHub issue digests
without copying large prompts or relying on manual GitHub page
summaries.

Solution: Add a reusable codex-issue-digest skill with a deterministic
GitHub collector, owner/all-label windows, reaction-aware activity
metrics, scaled attention markers, and focused tests.
2026-04-26 23:16:43 -07:00
Michael Bolin
a6ca39c630 permissions: derive legacy exec policies at boundaries (#19737)
## Why

After config and requirements store canonical profiles, exec requests
should not cache a derived `SandboxPolicy`. The cached legacy value can
drift from the richer profile state, and most execution paths already
have the filesystem and network runtime policies they need.

## What Changed

- Removes `sandbox_policy` from `codex_sandboxing::SandboxExecRequest`
and `codex_core::sandboxing::ExecRequest`.
- Adds an on-demand `ExecRequest::compatibility_sandbox_policy()` helper
for the Windows and legacy call sites that still need a `SandboxPolicy`
projection.
- Updates Windows filesystem override setup and unified exec policy
serialization to derive that compatibility policy at the boundary.
- Updates Unix escalation reruns and direct shell requests to
reconstruct exec requests from `PermissionProfile` plus runtime
filesystem/network policy, without carrying a cached legacy policy.
- Adjusts sandboxing manager tests to assert the effective profile
rather than the removed legacy field.

## Verification

- `cargo check -p codex-config -p codex-core -p codex-sandboxing -p
codex-app-server -p codex-cli -p codex-tui`
- `cargo test -p codex-sandboxing manager`
- `cargo test -p codex-core
exec_server_params_use_env_policy_overlay_contract`
- `cargo test -p codex-core unix_escalation`
- `cargo test -p codex-core exec::tests`
- `cargo test -p codex-core sandboxing::tests`
2026-04-26 22:11:49 -07:00
Michael Bolin
523e4aa8e3 permissions: constrain requirements as profiles (#19736) 2026-04-26 21:49:30 -07:00
Michael Bolin
0ccd659b4b permissions: store only constrained permission profiles (#19735) 2026-04-26 20:59:58 -07:00
Won Park
8033b6a449 Add /auto-review-denials retry approval flow (#19058)
## Why

Auto-review can deny an action that the user later decides they want to
retry. Today there is no TUI surface for selecting a recent denial and
sending explicit approval context back into the session, so users have
to restate intent manually and the retry can be reviewed without the
original denied action context.

This adds a narrow TUI-driven path for approving a recent denied action
while still keeping the retry inside the normal auto-review flow.

## What Changed

- Added `/auto-review-denials` to open a picker of recent denied
auto-review actions.
- Added a small in-memory TUI store for the 10 most recent denied
auto-review events.
- Selecting a denial sends the structured denied event back through the
existing core/app-server op path.
- Core now injects a developer message containing the approved action
JSON rather than the full assessment event.
- Auto-review transcript collection now preserves this specific approval
developer message so follow-up review sessions can see the user approval
context.
- Added TUI snapshot/unit coverage for the picker and approval dispatch
path.
- Added core coverage for retaining the approval developer message in
the auto-review transcript.

## Verification

- `cargo test -p codex-core
collect_guardian_transcript_entries_keeps_manual_approval_developer_message`
- `cargo test -p codex-tui auto_review_denials`
- `cargo test -p codex-tui
approving_recent_denial_emits_structured_core_op_once`

## Notes

This intentionally keeps retries going through auto-review. The approval
signal is context for the exact previously denied action, not a blanket
bypass for similar future actions.
2026-04-27 03:43:53 +00:00
Michael Bolin
0d8cdc0510 permissions: centralize legacy sandbox projection (#19734)
## Why

The remaining migration work still needs `SandboxPolicy` at a few
compatibility boundaries, but those projections should come from one
canonical path. Keeping ad hoc legacy projections scattered through
app-server, CLI, and config code makes it easy for behavior to drift as
`PermissionProfile` gains fidelity that the legacy enum cannot
represent.

## What Changed

- Adds `Permissions::legacy_sandbox_policy(cwd)` and
`Config::legacy_sandbox_policy()` as the compatibility projection from
the canonical `PermissionProfile`.
- Adds `Permissions::can_set_legacy_sandbox_policy()` so legacy inputs
are checked after they are converted into profile semantics.
- Updates app-server command handling, Windows sandbox setup, session
configuration, and sandbox summaries to use the centralized projection
helper.
- Leaves `SandboxPolicy` in place only for boundary inputs/outputs that
still speak the legacy abstraction.

## Verification

- `cargo check -p codex-config -p codex-core -p codex-sandboxing -p
codex-app-server -p codex-cli -p codex-tui`
- `cargo test -p codex-tui
permissions_selection_history_snapshot_full_access_to_default --
--nocapture`
- `cargo test -p codex-tui
permissions_selection_sends_approvals_reviewer_in_override_turn_context
-- --nocapture`
- `bazel test //codex-rs/tui:tui-unit-tests-bin
--test_arg=permissions_selection_history_snapshot_full_access_to_default
--test_output=errors`
- `bazel test //codex-rs/tui:tui-unit-tests-bin
--test_arg=permissions_selection_sends_approvals_reviewer_in_override_turn_context
--test_output=errors`


---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/19734).
* #19737
* #19736
* #19735
* __->__ #19734
2026-04-26 20:31:23 -07:00
Abhinav
c3e60849e5 inline hostname resolution for remote sandbox config (#19739)
# Why

Requirements support host-specific
`remote_sandbox_config.hostname_patterns`, but config loading previously
resolved and passed the system hostname through every config-loading
path even when no requirements layer used `remote_sandbox_config`. On
machines where hostname lookup is slow, startup and app-server config
reads paid for a feature that was not active.

We only need the hostname when a requirements layer actually declares
`remote_sandbox_config`, so this moves hostname resolution to the single
requirements merge point and keeps all other config callers unaware of
hostname matching.

# What

- Removed the eager `host_name` plumbing from
`load_config_layers_state`, `load_requirements_toml`, `ConfigBuilder`,
app-server `ConfigManager`, network proxy loading, and related call
sites.
- Resolve the hostname inside
`merge_requirements_with_remote_sandbox_config` only when the incoming
requirements contain `remote_sandbox_config`.
2026-04-27 03:18:57 +00:00
Michael Bolin
ad57a3fee2 permissions: finish profile-backed app surfaces (#19395) 2026-04-26 19:42:39 -07:00
Andrey Mishchenko
1f304dd1f2 Allow agents.max_threads to work with multi_agent_v2 (#19733) 2026-04-26 17:56:05 -07:00
Michael Bolin
2cb8746457 permissions: remove core legacy policy round trips (#19394)
## Why

Several execution paths still converted profile-backed permissions into
`SandboxPolicy` and then rebuilt runtime permissions from that legacy
shape. Those round trips are unnecessary after the preceding PRs and can
lose split filesystem semantics. Core approval and escalation should
carry the resolved profile directly.

## What Changed

- Removes `sandbox_policy` from `ResolvedPermissionProfile`; the
resolved permission object now carries the canonical `PermissionProfile`
directly.
- Updates exec-policy fallback, shell/unified-exec interception,
escalation reruns, and related tests to pass profiles instead of legacy
policies.
- Removes legacy additional-permission merge helpers that built an
effective `SandboxPolicy` before rebuilding runtime permissions.
- Keeps legacy projections only at compatibility boundaries that still
require `SandboxPolicy`, not in core permission computation.

## Verification

- `cargo test -p codex-core direct_write_roots`
- `cargo test -p codex-core runtime_roots_to_legacy_projection`
- `cargo test -p codex-app-server
requested_permissions_trust_project_uses_permission_profile_intent`







































































---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/19394).
* #19737
* #19736
* #19735
* #19734
* #19395
* __->__ #19394
2026-04-26 17:43:32 -07:00
Andrey Mishchenko
35bc6e3d01 Delete unused ResponseItem::Message.end_turn (#19605)
This field is unused. Delete it.
2026-04-26 17:18:09 -07:00
Ahmed Ibrahim
0bda8161a2 Split MCP connection modules (#19725)
## Why

The MCP connection manager module had grown to mix orchestration, RMCP
client startup, elicitation handling, Codex Apps cache and naming
behavior, tool qualification and filtering, and runtime data. The
previous stacked PRs split these responsibilities incrementally; this PR
collapses that work into one self-contained refactor on latest main.

## What changed

- Move McpConnectionManager into connection_manager.rs.
- Move RMCP client lifecycle, startup, and uncached tool listing into
rmcp_client.rs.
- Move elicitation request tracking and policy handling into
elicitation.rs.
- Move Codex Apps cache, key, filtering, and naming helpers into
codex_apps.rs.
- Rename the tool-name helper module to tools.rs and move ToolInfo, tool
filtering, schema masking, and qualification there.
- Move runtime and sandbox shared types into runtime.rs.
- Preserve latest main PermissionProfile-based MCP elicitation
auto-approval behavior.

## Verification

- just fmt
- cargo check -p codex-mcp
- cargo check -p codex-mcp --tests
- cargo check -p codex-core

---------

Co-authored-by: Codex <noreply@openai.com>
2026-04-26 23:23:34 +00:00
Michael Bolin
4c58e64f08 test: increase core-all-test shard count to 16 (#19727)
## Summary

Increase `core-all-test`'s Bazel shard count from `8` to `16`.

## Why

[#19609](https://github.com/openai/codex/pull/19609) restored
`bazel.yml` to a 30-minute timeout and increased `app-server-all-test`'s
shard count because the bigger timeout risk was not just a cold Windows
build. The more common problem was a long `rust_test()` shard failing
and getting retried multiple times.

Recent `main` runs show that `//codex-rs/core:core-all-test` still has
the same shape of problem on Windows:

- [Run
24943931330](https://github.com/openai/codex/actions/runs/24943931330)
reported `//codex-rs/core:core-all-test` as flaky after first-attempt
failures in shard `5/8` and shard `8/8`.
- Those retries were driven by
`suite::cli_stream::responses_mode_stream_cli_supports_openai_base_url_config_override`
and
`suite::pending_input::steered_user_input_waits_when_tool_output_triggers_compact_before_next_request`.
- The failed shard attempts in that run took `272.61s` and `259.27s`
before retrying, which is exactly the sort of wall-clock cost that burns
through the 30-minute budget.
- [Run
24966332583](https://github.com/openai/codex/actions/runs/24966332583)
also retried `//codex-rs/tui:tui-unit-tests` after
`app::tests::update_memory_settings_updates_current_thread_memory_mode`
failed once on Windows.
- [Run
24965527138](https://github.com/openai/codex/actions/runs/24965527138)
and its linked [BuildBuddy
invocation](https://app.buildbuddy.io/invocation/ac1a8265-06fa-4da5-9552-4715b7965bce)
show the other half of the problem: when Windows cache reuse is weak,
the `bazel test //...` step can already consume `24m11s` on its own,
leaving very little headroom for flaky retries.

Increasing `core-all-test` to `16` shards does not fix the flaky tests,
but it does reduce the wall-clock cost when a single shard has to be
retried. That matches the mitigation we already applied to
`app-server-all-test` in `#19609`.

## What Changed

- Update `codex-rs/core/BUILD.bazel` so `core-all-test` uses `16` shards
instead of `8`.
- Leave `core-unit-tests` unchanged.

## Follow-up Work

This change is meant to buy back CI headroom while we fix the flaky
tests themselves in subsequent commits. The recent Windows retries that
look worth addressing directly include:

-
`suite::cli_stream::responses_mode_stream_cli_supports_openai_base_url_config_override`
-
`suite::pending_input::steered_user_input_waits_when_tool_output_triggers_compact_before_next_request`
-
`app::tests::update_memory_settings_updates_current_thread_memory_mode`

## Verification

- Compared `core-all-test`'s current sharding against the
`app-server-all-test` precedent in
[#19609](https://github.com/openai/codex/pull/19609).
- Inspected recent `main` Bazel workflow logs and the linked BuildBuddy
invocation to confirm that Windows retries on long shards are still
consuming a meaningful fraction of the 30-minute timeout budget.
- Did not run local tests for this change because it only adjusts Bazel
sharding metadata.
2026-04-26 23:10:26 +00:00
pakrym-oai
ba159cbc79 Fix codex-core config test type paths (#19726)
Summary:
- Update config tests to reference config requirement types from
codex_config after the loader split.

Tests:
- just fmt
- cargo build -p codex-core --tests
- cargo clippy -p codex-core --tests -- -D warnings
2026-04-26 15:58:17 -07:00
Michael Bolin
dda8199b73 permissions: migrate approval and sandbox consumers to profiles (#19393)
## Why

Runtime decisions should not infer permissions from the lossy legacy
sandbox projection once `PermissionProfile` is available. In particular,
`Disabled` and `External` need to remain distinct, and managed profiles
with split filesystem or deny-read rules should not be collapsed before
approval, network, safety, or analytics code makes decisions.

## What Changed

- Changes managed network proxy setup and network approval logic to use
`PermissionProfile` when deciding whether a managed sandbox is active.
- Migrates patch safety, Guardian/user-shell approval paths, Landlock
helper setup, analytics sandbox classification, and selected
turn/session code to profile-backed permissions.
- Validates command-level profile overrides against the constrained
`PermissionProfile` rather than a strict `SandboxPolicy` round trip.
- Preserves configured deny-read restrictions when command profiles are
narrowed.
- Adds coverage for profile-backed trust, network proxy/approval
behavior, patch safety, analytics classification, and command-profile
narrowing.

## Verification

- `cargo test -p codex-core direct_write_roots`
- `cargo test -p codex-core runtime_roots_to_legacy_projection`
- `cargo test -p codex-app-server
requested_permissions_trust_project_uses_permission_profile_intent`




































































---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/19393).
* #19395
* #19394
* __->__ #19393
2026-04-26 15:30:40 -07:00
pakrym-oai
9c3abcd46c [codex] Move config loading into codex-config (#19487)
## Why

Config loading had become split across crates: `codex-config` owned the
config types and merge logic, while `codex-core` still owned the loader
that assembled the layer stack. This change consolidates that
responsibility in `codex-config`, so the crate that defines config
behavior also owns how configs are discovered and loaded.

To make that move possible without reintroducing the old dependency
cycle, the shell-environment policy types and helpers that
`codex-exec-server` needs now live in `codex-protocol` instead of
flowing through `codex-config`.

This also makes the migrated loader tests more deterministic on machines
that already have managed or system Codex config installed by letting
tests override the system config and requirements paths instead of
reading the host's `/etc/codex`.

## What Changed

- moved the config loader implementation from `codex-core` into
`codex-config::loader` and deleted the old `core::config_loader` module
instead of leaving a compatibility shim
- moved shell-environment policy types and helpers into
`codex-protocol`, then updated `codex-exec-server` and other downstream
crates to import them from their new home
- updated downstream callers to use loader/config APIs from
`codex-config`
- added test-only loader overrides for system config and requirements
paths so loader-focused tests do not depend on host-managed config state
- cleaned up now-unused dependency entries and platform-specific cfgs
that were surfaced by post-push CI

## Testing

- `cargo test -p codex-config`
- `cargo test -p codex-core config_loader_tests::`
- `cargo test -p codex-protocol -p codex-exec-server -p
codex-cloud-requirements -p codex-rmcp-client --lib`
- `cargo test --lib -p codex-app-server-client -p codex-exec`
- `cargo test --no-run --lib -p codex-app-server`
- `cargo test -p codex-linux-sandbox --lib`
- `cargo shear`
- `just bazel-lock-check`

## Notes

- I did not chase unrelated full-suite failures outside the migrated
loader surface.
- `cargo test -p codex-core --lib` still hits unrelated proxy-sensitive
failures on this machine, and Windows CI still shows unrelated
long-running/timeouting test noise outside the loader migration itself.
2026-04-26 15:10:53 -07:00
pakrym-oai
2a020f1a0a Lift app-server JSON-RPC error handling to request boundary (#19484)
## Why

App-server request handling had a lot of repeated JSON-RPC error
construction and one-off `send_error`/`return` branches. This made small
handlers noisy and pushed error response details into leaf code that
otherwise only needed to validate input or call the underlying API.

## What Changed

- Added shared JSON-RPC error constructors in
`codex-rs/app-server/src/error_code.rs`.
- Lifted straightforward request result emission into
`codex-rs/app-server/src/message_processor.rs` so response/error
dispatch happens at the request boundary.
- Reused the result helpers across command exec, config, filesystem,
device-key, external-agent config, fs-watch, and outgoing-message paths.
- Removed leaf wrapper handlers where the method body was only
forwarding to a response helper.
- Returned request validation errors upward in the simple cases instead
of sending an error locally and immediately returning.

## Verification

- `cargo test -p codex-app-server --lib command_exec::tests`
- `cargo test -p codex-app-server --lib outgoing_message::tests`
- `cargo test -p codex-app-server --lib in_process::tests`
- `cargo test -p codex-app-server --test all v2::fs`
- `cargo test -p codex-app-server --test all v2::config_rpc`
- `cargo test -p codex-app-server --test all v2::external_agent_config`
- `cargo test -p codex-app-server --test all v2::initialize`
- `just fix -p codex-app-server`
- `git diff --check`

Note: full `cargo test -p codex-app-server` was attempted and stopped in
`message_processor::tracing_tests::turn_start_jsonrpc_span_parents_core_turn_spans`
with a stack overflow after unrelated tests had already passed.
2026-04-26 15:10:35 -07:00
Michael Bolin
deaa307fb2 permissions: derive compatibility policies from profiles (#19392)
## Why

After #19391, `PermissionProfile` and the split filesystem/network
policies could still be stored in parallel. That creates drift risk: a
profile can preserve deny globs, external enforcement, or split
filesystem entries while a cached projection silently loses those
details. This PR makes the profile the runtime source and derives
compatibility views from it.

## What Changed

- Removes stored filesystem/network sandbox projections from
`Permissions` and `SessionConfiguration`; their accessors now derive
from the canonical `PermissionProfile`.
- Derives legacy `SandboxPolicy` snapshots from profiles only where an
older API still needs that field.
- Updates MCP connection and elicitation state to track
`PermissionProfile` instead of `SandboxPolicy` for auto-approval
decisions.
- Adds semantic filesystem-policy comparison so cwd changes can preserve
richer profiles while still recognizing equivalent legacy projections
independent of entry ordering.
- Updates config/session tests to assert profile-derived projections
instead of parallel stored fields.

## Verification

- `cargo test -p codex-core direct_write_roots`
- `cargo test -p codex-core runtime_roots_to_legacy_projection`
- `cargo test -p codex-app-server
requested_permissions_trust_project_uses_permission_profile_intent`



































































---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/19392).
* #19395
* #19394
* #19393
* __->__ #19392
2026-04-26 15:06:42 -07:00
Michael Bolin
4d7ce3447d permissions: make runtime config profile-backed (#19606)
## Why

This supersedes #19391. During stack repair, GitHub marked #19391 as
merged into a temporary stack branch rather than into `main`, so the
runtime-config change needed a fresh PR.

`PermissionProfile` is now the canonical permissions shape after #19231
because it can distinguish `Managed`, `Disabled`, and `External`
enforcement while also carrying filesystem rules that legacy
`SandboxPolicy` cannot represent cleanly. Core config and session state
still needed to accept profile-backed permissions without forcing every
profile through the strict legacy bridge, which rejected valid runtime
profiles such as direct write roots.

The unrelated CI/test hardening that previously rode along with this PR
has been split into #19683 so this PR stays focused on the permissions
model migration.

## What Changed

- Adds `Permissions.permission_profile` and
`SessionConfiguration.permission_profile` as constrained runtime state,
while keeping `sandbox_policy` as a legacy compatibility projection.
- Introduces profile setters that keep `PermissionProfile`, split
filesystem/network policies, and legacy `SandboxPolicy` projections
synchronized.
- Uses a compatibility projection for requirement checks and legacy
consumers instead of rejecting profiles that cannot round-trip through
`SandboxPolicy` exactly.
- Updates config loading, config overrides, session updates, turn
context plumbing, prompt permission text, sandbox tags, and exec request
construction to carry profile-backed runtime permissions.
- Preserves configured deny-read entries and `glob_scan_max_depth` when
command/session profiles are narrowed.
- Adds `PermissionProfile::read_only()` and
`PermissionProfile::workspace_write()` presets that match legacy
defaults.

## Verification

- `cargo test -p codex-core direct_write_roots`
- `cargo test -p codex-core runtime_roots_to_legacy_projection`
- `cargo test -p codex-app-server
requested_permissions_trust_project_uses_permission_profile_intent`




---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/19606).
* #19395
* #19394
* #19393
* #19392
* __->__ #19606
2026-04-26 13:29:54 -07:00
efrazer-oai
fed0a8f4fa feat: load AgentIdentity from JWT login/env (#18904)
## Summary

This PR lets programmatic AgentIdentity users provide one token through
either stdin login or environment auth.

`codex login --with-agent-identity` reads an Agent Identity JWT from
stdin, validates that it has the required claims, and stores that token
as the `agent_identity` value in `auth.json`. The file format is
token-only; the decoded account and key fields are runtime state, not
hand-authored auth.json fields.

The Agent Identity JWT claim shape and decoder live in
`codex-agent-identity`; `codex-login` only owns env/storage precedence
and conversion into `CodexAuth::AgentIdentity`.

When env auth is enabled, `CODEX_AGENT_IDENTITY` can provide the same
JWT without writing auth state to disk. `CODEX_API_KEY` still wins if
both env vars are set.

Reference old stack: https://github.com/openai/codex/pull/17387/changes
Reference JWT/env stack: https://github.com/openai/codex/pull/18176

## Stack

1. https://github.com/openai/codex/pull/18757: full revert
2. https://github.com/openai/codex/pull/18871: isolated Agent Identity
crate
3. https://github.com/openai/codex/pull/18785: explicit AgentIdentity
auth mode and startup task allocation
4. https://github.com/openai/codex/pull/18811: migrate Codex backend
auth callsites through AuthProvider
5. This PR: accept AgentIdentity JWTs through login/env

## Testing

Tests: targeted login and Agent Identity crate tests, CLI checks, scoped
formatter/linter cleanup, and CI.

---------

Co-authored-by: Shijie Rao <shijie.rao@openai.com>
2026-04-26 19:49:54 +00:00
Michael Bolin
ac2bffa443 test: harden app-server integration tests (#19683)
## Why

Windows Bazel runs in the permissions stack exposed that app-server
integration tests were launching normal plugin startup warmups in every
subprocess. Those warmups can call
`https://chatgpt.com/backend-api/plugins/featured` when a test is not
specifically exercising plugin startup, which adds slow background work,
noisy stderr, and dependence on external network state. The relevant
startup/featured-plugin behavior was introduced across #15042 and
#15264.

A few app-server tests also had long optional waits or unbounded cleanup
paths, making failures expensive to diagnose and contributing to slow
Windows shards. One external-agent config test from #18246 used a
GitHub-style marketplace source, which was enough to exercise the
pending remote-import path but also meant the background completion task
could attempt a real clone.

## What Changed

- Adds explicit `AppServerRuntimeOptions` / `PluginStartupTasks`
plumbing and a hidden debug-only
`--disable-plugin-startup-tasks-for-tests` app-server flag, so
integration tests can suppress startup plugin warmups without adding a
production env-var gate.
- Has the app-server test harness pass that hidden flag by default,
while opting plugin-startup coverage back in for tests that
intentionally exercise startup sync and featured-plugin warmup behavior.
- Lowers normal app-server subprocess logging from `info`/`debug` to
`warn` to avoid multi-megabyte stderr output in Bazel logs.
- Prevents the external-agent config test from attempting a real
marketplace clone by using an invalid non-local source while still
exercising the pending-import completion path.
- Bounds optional filesystem/realtime waits and fake WebSocket
test-server shutdown so failures produce targeted timeouts instead of
hanging a shard.
- Fixes the Unix script-resolution test in `rmcp-client` to exercise
PATH resolution directly and include the actual spawn error in failures.

## Verification

- `cargo check -p codex-app-server`
- `cargo clippy -p codex-app-server --tests -- -D warnings`
- `cargo test -p codex-rmcp-client
program_resolver::tests::test_unix_executes_script_without_extension`
- `cargo test -p codex-app-server --test all
external_agent_config_import_sends_completion_notification_after_pending_plugins_finish
-- --nocapture`
- `cargo test -p codex-app-server --test all
plugin_list_uses_warmed_featured_plugin_ids_cache_on_first_request --
--nocapture`
- Windows Local Bazel passed with this test-hardening bundle before it
was extracted from #19606.

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/19683).
* #19395
* #19394
* #19393
* #19392
* #19606
* __->__ #19683
2026-04-26 12:43:16 -07:00
Thibault Sottiaux
87bc72408c [codex] remove responses command (#19640)
This removes the hidden `codex responses` CLI subcommand after
confirming no downstream callers rely on it, deleting the raw Responses
passthrough implementation, unregistering the subcommand, and dropping
the now-unused CLI dependencies on `codex-api` and
`codex-model-provider`.
2026-04-25 23:10:38 -07:00
Andrey Mishchenko
355c40ad7e Support end_turn in response.completed (#19610)
Some providers of Responses API forward a model-defined `end_turn`
boolean indicating explicitly the model's indication of whether it would
like to end the turn or to be inferenced again. In this PR, we update
the sampling loop to use this field correctly if it's set. If the field
is not set by the provider, we fall back to the existing sampling logic.
2026-04-25 21:57:42 -07:00
Felipe Coury
5591912f0b fix(tui): reflow scrollback on terminal resize (#18575)
Fixes multiple scrollback and terminal resize issues: #5538, #5576,
#8352, #12223, #16165, and #15380.

## Why

Codex writes finalized transcript output into terminal scrollback after
wrapping it for the current viewport width. A later terminal resize
could leave that scrollback shaped for the old width, so wider windows
kept narrow output and narrower windows could show stale wrapping
artifacts until enough new output replaced the visible area.

This is also the foundation PR for responsive markdown tables. Table
rendering needs finalized transcript content to be width-sensitive after
insertion, not only while content is first streaming. Markdown table
rendering itself stays in #18576.

## Stack

- PR1: resize backlog reflow and interrupt cleanup
- #18576: markdown table support

## What Changed

- Rebuild source-backed transcript history when the terminal width
changes. `terminal_resize_reflow` is introduced through the experimental
feature system, but is enabled by default for this rollout so we can
validate behavior across real terminals.
- Preserve assistant and plan stream source so finalized streaming
output can participate in resize reflow after consolidation.
- Debounce resize work, but force a final source-backed reflow when a
resize happened during active or unconsolidated streaming output.
- Clear stale pending history lines on resize so old-width wrapped
output is not emitted just before rebuilt scrollback.
- Bound replay work with `[tui.terminal_resize_reflow].max_rows`:
omitted uses terminal-specific defaults, `0` keeps all rendered rows,
and a positive value sets an explicit cap. The cap applies both while
initially replaying a resumed transcript into scrollback and when
rebuilding scrollback after terminal resize.
- Consolidate interrupted assistant streams before cleanup, then clear
pending stream output and active-tail state consistently.
- Move resize reflow and thread event buffering helpers out of `app.rs`
into dedicated TUI modules.
- Add focused coverage for resize reflow, feature-gated behavior,
streaming source preservation, interrupted output cleanup,
unicode-neutral text, terminal-specific row caps, and composer/layout
stability.

## Runtime Bounds

Resize reflow keeps only the most recent rendered rows when a row cap is
active. The default is `auto`, which maps to the detected terminal's
default scrollback size where Codex can identify it: VS Code `1000`,
Windows Terminal `9001`, WezTerm `3500`, and Alacritty `10000`.
Terminals without a dedicated mapping use the conservative fallback of
`1000` rows. Users can override this with `[tui.terminal_resize_reflow]
max_rows = N`, or set `max_rows = 0` to disable row limiting.

## Validation

- `just fmt`
- `git diff --check`
- `cargo test --manifest-path codex-rs/Cargo.toml -p codex-tui reflow`
- `cargo test --manifest-path codex-rs/Cargo.toml -p codex-tui
transcript_reflow`
- `just fix -p codex-tui`
- PR CI in progress on the squashed branch
2026-04-25 22:00:32 -03:00
Shijie Rao
4e30281a13 Guard npm update readiness (#19389)
## Why
For npm/Bun-managed installs, the update prompt was treating the latest
GitHub release as ready to install. During the `0.124.0` release, GitHub
and npm visibility were not atomic: the root npm wrapper could become
visible before the npm registry marked that version as the package
`latest`. That left a window where users could be prompted to upgrade
before npm was ready for the release.

## What changed
- Keep GitHub Releases as the candidate latest-version source for
npm/Bun installs, but only write the existing `version.json` cache after
npm registry metadata proves that same root version is ready.
- Add `codex-rs/tui/src/npm_registry.rs` to validate npm readiness by
checking `dist-tags.latest` and root package `dist` metadata for the
GitHub candidate version.
- Move version parsing helpers into
`codex-rs/tui/src/update_versions.rs` so that logic can be tested
without compiling the release-only `updates.rs` module under tests.
- Update `.github/workflows/rust-release.yml` so the six known platform
tarballs publish before the root `@openai/codex` wrapper. Other npm
tarballs publish before the root wrapper, and the SDK publishes after
the root package it depends on.
2026-04-25 17:09:29 -07:00
Michael Bolin
9881dc7306 fix: restore 30-minute timeout for Bazel builds (#19609)
I think raising it to 45 minutes in
https://github.com/openai/codex/pull/19578 was a mistake for the reasons
explained in the comments in the code. Instead, we attempt to defend
against timeouts by increasing the number of shards in
`app-server-all-test` so that a "true failure" that gets run 3x should
not take as much wall clock time.
2026-04-25 16:34:06 -07:00
Michael Bolin
d54493ba1c test: stabilize app-server path assertions on Windows (#19604)
## Why

Windows can represent the same canonical local path with either a normal
drive path or a verbatim device path prefix. The failure pattern that
motivated this PR was an assertion diff like `C:\...` versus
`\\?\C:\...`: different spellings, same file.

That became visible while validating the permissions stack above this
PR. The stack increasingly routes paths through `AbsolutePathBuf`, which
normalizes supported Windows device prefixes, while several existing
tests still built expected values directly with
`std::fs::canonicalize()` or compared `AbsolutePathBuf::as_path()` to a
raw `PathBuf`. On Windows, that can make tests fail because the two
sides choose different textual forms for an otherwise equivalent
canonical path.

This PR is intentionally split out as the bottom PR below #19606. The
runtime permissions migration should not carry unrelated Windows test
stabilization, and reviewers should be able to verify this as a
test-only change before looking at the larger permissions changes.

## Failure Modes Covered

- `conversation_summary` expected rollout paths were built from raw
canonicalized `PathBuf`s, while app-server responses could carry
`AbsolutePathBuf`-normalized paths.
- `thread_resume` compared returned thread paths directly to previously
stored or fixture paths, so a verbatim-prefix spelling could fail an
otherwise correct resume.
- `marketplace_add` compared plugin install roots through `as_path()`
against raw canonicalized paths, reproducing the same `C:\...` versus
`\\?\C:\...` mismatch in both app-server and core-plugin coverage.

## What Changed

- In `app-server/tests/suite/conversation_summary.rs`, normalize both
expected rollout paths and received `ConversationSummary.path` values
through `AbsolutePathBuf` before comparing the full summary object.
- In `app-server/tests/suite/v2/thread_resume.rs`, normalize both sides
of thread path comparisons before asserting equality. This keeps the
tests focused on whether resume returned the same existing path, not
whether Windows used the same string spelling.
- In `app-server/tests/suite/v2/marketplace_add.rs` and
`core-plugins/src/marketplace_add.rs`, compare install roots as
`AbsolutePathBuf` values instead of comparing an absolute-path wrapper
to a raw canonicalized `PathBuf`.

## Behavior

This PR does not change production app-server or marketplace behavior.
It only changes tests to assert semantic path identity across Windows
path spelling variants. It also leaves API response values untouched;
the normalization happens inside assertions only.

## Verification

Targeted local checks run while extracting this fix:

- `cargo test -p codex-app-server
get_conversation_summary_by_thread_id_reads_rollout`
- `cargo test -p codex-app-server
get_conversation_summary_by_relative_rollout_path_resolves_from_codex_home`
- `cargo test -p codex-app-server
thread_resume_prefers_path_over_thread_id`

Windows-specific confidence comes from the Bazel Windows CI job for this
PR, since the failure is platform-specific.

## Docs

No docs update is needed because this is test-only infrastructure
stabilization.

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/19604).
* #19395
* #19394
* #19393
* #19392
* #19606
* __->__ #19604
2026-04-25 16:25:28 -07:00
viyatb-oai
9aaa5d9358 [codex] Bypass managed network for escalated exec (#19595)
## Why

`sandbox_permissions = "require_escalated"` is treated as an explicit
request to approve the command and run it outside the
filesystem/platform sandbox. Before this change, shell and unified exec
still registered managed network approval context and could inject
Codex-managed proxy state into the child process, which meant an
approved escalated command could still hit a second network approval
path.

This PR makes that escalation boundary consistent: once a command is
explicitly approved to run outside the sandbox, Codex does not also
route that process through the managed network proxy.

## Security impact

Command/filesystem sandbox approval now implies network approval for
that command. If an untrusted command or script is allowed to run with
`require_escalated`, its network calls are unsandboxed: Codex-managed
network allowlists and denylists are not respected for that process, so
the command can exfiltrate any data it can read.

## What changed

- Skip managed network approval specs for
`SandboxPermissions::RequireEscalated`.
- Pass `network: None` into shell, zsh-fork shell, and unified exec
sandbox preparation for explicitly escalated requests.
- Strip Codex-managed proxy environment variables when
`CODEX_NETWORK_PROXY_ACTIVE` is present, while preserving user proxy env
when the Codex marker is absent.
- Add regression coverage for the prepared exec request so the old
behavior cannot silently reappear.

## Verification

- `cargo test -p codex-core explicit_escalation`
- `cargo clippy -p codex-core --all-targets -- -D warnings`
2026-04-25 23:23:58 +00:00
Eric Traut
0c785598b3 Keep slash command popup columns stable while scrolling (#19511)
## Why

Fixes #19499.

The slash-command popup recalculated the command-name column from only
the rows visible in the current viewport. That made the description
column shift horizontally while scrolling through `/` commands whenever
longer command names entered or left the visible window.

## What Changed

`codex-rs/tui/src/bottom_pane/command_popup.rs` now uses the shared
selection-popup `AutoAllRows` column-width mode for both height
measurement and rendering. This keeps the command description column
based on the full filtered slash-command list instead of the current
viewport.

## Verification

- `cargo test -p codex-tui bottom_pane::command_popup`
2026-04-25 14:25:58 -07:00
Michael Bolin
f41306b4f3 test: isolate remote thread store regression from plugin warmups (#19593)
Follow-up to #19266.

## Why


`thread_start_with_non_local_thread_store_does_not_create_local_persistence`
is meant to catch accidental local thread persistence when a non-local
thread store is configured. The Windows flake reported in [this
BuildBuddy
invocation](https://app.buildbuddy.io/invocation/0b75dde4-6828-4e7b-a35b-e45b73fb005d)
showed that the assertion was tripping on an unexpected top-level `.tmp`
entry:

```diff
 {
+    ".tmp",
     "config.toml",
     "installation_id",
     "memories",
     "skills",
 }
```

That `.tmp` does not appear to come from `tempfile::TempDir`; it comes
from unrelated plugin startup work that can legitimately materialize
`codex_home/.tmp`, including the startup remote plugin sync marker in
[`core/src/plugins/startup_sync.rs`](bce74c70ce/codex-rs/core/src/plugins/startup_sync.rs (L13-L15))
and the curated plugin snapshot under
[`.tmp/plugins`](bce74c70ce/codex-rs/core-plugins/src/startup_sync.rs (L25-L26)).

That makes the regression race unrelated background startup tasks
instead of validating the thread-store invariant it was added to cover.
Rather than weakening the assertion to allow arbitrary `.tmp` entries,
this change isolates the test from plugin warmups so it can stay strict
about unexpected local thread persistence artifacts.

## What changed

- disable plugins in the generated config used by
`app-server/tests/suite/v2/remote_thread_store.rs`
- keep the existing `codex_home` assertions unchanged so the test still
fails if local session or sqlite persistence is introduced

## Verification

- `cargo test -p codex-app-server
suite::v2::remote_thread_store::thread_start_with_non_local_thread_store_does_not_create_local_persistence
-- --exact`
2026-04-25 20:45:31 +00:00
Eric Traut
bce74c70ce Restore persisted model provider on thread resume (#19287)
Fixes #15219.

## Why

`thread/resume` should continue a persisted thread with the same model
provider that created the thread. The app server already restores the
persisted model and reasoning effort before resuming, but it was leaving
`model_provider` unset. If a user created a thread with one provider and
later switched their active profile to another provider, resumed
encrypted history could be sent to the wrong endpoint and fail with
`invalid_encrypted_content`.

The thread metadata already records the original provider, so resume
should apply it when the caller has not explicitly requested a different
model/provider/reasoning configuration.

## What changed

This updates `merge_persisted_resume_metadata` in
`app-server/src/codex_message_processor.rs` to copy
`ThreadMetadata::model_provider` into `ConfigOverrides::model_provider`
alongside the persisted model.

The existing resume metadata tests now also assert that:

- the persisted provider is restored for normal resume
- explicit model, provider, or reasoning-effort overrides still prevent
persisted resume metadata from being applied
- a thread with no persisted model or reasoning effort still resumes
with its persisted provider

## Verification

- `cargo test -p codex-app-server` passed the app-server unit tests,
including the updated resume metadata coverage. The broader integration
portion of that command failed in an unrelated environment-sensitive
skills-budget warning assertion, where this run saw 8 omitted skills
instead of the expected 7.
- `just fix -p codex-app-server` completed successfully.
2026-04-25 12:40:00 -07:00
Michael Bolin
88f300d74d fix: increase Bazel timeout to 45 minutes (#19578)
Unfortunately, if most of the build graph is invalidated such that there
are few cache hits, the Windows Bazel build for all the tests often
takes more than `30` minutes, so this PR increases the timeout to `45`
minutes until we set up distributed builds.
2026-04-25 10:03:01 -07:00
Ahmed Ibrahim
022f81df1f [codex] Order codex-mcp items by visibility (#19526)
## Why

The visibility cleanup in the base PR reduced what `codex-mcp` exposes,
but several files still made reviewers read private support machinery
before the public or crate-facing entry points. This ordering pass makes
each file easier to scan: exported API first, crate-visible MCP
internals next, then private helpers in breadth-first order from the
higher-level MCP flows to leaf utilities.

## What Changed

- Reordered `codex-mcp` exports so the runtime, configuration, snapshot,
auth, and helper surfaces are grouped by visibility and reader
importance.
- Moved public and crate-visible MCP items ahead of private helpers in
the auth, MCP planning/snapshot, connection manager, and tool-name
modules.
- Kept the change mechanical, with no behavior changes intended.

## Verification

- `cargo check -p codex-mcp`
2026-04-25 07:17:30 -07:00
Ahmed Ibrahim
706490ab1b [codex] Prune unused codex-mcp API and duplicate helpers (#19524)
## Why

`codex-mcp` currently exposes more API than the rest of the workspace
uses. Some of that surface is simply visibility that can be tightened,
and some of it is public helper code that remains compiler-valid because
it is exported even though no workspace caller uses it.

That distinction matters: Rust does not warn on exported API just
because the current workspace does not call it. This PR intentionally
treats those exported-but-workspace-unreferenced paths as stale
`codex-mcp` surface. The main example is MCP skill dependency
collection, where the active implementation now lives in
`codex-rs/core/src/mcp_skill_dependencies.rs`; keeping the older
`codex-mcp` copy makes it unclear which implementation owns skill MCP
installation.

## What Changed

- Pruned unused `codex-mcp` re-exports from `codex-mcp/src/lib.rs`.
- Removed non-runtime helper methods from `McpConnectionManager` so it
stays focused on live MCP clients.
- Made `ToolPluginProvenance` lookup methods crate-private.
- Removed workspace-unreferenced snapshot wrapper APIs and
qualified-tool grouping helpers.
- Deleted the duplicate `codex-mcp` skill dependency module and tests
now that skill MCP dependency handling is owned by `core`.

## Verification

- `cargo check -p codex-mcp`
2026-04-25 06:36:07 -07:00
Matthew Zeng
6e838a19fa Enable unavailable dummy tools by default (#19459)
## Summary
- Mark `unavailable_dummy_tools` as a stable feature and enable it by
default
- Update the feature registry test to match the new default state

## Testing
- `just fmt`
- `cargo test -p codex-features`
2026-04-25 08:46:57 +00:00
Eric Traut
a2db6f97fb Fix codex-rs README grammar (#19514)
## Why

Issue #19418 points out a small grammar issue in `codex-rs/README.md`
under "Code Organization." The current sentence says "we hope this to
be," which reads awkwardly.

Fixes #19418.

## What changed

Updated the `core/` crate description so the sentence reads "we hope
this becomes a library crate."

## Verification

Documentation-only change. Reviewed the Markdown diff.
2026-04-24 23:31:47 -07:00
Dylan Hurd
f5497f4d65 Split approval matrix test groups (#19454)
## Why

Recent `main` CI repeatedly timed out in:

- `codex-core::all suite::approvals::approval_matrix_covers_all_modes`

It failed in runs
[24909500958](https://github.com/openai/codex/actions/runs/24909500958),
[24908076251](https://github.com/openai/codex/actions/runs/24908076251),
[24906197645](https://github.com/openai/codex/actions/runs/24906197645),
[24905823212](https://github.com/openai/codex/actions/runs/24905823212),
[24903439629](https://github.com/openai/codex/actions/runs/24903439629),
[24903336028](https://github.com/openai/codex/actions/runs/24903336028),
and
[24898949647](https://github.com/openai/codex/actions/runs/24898949647).

The failure pattern was a 60s Linux remote timeout. Logs showed many
approval scenarios completing before the single matrix test timed out.

## Root Cause

`approval_matrix_covers_all_modes` packed every approval/sandbox/tool
scenario into one test case. That made the test vulnerable to normal CI
variance: one slow scenario or a slow process startup could push the
whole monolithic case past the 60s per-test timeout. It also hid which
part of the matrix was slow because the runner only reported the one
large matrix test.

## What Changed

- Keep the shared `scenarios()` table as the single source of approval
matrix coverage.
- Use one `#[test_case]` per `ScenarioGroup` to generate five async
Tokio tests: danger/full-access, read-only, workspace-write,
apply-patch, and unified-exec.
- Keep the group runner small and add per-scenario error context so a
failure still reports the specific scenario name.

## Why This Should Be Reliable

Each scenario group now has its own test harness timeout instead of
sharing one timeout window with the full matrix. That removes the long
sequential loop from a single test while keeping the implementation
compact and easy to scan.

The tests still run through the same scenario definitions and runner, so
this preserves coverage. `test-case` already composes with
`#[tokio::test]` in this crate and is already available for test code.

## Verification

- `cargo test -p codex-core --test all approval_matrix_ -- --list`
- `cargo test -p codex-core --test all approval_matrix_`
2026-04-24 21:38:27 -07:00
Eric Traut
f1c963d77e Add goal TUI UX (5 / 5) (#18077)
Adds the TUI user experience for goals on top of the core runtime from
PR 4.

## Why

Users need a direct TUI control surface for long-running goals. The UI
should make the current goal visible, support common goal actions
without waiting for a model turn, and avoid confusing end-of-turn
notifications while an active goal is immediately continuing.

## What changed

- Added `/goal` summary rendering for the current goal, including
active, paused, budget-limited, and complete states.
- Added `/goal <objective>` creation/replacement through the app-server
goal API rather than a model prompt.
- Added `/goal clear`, `/goal pause`, and `/goal unpause` command
variants.
- Added a confirmation menu when the user enters a new goal while
another goal already exists.
- Updated `/goal` help and summary tip text so it reflects the supported
command variants without advertising slash-command token budgets.
- Added footer/statusline goal indicators, including elapsed time and
token budget display when a budget exists from API/tool-created goals.
- Consumes goal updated/cleared notifications so the TUI stays in sync
with external app-server changes.
- Suppresses end-of-turn desktop notifications only when a goal is still
active and follow-up work is expected.
- Preserves slash-command history behavior and avoids leaking queued
`/goal` state into unrelated submissions.

## Verification

- Added TUI unit and snapshot coverage for goal command availability,
summary rendering, control commands, replacement menu behavior,
status/footer display, notification handling, and command history.
2026-04-24 21:16:45 -07:00
Eric Traut
4167628622 Add goal core runtime (4 / 5) (#18076)
Adds the core runtime behavior for active goals on top of the model
tools from PR 3.

## Why

A long-running goal should be a core runtime concern, not something
every client has to implement. Core owns the turn lifecycle, tool
completion boundaries, interruptions, resume behavior, and token usage,
so it is the right place to account progress, enforce budgets, and
decide when to continue work.

## What changed

- Centralized goal lifecycle side effects behind
`Session::goal_runtime_apply(GoalRuntimeEvent::...)`.
- Starts goal continuation turns only when the session is idle; pending
user input and mailbox work take priority.
- Accounts token and wall-clock usage at turn, tool, mutation,
interrupt, and resume boundaries; `get_thread_goal` remains read-only.
- Preserves sub-second wall-clock remainder across accounting boundaries
so long-running goals do not drift downward over time.
- Treats token budget exhaustion as a soft stop by marking the goal
`budget_limited` and injecting wrap-up steering instead of aborting the
active turn.
- Suppresses budget steering when `update_goal` marks a goal complete.
- Pauses active goals on interrupt and auto-reactivates paused goals
when a thread resumes outside plan mode.
- Suppresses repeated automatic continuation when a continuation turn
makes no tool calls.
- Added continuation and budget-limit prompt templates.

## Verification

- Added focused core coverage for continuation scheduling, accounting
boundaries, budget-limit steering, completion accounting, interrupt
pause behavior, resume auto-activation, and wall-clock remainder
accounting.
2026-04-24 21:16:00 -07:00
Eric Traut
32ace07ac5 Add goal model tools (3 / 5) (#18075)
Adds the model-facing goal tools on top of the app-server API from PR 2.

## Why

Once goals are persisted and exposed to clients, the model needs a
small, constrained tool surface for goal workflows. The tool contract
should let the model inspect goals, create them only when explicitly
requested, and mark them complete without giving it broad control over
user/runtime-owned state.

## What changed

- Added `get_goal`, `create_goal`, and `update_goal` tool specs behind
the `goals` feature flag.
- Added core goal tool handlers that validate objectives and token
budgets before mutating persisted state.
- Constrained `create_goal` to create only when no goal exists, with
optional `token_budget` only when a budget is explicitly provided.
- Tightened the `create_goal` instructions so the model does not infer
goals from ordinary task requests.
- Constrained `update_goal` to expose only goal completion; pause,
resume, clear, and budget-limited transitions remain user- or
runtime-controlled.
- Registered the goal tools in the tool registry and kept them out of
review contexts where they should not appear.

## Verification

- Added tool-registry coverage for feature gating and tool availability.
- Added core session tests for create/get/update behavior, duplicate
goal rejection, budget validation, and completion-only updates.
2026-04-24 20:54:40 -07:00
Eric Traut
6c874f9b34 Add goal app-server API (2 / 5) (#18074)
Adds the app-server v2 goal API on top of the persisted goal state from
PR 1.

## Why

Clients need a stable app-server surface for reading and controlling
materialized thread goals before the model tools and TUI can use them.
Goal changes also need to be observable by app-server clients, including
clients that resume an existing thread.

## What changed

- Added v2 `thread/goal/get`, `thread/goal/set`, and `thread/goal/clear`
RPCs for materialized threads.
- Added `thread/goal/updated` and `thread/goal/cleared` notifications so
clients can keep local goal state in sync.
- Added resume/snapshot wiring so reconnecting clients see the current
goal state for a thread.
- Added app-server handlers that reconcile persisted rollout state
before direct goal mutations.
- Updated the app-server README plus generated JSON and TypeScript
schema fixtures for the new API surface.

## Verification

- Added app-server v2 coverage for goal get/set/clear behavior,
notification emission, resume snapshots, and non-local thread-store
interactions.
2026-04-24 20:53:41 -07:00
Eric Traut
0ee737cea6 Add goal persistence foundation (1 / 5) (#18073)
Adds the persisted goal foundation for the rest of the stack. This PR is
intentionally limited to feature flag and state-layer behavior;
app-server APIs, model tools, runtime continuation, and TUI UX are
layered in later PRs.

## Why

Goal mode needs durable thread-level state before clients or model tools
can safely build on it. The state layer needs to know whether a goal
exists, what objective it tracks, whether it is active, paused,
budget-limited, or complete, and how much time/token usage has already
been accounted.

## What changed

- Added the `goals` feature flag and generated config schema entry.
- Added the `thread_goals` state table and Rust model for persisted
thread goals.
- Added state runtime APIs for creating, replacing, updating, deleting,
and accounting goal usage.
- Added `goal_id`-based stale update protection so an old goal update
cannot overwrite a replacement.
- Kept this PR scoped to persistence and state runtime behavior, with no
app-server, model-facing, continuation, or TUI behavior yet.

## Verification

- Added state runtime coverage for goal creation, replacement, stale
update protection, status transitions, token-budget behavior, and usage
accounting.
2026-04-24 20:51:38 -07:00
Curtis 'Fjord' Hawthorne
8a559e7938 Remove js_repl feature (#19410) 2026-04-24 17:49:29 -07:00
Curtis 'Fjord' Hawthorne
cf02e9c052 Fix Bazel cargo_bin runfiles paths (#19468)
## Summary

Fix a Bazel-only path resolution bug in
`codex_utils_cargo_bin::cargo_bin`.

Under Bazel runfiles, `rlocation` can return a relative `bazel-out/...`
path even though `cargo_bin()` documents that it returns an absolute
path. That can break callers that store the returned binary path and
later spawn it after changing cwd, because the relative path is resolved
from the wrong directory.

This patch absolutizes the runfiles-resolved path before returning it.
2026-04-24 17:47:31 -07:00
viyatb-oai
1c3287125f ci: pin codex-action v1.7 (#19472)
## Summary
- update Codex issue automation to pin `openai/codex-action` to
`5c3f4ccdb2b8790f73d6b21751ac00e602aa0c02`, the commit for `v1.7`
- keep the release intent visible with `# v1.7` comments beside the hash
pins

## Test plan
- `git diff --check`
- `yq e '.' .github/workflows/issue-labeler.yml`
- `yq e '.' .github/workflows/issue-deduplicator.yml`

---------

Co-authored-by: Codex <noreply@openai.com>
2026-04-25 00:44:04 +00:00
Michael Bolin
789f387982 permissions: remove legacy read-only access modes (#19449)
## Why

`ReadOnlyAccess` was a transitional legacy shape on `SandboxPolicy`:
`FullAccess` meant the historical read-only/workspace-write modes could
read the full filesystem, while `Restricted` tried to carry partial
readable roots. The partial-read model now belongs in
`FileSystemSandboxPolicy` and `PermissionProfile`, so keeping it on
`SandboxPolicy` makes every legacy projection reintroduce lossy
read-root bookkeeping and creates unnecessary noise in the rest of the
permissions migration.

This PR makes the legacy policy model narrower and explicit:
`SandboxPolicy::ReadOnly` and `SandboxPolicy::WorkspaceWrite` represent
the old full-read sandbox modes only. Split readable roots, deny-read
globs, and platform-default/minimal read behavior stay in the runtime
permissions model.

## What changed

- Removes `ReadOnlyAccess` from
`codex_protocol::protocol::SandboxPolicy`, including the generated
`access` and `readOnlyAccess` API fields.
- Updates legacy policy/profile conversions so restricted filesystem
reads are represented only by `FileSystemSandboxPolicy` /
`PermissionProfile` entries.
- Keeps app-server v2 compatible with legacy `fullAccess` read-access
payloads by accepting and ignoring that no-op shape, while rejecting
legacy `restricted` read-access payloads instead of silently widening
them to full-read legacy policies.
- Carries Windows sandbox platform-default read behavior with an
explicit override flag instead of depending on
`ReadOnlyAccess::Restricted`.
- Refreshes generated app-server schema/types and updates tests/docs for
the simplified legacy policy shape.

## Verification

- `cargo check -p codex-app-server-protocol --tests`
- `cargo check -p codex-windows-sandbox --tests`
- `cargo test -p codex-app-server-protocol sandbox_policy_`


---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/19449).
* #19395
* #19394
* #19393
* #19392
* #19391
* __->__ #19449
2026-04-24 17:16:58 -07:00
Celia Chen
d19de6d150 fix: Bedrock GPT-5.4 reasoning levels (#19461)
## Why

When using the Amazon Bedrock provider with `openai.gpt-5.4-cmb`, the
model picker allowed `xhigh` because the CMB catalog entry was derived
from the bundled `gpt-5.4` reasoning metadata. Bedrock rejects that
effort level, causing the request to fail before the turn can run:

```text
{"error":{"code":"validation_error","message":"Failed to deserialize the JSON body into the target type: Invalid 'reasoning': Invalid 'effort': unknown variant `xhigh`, expected one of `high`, `low`, `medium`, `minimal` at line 1 column 77239","param":null,"type":"invalid_request_error"}}
```

## What Changed

- Replace the runtime lookup of bundled `gpt-5.4` metadata for
`openai.gpt-5.4-cmb` with an explicit Bedrock CMB `ModelInfo` entry.
- Advertise only the Bedrock-supported CMB reasoning levels: `minimal`,
`low`, `medium`, and `high`.
- Keep the existing GPT OSS Bedrock model metadata and reasoning levels
unchanged.
- Add catalog coverage for the hardcoded CMB metadata and
Bedrock-compatible reasoning level list.
2026-04-25 00:05:22 +00:00
736 changed files with 52387 additions and 35248 deletions

View File

@@ -1,6 +1,6 @@
[codespell]
# Ref: https://github.com/codespell-project/codespell#using-a-config-file
skip = .git*,vendor,*-lock.yaml,*.lock,.codespellrc,*test.ts,*.jsonl,frame*.txt,*.snap,*.snap.new,*meriyah.umd.min.js
skip = .git*,vendor,*-lock.yaml,*.lock,.codespellrc,*test.ts,*.jsonl,frame*.txt,*.snap,*.snap.new
check-hidden = true
ignore-regex = ^\s*"image/\S+": ".*|\b(afterAll)\b
ignore-words-list = ratatui,ser,iTerm,iterm2,iterm,te,TE,PASE,SEH

View File

@@ -0,0 +1,102 @@
---
name: codex-issue-digest
description: Run a GitHub issue digest for openai/codex by feature-area labels, all areas, and configurable time windows. Use when asked to summarize recent Codex bug reports or enhancement requests, especially for owner-specific labels such as tui, exec, app, or similar areas.
---
# Codex Issue Digest
## Objective
Produce a concise, insight-oriented digest of `openai/codex` issues for the requested feature-area labels over the previous 24 hours by default. Honor a different duration when the user asks for one, for example "past week" or "48 hours".
Include only issues that currently have `bug` or `enhancement` plus at least one requested owner label. If the user asks for all areas or all labels, collect `bug`/`enhancement` issues across all labels.
## Inputs
- Feature-area labels, for example `tui exec`
- `all areas` / `all labels` to scan all current feature labels
- Optional repo override, default `openai/codex`
- Optional time window, default previous 24 hours; examples: `48h`, `7d`, `1w`, `past week`
## Workflow
1. Run the collector from a current Codex repo checkout:
```bash
python3 .codex/skills/codex-issue-digest/scripts/collect_issue_digest.py --labels tui exec --window-hours 24
```
Use `--window "past week"` or `--window-hours 168` when the user asks for a non-default duration. Use `--all-labels` when the user says all areas or all labels.
2. Use the JSON as the source of truth. It includes new issues, new issue comments, new reactions/upvotes, current labels, current reaction counts, model-ready `summary_inputs`, and detailed `digest_rows`.
3. Start the report with `## Summary`, then `## Details`.
4. In `## Summary`, write skim-first headlines:
- Lead with the most important fact or judgment. Do not start with aggregate counts unless the aggregate itself is the story.
- Make the first 1-3 bullets answer "what should owners pay attention to right now?"
- Bold only the critical insight phrase in each high-priority bullet, for example `**GPT-5.5 context is the dominant pressure point**`.
- Keep summary bullets short enough to scan in about 20 seconds.
- Put broad stats near the end of the summary, after the owner-relevant takeaways.
- Say clearly when there is nothing significant to act on.
- Call out any areas or themes receiving lots of user attention.
- Cluster and name themes yourself from `summary_inputs`; the collector intentionally does not hard-code issue categories.
- Use a cluster only when the issues genuinely share the same product problem. If several issues merely share a broad platform or label, describe them individually.
- Do not omit a repeated theme just because its individual issues fall below the details table cutoff. Several similar reports should be called out as a repeated customer concern.
- For single-issue rows, summarize the concern directly instead of calling it a cluster.
- Use inline numbered issue links from each relevant row's `ref_markdown`.
5. In `## Details`, include a compact table only when useful:
- Prefer rows from `digest_rows`; include a `Refs` column using each row's `ref_markdown`.
- Keep the table short; omit low-signal rows when the summary already covers them.
- Use compact columns such as marker, area, type, description, interactions, and refs.
- The `Description` cell should be a short owner-readable phrase. Use row `description`, title, body excerpts, and recent comments, but do not mechanically copy the raw GitHub issue title when it contains incidental details.
- A clear quiet/no-concern sentence when there is no meaningful signal.
6. Use the JSON `attention_marker` exactly. It is empty for normal rows, `🔥` for elevated rows, and `🔥🔥` for very high-attention rows. The actual cutoffs are in `attention_thresholds`.
7. Use inline numbered references where a row or bullet points to issues, for example `Compaction bugs [1](https://github.com/openai/codex/issues/123), [2](https://github.com/openai/codex/issues/456)`. Do not add a separate footnotes section.
8. Label `interactions` as `Interactions`; it counts posts/comments/reactions during the requested window, not unique people.
9. Mention the collector `script_version`, repo checkout `git_head`, and time window in the digest footer or final line.
## Reaction Handling
The collector uses GitHub reactions endpoints, which include `created_at`, to count reactions created during the digest window for hydrated issues. It reports both in-window reaction counts and current reaction totals. Treat current reaction totals as standing engagement, and treat `new_reactions` / `new_upvotes` as windowed activity.
By default, the collector fetches issue comments with `since=<window start>` and caps the number of comment pages per issue. This keeps very long historical threads from dominating a digest run and focuses the report on recent posts. Use `--fetch-all-comments` only when exhaustive comment history is more important than runtime.
GitHub issue search is still seeded by issue `updated_at`, so a purely reaction-only issue may be missed if reactions do not bump `updated_at`. Covering every reaction-only case would require either a persisted snapshot store or a broader scan of labeled issues.
## Attention Markers
The collector scales attention markers by the requested time window. The baseline is 10 human user interactions for `🔥` and 20 for `🔥🔥` over 24 hours; longer or shorter windows scale those cutoffs linearly and round up. For example, a one-week report uses 70 and 140 interactions. Human user interactions are human-authored new issue posts, human-authored new comments, and human reactions created during the window, including upvotes. Bot posts and bot reactions are excluded. In prose, explain this as high user interaction rather than naming the emoji.
## Freshness
The automation should run from a repo checkout that contains this skill. For shared daily use, prefer one of these patterns:
- Run the automation in a checkout that is refreshed before the automation starts, for example with `git pull --ff-only`.
- If the automation cannot safely mutate the checkout, have it report the current `git_head` from the collector output so readers know which skill/script version produced the digest.
## Sample Owner Prompt
```text
Use $codex-issue-digest to run the Codex issue digest for labels tui and exec over the previous 24 hours.
```
```text
Use $codex-issue-digest to run the Codex issue digest for all areas over the past week.
```
## Validation
Dry run the collector against recent issues:
```bash
python3 .codex/skills/codex-issue-digest/scripts/collect_issue_digest.py --labels tui exec --window-hours 24
```
```bash
python3 .codex/skills/codex-issue-digest/scripts/collect_issue_digest.py --all-labels --window "past week" --limit-issues 10
```
Run the focused script tests:
```bash
pytest .codex/skills/codex-issue-digest/scripts/test_collect_issue_digest.py
```

View File

@@ -0,0 +1,4 @@
interface:
display_name: "Codex Issue Digest"
short_description: "Summarize Codex issues by labels or all areas"
default_prompt: "Use $codex-issue-digest to run the Codex issue digest for labels tui and exec over the previous 24 hours."

View File

@@ -0,0 +1,988 @@
#!/usr/bin/env python3
"""Collect recent openai/codex issue activity for owner-focused digests."""
import argparse
import json
import math
import re
import subprocess
import sys
from datetime import datetime, timedelta, timezone
from pathlib import Path
from urllib.parse import quote
SCRIPT_VERSION = 2
QUALIFYING_KIND_LABELS = ("bug", "enhancement")
REACTION_KEYS = ("+1", "-1", "laugh", "hooray", "confused", "heart", "rocket", "eyes")
BASE_ATTENTION_WINDOW_HOURS = 24.0
ONE_ATTENTION_INTERACTION_THRESHOLD = 10
TWO_ATTENTION_INTERACTION_THRESHOLD = 20
ALL_LABEL_PHRASES = {"all", "all areas", "all labels", "all-areas", "all-labels", "*"}
class GhCommandError(RuntimeError):
pass
def parse_args():
parser = argparse.ArgumentParser(
description="Collect recent GitHub issue activity for a Codex owner digest."
)
parser.add_argument(
"--repo", default="openai/codex", help="OWNER/REPO, default openai/codex"
)
parser.add_argument(
"--labels",
nargs="+",
default=[],
help="Feature-area labels owned by the digest recipient, for example: tui exec",
)
parser.add_argument(
"--all-labels",
action="store_true",
help="Collect bug/enhancement issues across all feature-area labels",
)
parser.add_argument(
"--window",
help='Lookback duration such as "24h", "7d", "1w", or "past week"',
)
parser.add_argument(
"--window-hours", type=float, default=24.0, help="Lookback window"
)
parser.add_argument(
"--since", help="UTC ISO timestamp override for the window start"
)
parser.add_argument("--until", help="UTC ISO timestamp override for the window end")
parser.add_argument(
"--limit-issues",
type=int,
default=200,
help="Maximum candidate issues to hydrate after search",
)
parser.add_argument(
"--body-chars", type=int, default=1200, help="Issue body excerpt length"
)
parser.add_argument(
"--comment-chars", type=int, default=900, help="Comment excerpt length"
)
parser.add_argument(
"--max-comment-pages",
type=int,
default=3,
help=(
"Maximum pages of issue comments to hydrate per issue after applying the "
"window filter. Use 0 with --fetch-all-comments for no page cap."
),
)
parser.add_argument(
"--fetch-all-comments",
action="store_true",
help="Hydrate complete issue comment histories instead of only window-updated comments.",
)
return parser.parse_args()
def parse_timestamp(value, arg_name):
if value is None:
return None
normalized = value.strip()
if not normalized:
return None
if normalized.endswith("Z"):
normalized = f"{normalized[:-1]}+00:00"
try:
parsed = datetime.fromisoformat(normalized)
except ValueError as err:
raise ValueError(f"{arg_name} must be an ISO timestamp") from err
if parsed.tzinfo is None:
parsed = parsed.replace(tzinfo=timezone.utc)
return parsed.astimezone(timezone.utc)
def format_timestamp(value):
return (
value.astimezone(timezone.utc)
.replace(microsecond=0)
.isoformat()
.replace("+00:00", "Z")
)
def resolve_window(args):
until = parse_timestamp(args.until, "--until") or datetime.now(timezone.utc)
since = parse_timestamp(args.since, "--since")
if since is None:
hours = parse_duration_hours(getattr(args, "window", None))
if hours is None:
hours = getattr(args, "window_hours", 24.0)
if hours <= 0:
raise ValueError("window duration must be > 0")
since = until - timedelta(hours=hours)
if since >= until:
raise ValueError("--since must be before --until")
return since, until
def parse_duration_hours(value):
if value is None:
return None
text = value.strip().casefold().replace("_", " ")
if not text:
return None
text = re.sub(r"^(past|last)\s+", "", text)
aliases = {
"day": 24.0,
"24h": 24.0,
"week": 168.0,
"7d": 168.0,
}
if text in aliases:
return aliases[text]
match = re.fullmatch(r"(\d+(?:\.\d+)?)\s*(h|hr|hrs|hour|hours)", text)
if match:
return float(match.group(1))
match = re.fullmatch(r"(\d+(?:\.\d+)?)\s*(d|day|days)", text)
if match:
return float(match.group(1)) * 24.0
match = re.fullmatch(r"(\d+(?:\.\d+)?)\s*(w|week|weeks)", text)
if match:
return float(match.group(1)) * 168.0
raise ValueError(f"Unsupported duration: {value}")
def normalize_requested_labels(labels, all_labels=False):
out = []
seen = set()
for raw in labels:
for piece in raw.split(","):
label = piece.strip()
if not label:
continue
key = label.casefold()
if key not in seen:
out.append(label)
seen.add(key)
phrase = " ".join(label.casefold() for label in out)
if all_labels or phrase in ALL_LABEL_PHRASES:
return [], True
if not out:
raise ValueError(
"At least one feature-area label is required, or use --all-labels"
)
return out, False
def quote_label(label):
if re.fullmatch(r"[A-Za-z0-9_.:-]+", label):
return f"label:{label}"
escaped = label.replace('"', '\\"')
return f'label:"{escaped}"'
def build_search_queries(
repo, owner_labels, since, kind_labels=QUALIFYING_KIND_LABELS, all_labels=False
):
since_date = since.date().isoformat()
queries = []
if all_labels:
for kind_label in kind_labels:
queries.append(
" ".join(
[
f"repo:{repo}",
"is:issue",
f"updated:>={since_date}",
quote_label(kind_label),
]
)
)
return queries
for owner_label in owner_labels:
for kind_label in kind_labels:
queries.append(
" ".join(
[
f"repo:{repo}",
"is:issue",
f"updated:>={since_date}",
quote_label(owner_label),
quote_label(kind_label),
]
)
)
return queries
def _format_gh_error(cmd, err):
stdout = (err.stdout or "").strip()
stderr = (err.stderr or "").strip()
parts = [f"GitHub CLI command failed: {' '.join(cmd)}"]
if stdout:
parts.append(f"stdout: {stdout}")
if stderr:
parts.append(f"stderr: {stderr}")
return "\n".join(parts)
def gh_json(args):
cmd = ["gh", *args]
try:
proc = subprocess.run(cmd, check=True, capture_output=True, text=True)
except FileNotFoundError as err:
raise GhCommandError("`gh` command not found") from err
except subprocess.CalledProcessError as err:
raise GhCommandError(_format_gh_error(cmd, err)) from err
raw = proc.stdout.strip()
if not raw:
return None
try:
return json.loads(raw)
except json.JSONDecodeError as err:
raise GhCommandError(
f"Failed to parse JSON from gh output for {' '.join(args)}"
) from err
def gh_text(args):
cmd = ["gh", *args]
try:
proc = subprocess.run(cmd, check=True, capture_output=True, text=True)
except (FileNotFoundError, subprocess.CalledProcessError):
return ""
return proc.stdout.strip()
def git_head():
try:
proc = subprocess.run(
["git", "rev-parse", "--short=12", "HEAD"],
check=True,
capture_output=True,
text=True,
)
except (FileNotFoundError, subprocess.CalledProcessError):
return None
return proc.stdout.strip() or None
def skill_relative_path():
try:
return str(Path(__file__).resolve().relative_to(Path.cwd().resolve()))
except ValueError:
return str(Path(__file__).resolve())
def gh_api_list_paginated(endpoint, per_page=100, max_pages=None, with_metadata=False):
items = []
page = 1
truncated = False
while True:
sep = "&" if "?" in endpoint else "?"
page_endpoint = f"{endpoint}{sep}per_page={per_page}&page={page}"
payload = gh_json(["api", page_endpoint])
if payload is None:
break
if not isinstance(payload, list):
raise GhCommandError(f"Unexpected paginated payload from gh api {endpoint}")
items.extend(payload)
if len(payload) < per_page:
break
if max_pages is not None and page >= max_pages:
truncated = True
break
page += 1
if with_metadata:
return {
"items": items,
"truncated": truncated,
"pages": page,
"max_pages": max_pages,
}
return items
def search_issue_numbers(queries, limit):
numbers = {}
for query in queries:
page = 1
while True:
payload = gh_json(
[
"api",
"search/issues",
"-X",
"GET",
"-f",
f"q={query}",
"-f",
"per_page=100",
"-f",
f"page={page}",
]
)
if not isinstance(payload, dict):
raise GhCommandError("Unexpected payload from GitHub issue search")
items = payload.get("items") or []
if not isinstance(items, list):
raise GhCommandError("Expected search `items` to be a list")
for item in items:
if not isinstance(item, dict):
continue
number = item.get("number")
if isinstance(number, int):
numbers[number] = str(item.get("updated_at") or "")
if len(items) < 100 or len(numbers) >= limit:
break
page += 1
ordered = sorted(
numbers, key=lambda number: (numbers[number], number), reverse=True
)
return ordered[:limit]
def fetch_issue(repo, number):
payload = gh_json(["api", f"repos/{repo}/issues/{number}"])
if not isinstance(payload, dict):
raise GhCommandError(f"Unexpected issue payload for #{number}")
return payload
def fetch_comments(repo, number, since=None, max_pages=None):
endpoint = f"repos/{repo}/issues/{number}/comments"
if since is not None:
endpoint = f"{endpoint}?since={quote(format_timestamp(since), safe='')}"
return gh_api_list_paginated(
endpoint,
max_pages=max_pages,
with_metadata=True,
)
def fetch_reactions_for_item(endpoint, item):
if reaction_summary(item)["total"] <= 0:
return []
return gh_api_list_paginated(endpoint)
def fetch_comment_reactions(repo, comments):
reactions_by_comment_id = {}
for comment in comments:
comment_id = comment.get("id")
if comment_id in (None, ""):
continue
endpoint = f"repos/{repo}/issues/comments/{comment_id}/reactions"
reactions_by_comment_id[comment_id] = fetch_reactions_for_item(
endpoint, comment
)
return reactions_by_comment_id
def extract_login(user_obj):
if isinstance(user_obj, dict):
return str(user_obj.get("login") or "")
return ""
def is_bot_login(login):
return bool(login) and login.lower().endswith("[bot]")
def is_human_user(user_obj):
login = extract_login(user_obj)
return bool(login) and not is_bot_login(login)
def label_names(issue):
labels = []
for label in issue.get("labels") or []:
if isinstance(label, dict) and label.get("name"):
labels.append(str(label["name"]))
return sorted(labels, key=str.casefold)
def matching_labels(labels, requested):
labels_by_key = {label.casefold(): label for label in labels}
return [label for label in requested if label.casefold() in labels_by_key]
def area_labels(labels):
kind_keys = {label.casefold() for label in QUALIFYING_KIND_LABELS}
return [label for label in labels if label.casefold() not in kind_keys]
def attention_thresholds_for_window(window_hours):
if window_hours <= 0:
raise ValueError("window_hours must be > 0")
window_hours = round(window_hours, 6)
scale = window_hours / BASE_ATTENTION_WINDOW_HOURS
elevated = max(1, math.ceil(ONE_ATTENTION_INTERACTION_THRESHOLD * scale))
very_high = max(
elevated + 1, math.ceil(TWO_ATTENTION_INTERACTION_THRESHOLD * scale)
)
return {
"base_window_hours": BASE_ATTENTION_WINDOW_HOURS,
"window_hours": round(window_hours, 3),
"scale": round(scale, 3),
"elevated": elevated,
"very_high": very_high,
}
def attention_level_for(user_interactions, attention_thresholds=None):
thresholds = attention_thresholds or attention_thresholds_for_window(
BASE_ATTENTION_WINDOW_HOURS
)
if user_interactions >= thresholds["very_high"]:
return 2
if user_interactions >= thresholds["elevated"]:
return 1
return 0
def attention_marker_for(user_interactions, attention_thresholds=None):
return "🔥" * attention_level_for(user_interactions, attention_thresholds)
def reaction_summary(item):
reactions = item.get("reactions")
if not isinstance(reactions, dict):
return {"total": 0, "counts": {}}
counts = {}
for key in REACTION_KEYS:
value = reactions.get(key, 0)
if isinstance(value, int) and value:
counts[key] = value
total = reactions.get("total_count")
if not isinstance(total, int):
total = sum(counts.values())
return {"total": total, "counts": counts}
def reaction_event_summary(reactions, since, until):
counts = {}
total = 0
for reaction in reactions or []:
if not isinstance(reaction, dict):
continue
if not is_in_window(str(reaction.get("created_at") or ""), since, until):
continue
if not is_human_user(reaction.get("user")):
continue
content = str(reaction.get("content") or "")
if not content:
continue
counts[content] = counts.get(content, 0) + 1
total += 1
return {
"total": total,
"counts": counts,
"upvotes": counts.get("+1", 0),
}
def compact_text(value, limit):
text = re.sub(r"\s+", " ", str(value or "")).strip()
if limit <= 0:
return ""
if len(text) <= limit:
return text
return f"{text[: max(limit - 1, 0)].rstrip()}..."
def clean_title_for_description(title):
cleaned = re.sub(r"\s+", " ", str(title or "")).strip()
cleaned = re.sub(
r"^(codex(?: desktop| app|\.app| cli)?|desktop|windows codex app)\s*[:,-]\s*",
"",
cleaned,
flags=re.IGNORECASE,
)
cleaned = re.sub(r"^on windows,\s*", "Windows: ", cleaned, flags=re.IGNORECASE)
cleaned = cleaned.strip(" -:;")
return compact_text(cleaned, 80) or "Issue needs owner review"
def issue_description(issue):
return clean_title_for_description(issue.get("title"))
def is_in_window(timestamp, since, until):
parsed = parse_timestamp(timestamp, "timestamp")
if parsed is None:
return False
return since <= parsed < until
def summarize_comment(
comment, comment_chars, reaction_events=None, since=None, until=None
):
reactions = reaction_summary(comment)
new_reactions = (
reaction_event_summary(reaction_events, since, until)
if since is not None and until is not None
else {"total": 0, "counts": {}, "upvotes": 0}
)
human_user_interaction = is_human_user(comment.get("user"))
return {
"id": comment.get("id"),
"author": extract_login(comment.get("user")),
"author_association": str(comment.get("author_association") or ""),
"created_at": str(comment.get("created_at") or ""),
"updated_at": str(comment.get("updated_at") or ""),
"url": str(comment.get("html_url") or ""),
"human_user_interaction": human_user_interaction,
"reactions": reactions["counts"],
"reaction_total": reactions["total"],
"new_reactions": new_reactions["total"],
"new_upvotes": new_reactions["upvotes"],
"new_reaction_counts": new_reactions["counts"],
"body_excerpt": compact_text(comment.get("body"), comment_chars),
}
def summarize_issue(
issue,
comments,
requested_labels,
since,
until,
body_chars,
comment_chars,
issue_reaction_events=None,
comment_reactions_by_id=None,
all_labels=False,
comments_hydration=None,
attention_thresholds=None,
):
labels = label_names(issue)
labels_by_key = {label.casefold() for label in labels}
kind_labels = [
label for label in QUALIFYING_KIND_LABELS if label.casefold() in labels_by_key
]
if all_labels:
owner_labels = area_labels(labels) or ["unlabeled"]
else:
owner_labels = matching_labels(labels, requested_labels)
if not kind_labels or not owner_labels:
return None
updated_at = str(issue.get("updated_at") or "")
if not is_in_window(updated_at, since, until):
return None
new_issue = is_in_window(str(issue.get("created_at") or ""), since, until)
comment_reactions_by_id = comment_reactions_by_id or {}
new_comments = [
summarize_comment(
comment,
comment_chars,
reaction_events=comment_reactions_by_id.get(comment.get("id")),
since=since,
until=until,
)
for comment in comments
if is_in_window(str(comment.get("created_at") or ""), since, until)
]
new_comments.sort(key=lambda item: (item["created_at"], str(item["id"])))
issue_reactions = reaction_summary(issue)
issue_reaction_events_summary = reaction_event_summary(
issue_reaction_events, since, until
)
comment_reaction_events_summary = reaction_event_summary(
[
reaction
for reactions in comment_reactions_by_id.values()
for reaction in reactions
],
since,
until,
)
new_reactions = (
issue_reaction_events_summary["total"]
+ comment_reaction_events_summary["total"]
)
new_upvotes = (
issue_reaction_events_summary["upvotes"]
+ comment_reaction_events_summary["upvotes"]
)
all_comment_reaction_total = sum(
reaction_summary(comment)["total"] for comment in comments
)
new_comment_reaction_total = sum(
comment["reaction_total"] for comment in new_comments
)
new_issue_user_interaction = new_issue and is_human_user(issue.get("user"))
new_comment_user_interactions = sum(
1 for comment in new_comments if comment["human_user_interaction"]
)
user_interactions = (
int(new_issue_user_interaction) + new_comment_user_interactions + new_reactions
)
attention_level = attention_level_for(user_interactions, attention_thresholds)
attention_marker = attention_marker_for(user_interactions, attention_thresholds)
updated_without_visible_new_post = (
not new_issue and not new_comments and new_reactions == 0
)
engagement_score = (
len(new_comments) * 3
+ new_reactions
+ issue_reactions["total"]
+ new_comment_reaction_total
+ min(int(issue.get("comments") or len(comments) or 0), 10)
)
return {
"number": issue.get("number"),
"title": str(issue.get("title") or ""),
"description": issue_description(issue),
"url": str(issue.get("html_url") or ""),
"state": str(issue.get("state") or ""),
"author": extract_login(issue.get("user")),
"author_association": str(issue.get("author_association") or ""),
"created_at": str(issue.get("created_at") or ""),
"updated_at": updated_at,
"labels": labels,
"kind_labels": kind_labels,
"owner_labels": owner_labels,
"comments_total": int(issue.get("comments") or len(comments) or 0),
"comments_hydration": comments_hydration
or {
"fetched": len(comments),
"since": None,
"truncated": False,
"max_pages": None,
},
"issue_reactions": issue_reactions["counts"],
"issue_reaction_total": issue_reactions["total"],
"comment_reaction_total": all_comment_reaction_total,
"new_comment_reaction_total": new_comment_reaction_total,
"new_issue_reactions": issue_reaction_events_summary["total"],
"new_issue_upvotes": issue_reaction_events_summary["upvotes"],
"new_comment_reactions": comment_reaction_events_summary["total"],
"new_comment_upvotes": comment_reaction_events_summary["upvotes"],
"new_reactions": new_reactions,
"new_upvotes": new_upvotes,
"user_interactions": user_interactions,
"attention": attention_level > 0,
"attention_level": attention_level,
"attention_marker": attention_marker,
"engagement_score": engagement_score,
"activity": {
"new_issue": new_issue,
"new_comments": len(new_comments),
"new_human_comments": new_comment_user_interactions,
"new_reactions": new_reactions,
"new_upvotes": new_upvotes,
"updated_without_visible_new_post": updated_without_visible_new_post,
},
"body_excerpt": compact_text(issue.get("body"), body_chars),
"new_comments": new_comments,
}
def count_by_label(issues, labels):
out = {}
for label in labels:
matching = [issue for issue in issues if label in issue["owner_labels"]]
out[label] = {
"issues": len(matching),
"new_issues": sum(
1 for issue in matching if issue["activity"]["new_issue"]
),
"new_comments": sum(
issue["activity"]["new_comments"] for issue in matching
),
}
return out
def count_by_kind(issues):
out = {}
for kind in QUALIFYING_KIND_LABELS:
matching = [issue for issue in issues if kind in issue["kind_labels"]]
out[kind] = {
"issues": len(matching),
"new_issues": sum(
1 for issue in matching if issue["activity"]["new_issue"]
),
"new_comments": sum(
issue["activity"]["new_comments"] for issue in matching
),
}
return out
def hot_items(issues, limit=8):
ranked = sorted(
issues,
key=lambda issue: (
issue["attention"],
issue["attention_level"],
issue["user_interactions"],
issue["engagement_score"],
issue["activity"]["new_comments"],
issue["issue_reaction_total"] + issue["comment_reaction_total"],
issue["updated_at"],
),
reverse=True,
)
return [
{
"number": issue["number"],
"title": issue["title"],
"url": issue["url"],
"owner_labels": issue["owner_labels"],
"kind_labels": issue["kind_labels"],
"attention": issue["attention"],
"attention_level": issue["attention_level"],
"attention_marker": issue["attention_marker"],
"user_interactions": issue["user_interactions"],
"new_reactions": issue["new_reactions"],
"new_upvotes": issue["new_upvotes"],
"engagement_score": issue["engagement_score"],
"new_comments": issue["activity"]["new_comments"],
"reaction_total": issue["issue_reaction_total"]
+ issue["comment_reaction_total"],
}
for issue in ranked[:limit]
if issue["engagement_score"] > 0
]
def ranked_digest_issues(issues):
return sorted(
issues,
key=lambda issue: (
issue["attention"],
issue["attention_level"],
issue["user_interactions"],
issue["engagement_score"],
issue["activity"]["new_comments"],
issue["updated_at"],
),
reverse=True,
)
def digest_rows(issues, limit=10, ref_map=None):
ranked = ranked_digest_issues(issues)
if ref_map is None:
ref_map = {issue["number"]: ref for ref, issue in enumerate(ranked, start=1)}
rows = []
for issue in ranked[:limit]:
ref = ref_map[issue["number"]]
reaction_total = issue["issue_reaction_total"] + issue["comment_reaction_total"]
rows.append(
{
"ref": ref,
"ref_markdown": f"[{ref}]({issue['url']})",
"marker": issue["attention_marker"],
"attention_marker": issue["attention_marker"],
"number": issue["number"],
"description": issue["description"],
"title": issue["title"],
"url": issue["url"],
"area": ", ".join(issue["owner_labels"]),
"kind": ", ".join(issue["kind_labels"]),
"state": issue["state"],
"interactions": issue["user_interactions"],
"user_interactions": issue["user_interactions"],
"new_reactions": issue["new_reactions"],
"new_upvotes": issue["new_upvotes"],
"current_reactions": reaction_total,
}
)
return rows
def issue_ref_markdown(issue, ref_map):
ref = ref_map[issue["number"]]
return f"[{ref}]({issue['url']})"
def summary_inputs(issues, limit=80, ref_map=None):
ranked = ranked_digest_issues(issues)
if ref_map is None:
ref_map = {issue["number"]: ref for ref, issue in enumerate(ranked, start=1)}
rows = []
for issue in ranked[:limit]:
rows.append(
{
"ref": ref_map[issue["number"]],
"ref_markdown": issue_ref_markdown(issue, ref_map),
"number": issue["number"],
"title": issue["title"],
"description": issue["description"],
"url": issue["url"],
"labels": issue["labels"],
"owner_labels": issue["owner_labels"],
"kind_labels": issue["kind_labels"],
"state": issue.get("state", ""),
"attention_marker": issue.get("attention_marker", ""),
"interactions": issue["user_interactions"],
"new_comments": issue["activity"].get("new_comments", 0),
"new_reactions": issue.get("new_reactions", 0),
"new_upvotes": issue.get("new_upvotes", 0),
"current_reactions": issue.get("issue_reaction_total", 0)
+ issue.get("comment_reaction_total", 0),
}
)
return rows
def collect_digest(args):
since, until = resolve_window(args)
window_hours = (until - since).total_seconds() / 3600
attention_thresholds = attention_thresholds_for_window(window_hours)
requested_labels, all_labels = normalize_requested_labels(
args.labels, all_labels=args.all_labels
)
queries = build_search_queries(
args.repo, requested_labels, since, all_labels=all_labels
)
numbers = search_issue_numbers(queries, args.limit_issues)
gh_version_output = gh_text(["--version"])
issues = []
max_comment_pages = None if args.max_comment_pages <= 0 else args.max_comment_pages
for number in numbers:
issue = fetch_issue(args.repo, number)
comments_since = None if args.fetch_all_comments else since
comments_payload = fetch_comments(
args.repo,
number,
since=comments_since,
max_pages=max_comment_pages,
)
comments = comments_payload["items"]
issue_reaction_events = fetch_reactions_for_item(
f"repos/{args.repo}/issues/{number}/reactions", issue
)
comment_reactions_by_id = fetch_comment_reactions(args.repo, comments)
comments_hydration = {
"fetched": len(comments),
"total": int(issue.get("comments") or len(comments) or 0),
"since": format_timestamp(comments_since) if comments_since else None,
"truncated": comments_payload["truncated"],
"max_pages": comments_payload["max_pages"],
"fetch_all_comments": args.fetch_all_comments,
}
summary = summarize_issue(
issue,
comments,
requested_labels,
since,
until,
args.body_chars,
args.comment_chars,
issue_reaction_events=issue_reaction_events,
comment_reactions_by_id=comment_reactions_by_id,
all_labels=all_labels,
comments_hydration=comments_hydration,
attention_thresholds=attention_thresholds,
)
if summary is not None:
issues.append(summary)
issues.sort(
key=lambda issue: (issue["updated_at"], int(issue["number"] or 0)), reverse=True
)
totals = {
"candidate_issues": len(numbers),
"included_issues": len(issues),
"new_issues": sum(1 for issue in issues if issue["activity"]["new_issue"]),
"issues_with_new_comments": sum(
1 for issue in issues if issue["activity"]["new_comments"] > 0
),
"new_comments": sum(issue["activity"]["new_comments"] for issue in issues),
"comments_fetched": sum(
issue["comments_hydration"]["fetched"] for issue in issues
),
"issues_with_truncated_comment_hydration": sum(
1 for issue in issues if issue["comments_hydration"]["truncated"]
),
"updated_without_visible_new_post": sum(
1
for issue in issues
if issue["activity"]["updated_without_visible_new_post"]
),
"issue_reactions_current_total": sum(
issue["issue_reaction_total"] for issue in issues
),
"comment_reactions_current_total": sum(
issue["comment_reaction_total"] for issue in issues
),
"new_reactions": sum(issue["new_reactions"] for issue in issues),
"new_upvotes": sum(issue["new_upvotes"] for issue in issues),
"user_interactions": sum(issue["user_interactions"] for issue in issues),
}
ranked = ranked_digest_issues(issues)
ref_map = {issue["number"]: ref for ref, issue in enumerate(ranked, start=1)}
filter_label = "all" if all_labels else requested_labels
return {
"generated_at": format_timestamp(datetime.now(timezone.utc)),
"source": {
"repo": args.repo,
"skill": "codex-issue-digest",
"collector": skill_relative_path(),
"script_version": SCRIPT_VERSION,
"git_head": git_head(),
"gh_version": gh_version_output.splitlines()[0]
if gh_version_output
else None,
},
"window": {
"since": format_timestamp(since),
"until": format_timestamp(until),
"hours": round(window_hours, 3),
},
"attention_thresholds": attention_thresholds,
"filters": {
"owner_labels": filter_label,
"all_labels": all_labels,
"kind_labels": list(QUALIFYING_KIND_LABELS),
},
"collection_notes": [
"Issues are selected when they currently have bug or enhancement plus at least one requested owner label and were updated during the window.",
"By default, issue comments are fetched with since=window_start and a max page cap to avoid long historical threads; use --fetch-all-comments when exhaustive comment history is needed.",
"New issue comments are filtered by comment creation time within the window from the fetched comment set.",
"Reaction events are counted by GitHub reaction created_at timestamps for hydrated issues and fetched comments.",
"Current reaction totals are standing engagement signals; new_reactions and new_upvotes are windowed activity.",
"The collector does not assign semantic clusters; use summary_inputs as model-ready evidence for report-time clustering.",
"Pure reaction-only issues may be missed if GitHub issue search does not surface them via updated_at.",
"Issues updated during the window without a new issue body or new comment are retained because label/status edits can still be useful owner signals.",
],
"totals": totals,
"by_owner_label": count_by_label(
issues,
sorted(
{area for issue in issues for area in issue["owner_labels"]},
key=str.casefold,
)
if all_labels
else requested_labels,
),
"by_kind_label": count_by_kind(issues),
"hot_items": hot_items(issues),
"summary_inputs": summary_inputs(issues, ref_map=ref_map),
"digest_rows": digest_rows(issues, ref_map=ref_map),
"issues": issues,
}
def main():
args = parse_args()
try:
digest = collect_digest(args)
except (GhCommandError, RuntimeError, ValueError) as err:
sys.stderr.write(f"collect_issue_digest.py error: {err}\n")
return 1
sys.stdout.write(json.dumps(digest, indent=2, sort_keys=True) + "\n")
return 0
if __name__ == "__main__":
raise SystemExit(main())

View File

@@ -0,0 +1,614 @@
import importlib.util
from datetime import timezone
from pathlib import Path
MODULE_PATH = Path(__file__).with_name("collect_issue_digest.py")
MODULE_SPEC = importlib.util.spec_from_file_location(
"collect_issue_digest", MODULE_PATH
)
collect_issue_digest = importlib.util.module_from_spec(MODULE_SPEC)
assert MODULE_SPEC.loader is not None
MODULE_SPEC.loader.exec_module(collect_issue_digest)
def test_build_search_queries_uses_each_owner_and_kind_label():
since = collect_issue_digest.parse_timestamp("2026-04-25T12:34:56Z", "--since")
queries = collect_issue_digest.build_search_queries(
"openai/codex", ["tui", "exec"], since
)
assert queries == [
"repo:openai/codex is:issue updated:>=2026-04-25 label:tui label:bug",
"repo:openai/codex is:issue updated:>=2026-04-25 label:tui label:enhancement",
"repo:openai/codex is:issue updated:>=2026-04-25 label:exec label:bug",
"repo:openai/codex is:issue updated:>=2026-04-25 label:exec label:enhancement",
]
def test_build_search_queries_can_scan_all_labels():
since = collect_issue_digest.parse_timestamp("2026-04-25T12:34:56Z", "--since")
queries = collect_issue_digest.build_search_queries(
"openai/codex", [], since, all_labels=True
)
assert queries == [
"repo:openai/codex is:issue updated:>=2026-04-25 label:bug",
"repo:openai/codex is:issue updated:>=2026-04-25 label:enhancement",
]
def test_normalize_requested_labels_accepts_all_area_phrases():
assert collect_issue_digest.normalize_requested_labels(["all", "areas"]) == (
[],
True,
)
assert collect_issue_digest.normalize_requested_labels(["all-labels"]) == (
[],
True,
)
def test_summarize_issue_keeps_new_comments_and_reaction_signals():
since = collect_issue_digest.parse_timestamp("2026-04-25T00:00:00Z", "--since")
until = collect_issue_digest.parse_timestamp("2026-04-26T00:00:00Z", "--until")
issue = {
"number": 123,
"title": "TUI does not redraw",
"html_url": "https://github.com/openai/codex/issues/123",
"state": "open",
"created_at": "2026-04-24T20:00:00Z",
"updated_at": "2026-04-25T10:00:00Z",
"user": {"login": "alice"},
"author_association": "NONE",
"comments": 2,
"body": "The terminal freezes after resize.",
"labels": [{"name": "bug"}, {"name": "tui"}],
"reactions": {"total_count": 3, "+1": 2, "rocket": 1},
}
comments = [
{
"id": 1,
"created_at": "2026-04-25T11:00:00Z",
"updated_at": "2026-04-25T11:00:00Z",
"html_url": "https://github.com/openai/codex/issues/123#issuecomment-1",
"user": {"login": "bob"},
"author_association": "MEMBER",
"body": "I can reproduce this on main.",
"reactions": {"total_count": 4, "heart": 1, "+1": 3},
},
{
"id": 2,
"created_at": "2026-04-24T11:00:00Z",
"updated_at": "2026-04-24T11:00:00Z",
"html_url": "https://github.com/openai/codex/issues/123#issuecomment-2",
"user": {"login": "carol"},
"author_association": "NONE",
"body": "Older comment.",
"reactions": {"total_count": 1, "eyes": 1},
},
]
summary = collect_issue_digest.summarize_issue(
issue,
comments,
["tui", "exec"],
since,
until,
body_chars=200,
comment_chars=200,
)
assert summary == {
"number": 123,
"title": "TUI does not redraw",
"description": "TUI does not redraw",
"url": "https://github.com/openai/codex/issues/123",
"state": "open",
"author": "alice",
"author_association": "NONE",
"created_at": "2026-04-24T20:00:00Z",
"updated_at": "2026-04-25T10:00:00Z",
"labels": ["bug", "tui"],
"kind_labels": ["bug"],
"owner_labels": ["tui"],
"comments_total": 2,
"comments_hydration": {
"fetched": 2,
"since": None,
"truncated": False,
"max_pages": None,
},
"issue_reactions": {"+1": 2, "rocket": 1},
"issue_reaction_total": 3,
"comment_reaction_total": 5,
"new_comment_reaction_total": 4,
"new_issue_reactions": 0,
"new_issue_upvotes": 0,
"new_comment_reactions": 0,
"new_comment_upvotes": 0,
"new_reactions": 0,
"new_upvotes": 0,
"user_interactions": 1,
"attention": False,
"attention_level": 0,
"attention_marker": "",
"engagement_score": 12,
"activity": {
"new_issue": False,
"new_comments": 1,
"new_human_comments": 1,
"new_reactions": 0,
"new_upvotes": 0,
"updated_without_visible_new_post": False,
},
"body_excerpt": "The terminal freezes after resize.",
"new_comments": [
{
"id": 1,
"author": "bob",
"author_association": "MEMBER",
"created_at": "2026-04-25T11:00:00Z",
"updated_at": "2026-04-25T11:00:00Z",
"url": "https://github.com/openai/codex/issues/123#issuecomment-1",
"human_user_interaction": True,
"reactions": {"+1": 3, "heart": 1},
"reaction_total": 4,
"new_reactions": 0,
"new_upvotes": 0,
"new_reaction_counts": {},
"body_excerpt": "I can reproduce this on main.",
}
],
}
def test_summarize_issue_filters_non_owner_or_non_kind_labels():
since = collect_issue_digest.parse_timestamp("2026-04-25T00:00:00Z", "--since")
until = collect_issue_digest.parse_timestamp("2026-04-26T00:00:00Z", "--until")
base_issue = {
"number": 1,
"title": "Question",
"created_at": "2026-04-25T01:00:00Z",
"updated_at": "2026-04-25T01:00:00Z",
"labels": [{"name": "question"}, {"name": "tui"}],
}
assert (
collect_issue_digest.summarize_issue(
base_issue,
[],
["tui"],
since,
until,
body_chars=100,
comment_chars=100,
)
is None
)
issue_without_owner = dict(base_issue)
issue_without_owner["labels"] = [{"name": "bug"}, {"name": "app"}]
assert (
collect_issue_digest.summarize_issue(
issue_without_owner,
[],
["tui"],
since,
until,
body_chars=100,
comment_chars=100,
)
is None
)
def test_resolve_window_defaults_to_previous_hours():
class Args:
since = None
until = "2026-04-26T12:00:00Z"
window_hours = 24
since, until = collect_issue_digest.resolve_window(Args())
assert since.isoformat() == "2026-04-25T12:00:00+00:00"
assert until.tzinfo == timezone.utc
def test_parse_duration_hours_accepts_common_phrases():
assert collect_issue_digest.parse_duration_hours("past week") == 168
assert collect_issue_digest.parse_duration_hours("48h") == 48
assert collect_issue_digest.parse_duration_hours("2 days") == 48
assert collect_issue_digest.parse_duration_hours("1w") == 168
def test_attention_thresholds_scale_by_window_length():
one_day = collect_issue_digest.attention_thresholds_for_window(24)
assert one_day["elevated"] == 10
assert one_day["very_high"] == 20
half_day = collect_issue_digest.attention_thresholds_for_window(12)
assert half_day["elevated"] == 5
assert half_day["very_high"] == 10
week = collect_issue_digest.attention_thresholds_for_window(168)
assert week["elevated"] == 70
assert week["very_high"] == 140
assert collect_issue_digest.attention_marker_for(69, week) == ""
assert collect_issue_digest.attention_marker_for(107, week) == "🔥"
assert collect_issue_digest.attention_marker_for(140, week) == "🔥🔥"
def test_fetch_comments_uses_since_filter_and_page_cap(monkeypatch):
calls = []
def fake_gh_json(args):
calls.append(args)
return [{"id": idx} for idx in range(100)]
monkeypatch.setattr(collect_issue_digest, "gh_json", fake_gh_json)
since = collect_issue_digest.parse_timestamp("2026-04-25T00:00:00Z", "--since")
payload = collect_issue_digest.fetch_comments(
"openai/codex", 123, since=since, max_pages=1
)
assert len(payload["items"]) == 100
assert payload["truncated"] is True
assert payload["max_pages"] == 1
assert calls == [
[
"api",
"repos/openai/codex/issues/123/comments?since=2026-04-25T00%3A00%3A00Z&per_page=100&page=1",
]
]
def test_issue_description_prefers_title_over_body_noise():
issue = {
"title": "Codex.app GUI: MCP child processes not reaped after task completion",
"body": "A later crash mention should not override the title-level symptom.",
"labels": [{"name": "app"}, {"name": "bug"}],
}
description = collect_issue_digest.issue_description(issue)
assert "MCP child processes" in description
assert "crash" not in description.casefold()
def test_attention_markers_count_human_user_interactions():
since = collect_issue_digest.parse_timestamp("2026-04-25T00:00:00Z", "--since")
until = collect_issue_digest.parse_timestamp("2026-04-26T00:00:00Z", "--until")
issue = {
"number": 456,
"title": "Agent context is exploding",
"html_url": "https://github.com/openai/codex/issues/456",
"state": "open",
"created_at": "2026-04-25T01:00:00Z",
"updated_at": "2026-04-25T12:00:00Z",
"user": {"login": "alice"},
"labels": [{"name": "bug"}, {"name": "agent"}],
}
comments = [
{
"id": idx,
"created_at": "2026-04-25T02:00:00Z",
"updated_at": "2026-04-25T02:00:00Z",
"user": {"login": f"user-{idx}"},
"body": "same here",
}
for idx in range(9)
]
comments.append(
{
"id": 99,
"created_at": "2026-04-25T02:00:00Z",
"updated_at": "2026-04-25T02:00:00Z",
"user": {"login": "github-actions[bot]"},
"body": "duplicate bot note",
}
)
summary = collect_issue_digest.summarize_issue(
issue,
comments,
["agent"],
since,
until,
body_chars=100,
comment_chars=100,
)
assert summary["user_interactions"] == 10
assert summary["activity"]["new_human_comments"] == 9
assert summary["attention"] is True
assert summary["attention_level"] == 1
assert summary["attention_marker"] == "🔥"
issue["created_at"] = "2026-04-24T01:00:00Z"
comments.extend(
{
"id": idx,
"created_at": "2026-04-25T03:00:00Z",
"updated_at": "2026-04-25T03:00:00Z",
"user": {"login": f"extra-user-{idx}"},
"body": "also seeing this",
}
for idx in range(11)
)
summary = collect_issue_digest.summarize_issue(
issue,
comments,
["agent"],
since,
until,
body_chars=100,
comment_chars=100,
)
assert summary["user_interactions"] == 20
assert summary["attention_level"] == 2
assert summary["attention_marker"] == "🔥🔥"
def test_reactions_count_toward_attention_markers():
since = collect_issue_digest.parse_timestamp("2026-04-25T00:00:00Z", "--since")
until = collect_issue_digest.parse_timestamp("2026-04-26T00:00:00Z", "--until")
issue = {
"number": 789,
"title": "Support 1M token context",
"html_url": "https://github.com/openai/codex/issues/789",
"state": "open",
"created_at": "2026-04-24T01:00:00Z",
"updated_at": "2026-04-25T12:00:00Z",
"user": {"login": "alice"},
"labels": [{"name": "enhancement"}, {"name": "context"}],
"reactions": {"total_count": 20, "+1": 20},
}
comments = [
{
"id": 1,
"created_at": "2026-04-25T02:00:00Z",
"updated_at": "2026-04-25T02:00:00Z",
"user": {"login": "commenter"},
"body": "please",
"reactions": {"total_count": 2, "+1": 2},
}
]
issue_reactions = [
{
"content": "+1",
"created_at": "2026-04-25T03:00:00Z",
"user": {"login": f"reactor-{idx}"},
}
for idx in range(18)
]
comment_reactions_by_id = {
1: [
{
"content": "heart",
"created_at": "2026-04-25T04:00:00Z",
"user": {"login": "human-reactor"},
},
{
"content": "+1",
"created_at": "2026-04-25T04:00:00Z",
"user": {"login": "github-actions[bot]"},
},
]
}
summary = collect_issue_digest.summarize_issue(
issue,
comments,
["context"],
since,
until,
body_chars=100,
comment_chars=100,
issue_reaction_events=issue_reactions,
comment_reactions_by_id=comment_reactions_by_id,
)
assert summary["new_reactions"] == 19
assert summary["new_upvotes"] == 18
assert summary["user_interactions"] == 20
assert summary["attention_level"] == 2
assert summary["attention_marker"] == "🔥🔥"
assert summary["new_comments"][0]["new_reactions"] == 1
assert summary["new_comments"][0]["new_upvotes"] == 0
def test_digest_rows_are_table_ready_with_concise_descriptions():
rows = collect_issue_digest.digest_rows(
[
{
"number": 1,
"title": "Quiet bug",
"description": "Quiet bug",
"url": "https://github.com/openai/codex/issues/1",
"owner_labels": ["context"],
"kind_labels": ["bug"],
"state": "open",
"attention": False,
"attention_level": 0,
"attention_marker": "",
"user_interactions": 1,
"new_reactions": 0,
"new_upvotes": 0,
"engagement_score": 3,
"issue_reaction_total": 0,
"comment_reaction_total": 0,
"updated_at": "2026-04-25T01:00:00Z",
"activity": {
"new_issue": True,
"new_comments": 0,
"new_reactions": 0,
"updated_without_visible_new_post": False,
},
},
{
"number": 2,
"title": "Busy bug",
"description": "High-volume bug report",
"url": "https://github.com/openai/codex/issues/2",
"owner_labels": ["agent"],
"kind_labels": ["bug"],
"state": "open",
"attention": True,
"attention_level": 1,
"attention_marker": "🔥",
"user_interactions": 17,
"new_reactions": 3,
"new_upvotes": 2,
"engagement_score": 20,
"issue_reaction_total": 5,
"comment_reaction_total": 2,
"updated_at": "2026-04-25T02:00:00Z",
"activity": {
"new_issue": False,
"new_comments": 16,
"new_reactions": 3,
"updated_without_visible_new_post": False,
},
},
]
)
assert rows[0] == {
"ref": 1,
"ref_markdown": "[1](https://github.com/openai/codex/issues/2)",
"marker": "🔥",
"attention_marker": "🔥",
"number": 2,
"description": "High-volume bug report",
"title": "Busy bug",
"url": "https://github.com/openai/codex/issues/2",
"area": "agent",
"kind": "bug",
"state": "open",
"interactions": 17,
"user_interactions": 17,
"new_reactions": 3,
"new_upvotes": 2,
"current_reactions": 7,
}
def test_summary_inputs_are_model_ready_without_preclustering():
issues = [
{
"number": 20,
"title": "Windows app Browser Use external navigation fails",
"description": "Browser Use navigation or app-server failure",
"url": "https://github.com/openai/codex/issues/20",
"labels": ["app", "bug"],
"owner_labels": ["app"],
"kind_labels": ["bug"],
"attention": False,
"attention_level": 0,
"attention_marker": "",
"user_interactions": 3,
"new_reactions": 1,
"engagement_score": 8,
"updated_at": "2026-04-25T04:00:00Z",
"activity": {"new_comments": 2},
},
{
"number": 21,
"title": "On Windows, cmake output waits until timeout",
"description": "Windows command timeout/capture problem",
"url": "https://github.com/openai/codex/issues/21",
"labels": ["app", "bug"],
"owner_labels": ["app"],
"kind_labels": ["bug"],
"attention": False,
"attention_level": 0,
"attention_marker": "",
"user_interactions": 3,
"new_reactions": 0,
"engagement_score": 7,
"updated_at": "2026-04-25T03:00:00Z",
"activity": {"new_comments": 3},
},
{
"number": 22,
"title": "Windows computer use tool fails to click buttons",
"description": "Computer-use workflow failure",
"url": "https://github.com/openai/codex/issues/22",
"labels": ["app", "bug"],
"owner_labels": ["app"],
"kind_labels": ["bug"],
"attention": False,
"attention_level": 0,
"attention_marker": "",
"user_interactions": 3,
"new_reactions": 0,
"engagement_score": 6,
"updated_at": "2026-04-25T02:00:00Z",
"activity": {"new_comments": 3},
},
]
rows = collect_issue_digest.summary_inputs(issues, ref_map={20: 1, 21: 2, 22: 3})
assert rows == [
{
"ref": 1,
"ref_markdown": "[1](https://github.com/openai/codex/issues/20)",
"number": 20,
"title": "Windows app Browser Use external navigation fails",
"description": "Browser Use navigation or app-server failure",
"url": "https://github.com/openai/codex/issues/20",
"labels": ["app", "bug"],
"owner_labels": ["app"],
"kind_labels": ["bug"],
"state": "",
"attention_marker": "",
"interactions": 3,
"new_comments": 2,
"new_reactions": 1,
"new_upvotes": 0,
"current_reactions": 0,
},
{
"ref": 2,
"ref_markdown": "[2](https://github.com/openai/codex/issues/21)",
"number": 21,
"title": "On Windows, cmake output waits until timeout",
"description": "Windows command timeout/capture problem",
"url": "https://github.com/openai/codex/issues/21",
"labels": ["app", "bug"],
"owner_labels": ["app"],
"kind_labels": ["bug"],
"state": "",
"attention_marker": "",
"interactions": 3,
"new_comments": 3,
"new_reactions": 0,
"new_upvotes": 0,
"current_reactions": 0,
},
{
"ref": 3,
"ref_markdown": "[3](https://github.com/openai/codex/issues/22)",
"number": 22,
"title": "Windows computer use tool fails to click buttons",
"description": "Computer-use workflow failure",
"url": "https://github.com/openai/codex/issues/22",
"labels": ["app", "bug"],
"owner_labels": ["app"],
"kind_labels": ["bug"],
"state": "",
"attention_marker": "",
"interactions": 3,
"new_comments": 3,
"new_reactions": 0,
"new_upvotes": 0,
"current_reactions": 0,
},
]

View File

@@ -8,7 +8,7 @@ inputs:
description: Logical namespace used to keep concurrent Bazel jobs from reserving the same repository cache key.
required: true
install-test-prereqs:
description: Install Node.js and DotSlash for Bazel-backed test jobs.
description: Install DotSlash for Bazel-backed test jobs.
required: false
default: "false"
outputs:

View File

@@ -5,7 +5,7 @@ inputs:
description: Target triple used for cache namespacing.
required: true
install-test-prereqs:
description: Install Node.js and DotSlash for Bazel-backed test jobs.
description: Install DotSlash for Bazel-backed test jobs.
required: false
default: "false"
outputs:
@@ -16,12 +16,6 @@ outputs:
runs:
using: composite
steps:
- name: Set up Node.js for js_repl tests
if: inputs.install-test-prereqs == 'true'
uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6
with:
node-version-file: codex-rs/node-version.txt
# Some integration tests rely on DotSlash being installed.
# See https://github.com/openai/codex/pull/7617.
- name: Install DotSlash
@@ -39,7 +33,7 @@ runs:
run: Copy-Item (Get-Command dotslash).Source -Destination "$env:LOCALAPPDATA\Microsoft\WindowsApps\dotslash.exe"
- name: Set up Bazel
uses: bazelbuild/setup-bazelisk@b39c379c82683a5f25d34f0d062761f62693e0b2 # v3
uses: bazel-contrib/setup-bazel@c5acdfb288317d0b5c0bbd7a396a3dc868bb0f86 # 0.19.0
- name: Configure Bazel repository cache
id: configure_bazel_repository_cache

View File

@@ -1,6 +1,6 @@
# External (non-OpenAI) Pull Request Requirements
Before opening this Pull Request, please read the dedicated "Contributing" markdown file or your PR may be closed:
External code contributions are by invitation only. Please read the dedicated "Contributing" markdown file for details:
https://github.com/openai/codex/blob/main/docs/contributing.md
If your PR conforms to our contribution guidelines, replace this text with a detailed and high quality description of your changes.

View File

@@ -4,7 +4,6 @@ set -euo pipefail
print_failed_bazel_test_logs=0
print_failed_bazel_action_summary=0
use_node_test_env=0
remote_download_toplevel=0
windows_msvc_host_platform=0
@@ -18,10 +17,6 @@ while [[ $# -gt 0 ]]; do
print_failed_bazel_action_summary=1
shift
;;
--use-node-test-env)
use_node_test_env=1
shift
;;
--remote-download-toplevel)
remote_download_toplevel=1
shift
@@ -42,7 +37,7 @@ while [[ $# -gt 0 ]]; do
done
if [[ $# -eq 0 ]]; then
echo "Usage: $0 [--print-failed-test-logs] [--print-failed-action-summary] [--use-node-test-env] [--remote-download-toplevel] [--windows-msvc-host-platform] -- <bazel args> -- <targets>" >&2
echo "Usage: $0 [--print-failed-test-logs] [--print-failed-action-summary] [--remote-download-toplevel] [--windows-msvc-host-platform] -- <bazel args> -- <targets>" >&2
exit 1
fi
@@ -249,16 +244,6 @@ if [[ ${#bazel_args[@]} -eq 0 || ${#bazel_targets[@]} -eq 0 ]]; then
exit 1
fi
if [[ $use_node_test_env -eq 1 ]]; then
# Bazel test sandboxes on macOS may resolve an older Homebrew `node`
# before the `actions/setup-node` runtime on PATH.
node_bin="$(which node)"
if [[ "${RUNNER_OS:-}" == "Windows" ]]; then
node_bin="$(cygpath -w "${node_bin}")"
fi
bazel_args+=("--test_env=CODEX_JS_REPL_NODE_PATH=${node_bin}")
fi
post_config_bazel_args=()
if [[ "${RUNNER_OS:-}" == "Windows" && $windows_msvc_host_platform -eq 1 ]]; then
has_host_platform_override=0

View File

@@ -8,25 +8,9 @@ FROM ubuntu:24.04
RUN apt-get update && \
apt-get install -y --no-install-recommends \
curl git python3 ca-certificates xz-utils && \
curl git python3 ca-certificates && \
rm -rf /var/lib/apt/lists/*
COPY codex-rs/node-version.txt /tmp/node-version.txt
RUN set -eux; \
node_arch="$(dpkg --print-architecture)"; \
case "${node_arch}" in \
amd64) node_dist_arch="x64" ;; \
arm64) node_dist_arch="arm64" ;; \
*) echo "unsupported architecture: ${node_arch}"; exit 1 ;; \
esac; \
node_version="$(tr -d '[:space:]' </tmp/node-version.txt)"; \
curl -fsSLO "https://nodejs.org/dist/v${node_version}/node-v${node_version}-linux-${node_dist_arch}.tar.xz"; \
tar -xJf "node-v${node_version}-linux-${node_dist_arch}.tar.xz" -C /usr/local --strip-components=1; \
rm "node-v${node_version}-linux-${node_dist_arch}.tar.xz" /tmp/node-version.txt; \
node --version; \
npm --version
# Install dotslash.
RUN curl -LSfs "https://github.com/facebook/dotslash/releases/download/v0.5.8/dotslash-ubuntu-22.04.$(uname -m).tar.gz" | tar fxz - -C /usr/local/bin

View File

@@ -17,6 +17,13 @@ concurrency:
cancel-in-progress: ${{ github.ref_name != 'main' }}
jobs:
test:
# Even though a no-cache-hit Windows build seems to exceed the 30-minute
# limit on occasion, the more common reason for exceeding the limit is a
# true test failure in a rust_test() marked "flaky" that gets run 3x.
# In that case, extra time generally does not give us more signal.
#
# Ultimately we need true distributed builds (e.g.,
# https://www.buildbuddy.io/docs/rbe-setup/) to speed things up.
timeout-minutes: 30
strategy:
fail-fast: false
@@ -85,7 +92,6 @@ jobs:
bazel_wrapper_args=(
--print-failed-test-logs
--use-node-test-env
)
bazel_test_args=(
test

View File

@@ -45,11 +45,16 @@ jobs:
GH_TOKEN: ${{ github.token }}
run: |
set -euo pipefail
# Use a rust-release version that includes all native binaries.
CODEX_VERSION=0.115.0
# Use a recent successful rust-release run that published the full
# cross-platform native payload required by the npm package layout.
# Passing the workflow URL directly avoids relying on old rust-v*
# branches remaining discoverable via `gh run list --branch ...`.
CODEX_VERSION=0.125.0
WORKFLOW_URL="https://github.com/openai/codex/actions/runs/24901475298"
OUTPUT_DIR="${RUNNER_TEMP}"
python3 ./scripts/stage_npm_packages.py \
--release-version "$CODEX_VERSION" \
--workflow-url "$WORKFLOW_URL" \
--package codex \
--output-dir "$OUTPUT_DIR"
PACK_OUTPUT="${OUTPUT_DIR}/codex-npm-${CODEX_VERSION}.tgz"

View File

@@ -61,7 +61,7 @@ jobs:
# .github/prompts/issue-deduplicator.txt file is obsolete and removed.
- id: codex-all
name: Find duplicates (pass 1, all issues)
uses: openai/codex-action@0b91f4a2703c23df3102c3f0967d3c6db34eedef # v1
uses: openai/codex-action@5c3f4ccdb2b8790f73d6b21751ac00e602aa0c02 # v1.7
with:
openai-api-key: ${{ secrets.CODEX_OPENAI_API_KEY }}
allow-users: "*"
@@ -195,7 +195,7 @@ jobs:
- id: codex-open
name: Find duplicates (pass 2, open issues)
uses: openai/codex-action@0b91f4a2703c23df3102c3f0967d3c6db34eedef # v1
uses: openai/codex-action@5c3f4ccdb2b8790f73d6b21751ac00e602aa0c02 # v1.7
with:
openai-api-key: ${{ secrets.CODEX_OPENAI_API_KEY }}
allow-users: "*"

View File

@@ -20,7 +20,7 @@ jobs:
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
- id: codex
uses: openai/codex-action@0b91f4a2703c23df3102c3f0967d3c6db34eedef # v1
uses: openai/codex-action@5c3f4ccdb2b8790f73d6b21751ac00e602aa0c02 # v1.7
with:
openai-api-key: ${{ secrets.CODEX_OPENAI_API_KEY }}
allow-users: "*"

View File

@@ -560,10 +560,6 @@ jobs:
steps:
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
- name: Set up Node.js for js_repl tests
uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6
with:
node-version-file: codex-rs/node-version.txt
- name: Install Linux build dependencies
if: ${{ runner.os == 'Linux' }}
shell: bash

View File

@@ -651,11 +651,59 @@ jobs:
prefix="${NPM_TAG}-"
fi
root_tarball="dist/npm/codex-npm-${VERSION}.tgz"
sdk_tarball="dist/npm/codex-sdk-npm-${VERSION}.tgz"
# Keep this list in sync with CODEX_PLATFORM_PACKAGES in
# codex-cli/scripts/build_npm_package.py. The root wrapper advances
# @openai/codex@latest as soon as it publishes, so every platform
# package it aliases must already exist in the registry first.
platform_tarballs=(
"dist/npm/codex-npm-linux-x64-${VERSION}.tgz"
"dist/npm/codex-npm-linux-arm64-${VERSION}.tgz"
"dist/npm/codex-npm-darwin-x64-${VERSION}.tgz"
"dist/npm/codex-npm-darwin-arm64-${VERSION}.tgz"
"dist/npm/codex-npm-win32-x64-${VERSION}.tgz"
"dist/npm/codex-npm-win32-arm64-${VERSION}.tgz"
)
for required_tarball in "${platform_tarballs[@]}" "${root_tarball}"; do
if [[ ! -f "${required_tarball}" ]]; then
echo "Missing npm tarball: ${required_tarball}"
exit 1
fi
done
shopt -s nullglob
tarballs=(dist/npm/*-"${VERSION}".tgz)
if [[ ${#tarballs[@]} -eq 0 ]]; then
echo "No npm tarballs found in dist/npm for version ${VERSION}"
exit 1
other_tarballs=()
for tarball in dist/npm/*-"${VERSION}".tgz; do
if [[ "${tarball}" == "${root_tarball}" || "${tarball}" == "${sdk_tarball}" ]]; then
continue
fi
is_platform_tarball=false
for platform_tarball in "${platform_tarballs[@]}"; do
if [[ "${tarball}" == "${platform_tarball}" ]]; then
is_platform_tarball=true
break
fi
done
if [[ "${is_platform_tarball}" == true ]]; then
continue
fi
other_tarballs+=("${tarball}")
done
# Publish the platform packages before the root CLI wrapper. The root
# wrapper advances @openai/codex@latest, so it should only publish
# after the optional dependency versions it references exist.
tarballs=(
"${platform_tarballs[@]}"
"${other_tarballs[@]}"
"${root_tarball}"
)
if [[ -f "${sdk_tarball}" ]]; then
tarballs+=("${sdk_tarball}")
fi
for tarball in "${tarballs[@]}"; do

View File

@@ -78,7 +78,9 @@ jobs:
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
- name: Set up Bazel
uses: bazelbuild/setup-bazelisk@b39c379c82683a5f25d34f0d062761f62693e0b2 # v3
uses: ./.github/actions/setup-bazel-ci
with:
target: ${{ matrix.target }}
- name: Set up Python
uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6

View File

@@ -3,6 +3,7 @@ name: v8-canary
on:
pull_request:
paths:
- ".github/actions/setup-bazel-ci/**"
- ".github/scripts/rusty_v8_bazel.py"
- ".github/workflows/rusty-v8-release.yml"
- ".github/workflows/v8-canary.yml"
@@ -16,6 +17,7 @@ on:
branches:
- main
paths:
- ".github/actions/setup-bazel-ci/**"
- ".github/scripts/rusty_v8_bazel.py"
- ".github/workflows/rusty-v8-release.yml"
- ".github/workflows/v8-canary.yml"
@@ -75,7 +77,9 @@ jobs:
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
- name: Set up Bazel
uses: bazelbuild/setup-bazelisk@b39c379c82683a5f25d34f0d062761f62693e0b2 # v3
uses: ./.github/actions/setup-bazel-ci
with:
target: ${{ matrix.target }}
- name: Set up Python
uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6

1
MODULE.bazel.lock generated
View File

@@ -1560,6 +1560,7 @@
"system-deps_7.0.7": "{\"dependencies\":[{\"kind\":\"dev\",\"name\":\"assert_matches\",\"req\":\"^1.5\"},{\"features\":[\"targets\"],\"name\":\"cfg-expr\",\"req\":\">=0.17, <0.21\"},{\"name\":\"heck\",\"req\":\"^0.5\"},{\"kind\":\"dev\",\"name\":\"itertools\",\"req\":\"^0.14\"},{\"kind\":\"dev\",\"name\":\"lazy_static\",\"req\":\"^1\"},{\"name\":\"pkg-config\",\"req\":\"^0.3.25\"},{\"default_features\":false,\"features\":[\"parse\",\"std\"],\"name\":\"toml\",\"req\":\"^0.9\"},{\"name\":\"version-compare\",\"req\":\"^0.2\"}],\"features\":{}}",
"tagptr_0.2.0": "{\"dependencies\":[],\"features\":{}}",
"tar_0.4.44": "{\"dependencies\":[{\"name\":\"filetime\",\"req\":\"^0.2.8\"},{\"name\":\"libc\",\"req\":\"^0.2\",\"target\":\"cfg(unix)\"},{\"kind\":\"dev\",\"name\":\"tempfile\",\"req\":\"^3\"},{\"name\":\"xattr\",\"optional\":true,\"req\":\"^1.1.3\",\"target\":\"cfg(unix)\"}],\"features\":{\"default\":[\"xattr\"]}}",
"tar_0.4.45": "{\"dependencies\":[{\"kind\":\"dev\",\"name\":\"astral-tokio-tar\",\"req\":\"^0.5\"},{\"name\":\"filetime\",\"req\":\"^0.2.8\"},{\"name\":\"libc\",\"req\":\"^0.2\",\"target\":\"cfg(unix)\"},{\"features\":[\"small_rng\"],\"kind\":\"dev\",\"name\":\"rand\",\"req\":\"^0.8\"},{\"kind\":\"dev\",\"name\":\"tempfile\",\"req\":\"^3\"},{\"features\":[\"macros\",\"rt\"],\"kind\":\"dev\",\"name\":\"tokio\",\"req\":\"^1\"},{\"kind\":\"dev\",\"name\":\"tokio-stream\",\"req\":\"^0.1\"},{\"name\":\"xattr\",\"optional\":true,\"req\":\"^1.1.3\",\"target\":\"cfg(unix)\"}],\"features\":{\"default\":[\"xattr\"]}}",
"target-lexicon_0.13.3": "{\"dependencies\":[{\"name\":\"serde\",\"optional\":true,\"req\":\"^1.0\"},{\"kind\":\"dev\",\"name\":\"serde_json\",\"req\":\"^1.0\"}],\"features\":{\"arch_z80\":[],\"arch_zkasm\":[],\"default\":[],\"serde_support\":[\"serde\",\"std\"],\"std\":[]}}",
"tempfile_3.27.0": "{\"dependencies\":[{\"kind\":\"dev\",\"name\":\"doc-comment\",\"req\":\"^0.3\"},{\"name\":\"fastrand\",\"req\":\"^2.1.1\"},{\"default_features\":false,\"name\":\"getrandom\",\"optional\":true,\"req\":\">=0.3.0, <0.5\",\"target\":\"cfg(any(unix, windows, target_os = \\\"wasi\\\"))\"},{\"default_features\":false,\"features\":[\"std\"],\"name\":\"once_cell\",\"req\":\"^1.19.0\"},{\"features\":[\"fs\"],\"name\":\"rustix\",\"req\":\"^1.1.4\",\"target\":\"cfg(any(unix, target_os = \\\"wasi\\\"))\"},{\"features\":[\"Win32_Storage_FileSystem\",\"Win32_Foundation\"],\"name\":\"windows-sys\",\"req\":\">=0.52, <0.62\",\"target\":\"cfg(windows)\"}],\"features\":{\"default\":[\"getrandom\"],\"nightly\":[]}}",
"temporal_capi_0.1.2": "{\"dependencies\":[{\"default_features\":false,\"name\":\"diplomat\",\"req\":\"^0.14.0\"},{\"default_features\":false,\"name\":\"diplomat-runtime\",\"req\":\"^0.14.0\"},{\"default_features\":false,\"features\":[\"unstable\"],\"name\":\"icu_calendar\",\"req\":\"^2.1.0\"},{\"name\":\"icu_locale\",\"req\":\"^2.1.0\"},{\"default_features\":false,\"name\":\"num-traits\",\"req\":\"^0.2.19\"},{\"default_features\":false,\"name\":\"temporal_rs\",\"req\":\"^0.1.2\"},{\"name\":\"timezone_provider\",\"req\":\"^0.1.2\"},{\"name\":\"writeable\",\"req\":\"^0.6.0\"},{\"name\":\"zoneinfo64\",\"optional\":true,\"req\":\"^0.2.0\"}],\"features\":{\"compiled_data\":[\"temporal_rs/compiled_data\"],\"zoneinfo64\":[\"dep:zoneinfo64\",\"timezone_provider/zoneinfo64\"]}}",

3
NOTICE
View File

@@ -4,6 +4,3 @@ Copyright 2025 OpenAI
This project includes code derived from [Ratatui](https://github.com/ratatui/ratatui), licensed under the MIT license.
Copyright (c) 2016-2022 Florian Dehau
Copyright (c) 2023-2025 The Ratatui Developers
This project includes Meriyah parser assets from [meriyah](https://github.com/meriyah/meriyah), licensed under the ISC license.
Copyright (c) 2019 and later, KFlash and others.

View File

@@ -1,6 +1,5 @@
exports_files([
"clippy.toml",
"node-version.txt",
])
filegroup(

135
codex-rs/Cargo.lock generated
View File

@@ -1748,26 +1748,6 @@ dependencies = [
"unicode-width 0.2.1",
]
[[package]]
name = "codex-agent-graph-store"
version = "0.0.0"
dependencies = [
"async-trait",
"codex-protocol",
"codex-state",
"pretty_assertions",
"prost 0.14.3",
"serde",
"serde_json",
"tempfile",
"thiserror 2.0.18",
"tokio",
"tokio-stream",
"tonic",
"tonic-prost",
"tonic-prost-build",
]
[[package]]
name = "codex-agent-identity"
version = "0.0.0"
@@ -1778,6 +1758,7 @@ dependencies = [
"codex-protocol",
"crypto_box",
"ed25519-dalek",
"jsonwebtoken",
"pretty_assertions",
"rand 0.9.3",
"reqwest",
@@ -1872,12 +1853,14 @@ dependencies = [
"codex-core-plugins",
"codex-device-key",
"codex-exec-server",
"codex-external-agent-sessions",
"codex-features",
"codex-feedback",
"codex-file-search",
"codex-git-utils",
"codex-login",
"codex-mcp",
"codex-memories-write",
"codex-model-provider",
"codex-model-provider-info",
"codex-models-manager",
@@ -1899,6 +1882,7 @@ dependencies = [
"codex-utils-rustls-provider",
"constant_time_eq 0.3.1",
"core_test_support",
"flate2",
"futures",
"gethostname",
"hmac",
@@ -1914,6 +1898,7 @@ dependencies = [
"serial_test",
"sha2",
"shlex",
"tar",
"tempfile",
"thiserror 2.0.18",
"time",
@@ -2119,7 +2104,6 @@ dependencies = [
"assert_matches",
"clap",
"clap_complete",
"codex-api",
"codex-app-server",
"codex-app-server-protocol",
"codex-app-server-test-client",
@@ -2136,7 +2120,7 @@ dependencies = [
"codex-login",
"codex-mcp",
"codex-mcp-server",
"codex-model-provider",
"codex-memories-write",
"codex-models-manager",
"codex-protocol",
"codex-responses-api-proxy",
@@ -2307,15 +2291,20 @@ version = "0.0.0"
dependencies = [
"anyhow",
"async-trait",
"base64 0.22.1",
"codex-app-server-protocol",
"codex-execpolicy",
"codex-features",
"codex-file-system",
"codex-git-utils",
"codex-model-provider-info",
"codex-network-proxy",
"codex-protocol",
"codex-utils-absolute-path",
"codex-utils-path",
"core-foundation 0.9.4",
"dns-lookup",
"dunce",
"futures",
"gethostname",
"libc",
@@ -2339,6 +2328,7 @@ dependencies = [
"tracing",
"wildmatch",
"winapi-util",
"windows-sys 0.52.0",
]
[[package]]
@@ -2385,6 +2375,7 @@ dependencies = [
"codex-hooks",
"codex-login",
"codex-mcp",
"codex-memories-read",
"codex-model-provider",
"codex-model-provider-info",
"codex-models-manager",
@@ -2397,7 +2388,6 @@ dependencies = [
"codex-rollout",
"codex-rollout-trace",
"codex-sandboxing",
"codex-secrets",
"codex-shell-command",
"codex-shell-escalation",
"codex-state",
@@ -2419,7 +2409,6 @@ dependencies = [
"codex-utils-string",
"codex-utils-template",
"codex-windows-sandbox",
"core-foundation 0.9.4",
"core_test_support",
"csv",
"ctor 0.6.3",
@@ -2470,7 +2459,6 @@ dependencies = [
"walkdir",
"which 8.0.0",
"whoami",
"windows-sys 0.52.0",
"wiremock",
"zstd 0.13.3",
]
@@ -2494,11 +2482,13 @@ dependencies = [
"codex-utils-absolute-path",
"codex-utils-plugins",
"dirs",
"flate2",
"libc",
"pretty_assertions",
"reqwest",
"serde",
"serde_json",
"tar",
"tempfile",
"thiserror 2.0.18",
"tokio",
@@ -2580,6 +2570,7 @@ dependencies = [
"codex-apply-patch",
"codex-arg0",
"codex-cloud-requirements",
"codex-config",
"codex-core",
"codex-feedback",
"codex-git-utils",
@@ -2623,7 +2614,7 @@ dependencies = [
"bytes",
"codex-app-server-protocol",
"codex-client",
"codex-config",
"codex-file-system",
"codex-protocol",
"codex-sandboxing",
"codex-test-binary-support",
@@ -2692,6 +2683,20 @@ dependencies = [
"syn 2.0.114",
]
[[package]]
name = "codex-external-agent-sessions"
version = "0.0.0"
dependencies = [
"chrono",
"codex-app-server-protocol",
"codex-protocol",
"codex-utils-output-truncation",
"serde",
"serde_json",
"sha2",
"tempfile",
]
[[package]]
name = "codex-features"
version = "0.0.0"
@@ -2734,14 +2739,23 @@ dependencies = [
"tokio",
]
[[package]]
name = "codex-file-system"
version = "0.0.0"
dependencies = [
"async-trait",
"codex-protocol",
"codex-utils-absolute-path",
"serde",
]
[[package]]
name = "codex-git-utils"
version = "0.0.0"
dependencies = [
"anyhow",
"assert_matches",
"chrono",
"codex-exec-server",
"codex-file-system",
"codex-protocol",
"codex-utils-absolute-path",
"futures",
@@ -2801,8 +2815,8 @@ version = "0.0.0"
dependencies = [
"cc",
"clap",
"codex-config",
"codex-core",
"codex-process-hardening",
"codex-protocol",
"codex-sandboxing",
"codex-utils-absolute-path",
@@ -2852,6 +2866,7 @@ dependencies = [
"codex-terminal-detection",
"codex-utils-template",
"core_test_support",
"jsonwebtoken",
"keyring",
"once_cell",
"os_info",
@@ -2890,7 +2905,6 @@ dependencies = [
"codex-plugin",
"codex-protocol",
"codex-rmcp-client",
"codex-utils-absolute-path",
"codex-utils-plugins",
"futures",
"pretty_assertions",
@@ -2940,6 +2954,55 @@ dependencies = [
"wiremock",
]
[[package]]
name = "codex-memories-read"
version = "0.0.0"
dependencies = [
"codex-protocol",
"codex-shell-command",
"codex-utils-absolute-path",
"codex-utils-output-truncation",
"codex-utils-template",
"pretty_assertions",
"tempfile",
"tokio",
]
[[package]]
name = "codex-memories-write"
version = "0.0.0"
dependencies = [
"anyhow",
"chrono",
"codex-backend-client",
"codex-config",
"codex-core",
"codex-features",
"codex-git-utils",
"codex-login",
"codex-models-manager",
"codex-otel",
"codex-protocol",
"codex-rollout",
"codex-rollout-trace",
"codex-secrets",
"codex-state",
"codex-terminal-detection",
"codex-utils-absolute-path",
"codex-utils-output-truncation",
"codex-utils-template",
"core_test_support",
"futures",
"pretty_assertions",
"serde",
"serde_json",
"tempfile",
"tokio",
"tracing",
"uuid",
"wiremock",
]
[[package]]
name = "codex-model-provider"
version = "0.0.0"
@@ -3139,6 +3202,7 @@ dependencies = [
"tracing",
"ts-rs",
"uuid",
"wildmatch",
]
[[package]]
@@ -4031,6 +4095,7 @@ dependencies = [
"assert_cmd",
"base64 0.22.1",
"codex-arg0",
"codex-config",
"codex-core",
"codex-exec-server",
"codex-features",
@@ -12250,6 +12315,16 @@ version = "0.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7b2093cf4c8eb1e67749a6762251bc9cd836b6fc171623bd0a9d324d37af2417"
[[package]]
name = "tar"
version = "0.4.45"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "22692a6476a21fa75fdfc11d452fda482af402c008cdbaf3476414e122040973"
dependencies = [
"filetime",
"libc",
]
[[package]]
name = "target-lexicon"
version = "0.13.3"

View File

@@ -2,7 +2,6 @@
members = [
"aws-auth",
"analytics",
"agent-graph-store",
"agent-identity",
"backend-client",
"ansi-escape",
@@ -37,9 +36,11 @@ members = [
"hooks",
"secrets",
"exec",
"file-system",
"exec-server",
"execpolicy",
"execpolicy-legacy",
"external-agent-sessions",
"keyring-store",
"file-search",
"linux-sandbox",
@@ -47,6 +48,8 @@ members = [
"login",
"codex-mcp",
"mcp-server",
"memories/read",
"memories/write",
"model-provider-info",
"models-manager",
"network-proxy",
@@ -114,7 +117,6 @@ license = "Apache-2.0"
# Internal
app_test_support = { path = "app-server/tests/common" }
codex-analytics = { path = "analytics" }
codex-agent-graph-store = { path = "agent-graph-store" }
codex-agent-identity = { path = "agent-identity" }
codex-ansi-escape = { path = "ansi-escape" }
codex-api = { path = "codex-api" }
@@ -142,8 +144,10 @@ codex-core-plugins = { path = "core-plugins" }
codex-core-skills = { path = "core-skills" }
codex-device-key = { path = "device-key" }
codex-exec = { path = "exec" }
codex-file-system = { path = "file-system" }
codex-exec-server = { path = "exec-server" }
codex-execpolicy = { path = "execpolicy" }
codex-external-agent-sessions = { path = "external-agent-sessions" }
codex-experimental-api-macros = { path = "codex-experimental-api-macros" }
codex-features = { path = "features" }
codex-feedback = { path = "feedback" }
@@ -155,6 +159,8 @@ codex-keyring-store = { path = "keyring-store" }
codex-linux-sandbox = { path = "linux-sandbox" }
codex-lmstudio = { path = "lmstudio" }
codex-login = { path = "login" }
codex-memories-read = { path = "memories/read" }
codex-memories-write = { path = "memories/write" }
codex-mcp = { path = "codex-mcp" }
codex-mcp-server = { path = "mcp-server" }
codex-model-provider-info = { path = "model-provider-info" }
@@ -256,6 +262,7 @@ encoding_rs = "0.8.35"
env-flags = "0.1.1"
env_logger = "0.11.9"
eventsource-stream = "0.2.3"
flate2 = "1.1.8"
futures = { version = "0.3", default-features = false }
gethostname = "1.1.0"
gix = { version = "0.81.0", default-features = false, features = ["sha1"] }
@@ -348,6 +355,7 @@ strum_macros = "0.28.0"
supports-color = "3.0.2"
syntect = "5"
sys-locale = "0.3.2"
tar = { version = "=0.4.45", default-features = false }
tempfile = "3.23.0"
test-log = "0.2.19"
textwrap = "0.16.2"
@@ -439,7 +447,6 @@ unwrap_used = "deny"
# silence the false positive here instead of deleting a real dependency.
[workspace.metadata.cargo-shear]
ignored = [
"codex-agent-graph-store",
"icu_provider",
"openssl-sys",
"codex-utils-readiness",

View File

@@ -94,7 +94,7 @@ In `workspace-write`, Codex also includes `~/.codex/memories` in its writable ro
This folder is the root of a Cargo workspace. It contains quite a bit of experimental code, but here are the key crates:
- [`core/`](./core) contains the business logic for Codex. Ultimately, we hope this to be a library crate that is generally useful for building other Rust/native applications that use Codex.
- [`core/`](./core) contains the business logic for Codex. Ultimately, we hope this becomes a library crate that is generally useful for building other Rust/native applications that use Codex.
- [`exec/`](./exec) "headless" CLI for use in automation.
- [`tui/`](./tui) CLI that launches a fullscreen TUI built with [Ratatui](https://ratatui.rs/).
- [`cli/`](./cli) CLI multitool that provides the aforementioned CLIs via subcommands.

View File

@@ -1,6 +0,0 @@
load("//:defs.bzl", "codex_rust_crate")
codex_rust_crate(
name = "agent-graph-store",
crate_name = "codex_agent_graph_store",
)

View File

@@ -1,35 +0,0 @@
[package]
edition.workspace = true
license.workspace = true
name = "codex-agent-graph-store"
version.workspace = true
[lib]
name = "codex_agent_graph_store"
path = "src/lib.rs"
[[example]]
name = "generate-proto"
path = "examples/generate-proto.rs"
[lints]
workspace = true
[dependencies]
async-trait = { workspace = true }
codex-protocol = { workspace = true }
codex-state = { workspace = true }
prost = "0.14.3"
serde = { workspace = true, features = ["derive"] }
thiserror = { workspace = true }
tonic = { workspace = true }
tonic-prost = { workspace = true }
[dev-dependencies]
pretty_assertions = { workspace = true }
serde_json = { workspace = true }
tempfile = { workspace = true }
tokio = { workspace = true, features = ["macros", "rt-multi-thread"] }
tokio-stream = { workspace = true, features = ["net"] }
tonic = { workspace = true, features = ["router", "transport"] }
tonic-prost-build = { version = "=0.14.3", default-features = false, features = ["transport"] }

View File

@@ -1,19 +0,0 @@
use std::path::PathBuf;
fn main() -> Result<(), Box<dyn std::error::Error>> {
let Some(proto_dir_arg) = std::env::args().nth(1) else {
eprintln!("Usage: generate-proto <proto-dir>");
std::process::exit(1);
};
let proto_dir = PathBuf::from(proto_dir_arg);
let proto_file = proto_dir.join("codex.agent_graph_store.v1.proto");
tonic_prost_build::configure()
.build_client(true)
.build_server(true)
.out_dir(&proto_dir)
.compile_protos(&[proto_file], &[proto_dir])?;
Ok(())
}

View File

@@ -1,38 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
repo_root="$(cd "$script_dir/../../.." && pwd)"
proto_dir="$repo_root/codex-rs/agent-graph-store/src/remote/proto"
generated="$proto_dir/codex.agent_graph_store.v1.rs"
tmpdir="$(mktemp -d)"
cleanup() {
rm -rf "$tmpdir"
}
trap cleanup EXIT
(
cd "$repo_root/codex-rs"
CARGO_TARGET_DIR="$tmpdir/target" cargo run \
-p codex-agent-graph-store \
--example generate-proto \
-- "$proto_dir"
)
if ! sed -n '2p' "$generated" | grep -q 'clippy::trivially_copy_pass_by_ref'; then
{
sed -n '1p' "$generated"
printf '#![allow(clippy::trivially_copy_pass_by_ref)]\n'
sed '1d' "$generated"
} > "$tmpdir/generated.rs"
mv "$tmpdir/generated.rs" "$generated"
fi
rustfmt --edition 2024 "$generated"
awk '
NR == 3 && previous ~ /clippy::trivially_copy_pass_by_ref/ && $0 != "" { print "" }
{ print; previous = $0 }
' "$generated" > "$tmpdir/formatted.rs"
mv "$tmpdir/formatted.rs" "$generated"

View File

@@ -1,20 +0,0 @@
/// Result type returned by agent graph store operations.
pub type AgentGraphStoreResult<T> = Result<T, AgentGraphStoreError>;
/// Error type shared by agent graph store implementations.
#[derive(Debug, thiserror::Error)]
pub enum AgentGraphStoreError {
/// The caller supplied invalid request data.
#[error("invalid agent graph store request: {message}")]
InvalidRequest {
/// User-facing explanation of the invalid request.
message: String,
},
/// Catch-all for implementation failures that do not fit a more specific category.
#[error("agent graph store internal error: {message}")]
Internal {
/// User-facing explanation of the implementation failure.
message: String,
},
}

View File

@@ -1,14 +0,0 @@
//! Storage-neutral parent/child topology for thread-spawned agents.
mod error;
mod local;
mod remote;
mod store;
mod types;
pub use error::AgentGraphStoreError;
pub use error::AgentGraphStoreResult;
pub use local::LocalAgentGraphStore;
pub use remote::RemoteAgentGraphStore;
pub use store::AgentGraphStore;
pub use types::ThreadSpawnEdgeStatus;

View File

@@ -1,325 +0,0 @@
use async_trait::async_trait;
use codex_protocol::ThreadId;
use codex_state::StateRuntime;
use std::sync::Arc;
use crate::AgentGraphStore;
use crate::AgentGraphStoreError;
use crate::AgentGraphStoreResult;
use crate::ThreadSpawnEdgeStatus;
/// SQLite-backed implementation of [`AgentGraphStore`] using an existing state runtime.
#[derive(Clone)]
pub struct LocalAgentGraphStore {
state_db: Arc<StateRuntime>,
}
impl std::fmt::Debug for LocalAgentGraphStore {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
f.debug_struct("LocalAgentGraphStore")
.field("codex_home", &self.state_db.codex_home())
.finish_non_exhaustive()
}
}
impl LocalAgentGraphStore {
/// Create a local graph store from an already-initialized state runtime.
pub fn new(state_db: Arc<StateRuntime>) -> Self {
Self { state_db }
}
}
#[async_trait]
impl AgentGraphStore for LocalAgentGraphStore {
async fn upsert_thread_spawn_edge(
&self,
parent_thread_id: ThreadId,
child_thread_id: ThreadId,
status: ThreadSpawnEdgeStatus,
) -> AgentGraphStoreResult<()> {
self.state_db
.upsert_thread_spawn_edge(parent_thread_id, child_thread_id, to_state_status(status))
.await
.map_err(internal_error)
}
async fn set_thread_spawn_edge_status(
&self,
child_thread_id: ThreadId,
status: ThreadSpawnEdgeStatus,
) -> AgentGraphStoreResult<()> {
self.state_db
.set_thread_spawn_edge_status(child_thread_id, to_state_status(status))
.await
.map_err(internal_error)
}
async fn list_thread_spawn_children(
&self,
parent_thread_id: ThreadId,
status_filter: Option<ThreadSpawnEdgeStatus>,
) -> AgentGraphStoreResult<Vec<ThreadId>> {
if let Some(status) = status_filter {
return self
.state_db
.list_thread_spawn_children_with_status(parent_thread_id, to_state_status(status))
.await
.map_err(internal_error);
}
self.state_db
.list_thread_spawn_children(parent_thread_id)
.await
.map_err(internal_error)
}
async fn list_thread_spawn_descendants(
&self,
root_thread_id: ThreadId,
status_filter: Option<ThreadSpawnEdgeStatus>,
) -> AgentGraphStoreResult<Vec<ThreadId>> {
match status_filter {
Some(status) => self
.state_db
.list_thread_spawn_descendants_with_status(root_thread_id, to_state_status(status))
.await
.map_err(internal_error),
None => self
.state_db
.list_thread_spawn_descendants(root_thread_id)
.await
.map_err(internal_error),
}
}
}
fn to_state_status(status: ThreadSpawnEdgeStatus) -> codex_state::DirectionalThreadSpawnEdgeStatus {
match status {
ThreadSpawnEdgeStatus::Open => codex_state::DirectionalThreadSpawnEdgeStatus::Open,
ThreadSpawnEdgeStatus::Closed => codex_state::DirectionalThreadSpawnEdgeStatus::Closed,
}
}
fn internal_error(err: impl std::fmt::Display) -> AgentGraphStoreError {
AgentGraphStoreError::Internal {
message: err.to_string(),
}
}
#[cfg(test)]
mod tests {
use super::*;
use codex_state::DirectionalThreadSpawnEdgeStatus;
use pretty_assertions::assert_eq;
use tempfile::TempDir;
struct TestRuntime {
state_db: Arc<StateRuntime>,
_codex_home: TempDir,
}
fn thread_id(suffix: u128) -> ThreadId {
ThreadId::from_string(&format!("00000000-0000-0000-0000-{suffix:012}"))
.expect("valid thread id")
}
async fn state_runtime() -> TestRuntime {
let codex_home = TempDir::new().expect("tempdir should be created");
let state_db =
StateRuntime::init(codex_home.path().to_path_buf(), "test-provider".to_string())
.await
.expect("state db should initialize");
TestRuntime {
state_db,
_codex_home: codex_home,
}
}
#[tokio::test]
async fn local_store_upserts_and_lists_direct_children_with_status_filters() {
let fixture = state_runtime().await;
let state_db = fixture.state_db;
let store = LocalAgentGraphStore::new(state_db.clone());
let parent_thread_id = thread_id(/*suffix*/ 1);
let first_child_thread_id = thread_id(/*suffix*/ 2);
let second_child_thread_id = thread_id(/*suffix*/ 3);
store
.upsert_thread_spawn_edge(
parent_thread_id,
second_child_thread_id,
ThreadSpawnEdgeStatus::Closed,
)
.await
.expect("closed child edge should insert");
store
.upsert_thread_spawn_edge(
parent_thread_id,
first_child_thread_id,
ThreadSpawnEdgeStatus::Open,
)
.await
.expect("open child edge should insert");
let all_children = store
.list_thread_spawn_children(parent_thread_id, /*status_filter*/ None)
.await
.expect("all children should load");
assert_eq!(
all_children,
vec![first_child_thread_id, second_child_thread_id]
);
let open_children = store
.list_thread_spawn_children(parent_thread_id, Some(ThreadSpawnEdgeStatus::Open))
.await
.expect("open children should load");
let state_open_children = state_db
.list_thread_spawn_children_with_status(
parent_thread_id,
DirectionalThreadSpawnEdgeStatus::Open,
)
.await
.expect("state open children should load");
assert_eq!(open_children, state_open_children);
assert_eq!(open_children, vec![first_child_thread_id]);
let closed_children = store
.list_thread_spawn_children(parent_thread_id, Some(ThreadSpawnEdgeStatus::Closed))
.await
.expect("closed children should load");
assert_eq!(closed_children, vec![second_child_thread_id]);
}
#[tokio::test]
async fn local_store_updates_edge_status() {
let fixture = state_runtime().await;
let state_db = fixture.state_db;
let store = LocalAgentGraphStore::new(state_db);
let parent_thread_id = thread_id(/*suffix*/ 10);
let child_thread_id = thread_id(/*suffix*/ 11);
store
.upsert_thread_spawn_edge(
parent_thread_id,
child_thread_id,
ThreadSpawnEdgeStatus::Open,
)
.await
.expect("child edge should insert");
store
.set_thread_spawn_edge_status(child_thread_id, ThreadSpawnEdgeStatus::Closed)
.await
.expect("child edge should close");
let open_children = store
.list_thread_spawn_children(parent_thread_id, Some(ThreadSpawnEdgeStatus::Open))
.await
.expect("open children should load");
assert_eq!(open_children, Vec::<ThreadId>::new());
let closed_children = store
.list_thread_spawn_children(parent_thread_id, Some(ThreadSpawnEdgeStatus::Closed))
.await
.expect("closed children should load");
assert_eq!(closed_children, vec![child_thread_id]);
}
#[tokio::test]
async fn local_store_lists_descendants_breadth_first_with_status_filters() {
let fixture = state_runtime().await;
let state_db = fixture.state_db;
let store = LocalAgentGraphStore::new(state_db.clone());
let root_thread_id = thread_id(/*suffix*/ 20);
let later_child_thread_id = thread_id(/*suffix*/ 22);
let earlier_child_thread_id = thread_id(/*suffix*/ 21);
let closed_grandchild_thread_id = thread_id(/*suffix*/ 23);
let open_grandchild_thread_id = thread_id(/*suffix*/ 24);
let closed_child_thread_id = thread_id(/*suffix*/ 25);
let closed_great_grandchild_thread_id = thread_id(/*suffix*/ 26);
for (parent_thread_id, child_thread_id, status) in [
(
root_thread_id,
later_child_thread_id,
ThreadSpawnEdgeStatus::Open,
),
(
root_thread_id,
earlier_child_thread_id,
ThreadSpawnEdgeStatus::Open,
),
(
earlier_child_thread_id,
open_grandchild_thread_id,
ThreadSpawnEdgeStatus::Open,
),
(
later_child_thread_id,
closed_grandchild_thread_id,
ThreadSpawnEdgeStatus::Closed,
),
(
root_thread_id,
closed_child_thread_id,
ThreadSpawnEdgeStatus::Closed,
),
(
closed_child_thread_id,
closed_great_grandchild_thread_id,
ThreadSpawnEdgeStatus::Closed,
),
] {
store
.upsert_thread_spawn_edge(parent_thread_id, child_thread_id, status)
.await
.expect("edge should insert");
}
let all_descendants = store
.list_thread_spawn_descendants(root_thread_id, /*status_filter*/ None)
.await
.expect("all descendants should load");
assert_eq!(
all_descendants,
vec![
earlier_child_thread_id,
later_child_thread_id,
closed_child_thread_id,
closed_grandchild_thread_id,
open_grandchild_thread_id,
closed_great_grandchild_thread_id,
]
);
let open_descendants = store
.list_thread_spawn_descendants(root_thread_id, Some(ThreadSpawnEdgeStatus::Open))
.await
.expect("open descendants should load");
let state_open_descendants = state_db
.list_thread_spawn_descendants_with_status(
root_thread_id,
DirectionalThreadSpawnEdgeStatus::Open,
)
.await
.expect("state open descendants should load");
assert_eq!(open_descendants, state_open_descendants);
assert_eq!(
open_descendants,
vec![
earlier_child_thread_id,
later_child_thread_id,
open_grandchild_thread_id,
]
);
let closed_descendants = store
.list_thread_spawn_descendants(root_thread_id, Some(ThreadSpawnEdgeStatus::Closed))
.await
.expect("closed descendants should load");
assert_eq!(
closed_descendants,
vec![closed_child_thread_id, closed_great_grandchild_thread_id]
);
}
}

View File

@@ -1,13 +0,0 @@
# Remote Agent Graph Store
- The Rust protobuf output in `proto/codex.agent_graph_store.v1.rs` is checked in.
- Do not add build-time protobuf generation to `codex-agent-graph-store` unless the Bazel/Cargo story is intentionally changed.
- When `proto/codex.agent_graph_store.v1.proto` changes, regenerate the Rust file manually and include both files in the same commit.
Run this from the repository root:
```sh
./codex-rs/agent-graph-store/scripts/generate-proto.sh
```
The command requires `protoc` to be available on `PATH`.

View File

@@ -1,42 +0,0 @@
use codex_protocol::ThreadId;
use super::proto;
use crate::AgentGraphStoreError;
use crate::AgentGraphStoreResult;
use crate::ThreadSpawnEdgeStatus;
pub(super) fn proto_status(status: ThreadSpawnEdgeStatus) -> proto::ThreadSpawnEdgeStatus {
match status {
ThreadSpawnEdgeStatus::Open => proto::ThreadSpawnEdgeStatus::Open,
ThreadSpawnEdgeStatus::Closed => proto::ThreadSpawnEdgeStatus::Closed,
}
}
pub(super) fn proto_status_filter(status: Option<ThreadSpawnEdgeStatus>) -> Option<i32> {
status.map(proto_status).map(Into::into)
}
pub(super) fn thread_ids_from_proto(
thread_ids: Vec<String>,
field_name: &str,
) -> AgentGraphStoreResult<Vec<ThreadId>> {
thread_ids
.into_iter()
.map(|thread_id| {
ThreadId::from_string(&thread_id).map_err(|err| AgentGraphStoreError::InvalidRequest {
message: format!("remote agent graph store returned invalid {field_name}: {err}"),
})
})
.collect()
}
pub(super) fn remote_status_to_error(status: tonic::Status) -> AgentGraphStoreError {
match status.code() {
tonic::Code::InvalidArgument => AgentGraphStoreError::InvalidRequest {
message: status.message().to_string(),
},
_ => AgentGraphStoreError::Internal {
message: format!("remote agent graph store request failed: {status}"),
},
}
}

View File

@@ -1,339 +0,0 @@
mod helpers;
use async_trait::async_trait;
use codex_protocol::ThreadId;
use proto::agent_graph_store_client::AgentGraphStoreClient;
use crate::AgentGraphStore;
use crate::AgentGraphStoreError;
use crate::AgentGraphStoreResult;
use crate::ThreadSpawnEdgeStatus;
#[path = "proto/codex.agent_graph_store.v1.rs"]
mod proto;
/// gRPC-backed [`AgentGraphStore`] implementation for deployments whose durable
/// subagent graph lives outside the app-server process.
#[derive(Clone, Debug)]
pub struct RemoteAgentGraphStore {
endpoint: String,
}
impl RemoteAgentGraphStore {
pub fn new(endpoint: impl Into<String>) -> Self {
Self {
endpoint: endpoint.into(),
}
}
async fn client(
&self,
) -> AgentGraphStoreResult<AgentGraphStoreClient<tonic::transport::Channel>> {
AgentGraphStoreClient::connect(self.endpoint.clone())
.await
.map_err(|err| AgentGraphStoreError::Internal {
message: format!("failed to connect to remote agent graph store: {err}"),
})
}
}
#[async_trait]
impl AgentGraphStore for RemoteAgentGraphStore {
async fn upsert_thread_spawn_edge(
&self,
parent_thread_id: ThreadId,
child_thread_id: ThreadId,
status: ThreadSpawnEdgeStatus,
) -> AgentGraphStoreResult<()> {
let request = proto::UpsertThreadSpawnEdgeRequest {
parent_thread_id: parent_thread_id.to_string(),
child_thread_id: child_thread_id.to_string(),
status: helpers::proto_status(status).into(),
};
self.client()
.await?
.upsert_thread_spawn_edge(request)
.await
.map_err(helpers::remote_status_to_error)?;
Ok(())
}
async fn set_thread_spawn_edge_status(
&self,
child_thread_id: ThreadId,
status: ThreadSpawnEdgeStatus,
) -> AgentGraphStoreResult<()> {
let request = proto::SetThreadSpawnEdgeStatusRequest {
child_thread_id: child_thread_id.to_string(),
status: helpers::proto_status(status).into(),
};
self.client()
.await?
.set_thread_spawn_edge_status(request)
.await
.map_err(helpers::remote_status_to_error)?;
Ok(())
}
async fn list_thread_spawn_children(
&self,
parent_thread_id: ThreadId,
status_filter: Option<ThreadSpawnEdgeStatus>,
) -> AgentGraphStoreResult<Vec<ThreadId>> {
let response = self
.client()
.await?
.list_thread_spawn_children(proto::ListThreadSpawnChildrenRequest {
parent_thread_id: parent_thread_id.to_string(),
status_filter: helpers::proto_status_filter(status_filter),
})
.await
.map_err(helpers::remote_status_to_error)?
.into_inner();
helpers::thread_ids_from_proto(response.thread_ids, "child thread_id")
}
async fn list_thread_spawn_descendants(
&self,
root_thread_id: ThreadId,
status_filter: Option<ThreadSpawnEdgeStatus>,
) -> AgentGraphStoreResult<Vec<ThreadId>> {
let response = self
.client()
.await?
.list_thread_spawn_descendants(proto::ListThreadSpawnDescendantsRequest {
root_thread_id: root_thread_id.to_string(),
status_filter: helpers::proto_status_filter(status_filter),
})
.await
.map_err(helpers::remote_status_to_error)?
.into_inner();
helpers::thread_ids_from_proto(response.thread_ids, "descendant thread_id")
}
}
#[cfg(test)]
mod tests {
use super::proto;
use super::proto::agent_graph_store_server;
use super::proto::agent_graph_store_server::AgentGraphStoreServer;
use super::*;
use pretty_assertions::assert_eq;
use tonic::Request;
use tonic::Response;
use tonic::Status;
use tonic::transport::Server;
fn thread_id(suffix: u128) -> ThreadId {
ThreadId::from_string(&format!("00000000-0000-0000-0000-{suffix:012}"))
.expect("valid thread id")
}
async fn serve_test_server(server: TestServer) -> (RemoteAgentGraphStore, ServerShutdown) {
let listener = tokio::net::TcpListener::bind("127.0.0.1:0")
.await
.expect("bind test server");
let addr = listener.local_addr().expect("test server addr");
let (shutdown_tx, shutdown_rx) = tokio::sync::oneshot::channel();
let handle = tokio::spawn(async move {
Server::builder()
.add_service(AgentGraphStoreServer::new(server))
.serve_with_incoming_shutdown(
tokio_stream::wrappers::TcpListenerStream::new(listener),
async {
let _ = shutdown_rx.await;
},
)
.await
});
(
RemoteAgentGraphStore::new(format!("http://{addr}")),
ServerShutdown {
shutdown_tx,
handle,
},
)
}
struct ServerShutdown {
shutdown_tx: tokio::sync::oneshot::Sender<()>,
handle: tokio::task::JoinHandle<Result<(), tonic::transport::Error>>,
}
impl ServerShutdown {
async fn shutdown(self) {
let _ = self.shutdown_tx.send(());
self.handle.await.expect("join server").expect("server");
}
}
#[derive(Clone, Copy, Debug)]
enum TestServer {
HappyPath,
InvalidThreadIdResponse,
InvalidArgumentStatus,
}
#[tonic::async_trait]
impl agent_graph_store_server::AgentGraphStore for TestServer {
async fn upsert_thread_spawn_edge(
&self,
request: Request<proto::UpsertThreadSpawnEdgeRequest>,
) -> Result<Response<proto::Empty>, Status> {
match self {
TestServer::InvalidArgumentStatus => {
Err(Status::invalid_argument("status must be specified"))
}
TestServer::HappyPath | TestServer::InvalidThreadIdResponse => {
let request = request.into_inner();
assert_eq!(
request.parent_thread_id,
"00000000-0000-0000-0000-000000000001"
);
assert_eq!(
request.child_thread_id,
"00000000-0000-0000-0000-000000000002"
);
assert_eq!(
proto::ThreadSpawnEdgeStatus::try_from(request.status),
Ok(proto::ThreadSpawnEdgeStatus::Open)
);
Ok(Response::new(proto::Empty {}))
}
}
}
async fn set_thread_spawn_edge_status(
&self,
request: Request<proto::SetThreadSpawnEdgeStatusRequest>,
) -> Result<Response<proto::Empty>, Status> {
let request = request.into_inner();
assert_eq!(
request.child_thread_id,
"00000000-0000-0000-0000-000000000002"
);
assert_eq!(
proto::ThreadSpawnEdgeStatus::try_from(request.status),
Ok(proto::ThreadSpawnEdgeStatus::Closed)
);
Ok(Response::new(proto::Empty {}))
}
async fn list_thread_spawn_children(
&self,
request: Request<proto::ListThreadSpawnChildrenRequest>,
) -> Result<Response<proto::ListThreadSpawnChildrenResponse>, Status> {
let request = request.into_inner();
assert_eq!(
request.parent_thread_id,
"00000000-0000-0000-0000-000000000001"
);
assert_eq!(
request
.status_filter
.map(proto::ThreadSpawnEdgeStatus::try_from),
Some(Ok(proto::ThreadSpawnEdgeStatus::Open))
);
let thread_ids = match self {
TestServer::InvalidThreadIdResponse => vec!["not-a-thread-id".to_string()],
TestServer::HappyPath | TestServer::InvalidArgumentStatus => {
vec![
"00000000-0000-0000-0000-000000000002".to_string(),
"00000000-0000-0000-0000-000000000003".to_string(),
]
}
};
Ok(Response::new(proto::ListThreadSpawnChildrenResponse {
thread_ids,
}))
}
async fn list_thread_spawn_descendants(
&self,
request: Request<proto::ListThreadSpawnDescendantsRequest>,
) -> Result<Response<proto::ListThreadSpawnDescendantsResponse>, Status> {
let request = request.into_inner();
assert_eq!(
request.root_thread_id,
"00000000-0000-0000-0000-000000000001"
);
assert_eq!(request.status_filter, None);
Ok(Response::new(proto::ListThreadSpawnDescendantsResponse {
thread_ids: vec![
"00000000-0000-0000-0000-000000000002".to_string(),
"00000000-0000-0000-0000-000000000003".to_string(),
"00000000-0000-0000-0000-000000000004".to_string(),
],
}))
}
}
#[tokio::test]
async fn remote_store_calls_agent_graph_service() {
let (store, shutdown) = serve_test_server(TestServer::HappyPath).await;
let parent_thread_id = thread_id(1);
let child_thread_id = thread_id(2);
store
.upsert_thread_spawn_edge(
parent_thread_id,
child_thread_id,
ThreadSpawnEdgeStatus::Open,
)
.await
.expect("upsert should succeed");
store
.set_thread_spawn_edge_status(child_thread_id, ThreadSpawnEdgeStatus::Closed)
.await
.expect("status update should succeed");
let children = store
.list_thread_spawn_children(parent_thread_id, Some(ThreadSpawnEdgeStatus::Open))
.await
.expect("children should load");
assert_eq!(children, vec![thread_id(2), thread_id(3)]);
let descendants = store
.list_thread_spawn_descendants(parent_thread_id, None)
.await
.expect("descendants should load");
assert_eq!(descendants, vec![thread_id(2), thread_id(3), thread_id(4)]);
shutdown.shutdown().await;
}
#[tokio::test]
async fn remote_store_maps_invalid_response_thread_id_to_invalid_request() {
let (store, shutdown) = serve_test_server(TestServer::InvalidThreadIdResponse).await;
let err = store
.list_thread_spawn_children(thread_id(1), Some(ThreadSpawnEdgeStatus::Open))
.await
.expect_err("invalid response thread id should fail");
assert!(matches!(
err,
AgentGraphStoreError::InvalidRequest { message } if message.contains("invalid child thread_id")
));
shutdown.shutdown().await;
}
#[tokio::test]
async fn remote_store_maps_invalid_argument_status_to_invalid_request() {
let (store, shutdown) = serve_test_server(TestServer::InvalidArgumentStatus).await;
let err = store
.upsert_thread_spawn_edge(thread_id(1), thread_id(2), ThreadSpawnEdgeStatus::Open)
.await
.expect_err("invalid argument should fail");
assert!(matches!(
err,
AgentGraphStoreError::InvalidRequest { message } if message == "status must be specified"
));
shutdown.shutdown().await;
}
}

View File

@@ -1,53 +0,0 @@
syntax = "proto3";
package codex.agent_graph_store.v1;
service AgentGraphStore {
rpc UpsertThreadSpawnEdge(UpsertThreadSpawnEdgeRequest) returns (Empty);
rpc SetThreadSpawnEdgeStatus(SetThreadSpawnEdgeStatusRequest) returns (Empty);
rpc ListThreadSpawnChildren(ListThreadSpawnChildrenRequest) returns (ListThreadSpawnChildrenResponse);
rpc ListThreadSpawnDescendants(ListThreadSpawnDescendantsRequest) returns (ListThreadSpawnDescendantsResponse);
}
message Empty {}
message UpsertThreadSpawnEdgeRequest {
string parent_thread_id = 1;
string child_thread_id = 2;
// Servers must reject THREAD_SPAWN_EDGE_STATUS_UNSPECIFIED.
ThreadSpawnEdgeStatus status = 3;
}
message SetThreadSpawnEdgeStatusRequest {
string child_thread_id = 1;
// Servers must reject THREAD_SPAWN_EDGE_STATUS_UNSPECIFIED.
ThreadSpawnEdgeStatus status = 2;
}
message ListThreadSpawnChildrenRequest {
string parent_thread_id = 1;
// Absent means all statuses.
optional ThreadSpawnEdgeStatus status_filter = 2;
}
message ListThreadSpawnChildrenResponse {
// Ordered child thread ids.
repeated string thread_ids = 1;
}
message ListThreadSpawnDescendantsRequest {
string root_thread_id = 1;
// Absent means all statuses.
optional ThreadSpawnEdgeStatus status_filter = 2;
}
message ListThreadSpawnDescendantsResponse {
// Ordered descendant thread ids.
repeated string thread_ids = 1;
}
enum ThreadSpawnEdgeStatus {
THREAD_SPAWN_EDGE_STATUS_UNSPECIFIED = 0;
THREAD_SPAWN_EDGE_STATUS_OPEN = 1;
THREAD_SPAWN_EDGE_STATUS_CLOSED = 2;
}

View File

@@ -1,569 +0,0 @@
// This file is @generated by prost-build.
#![allow(clippy::trivially_copy_pass_by_ref)]
#[derive(Clone, Copy, PartialEq, Eq, Hash, ::prost::Message)]
pub struct Empty {}
#[derive(Clone, PartialEq, Eq, Hash, ::prost::Message)]
pub struct UpsertThreadSpawnEdgeRequest {
#[prost(string, tag = "1")]
pub parent_thread_id: ::prost::alloc::string::String,
#[prost(string, tag = "2")]
pub child_thread_id: ::prost::alloc::string::String,
/// Servers must reject THREAD_SPAWN_EDGE_STATUS_UNSPECIFIED.
#[prost(enumeration = "ThreadSpawnEdgeStatus", tag = "3")]
pub status: i32,
}
#[derive(Clone, PartialEq, Eq, Hash, ::prost::Message)]
pub struct SetThreadSpawnEdgeStatusRequest {
#[prost(string, tag = "1")]
pub child_thread_id: ::prost::alloc::string::String,
/// Servers must reject THREAD_SPAWN_EDGE_STATUS_UNSPECIFIED.
#[prost(enumeration = "ThreadSpawnEdgeStatus", tag = "2")]
pub status: i32,
}
#[derive(Clone, PartialEq, Eq, Hash, ::prost::Message)]
pub struct ListThreadSpawnChildrenRequest {
#[prost(string, tag = "1")]
pub parent_thread_id: ::prost::alloc::string::String,
/// Absent means all statuses.
#[prost(enumeration = "ThreadSpawnEdgeStatus", optional, tag = "2")]
pub status_filter: ::core::option::Option<i32>,
}
#[derive(Clone, PartialEq, Eq, Hash, ::prost::Message)]
pub struct ListThreadSpawnChildrenResponse {
/// Ordered child thread ids.
#[prost(string, repeated, tag = "1")]
pub thread_ids: ::prost::alloc::vec::Vec<::prost::alloc::string::String>,
}
#[derive(Clone, PartialEq, Eq, Hash, ::prost::Message)]
pub struct ListThreadSpawnDescendantsRequest {
#[prost(string, tag = "1")]
pub root_thread_id: ::prost::alloc::string::String,
/// Absent means all statuses.
#[prost(enumeration = "ThreadSpawnEdgeStatus", optional, tag = "2")]
pub status_filter: ::core::option::Option<i32>,
}
#[derive(Clone, PartialEq, Eq, Hash, ::prost::Message)]
pub struct ListThreadSpawnDescendantsResponse {
/// Ordered descendant thread ids.
#[prost(string, repeated, tag = "1")]
pub thread_ids: ::prost::alloc::vec::Vec<::prost::alloc::string::String>,
}
#[derive(Clone, Copy, Debug, PartialEq, Eq, Hash, PartialOrd, Ord, ::prost::Enumeration)]
#[repr(i32)]
pub enum ThreadSpawnEdgeStatus {
Unspecified = 0,
Open = 1,
Closed = 2,
}
impl ThreadSpawnEdgeStatus {
/// String value of the enum field names used in the ProtoBuf definition.
///
/// The values are not transformed in any way and thus are considered stable
/// (if the ProtoBuf definition does not change) and safe for programmatic use.
pub fn as_str_name(&self) -> &'static str {
match self {
Self::Unspecified => "THREAD_SPAWN_EDGE_STATUS_UNSPECIFIED",
Self::Open => "THREAD_SPAWN_EDGE_STATUS_OPEN",
Self::Closed => "THREAD_SPAWN_EDGE_STATUS_CLOSED",
}
}
/// Creates an enum from field names used in the ProtoBuf definition.
pub fn from_str_name(value: &str) -> ::core::option::Option<Self> {
match value {
"THREAD_SPAWN_EDGE_STATUS_UNSPECIFIED" => Some(Self::Unspecified),
"THREAD_SPAWN_EDGE_STATUS_OPEN" => Some(Self::Open),
"THREAD_SPAWN_EDGE_STATUS_CLOSED" => Some(Self::Closed),
_ => None,
}
}
}
/// Generated client implementations.
pub mod agent_graph_store_client {
#![allow(
unused_variables,
dead_code,
missing_docs,
clippy::wildcard_imports,
clippy::let_unit_value
)]
use tonic::codegen::http::Uri;
use tonic::codegen::*;
#[derive(Debug, Clone)]
pub struct AgentGraphStoreClient<T> {
inner: tonic::client::Grpc<T>,
}
impl AgentGraphStoreClient<tonic::transport::Channel> {
/// Attempt to create a new client by connecting to a given endpoint.
pub async fn connect<D>(dst: D) -> Result<Self, tonic::transport::Error>
where
D: TryInto<tonic::transport::Endpoint>,
D::Error: Into<StdError>,
{
let conn = tonic::transport::Endpoint::new(dst)?.connect().await?;
Ok(Self::new(conn))
}
}
impl<T> AgentGraphStoreClient<T>
where
T: tonic::client::GrpcService<tonic::body::Body>,
T::Error: Into<StdError>,
T::ResponseBody: Body<Data = Bytes> + std::marker::Send + 'static,
<T::ResponseBody as Body>::Error: Into<StdError> + std::marker::Send,
{
pub fn new(inner: T) -> Self {
let inner = tonic::client::Grpc::new(inner);
Self { inner }
}
pub fn with_origin(inner: T, origin: Uri) -> Self {
let inner = tonic::client::Grpc::with_origin(inner, origin);
Self { inner }
}
pub fn with_interceptor<F>(
inner: T,
interceptor: F,
) -> AgentGraphStoreClient<InterceptedService<T, F>>
where
F: tonic::service::Interceptor,
T::ResponseBody: Default,
T: tonic::codegen::Service<
http::Request<tonic::body::Body>,
Response = http::Response<
<T as tonic::client::GrpcService<tonic::body::Body>>::ResponseBody,
>,
>,
<T as tonic::codegen::Service<http::Request<tonic::body::Body>>>::Error:
Into<StdError> + std::marker::Send + std::marker::Sync,
{
AgentGraphStoreClient::new(InterceptedService::new(inner, interceptor))
}
/// Compress requests with the given encoding.
///
/// This requires the server to support it otherwise it might respond with an
/// error.
#[must_use]
pub fn send_compressed(mut self, encoding: CompressionEncoding) -> Self {
self.inner = self.inner.send_compressed(encoding);
self
}
/// Enable decompressing responses.
#[must_use]
pub fn accept_compressed(mut self, encoding: CompressionEncoding) -> Self {
self.inner = self.inner.accept_compressed(encoding);
self
}
/// Limits the maximum size of a decoded message.
///
/// Default: `4MB`
#[must_use]
pub fn max_decoding_message_size(mut self, limit: usize) -> Self {
self.inner = self.inner.max_decoding_message_size(limit);
self
}
/// Limits the maximum size of an encoded message.
///
/// Default: `usize::MAX`
#[must_use]
pub fn max_encoding_message_size(mut self, limit: usize) -> Self {
self.inner = self.inner.max_encoding_message_size(limit);
self
}
pub async fn upsert_thread_spawn_edge(
&mut self,
request: impl tonic::IntoRequest<super::UpsertThreadSpawnEdgeRequest>,
) -> std::result::Result<tonic::Response<super::Empty>, tonic::Status> {
self.inner.ready().await.map_err(|e| {
tonic::Status::unknown(format!("Service was not ready: {}", e.into()))
})?;
let codec = tonic_prost::ProstCodec::default();
let path = http::uri::PathAndQuery::from_static(
"/codex.agent_graph_store.v1.AgentGraphStore/UpsertThreadSpawnEdge",
);
let mut req = request.into_request();
req.extensions_mut().insert(GrpcMethod::new(
"codex.agent_graph_store.v1.AgentGraphStore",
"UpsertThreadSpawnEdge",
));
self.inner.unary(req, path, codec).await
}
pub async fn set_thread_spawn_edge_status(
&mut self,
request: impl tonic::IntoRequest<super::SetThreadSpawnEdgeStatusRequest>,
) -> std::result::Result<tonic::Response<super::Empty>, tonic::Status> {
self.inner.ready().await.map_err(|e| {
tonic::Status::unknown(format!("Service was not ready: {}", e.into()))
})?;
let codec = tonic_prost::ProstCodec::default();
let path = http::uri::PathAndQuery::from_static(
"/codex.agent_graph_store.v1.AgentGraphStore/SetThreadSpawnEdgeStatus",
);
let mut req = request.into_request();
req.extensions_mut().insert(GrpcMethod::new(
"codex.agent_graph_store.v1.AgentGraphStore",
"SetThreadSpawnEdgeStatus",
));
self.inner.unary(req, path, codec).await
}
pub async fn list_thread_spawn_children(
&mut self,
request: impl tonic::IntoRequest<super::ListThreadSpawnChildrenRequest>,
) -> std::result::Result<
tonic::Response<super::ListThreadSpawnChildrenResponse>,
tonic::Status,
> {
self.inner.ready().await.map_err(|e| {
tonic::Status::unknown(format!("Service was not ready: {}", e.into()))
})?;
let codec = tonic_prost::ProstCodec::default();
let path = http::uri::PathAndQuery::from_static(
"/codex.agent_graph_store.v1.AgentGraphStore/ListThreadSpawnChildren",
);
let mut req = request.into_request();
req.extensions_mut().insert(GrpcMethod::new(
"codex.agent_graph_store.v1.AgentGraphStore",
"ListThreadSpawnChildren",
));
self.inner.unary(req, path, codec).await
}
pub async fn list_thread_spawn_descendants(
&mut self,
request: impl tonic::IntoRequest<super::ListThreadSpawnDescendantsRequest>,
) -> std::result::Result<
tonic::Response<super::ListThreadSpawnDescendantsResponse>,
tonic::Status,
> {
self.inner.ready().await.map_err(|e| {
tonic::Status::unknown(format!("Service was not ready: {}", e.into()))
})?;
let codec = tonic_prost::ProstCodec::default();
let path = http::uri::PathAndQuery::from_static(
"/codex.agent_graph_store.v1.AgentGraphStore/ListThreadSpawnDescendants",
);
let mut req = request.into_request();
req.extensions_mut().insert(GrpcMethod::new(
"codex.agent_graph_store.v1.AgentGraphStore",
"ListThreadSpawnDescendants",
));
self.inner.unary(req, path, codec).await
}
}
}
/// Generated server implementations.
pub mod agent_graph_store_server {
#![allow(
unused_variables,
dead_code,
missing_docs,
clippy::wildcard_imports,
clippy::let_unit_value
)]
use tonic::codegen::*;
/// Generated trait containing gRPC methods that should be implemented for use with AgentGraphStoreServer.
#[async_trait]
pub trait AgentGraphStore: std::marker::Send + std::marker::Sync + 'static {
async fn upsert_thread_spawn_edge(
&self,
request: tonic::Request<super::UpsertThreadSpawnEdgeRequest>,
) -> std::result::Result<tonic::Response<super::Empty>, tonic::Status>;
async fn set_thread_spawn_edge_status(
&self,
request: tonic::Request<super::SetThreadSpawnEdgeStatusRequest>,
) -> std::result::Result<tonic::Response<super::Empty>, tonic::Status>;
async fn list_thread_spawn_children(
&self,
request: tonic::Request<super::ListThreadSpawnChildrenRequest>,
) -> std::result::Result<
tonic::Response<super::ListThreadSpawnChildrenResponse>,
tonic::Status,
>;
async fn list_thread_spawn_descendants(
&self,
request: tonic::Request<super::ListThreadSpawnDescendantsRequest>,
) -> std::result::Result<
tonic::Response<super::ListThreadSpawnDescendantsResponse>,
tonic::Status,
>;
}
#[derive(Debug)]
pub struct AgentGraphStoreServer<T> {
inner: Arc<T>,
accept_compression_encodings: EnabledCompressionEncodings,
send_compression_encodings: EnabledCompressionEncodings,
max_decoding_message_size: Option<usize>,
max_encoding_message_size: Option<usize>,
}
impl<T> AgentGraphStoreServer<T> {
pub fn new(inner: T) -> Self {
Self::from_arc(Arc::new(inner))
}
pub fn from_arc(inner: Arc<T>) -> Self {
Self {
inner,
accept_compression_encodings: Default::default(),
send_compression_encodings: Default::default(),
max_decoding_message_size: None,
max_encoding_message_size: None,
}
}
pub fn with_interceptor<F>(inner: T, interceptor: F) -> InterceptedService<Self, F>
where
F: tonic::service::Interceptor,
{
InterceptedService::new(Self::new(inner), interceptor)
}
/// Enable decompressing requests with the given encoding.
#[must_use]
pub fn accept_compressed(mut self, encoding: CompressionEncoding) -> Self {
self.accept_compression_encodings.enable(encoding);
self
}
/// Compress responses with the given encoding, if the client supports it.
#[must_use]
pub fn send_compressed(mut self, encoding: CompressionEncoding) -> Self {
self.send_compression_encodings.enable(encoding);
self
}
/// Limits the maximum size of a decoded message.
///
/// Default: `4MB`
#[must_use]
pub fn max_decoding_message_size(mut self, limit: usize) -> Self {
self.max_decoding_message_size = Some(limit);
self
}
/// Limits the maximum size of an encoded message.
///
/// Default: `usize::MAX`
#[must_use]
pub fn max_encoding_message_size(mut self, limit: usize) -> Self {
self.max_encoding_message_size = Some(limit);
self
}
}
impl<T, B> tonic::codegen::Service<http::Request<B>> for AgentGraphStoreServer<T>
where
T: AgentGraphStore,
B: Body + std::marker::Send + 'static,
B::Error: Into<StdError> + std::marker::Send + 'static,
{
type Response = http::Response<tonic::body::Body>;
type Error = std::convert::Infallible;
type Future = BoxFuture<Self::Response, Self::Error>;
fn poll_ready(
&mut self,
_cx: &mut Context<'_>,
) -> Poll<std::result::Result<(), Self::Error>> {
Poll::Ready(Ok(()))
}
fn call(&mut self, req: http::Request<B>) -> Self::Future {
match req.uri().path() {
"/codex.agent_graph_store.v1.AgentGraphStore/UpsertThreadSpawnEdge" => {
#[allow(non_camel_case_types)]
struct UpsertThreadSpawnEdgeSvc<T: AgentGraphStore>(pub Arc<T>);
impl<T: AgentGraphStore>
tonic::server::UnaryService<super::UpsertThreadSpawnEdgeRequest>
for UpsertThreadSpawnEdgeSvc<T>
{
type Response = super::Empty;
type Future = BoxFuture<tonic::Response<Self::Response>, tonic::Status>;
fn call(
&mut self,
request: tonic::Request<super::UpsertThreadSpawnEdgeRequest>,
) -> Self::Future {
let inner = Arc::clone(&self.0);
let fut = async move {
<T as AgentGraphStore>::upsert_thread_spawn_edge(&inner, request)
.await
};
Box::pin(fut)
}
}
let accept_compression_encodings = self.accept_compression_encodings;
let send_compression_encodings = self.send_compression_encodings;
let max_decoding_message_size = self.max_decoding_message_size;
let max_encoding_message_size = self.max_encoding_message_size;
let inner = self.inner.clone();
let fut = async move {
let method = UpsertThreadSpawnEdgeSvc(inner);
let codec = tonic_prost::ProstCodec::default();
let mut grpc = tonic::server::Grpc::new(codec)
.apply_compression_config(
accept_compression_encodings,
send_compression_encodings,
)
.apply_max_message_size_config(
max_decoding_message_size,
max_encoding_message_size,
);
let res = grpc.unary(method, req).await;
Ok(res)
};
Box::pin(fut)
}
"/codex.agent_graph_store.v1.AgentGraphStore/SetThreadSpawnEdgeStatus" => {
#[allow(non_camel_case_types)]
struct SetThreadSpawnEdgeStatusSvc<T: AgentGraphStore>(pub Arc<T>);
impl<T: AgentGraphStore>
tonic::server::UnaryService<super::SetThreadSpawnEdgeStatusRequest>
for SetThreadSpawnEdgeStatusSvc<T>
{
type Response = super::Empty;
type Future = BoxFuture<tonic::Response<Self::Response>, tonic::Status>;
fn call(
&mut self,
request: tonic::Request<super::SetThreadSpawnEdgeStatusRequest>,
) -> Self::Future {
let inner = Arc::clone(&self.0);
let fut = async move {
<T as AgentGraphStore>::set_thread_spawn_edge_status(
&inner, request,
)
.await
};
Box::pin(fut)
}
}
let accept_compression_encodings = self.accept_compression_encodings;
let send_compression_encodings = self.send_compression_encodings;
let max_decoding_message_size = self.max_decoding_message_size;
let max_encoding_message_size = self.max_encoding_message_size;
let inner = self.inner.clone();
let fut = async move {
let method = SetThreadSpawnEdgeStatusSvc(inner);
let codec = tonic_prost::ProstCodec::default();
let mut grpc = tonic::server::Grpc::new(codec)
.apply_compression_config(
accept_compression_encodings,
send_compression_encodings,
)
.apply_max_message_size_config(
max_decoding_message_size,
max_encoding_message_size,
);
let res = grpc.unary(method, req).await;
Ok(res)
};
Box::pin(fut)
}
"/codex.agent_graph_store.v1.AgentGraphStore/ListThreadSpawnChildren" => {
#[allow(non_camel_case_types)]
struct ListThreadSpawnChildrenSvc<T: AgentGraphStore>(pub Arc<T>);
impl<T: AgentGraphStore>
tonic::server::UnaryService<super::ListThreadSpawnChildrenRequest>
for ListThreadSpawnChildrenSvc<T>
{
type Response = super::ListThreadSpawnChildrenResponse;
type Future = BoxFuture<tonic::Response<Self::Response>, tonic::Status>;
fn call(
&mut self,
request: tonic::Request<super::ListThreadSpawnChildrenRequest>,
) -> Self::Future {
let inner = Arc::clone(&self.0);
let fut = async move {
<T as AgentGraphStore>::list_thread_spawn_children(&inner, request)
.await
};
Box::pin(fut)
}
}
let accept_compression_encodings = self.accept_compression_encodings;
let send_compression_encodings = self.send_compression_encodings;
let max_decoding_message_size = self.max_decoding_message_size;
let max_encoding_message_size = self.max_encoding_message_size;
let inner = self.inner.clone();
let fut = async move {
let method = ListThreadSpawnChildrenSvc(inner);
let codec = tonic_prost::ProstCodec::default();
let mut grpc = tonic::server::Grpc::new(codec)
.apply_compression_config(
accept_compression_encodings,
send_compression_encodings,
)
.apply_max_message_size_config(
max_decoding_message_size,
max_encoding_message_size,
);
let res = grpc.unary(method, req).await;
Ok(res)
};
Box::pin(fut)
}
"/codex.agent_graph_store.v1.AgentGraphStore/ListThreadSpawnDescendants" => {
#[allow(non_camel_case_types)]
struct ListThreadSpawnDescendantsSvc<T: AgentGraphStore>(pub Arc<T>);
impl<T: AgentGraphStore>
tonic::server::UnaryService<super::ListThreadSpawnDescendantsRequest>
for ListThreadSpawnDescendantsSvc<T>
{
type Response = super::ListThreadSpawnDescendantsResponse;
type Future = BoxFuture<tonic::Response<Self::Response>, tonic::Status>;
fn call(
&mut self,
request: tonic::Request<super::ListThreadSpawnDescendantsRequest>,
) -> Self::Future {
let inner = Arc::clone(&self.0);
let fut = async move {
<T as AgentGraphStore>::list_thread_spawn_descendants(
&inner, request,
)
.await
};
Box::pin(fut)
}
}
let accept_compression_encodings = self.accept_compression_encodings;
let send_compression_encodings = self.send_compression_encodings;
let max_decoding_message_size = self.max_decoding_message_size;
let max_encoding_message_size = self.max_encoding_message_size;
let inner = self.inner.clone();
let fut = async move {
let method = ListThreadSpawnDescendantsSvc(inner);
let codec = tonic_prost::ProstCodec::default();
let mut grpc = tonic::server::Grpc::new(codec)
.apply_compression_config(
accept_compression_encodings,
send_compression_encodings,
)
.apply_max_message_size_config(
max_decoding_message_size,
max_encoding_message_size,
);
let res = grpc.unary(method, req).await;
Ok(res)
};
Box::pin(fut)
}
_ => Box::pin(async move {
let mut response = http::Response::new(tonic::body::Body::default());
let headers = response.headers_mut();
headers.insert(
tonic::Status::GRPC_STATUS,
(tonic::Code::Unimplemented as i32).into(),
);
headers.insert(
http::header::CONTENT_TYPE,
tonic::metadata::GRPC_CONTENT_TYPE,
);
Ok(response)
}),
}
}
}
impl<T> Clone for AgentGraphStoreServer<T> {
fn clone(&self) -> Self {
let inner = self.inner.clone();
Self {
inner,
accept_compression_encodings: self.accept_compression_encodings,
send_compression_encodings: self.send_compression_encodings,
max_decoding_message_size: self.max_decoding_message_size,
max_encoding_message_size: self.max_encoding_message_size,
}
}
}
/// Generated gRPC service name
pub const SERVICE_NAME: &str = "codex.agent_graph_store.v1.AgentGraphStore";
impl<T> tonic::server::NamedService for AgentGraphStoreServer<T> {
const NAME: &'static str = SERVICE_NAME;
}
}

View File

@@ -1,55 +0,0 @@
use async_trait::async_trait;
use codex_protocol::ThreadId;
use crate::AgentGraphStoreResult;
use crate::ThreadSpawnEdgeStatus;
/// Storage-neutral boundary for persisted thread-spawn parent/child topology.
///
/// Implementations are expected to return stable ordering for list methods so callers can merge
/// persisted graph state with live in-memory state without introducing nondeterministic output.
#[async_trait]
pub trait AgentGraphStore: Send + Sync {
/// Insert or replace the directional parent/child edge for a spawned thread.
///
/// `child_thread_id` has at most one persisted parent. Re-inserting the same child should
/// update both the parent and status to match the supplied values.
async fn upsert_thread_spawn_edge(
&self,
parent_thread_id: ThreadId,
child_thread_id: ThreadId,
status: ThreadSpawnEdgeStatus,
) -> AgentGraphStoreResult<()>;
/// Update the persisted lifecycle status of a spawned thread's incoming edge.
///
/// Implementations should treat missing children as a successful no-op.
async fn set_thread_spawn_edge_status(
&self,
child_thread_id: ThreadId,
status: ThreadSpawnEdgeStatus,
) -> AgentGraphStoreResult<()>;
/// List direct spawned children of a parent thread.
///
/// When `status_filter` is `Some`, only child edges with that exact status are returned. When
/// it is `None`, all direct child edges are returned regardless of status, including statuses
/// that may be added by a future store implementation.
async fn list_thread_spawn_children(
&self,
parent_thread_id: ThreadId,
status_filter: Option<ThreadSpawnEdgeStatus>,
) -> AgentGraphStoreResult<Vec<ThreadId>>;
/// List spawned descendants breadth-first by depth, then by thread id.
///
/// `status_filter` is applied to every traversed edge, not just to the returned descendants.
/// For example, `Some(Open)` walks only open edges, so descendants under a closed edge are not
/// included even if their own incoming edge is open. `None` walks and returns every persisted
/// edge regardless of status.
async fn list_thread_spawn_descendants(
&self,
root_thread_id: ThreadId,
status_filter: Option<ThreadSpawnEdgeStatus>,
) -> AgentGraphStoreResult<Vec<ThreadId>>;
}

View File

@@ -1,42 +0,0 @@
use serde::Deserialize;
use serde::Serialize;
/// Lifecycle status attached to a directional thread-spawn edge.
#[derive(Clone, Copy, Debug, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "snake_case")]
pub enum ThreadSpawnEdgeStatus {
/// The child thread is still live or resumable as an open spawned agent.
Open,
/// The child thread has been closed from the parent/child graph's perspective.
Closed,
}
#[cfg(test)]
mod tests {
use super::*;
use pretty_assertions::assert_eq;
#[test]
fn thread_spawn_edge_status_serializes_as_snake_case() {
assert_eq!(
serde_json::to_string(&ThreadSpawnEdgeStatus::Open)
.expect("open status should serialize"),
"\"open\""
);
assert_eq!(
serde_json::to_string(&ThreadSpawnEdgeStatus::Closed)
.expect("closed status should serialize"),
"\"closed\""
);
assert_eq!(
serde_json::from_str::<ThreadSpawnEdgeStatus>("\"open\"")
.expect("open status should deserialize"),
ThreadSpawnEdgeStatus::Open
);
assert_eq!(
serde_json::from_str::<ThreadSpawnEdgeStatus>("\"closed\"")
.expect("closed status should deserialize"),
ThreadSpawnEdgeStatus::Closed
);
}
}

View File

@@ -19,6 +19,7 @@ chrono = { workspace = true }
codex-protocol = { workspace = true }
crypto_box = { workspace = true }
ed25519-dalek = { workspace = true }
jsonwebtoken = { workspace = true }
rand = { workspace = true }
reqwest = { workspace = true, features = ["json"] }
serde = { workspace = true, features = ["derive"] }

View File

@@ -8,6 +8,7 @@ use base64::engine::general_purpose::STANDARD as BASE64_STANDARD;
use base64::engine::general_purpose::URL_SAFE_NO_PAD;
use chrono::SecondsFormat;
use chrono::Utc;
use codex_protocol::account::PlanType as AccountPlanType;
use codex_protocol::protocol::SessionSource;
use crypto_box::SecretKey as Curve25519SecretKey;
use ed25519_dalek::Signer as _;
@@ -15,14 +16,24 @@ use ed25519_dalek::SigningKey;
use ed25519_dalek::VerifyingKey;
use ed25519_dalek::pkcs8::DecodePrivateKey;
use ed25519_dalek::pkcs8::EncodePrivateKey;
use jsonwebtoken::Algorithm;
use jsonwebtoken::DecodingKey;
use jsonwebtoken::Validation;
use jsonwebtoken::decode;
use jsonwebtoken::decode_header;
use jsonwebtoken::jwk::JwkSet;
use rand::TryRngCore;
use rand::rngs::OsRng;
use serde::Deserialize;
use serde::Serialize;
use serde::de::DeserializeOwned;
use sha2::Digest as _;
use sha2::Sha512;
const AGENT_TASK_REGISTRATION_TIMEOUT: Duration = Duration::from_secs(30);
const AGENT_IDENTITY_JWKS_TIMEOUT: Duration = Duration::from_secs(10);
const AGENT_IDENTITY_JWT_AUDIENCE: &str = "codex-app-server";
const AGENT_IDENTITY_JWT_ISSUER: &str = "https://chatgpt.com/codex-backend/agent-identity";
/// Stored key material for a registered agent identity.
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
@@ -50,6 +61,22 @@ pub struct GeneratedAgentKeyMaterial {
pub public_key_ssh: String,
}
/// Claims carried by an Agent Identity JWT.
#[derive(Clone, Debug, Deserialize, PartialEq, Eq)]
pub struct AgentIdentityJwtClaims {
pub iss: String,
pub aud: String,
pub iat: usize,
pub exp: usize,
pub agent_runtime_id: String,
pub agent_private_key: String,
pub account_id: String,
pub chatgpt_user_id: String,
pub email: String,
pub plan_type: AccountPlanType,
pub chatgpt_account_is_fedramp: bool,
}
#[derive(Clone, Debug, Serialize, Deserialize, PartialEq, Eq)]
struct AgentAssertionEnvelope {
agent_runtime_id: String,
@@ -98,6 +125,65 @@ pub fn authorization_header_for_agent_task(
Ok(format!("AgentAssertion {serialized_assertion}"))
}
pub async fn fetch_agent_identity_jwks(
client: &reqwest::Client,
chatgpt_base_url: &str,
) -> Result<JwkSet> {
let response = client
.get(agent_identity_jwks_url(chatgpt_base_url))
.timeout(AGENT_IDENTITY_JWKS_TIMEOUT)
.send()
.await
.context("failed to request agent identity JWKS")?
.error_for_status()
.context("agent identity JWKS endpoint returned an error")?;
response
.json()
.await
.context("failed to decode agent identity JWKS")
}
pub fn decode_agent_identity_jwt(
jwt: &str,
jwks: Option<&JwkSet>,
) -> Result<AgentIdentityJwtClaims> {
let Some(jwks) = jwks else {
return decode_agent_identity_jwt_payload(jwt);
};
let header = decode_header(jwt).context("failed to decode agent identity JWT header")?;
let kid = header
.kid
.context("agent identity JWT header does not include a kid")?;
let jwk = jwks
.find(&kid)
.with_context(|| format!("agent identity JWT kid {kid} is not trusted"))?;
let decoding_key = DecodingKey::from_jwk(jwk).context("failed to build JWT decoding key")?;
let mut validation = Validation::new(Algorithm::RS256);
validation.set_audience(&[AGENT_IDENTITY_JWT_AUDIENCE]);
validation.set_issuer(&[AGENT_IDENTITY_JWT_ISSUER]);
validation.required_spec_claims.insert("iss".to_string());
validation.required_spec_claims.insert("aud".to_string());
decode::<AgentIdentityJwtClaims>(jwt, &decoding_key, &validation)
.map(|data| data.claims)
.context("failed to verify agent identity JWT")
}
fn decode_agent_identity_jwt_payload<T: DeserializeOwned>(jwt: &str) -> Result<T> {
let mut parts = jwt.split('.');
let (_header_b64, payload_b64, _sig_b64) = match (parts.next(), parts.next(), parts.next()) {
(Some(h), Some(p), Some(s)) if !h.is_empty() && !p.is_empty() && !s.is_empty() => (h, p, s),
_ => anyhow::bail!("invalid agent identity JWT format"),
};
anyhow::ensure!(parts.next().is_none(), "invalid agent identity JWT format");
let payload_bytes = URL_SAFE_NO_PAD
.decode(payload_b64)
.context("agent identity JWT payload is not valid base64url")?;
serde_json::from_slice(&payload_bytes).context("agent identity JWT payload is not valid JSON")
}
pub fn sign_task_registration_payload(
key: AgentIdentityKey<'_>,
timestamp: &str,
@@ -117,19 +203,27 @@ pub async fn register_agent_task(
signature: sign_task_registration_payload(key, &timestamp)?,
timestamp,
};
let url = agent_task_registration_url(chatgpt_base_url, key.agent_runtime_id);
let response = client
.post(agent_task_registration_url(
chatgpt_base_url,
key.agent_runtime_id,
))
.post(url)
.timeout(AGENT_TASK_REGISTRATION_TIMEOUT)
.json(&request)
.send()
.await
.context("failed to register agent task")?
.error_for_status()
.context("failed to register agent task")?
.context("failed to register agent task")?;
if !response.status().is_success() {
let status = response.status();
let body = response.text().await.unwrap_or_default();
let body = if body.len() > 512 {
format!("{}...", body.chars().take(512).collect::<String>())
} else {
body
};
anyhow::bail!("failed to register agent task with status {status}: {body}");
}
let response = response
.json()
.await
.context("failed to decode agent task registration response")?;
@@ -217,6 +311,15 @@ pub fn agent_identity_biscuit_url(chatgpt_base_url: &str) -> String {
format!("{trimmed}/authenticate_app_v2")
}
pub fn agent_identity_jwks_url(chatgpt_base_url: &str) -> String {
let trimmed = chatgpt_base_url.trim_end_matches('/');
if trimmed.contains("/backend-api") {
format!("{trimmed}/wham/agent-identities/jwks")
} else {
format!("{trimmed}/agent-identities/jwks")
}
}
pub fn agent_identity_request_id() -> Result<String> {
let mut request_id_bytes = [0u8; 16];
OsRng
@@ -228,29 +331,6 @@ pub fn agent_identity_request_id() -> Result<String> {
))
}
pub fn normalize_chatgpt_base_url(chatgpt_base_url: &str) -> String {
let mut base_url = chatgpt_base_url.trim_end_matches('/').to_string();
for suffix in [
"/wham/remote/control/server/enroll",
"/wham/remote/control/server",
] {
if let Some(stripped) = base_url.strip_suffix(suffix) {
base_url = stripped.to_string();
break;
}
}
if let Some(stripped) = base_url.strip_suffix("/codex") {
base_url = stripped.to_string();
}
if (base_url.starts_with("https://chatgpt.com")
|| base_url.starts_with("https://chat.openai.com"))
&& !base_url.contains("/backend-api")
{
base_url = format!("{base_url}/backend-api");
}
base_url
}
pub fn build_abom(session_source: SessionSource) -> AgentBillOfMaterials {
AgentBillOfMaterials {
agent_version: env!("CARGO_PKG_VERSION").to_string(),
@@ -260,6 +340,7 @@ pub fn build_abom(session_source: SessionSource) -> AgentBillOfMaterials {
| SessionSource::Exec
| SessionSource::Mcp
| SessionSource::Custom(_)
| SessionSource::Internal(_)
| SessionSource::SubAgent(_)
| SessionSource::Unknown => "codex-cli".to_string(),
},
@@ -323,6 +404,8 @@ mod tests {
use base64::Engine as _;
use ed25519_dalek::Signature;
use ed25519_dalek::Verifier as _;
use jsonwebtoken::EncodingKey;
use jsonwebtoken::Header;
use pretty_assertions::assert_eq;
use super::*;
@@ -405,10 +488,227 @@ mod tests {
}
#[test]
fn normalize_chatgpt_base_url_strips_codex_before_backend_api() {
fn decode_agent_identity_jwt_reads_claims() {
let jwt = jwt_with_payload(serde_json::json!({
"iss": AGENT_IDENTITY_JWT_ISSUER,
"aud": AGENT_IDENTITY_JWT_AUDIENCE,
"iat": 1_700_000_000usize,
"exp": 4_000_000_000usize,
"agent_runtime_id": "agent-runtime-id",
"agent_private_key": "private-key",
"account_id": "account-id",
"chatgpt_user_id": "user-id",
"email": "user@example.com",
"plan_type": "pro",
"chatgpt_account_is_fedramp": false,
}));
let claims = decode_agent_identity_jwt(&jwt, /*jwks*/ None).expect("JWT should decode");
assert_eq!(
normalize_chatgpt_base_url("https://chatgpt.com/codex"),
"https://chatgpt.com/backend-api"
claims,
AgentIdentityJwtClaims {
iss: AGENT_IDENTITY_JWT_ISSUER.to_string(),
aud: AGENT_IDENTITY_JWT_AUDIENCE.to_string(),
iat: 1_700_000_000,
exp: 4_000_000_000,
agent_runtime_id: "agent-runtime-id".to_string(),
agent_private_key: "private-key".to_string(),
account_id: "account-id".to_string(),
chatgpt_user_id: "user-id".to_string(),
email: "user@example.com".to_string(),
plan_type: AccountPlanType::Pro,
chatgpt_account_is_fedramp: false,
}
);
}
#[test]
fn decode_agent_identity_jwt_verifies_when_jwks_is_present() {
let jwks = test_jwks("test-key");
let claims = AgentIdentityJwtClaims {
iss: AGENT_IDENTITY_JWT_ISSUER.to_string(),
aud: AGENT_IDENTITY_JWT_AUDIENCE.to_string(),
iat: 1_700_000_000,
exp: 4_000_000_000,
agent_runtime_id: "agent-runtime-id".to_string(),
agent_private_key: "private-key".to_string(),
account_id: "account-id".to_string(),
chatgpt_user_id: "user-id".to_string(),
email: "user@example.com".to_string(),
plan_type: AccountPlanType::Pro,
chatgpt_account_is_fedramp: false,
};
let jwt = jsonwebtoken::encode(
&test_jwt_header("test-key"),
&serde_json::json!({
"iss": claims.iss,
"aud": claims.aud,
"iat": claims.iat,
"exp": claims.exp,
"agent_runtime_id": claims.agent_runtime_id,
"agent_private_key": claims.agent_private_key,
"account_id": claims.account_id,
"chatgpt_user_id": claims.chatgpt_user_id,
"email": claims.email,
"plan_type": "pro",
"chatgpt_account_is_fedramp": claims.chatgpt_account_is_fedramp,
}),
&test_rsa_encoding_key(),
)
.expect("JWT should encode");
let expected_claims = AgentIdentityJwtClaims {
iss: AGENT_IDENTITY_JWT_ISSUER.to_string(),
aud: AGENT_IDENTITY_JWT_AUDIENCE.to_string(),
iat: 1_700_000_000,
exp: 4_000_000_000,
agent_runtime_id: "agent-runtime-id".to_string(),
agent_private_key: "private-key".to_string(),
account_id: "account-id".to_string(),
chatgpt_user_id: "user-id".to_string(),
email: "user@example.com".to_string(),
plan_type: AccountPlanType::Pro,
chatgpt_account_is_fedramp: false,
};
assert_eq!(
decode_agent_identity_jwt(&jwt, Some(&jwks)).expect("JWT should verify"),
expected_claims
);
}
#[test]
fn decode_agent_identity_jwt_rejects_untrusted_kid() {
let jwks = test_jwks("other-key");
let jwt = jsonwebtoken::encode(
&test_jwt_header("test-key"),
&serde_json::json!({
"iss": AGENT_IDENTITY_JWT_ISSUER,
"aud": AGENT_IDENTITY_JWT_AUDIENCE,
"iat": 1_700_000_000,
"exp": 4_000_000_000usize,
"agent_runtime_id": "agent-runtime-id",
"agent_private_key": "private-key",
"account_id": "account-id",
"chatgpt_user_id": "user-id",
"email": "user@example.com",
"plan_type": "pro",
"chatgpt_account_is_fedramp": false,
}),
&test_rsa_encoding_key(),
)
.expect("JWT should encode");
decode_agent_identity_jwt(&jwt, Some(&jwks)).expect_err("JWT should not verify");
}
#[test]
fn decode_agent_identity_jwt_requires_issuer_and_audience() {
let jwks = test_jwks("test-key");
let jwt = jsonwebtoken::encode(
&test_jwt_header("test-key"),
&serde_json::json!({
"iat": 1_700_000_000,
"exp": 4_000_000_000usize,
"agent_runtime_id": "agent-runtime-id",
"agent_private_key": "private-key",
"account_id": "account-id",
"chatgpt_user_id": "user-id",
"email": "user@example.com",
"plan_type": "pro",
"chatgpt_account_is_fedramp": false,
}),
&test_rsa_encoding_key(),
)
.expect("JWT should encode");
decode_agent_identity_jwt(&jwt, Some(&jwks)).expect_err("JWT should not verify");
}
fn test_jwt_header(kid: &str) -> Header {
let mut header = Header::new(Algorithm::RS256);
header.kid = Some(kid.to_string());
header
}
fn test_rsa_encoding_key() -> EncodingKey {
EncodingKey::from_rsa_pem(
br#"-----BEGIN PRIVATE KEY-----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-----END PRIVATE KEY-----"#,
)
.expect("test RSA key should parse")
}
fn test_jwks(kid: &str) -> jsonwebtoken::jwk::JwkSet {
serde_json::from_value(serde_json::json!({
"keys": [{
"kty": "RSA",
"kid": kid,
"use": "sig",
"alg": "RS256",
"n": "1qQF2MqTrGAMDm7wXbjJP5sWqGA83tAGUs2ksy7iJXLJdhCg4AtwGm4SFl4f6kxhCSzlN1QdXuZjvRT2wZZiGUi9xUE28rf4WLrTxSnwqLuTy5knMP08yC0t_0YU_FGPZMcWb14hG05IvZr8UbmRaVagxSR8H4rSIymRoVwwmFSrqz068XrWGSYNIfLEASyo5GdAaqmk1JALINHgYGQJVxMxtwcvDxoVKmC7eltUNymMNBZhsv4E8sx9YNLpBoEibznfEpDU_DGzrM5eZCsQzaqbhBOlGd427ifud_Nnd9cPqzgCUc23-0FXSPfpbgksCXAwAmD0OFjQWrgqVdKL6Q",
"e": "AQAB",
}]
}))
.expect("test JWKS should parse")
}
#[test]
fn agent_identity_jwks_url_uses_backend_api_base_url() {
assert_eq!(
agent_identity_jwks_url("https://chatgpt.com/backend-api"),
"https://chatgpt.com/backend-api/wham/agent-identities/jwks"
);
assert_eq!(
agent_identity_jwks_url("https://chatgpt.com/backend-api/"),
"https://chatgpt.com/backend-api/wham/agent-identities/jwks"
);
}
#[test]
fn agent_identity_jwks_url_uses_codex_api_base_url() {
assert_eq!(
agent_identity_jwks_url("http://localhost:8080/api/codex"),
"http://localhost:8080/api/codex/agent-identities/jwks"
);
assert_eq!(
agent_identity_jwks_url("http://localhost:8080/api/codex/"),
"http://localhost:8080/api/codex/agent-identities/jwks"
);
}
fn jwt_with_payload(payload: serde_json::Value) -> String {
let encode = |bytes: &[u8]| URL_SAFE_NO_PAD.encode(bytes);
let header_b64 = encode(br#"{"alg":"none","typ":"JWT"}"#);
let payload_b64 = encode(&serde_json::to_vec(&payload).expect("payload should serialize"));
let signature_b64 = encode(b"sig");
format!("{header_b64}.{payload_b64}.{signature_b64}")
}
}

View File

@@ -161,7 +161,7 @@ fn sample_thread_start_response(thread_id: &str, ephemeral: bool, model: &str) -
}
fn sample_permission_profile() -> AppServerPermissionProfile {
CorePermissionProfile::from_legacy_sandbox_policy(&SandboxPolicy::DangerFullAccess).into()
CorePermissionProfile::Disabled.into()
}
fn sample_app_server_client_metadata() -> CodexAppServerClientMetadata {
@@ -315,7 +315,10 @@ fn sample_turn_resolved_config(turn_id: &str) -> TurnResolvedConfigFact {
session_source: SessionSource::Exec,
model: "gpt-5".to_string(),
model_provider: "openai".to_string(),
sandbox_policy: SandboxPolicy::new_read_only_policy(),
permission_profile: CorePermissionProfile::from_legacy_sandbox_policy(
&SandboxPolicy::new_read_only_policy(),
),
permission_profile_cwd: PathBuf::from("/tmp"),
reasoning_effort: None,
reasoning_summary: None,
service_tier: None,

View File

@@ -13,12 +13,12 @@ use codex_protocol::config_types::ModeKind;
use codex_protocol::config_types::Personality;
use codex_protocol::config_types::ReasoningSummary;
use codex_protocol::config_types::ServiceTier;
use codex_protocol::models::PermissionProfile;
use codex_protocol::openai_models::ReasoningEffort;
use codex_protocol::protocol::AskForApproval;
use codex_protocol::protocol::HookEventName;
use codex_protocol::protocol::HookRunStatus;
use codex_protocol::protocol::HookSource;
use codex_protocol::protocol::SandboxPolicy;
use codex_protocol::protocol::SessionSource;
use codex_protocol::protocol::SkillScope;
use codex_protocol::protocol::SubAgentSource;
@@ -62,7 +62,8 @@ pub struct TurnResolvedConfigFact {
pub session_source: SessionSource,
pub model: String,
pub model_provider: String,
pub sandbox_policy: SandboxPolicy,
pub permission_profile: PermissionProfile,
pub permission_profile_cwd: PathBuf,
pub reasoning_effort: Option<ReasoningEffort>,
pub reasoning_summary: Option<ReasoningSummary>,
pub service_tier: Option<ServiceTier>,

View File

@@ -61,7 +61,7 @@ use codex_login::default_client::originator;
use codex_protocol::config_types::ModeKind;
use codex_protocol::config_types::Personality;
use codex_protocol::config_types::ReasoningSummary;
use codex_protocol::protocol::SandboxPolicy;
use codex_protocol::models::PermissionProfile;
use codex_protocol::protocol::SessionSource;
use codex_protocol::protocol::SkillScope;
use codex_protocol::protocol::TokenUsage;
@@ -106,6 +106,7 @@ impl ThreadMetadataState {
| SessionSource::Exec
| SessionSource::Mcp
| SessionSource::Custom(_)
| SessionSource::Internal(_)
| SessionSource::Unknown => (None, None),
};
Self {
@@ -884,7 +885,8 @@ fn codex_turn_event_params(
session_source: _session_source,
model,
model_provider,
sandbox_policy,
permission_profile,
permission_profile_cwd,
reasoning_effort,
reasoning_summary,
service_tier,
@@ -909,7 +911,10 @@ fn codex_turn_event_params(
parent_thread_id: thread_metadata.parent_thread_id.clone(),
model: Some(model),
model_provider,
sandbox_policy: Some(sandbox_policy_mode(&sandbox_policy)),
sandbox_policy: Some(sandbox_policy_mode(
&permission_profile,
permission_profile_cwd.as_path(),
)),
reasoning_effort: reasoning_effort.map(|value| value.to_string()),
reasoning_summary: reasoning_summary_mode(reasoning_summary),
service_tier: service_tier
@@ -954,12 +959,27 @@ fn codex_turn_event_params(
}
}
fn sandbox_policy_mode(sandbox_policy: &SandboxPolicy) -> &'static str {
match sandbox_policy {
SandboxPolicy::DangerFullAccess => "full_access",
SandboxPolicy::ReadOnly { .. } => "read_only",
SandboxPolicy::WorkspaceWrite { .. } => "workspace_write",
SandboxPolicy::ExternalSandbox { .. } => "external_sandbox",
fn sandbox_policy_mode(permission_profile: &PermissionProfile, cwd: &Path) -> &'static str {
match permission_profile {
PermissionProfile::Disabled => "full_access",
PermissionProfile::External { .. } => "external_sandbox",
PermissionProfile::Managed { .. } => {
let file_system_policy = permission_profile.file_system_sandbox_policy();
if file_system_policy.has_full_disk_write_access() {
if permission_profile.network_sandbox_policy().is_enabled() {
"full_access"
} else {
"external_sandbox"
}
} else if file_system_policy
.get_writable_roots_with_cwd(cwd)
.is_empty()
{
"read_only"
} else {
"workspace_write"
}
}
}
}
@@ -1050,3 +1070,25 @@ pub(crate) fn normalize_path_for_skill_id(
_ => resolved_path.to_string_lossy().replace('\\', "/"),
}
}
#[cfg(test)]
mod tests {
use super::*;
use codex_protocol::models::SandboxEnforcement;
use codex_protocol::permissions::FileSystemSandboxPolicy;
use codex_protocol::permissions::NetworkSandboxPolicy;
#[test]
fn managed_full_disk_with_restricted_network_reports_external_sandbox() {
let permission_profile = PermissionProfile::from_runtime_permissions_with_enforcement(
SandboxEnforcement::Managed,
&FileSystemSandboxPolicy::unrestricted(),
NetworkSandboxPolicy::Restricted,
);
assert_eq!(
sandbox_policy_mode(&permission_profile, Path::new("/")),
"external_sandbox"
);
}
}

View File

@@ -41,12 +41,12 @@ use codex_app_server_protocol::Result as JsonRpcResult;
use codex_app_server_protocol::ServerNotification;
use codex_app_server_protocol::ServerRequest;
use codex_arg0::Arg0DispatchPaths;
use codex_config::CloudRequirementsLoader;
use codex_config::LoaderOverrides;
use codex_config::NoopThreadConfigLoader;
use codex_config::RemoteThreadConfigLoader;
use codex_config::ThreadConfigLoader;
use codex_core::config::Config;
use codex_core::config_loader::CloudRequirementsLoader;
use codex_core::config_loader::LoaderOverrides;
pub use codex_exec_server::EnvironmentManager;
pub use codex_exec_server::EnvironmentManagerArgs;
pub use codex_exec_server::ExecServerRuntimePaths;
@@ -1396,6 +1396,55 @@ mod tests {
client.shutdown().await.expect("shutdown should complete");
}
#[tokio::test]
async fn remote_typed_request_accepts_large_single_frame_response() {
let padding = "x".repeat((17 << 20) + 1024);
let websocket_url = start_test_remote_server(move |mut websocket| async move {
expect_remote_initialize(&mut websocket).await;
let JSONRPCMessage::Request(request) = read_websocket_message(&mut websocket).await
else {
panic!("expected account/read request");
};
assert_eq!(request.method, "account/read");
write_websocket_message(
&mut websocket,
JSONRPCMessage::Response(JSONRPCResponse {
id: request.id,
result: serde_json::json!({
"account": null,
"requiresOpenaiAuth": false,
"padding": padding,
}),
}),
)
.await;
websocket.close(None).await.expect("close should succeed");
})
.await;
let client = RemoteAppServerClient::connect(test_remote_connect_args(websocket_url))
.await
.expect("remote client should connect");
let response: GetAccountResponse = client
.request_typed(ClientRequest::GetAccount {
request_id: RequestId::Integer(1),
params: codex_app_server_protocol::GetAccountParams {
refresh_token: false,
},
})
.await
.expect("large typed request should succeed");
assert_eq!(
response,
GetAccountResponse {
account: None,
requires_openai_auth: false,
}
);
client.shutdown().await.expect("shutdown should complete");
}
#[tokio::test]
async fn remote_connect_includes_auth_header_when_configured() {
let auth_token = "remote-bearer-token".to_string();

View File

@@ -45,16 +45,18 @@ use tokio::sync::oneshot;
use tokio::time::timeout;
use tokio_tungstenite::MaybeTlsStream;
use tokio_tungstenite::WebSocketStream;
use tokio_tungstenite::connect_async;
use tokio_tungstenite::connect_async_with_config;
use tokio_tungstenite::tungstenite::Message;
use tokio_tungstenite::tungstenite::client::IntoClientRequest;
use tokio_tungstenite::tungstenite::http::HeaderValue;
use tokio_tungstenite::tungstenite::http::header::AUTHORIZATION;
use tokio_tungstenite::tungstenite::protocol::WebSocketConfig;
use tracing::warn;
use url::Url;
const CONNECT_TIMEOUT: Duration = Duration::from_secs(10);
const INITIALIZE_TIMEOUT: Duration = Duration::from_secs(10);
const REMOTE_APP_SERVER_MAX_WEBSOCKET_MESSAGE_SIZE: usize = 128 << 20;
#[derive(Debug, Clone)]
pub struct RemoteAppServerConnectArgs {
@@ -170,20 +172,32 @@ impl RemoteAppServerClient {
request.headers_mut().insert(AUTHORIZATION, header_value);
}
ensure_rustls_crypto_provider();
let stream = timeout(CONNECT_TIMEOUT, connect_async(request))
.await
.map_err(|_| {
IoError::new(
ErrorKind::TimedOut,
format!("timed out connecting to remote app server at `{websocket_url}`"),
)
})?
.map(|(stream, _response)| stream)
.map_err(|err| {
IoError::other(format!(
"failed to connect to remote app server at `{websocket_url}`: {err}"
))
})?;
// Remote resume responses can legitimately carry large thread histories.
// Keep a bounded cap, but raise it above tungstenite's 16 MiB frame default.
let websocket_config = WebSocketConfig::default()
.max_frame_size(Some(REMOTE_APP_SERVER_MAX_WEBSOCKET_MESSAGE_SIZE))
.max_message_size(Some(REMOTE_APP_SERVER_MAX_WEBSOCKET_MESSAGE_SIZE));
let stream = timeout(
CONNECT_TIMEOUT,
connect_async_with_config(
request,
Some(websocket_config),
/*disable_nagle*/ false,
),
)
.await
.map_err(|_| {
IoError::new(
ErrorKind::TimedOut,
format!("timed out connecting to remote app server at `{websocket_url}`"),
)
})?
.map(|(stream, _response)| stream)
.map_err(|err| {
IoError::other(format!(
"failed to connect to remote app server at `{websocket_url}`: {err}"
))
})?;
let mut stream = stream;
let pending_events = initialize_remote_connection(
&mut stream,
@@ -198,6 +212,7 @@ impl RemoteAppServerClient {
let worker_handle = tokio::spawn(async move {
let mut pending_requests =
HashMap::<RequestId, oneshot::Sender<IoResult<RequestResult>>>::new();
let mut worker_exit_error: Option<(ErrorKind, String)> = None;
loop {
tokio::select! {
command = command_rx.recv() => {
@@ -224,17 +239,19 @@ impl RemoteAppServerClient {
.await
{
let err_message = err.to_string();
let message = format!(
"remote app server at `{websocket_url}` write failed: {err_message}"
);
if let Some(response_tx) = pending_requests.remove(&request_id) {
let _ = response_tx.send(Err(err));
}
let _ = deliver_event(
&event_tx,
AppServerEvent::Disconnected {
message: format!(
"remote app server at `{websocket_url}` write failed: {err_message}"
),
message: message.clone(),
},
);
worker_exit_error = Some((ErrorKind::BrokenPipe, message));
break;
}
}
@@ -351,28 +368,34 @@ impl RemoteAppServerClient {
.await
{
let err_message = reject_err.to_string();
let message = format!(
"remote app server at `{websocket_url}` write failed: {err_message}"
);
let _ = deliver_event(
&event_tx,
AppServerEvent::Disconnected {
message: format!(
"remote app server at `{websocket_url}` write failed: {err_message}"
),
message: message.clone(),
},
);
worker_exit_error =
Some((ErrorKind::BrokenPipe, message));
break;
}
}
}
}
Err(err) => {
let message = format!(
"remote app server at `{websocket_url}` sent invalid JSON-RPC: {err}"
);
let _ = deliver_event(
&event_tx,
AppServerEvent::Disconnected {
message: format!(
"remote app server at `{websocket_url}` sent invalid JSON-RPC: {err}"
),
message: message.clone(),
},
);
worker_exit_error =
Some((ErrorKind::InvalidData, message));
break;
}
}
@@ -383,14 +406,19 @@ impl RemoteAppServerClient {
.map(|frame| frame.reason.to_string())
.filter(|reason| !reason.is_empty())
.unwrap_or_else(|| "connection closed".to_string());
let message = format!(
"remote app server at `{websocket_url}` disconnected: {reason}"
);
let _ = deliver_event(
&event_tx,
AppServerEvent::Disconnected {
message: format!(
"remote app server at `{websocket_url}` disconnected: {reason}"
),
message: message.clone(),
},
);
worker_exit_error = Some((
ErrorKind::ConnectionAborted,
message,
));
break;
}
Some(Ok(Message::Binary(_)))
@@ -398,25 +426,29 @@ impl RemoteAppServerClient {
| Some(Ok(Message::Pong(_)))
| Some(Ok(Message::Frame(_))) => {}
Some(Err(err)) => {
let message = format!(
"remote app server at `{websocket_url}` transport failed: {err}"
);
let _ = deliver_event(
&event_tx,
AppServerEvent::Disconnected {
message: format!(
"remote app server at `{websocket_url}` transport failed: {err}"
),
message: message.clone(),
},
);
worker_exit_error = Some((ErrorKind::InvalidData, message));
break;
}
None => {
let message = format!(
"remote app server at `{websocket_url}` closed the connection"
);
let _ = deliver_event(
&event_tx,
AppServerEvent::Disconnected {
message: format!(
"remote app server at `{websocket_url}` closed the connection"
),
message: message.clone(),
},
);
worker_exit_error = Some((ErrorKind::UnexpectedEof, message));
break;
}
}
@@ -424,12 +456,14 @@ impl RemoteAppServerClient {
}
}
let err = IoError::new(
ErrorKind::BrokenPipe,
"remote app-server worker channel is closed",
);
let (err_kind, err_message) = worker_exit_error.unwrap_or_else(|| {
(
ErrorKind::BrokenPipe,
"remote app-server worker channel is closed".to_string(),
)
});
for (_, response_tx) in pending_requests {
let _ = response_tx.send(Err(IoError::new(err.kind(), err.to_string())));
let _ = response_tx.send(Err(IoError::new(err_kind, err_message.clone())));
}
});

View File

@@ -218,17 +218,6 @@
"null"
]
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/PermissionProfile"
},
{
"type": "null"
}
],
"description": "Optional full permissions profile for this command.\n\nDefaults to the user's configured permissions when omitted. Cannot be combined with `sandboxPolicy`."
},
"processId": {
"description": "Optional client-supplied, connection-scoped process id.\n\nRequired for `tty`, `streamStdin`, `streamStdoutStderr`, and follow-up `command/exec/write`, `command/exec/resize`, and `command/exec/terminate` calls. When omitted, buffered execution gets an internal id that is not exposed to the client.",
"type": [
@@ -860,7 +849,8 @@
"CONFIG",
"SKILLS",
"PLUGINS",
"MCP_SERVER_CONFIG"
"MCP_SERVER_CONFIG",
"SESSIONS"
],
"type": "string"
},
@@ -1028,21 +1018,6 @@
"title": "MinimalFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
"enum": [
"current_working_directory"
],
"type": "string"
}
},
"required": [
"kind"
],
"title": "CurrentWorkingDirectoryFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
@@ -1415,38 +1390,6 @@
},
"type": "object"
},
"GhostCommit": {
"description": "Details of a ghost commit created from a repository state.",
"properties": {
"id": {
"type": "string"
},
"parent": {
"type": [
"string",
"null"
]
},
"preexisting_untracked_dirs": {
"items": {
"type": "string"
},
"type": "array"
},
"preexisting_untracked_files": {
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"id",
"preexisting_untracked_dirs",
"preexisting_untracked_files"
],
"type": "object"
},
"ImageDetail": {
"enum": [
"auto",
@@ -1837,15 +1780,20 @@
"MigrationDetails": {
"properties": {
"plugins": {
"default": [],
"items": {
"$ref": "#/definitions/PluginsMigration"
},
"type": "array"
},
"sessions": {
"default": [],
"items": {
"$ref": "#/definitions/SessionMigration"
},
"type": "array"
}
},
"required": [
"plugins"
],
"type": "object"
},
"ModeKind": {
@@ -2126,53 +2074,6 @@
],
"type": "object"
},
"ReadOnlyAccess": {
"oneOf": [
{
"properties": {
"includePlatformDefaults": {
"default": true,
"type": "boolean"
},
"readableRoots": {
"default": [],
"items": {
"$ref": "#/definitions/AbsolutePathBuf"
},
"type": "array"
},
"type": {
"enum": [
"restricted"
],
"title": "RestrictedReadOnlyAccessType",
"type": "string"
}
},
"required": [
"type"
],
"title": "RestrictedReadOnlyAccess",
"type": "object"
},
{
"properties": {
"type": {
"enum": [
"fullAccess"
],
"title": "FullAccessReadOnlyAccessType",
"type": "string"
}
},
"required": [
"type"
],
"title": "FullAccessReadOnlyAccess",
"type": "object"
}
]
},
"RealtimeOutputModality": {
"enum": [
"text",
@@ -2339,12 +2240,6 @@
},
"type": "array"
},
"end_turn": {
"type": [
"boolean",
"null"
]
},
"id": {
"type": [
"string",
@@ -2744,26 +2639,6 @@
"title": "ImageGenerationCallResponseItem",
"type": "object"
},
{
"properties": {
"ghost_commit": {
"$ref": "#/definitions/GhostCommit"
},
"type": {
"enum": [
"ghost_snapshot"
],
"title": "GhostSnapshotResponseItemType",
"type": "string"
}
},
"required": [
"ghost_commit",
"type"
],
"title": "GhostSnapshotResponseItem",
"type": "object"
},
{
"properties": {
"encrypted_content": {
@@ -3056,16 +2931,6 @@
},
{
"properties": {
"access": {
"allOf": [
{
"$ref": "#/definitions/ReadOnlyAccess"
}
],
"default": {
"type": "fullAccess"
}
},
"networkAccess": {
"default": false,
"type": "boolean"
@@ -3122,16 +2987,6 @@
"default": false,
"type": "boolean"
},
"readOnlyAccess": {
"allOf": [
{
"$ref": "#/definitions/ReadOnlyAccess"
}
],
"default": {
"type": "fullAccess"
}
},
"type": {
"enum": [
"workspaceWrite"
@@ -3173,6 +3028,27 @@
],
"type": "string"
},
"SessionMigration": {
"properties": {
"cwd": {
"type": "string"
},
"path": {
"type": "string"
},
"title": {
"type": [
"string",
"null"
]
}
},
"required": [
"cwd",
"path"
],
"type": "object"
},
"Settings": {
"description": "Settings for a collaboration mode.",
"properties": {
@@ -3411,17 +3287,6 @@
"null"
]
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/PermissionProfile"
},
{
"type": "null"
}
],
"description": "Full permissions override for the forked thread. Cannot be combined with `sandbox`."
},
"sandbox": {
"anyOf": [
{
@@ -3458,6 +3323,15 @@
],
"type": "object"
},
"ThreadGoalStatus": {
"enum": [
"active",
"paused",
"budgetLimited",
"complete"
],
"type": "string"
},
"ThreadInjectItemsParams": {
"properties": {
"items": {
@@ -3818,17 +3692,6 @@
"null"
]
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/PermissionProfile"
},
{
"type": "null"
}
],
"description": "Full permissions override for the resumed thread. Cannot be combined with `sandbox`."
},
"personality": {
"anyOf": [
{
@@ -4012,17 +3875,6 @@
"null"
]
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/PermissionProfile"
},
{
"type": "null"
}
],
"description": "Full permissions override for this thread. Cannot be combined with `sandbox`."
},
"personality": {
"anyOf": [
{
@@ -4234,17 +4086,6 @@
"outputSchema": {
"description": "Optional JSON Schema used to constrain the final assistant message for this turn."
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/PermissionProfile"
},
{
"type": "null"
}
],
"description": "Override the full permissions profile for this turn and subsequent turns. Cannot be combined with `sandboxPolicy`."
},
"personality": {
"anyOf": [
{

View File

@@ -392,21 +392,6 @@
"title": "MinimalFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
"enum": [
"current_working_directory"
],
"type": "string"
}
},
"required": [
"kind"
],
"title": "CurrentWorkingDirectoryFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {

View File

@@ -177,21 +177,6 @@
"title": "MinimalFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
"enum": [
"current_working_directory"
],
"type": "string"
}
},
"required": [
"kind"
],
"title": "CurrentWorkingDirectoryFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {

View File

@@ -177,21 +177,6 @@
"title": "MinimalFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
"enum": [
"current_working_directory"
],
"type": "string"
}
},
"required": [
"kind"
],
"title": "CurrentWorkingDirectoryFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {

View File

@@ -1199,21 +1199,6 @@
"title": "MinimalFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
"enum": [
"current_working_directory"
],
"type": "string"
}
},
"required": [
"kind"
],
"title": "CurrentWorkingDirectoryFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
@@ -3028,6 +3013,93 @@
],
"type": "object"
},
"ThreadGoal": {
"properties": {
"createdAt": {
"format": "int64",
"type": "integer"
},
"objective": {
"type": "string"
},
"status": {
"$ref": "#/definitions/ThreadGoalStatus"
},
"threadId": {
"type": "string"
},
"timeUsedSeconds": {
"format": "int64",
"type": "integer"
},
"tokenBudget": {
"format": "int64",
"type": [
"integer",
"null"
]
},
"tokensUsed": {
"format": "int64",
"type": "integer"
},
"updatedAt": {
"format": "int64",
"type": "integer"
}
},
"required": [
"createdAt",
"objective",
"status",
"threadId",
"timeUsedSeconds",
"tokensUsed",
"updatedAt"
],
"type": "object"
},
"ThreadGoalClearedNotification": {
"properties": {
"threadId": {
"type": "string"
}
},
"required": [
"threadId"
],
"type": "object"
},
"ThreadGoalStatus": {
"enum": [
"active",
"paused",
"budgetLimited",
"complete"
],
"type": "string"
},
"ThreadGoalUpdatedNotification": {
"properties": {
"goal": {
"$ref": "#/definitions/ThreadGoal"
},
"threadId": {
"type": "string"
},
"turnId": {
"type": [
"string",
"null"
]
}
},
"required": [
"goal",
"threadId"
],
"type": "object"
},
"ThreadId": {
"type": "string"
},
@@ -4727,6 +4799,46 @@
"title": "Thread/name/updatedNotification",
"type": "object"
},
{
"properties": {
"method": {
"enum": [
"thread/goal/updated"
],
"title": "Thread/goal/updatedNotificationMethod",
"type": "string"
},
"params": {
"$ref": "#/definitions/ThreadGoalUpdatedNotification"
}
},
"required": [
"method",
"params"
],
"title": "Thread/goal/updatedNotification",
"type": "object"
},
{
"properties": {
"method": {
"enum": [
"thread/goal/cleared"
],
"title": "Thread/goal/clearedNotificationMethod",
"type": "string"
},
"params": {
"$ref": "#/definitions/ThreadGoalClearedNotification"
}
},
"required": [
"method",
"params"
],
"title": "Thread/goal/clearedNotification",
"type": "object"
},
{
"properties": {
"method": {

View File

@@ -731,21 +731,6 @@
"title": "MinimalFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
"enum": [
"current_working_directory"
],
"type": "string"
}
},
"required": [
"kind"
],
"title": "CurrentWorkingDirectoryFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {

View File

@@ -3806,6 +3806,46 @@
"title": "Thread/name/updatedNotification",
"type": "object"
},
{
"properties": {
"method": {
"enum": [
"thread/goal/updated"
],
"title": "Thread/goal/updatedNotificationMethod",
"type": "string"
},
"params": {
"$ref": "#/definitions/v2/ThreadGoalUpdatedNotification"
}
},
"required": [
"method",
"params"
],
"title": "Thread/goal/updatedNotification",
"type": "object"
},
{
"properties": {
"method": {
"enum": [
"thread/goal/cleared"
],
"title": "Thread/goal/clearedNotificationMethod",
"type": "string"
},
"params": {
"$ref": "#/definitions/v2/ThreadGoalClearedNotification"
}
},
"required": [
"method",
"params"
],
"title": "Thread/goal/clearedNotification",
"type": "object"
},
{
"properties": {
"method": {
@@ -6496,17 +6536,6 @@
"null"
]
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/v2/PermissionProfile"
},
{
"type": "null"
}
],
"description": "Optional full permissions profile for this command.\n\nDefaults to the user's configured permissions when omitted. Cannot be combined with `sandboxPolicy`."
},
"processId": {
"description": "Optional client-supplied, connection-scoped process id.\n\nRequired for `tty`, `streamStdin`, `streamStdoutStderr`, and follow-up `command/exec/write`, `command/exec/resize`, and `command/exec/terminate` calls. When omitted, buffered execution gets an internal id that is not exposed to the client.",
"type": [
@@ -8297,7 +8326,8 @@
"CONFIG",
"SKILLS",
"PLUGINS",
"MCP_SERVER_CONFIG"
"MCP_SERVER_CONFIG",
"SESSIONS"
],
"type": "string"
},
@@ -8533,21 +8563,6 @@
"title": "MinimalFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
"enum": [
"current_working_directory"
],
"type": "string"
}
},
"required": [
"kind"
],
"title": "CurrentWorkingDirectoryFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
@@ -9158,38 +9173,6 @@
"title": "GetAccountResponse",
"type": "object"
},
"GhostCommit": {
"description": "Details of a ghost commit created from a repository state.",
"properties": {
"id": {
"type": "string"
},
"parent": {
"type": [
"string",
"null"
]
},
"preexisting_untracked_dirs": {
"items": {
"type": "string"
},
"type": "array"
},
"preexisting_untracked_files": {
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"id",
"preexisting_untracked_dirs",
"preexisting_untracked_files"
],
"type": "object"
},
"GitInfo": {
"properties": {
"branch": {
@@ -10790,15 +10773,20 @@
"MigrationDetails": {
"properties": {
"plugins": {
"default": [],
"items": {
"$ref": "#/definitions/v2/PluginsMigration"
},
"type": "array"
},
"sessions": {
"default": [],
"items": {
"$ref": "#/definitions/v2/SessionMigration"
},
"type": "array"
}
},
"required": [
"plugins"
],
"type": "object"
},
"ModeKind": {
@@ -12228,53 +12216,6 @@
"title": "RawResponseItemCompletedNotification",
"type": "object"
},
"ReadOnlyAccess": {
"oneOf": [
{
"properties": {
"includePlatformDefaults": {
"default": true,
"type": "boolean"
},
"readableRoots": {
"default": [],
"items": {
"$ref": "#/definitions/v2/AbsolutePathBuf"
},
"type": "array"
},
"type": {
"enum": [
"restricted"
],
"title": "RestrictedReadOnlyAccessType",
"type": "string"
}
},
"required": [
"type"
],
"title": "RestrictedReadOnlyAccess",
"type": "object"
},
{
"properties": {
"type": {
"enum": [
"fullAccess"
],
"title": "FullAccessReadOnlyAccessType",
"type": "string"
}
},
"required": [
"type"
],
"title": "FullAccessReadOnlyAccess",
"type": "object"
}
]
},
"RealtimeConversationVersion": {
"enum": [
"v1",
@@ -12746,12 +12687,6 @@
},
"type": "array"
},
"end_turn": {
"type": [
"boolean",
"null"
]
},
"id": {
"type": [
"string",
@@ -13151,26 +13086,6 @@
"title": "ImageGenerationCallResponseItem",
"type": "object"
},
{
"properties": {
"ghost_commit": {
"$ref": "#/definitions/v2/GhostCommit"
},
"type": {
"enum": [
"ghost_snapshot"
],
"title": "GhostSnapshotResponseItemType",
"type": "string"
}
},
"required": [
"ghost_commit",
"type"
],
"title": "GhostSnapshotResponseItem",
"type": "object"
},
{
"properties": {
"encrypted_content": {
@@ -13483,16 +13398,6 @@
},
{
"properties": {
"access": {
"allOf": [
{
"$ref": "#/definitions/v2/ReadOnlyAccess"
}
],
"default": {
"type": "fullAccess"
}
},
"networkAccess": {
"default": false,
"type": "boolean"
@@ -13549,16 +13454,6 @@
"default": false,
"type": "boolean"
},
"readOnlyAccess": {
"allOf": [
{
"$ref": "#/definitions/v2/ReadOnlyAccess"
}
],
"default": {
"type": "fullAccess"
}
},
"type": {
"enum": [
"workspaceWrite"
@@ -13656,6 +13551,27 @@
],
"type": "string"
},
"SessionMigration": {
"properties": {
"cwd": {
"type": "string"
},
"path": {
"type": "string"
},
"title": {
"type": [
"string",
"null"
]
}
},
"required": [
"cwd",
"path"
],
"type": "object"
},
"SessionSource": {
"oneOf": [
{
@@ -14543,17 +14459,6 @@
"null"
]
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/v2/PermissionProfile"
},
{
"type": "null"
}
],
"description": "Full permissions override for the forked thread. Cannot be combined with `sandbox`."
},
"sandbox": {
"anyOf": [
{
@@ -14622,18 +14527,6 @@
"modelProvider": {
"type": "string"
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/v2/PermissionProfile"
},
{
"type": "null"
}
],
"default": null,
"description": "Canonical active permissions view for this thread."
},
"reasoningEffort": {
"anyOf": [
{
@@ -14678,6 +14571,97 @@
"title": "ThreadForkResponse",
"type": "object"
},
"ThreadGoal": {
"properties": {
"createdAt": {
"format": "int64",
"type": "integer"
},
"objective": {
"type": "string"
},
"status": {
"$ref": "#/definitions/v2/ThreadGoalStatus"
},
"threadId": {
"type": "string"
},
"timeUsedSeconds": {
"format": "int64",
"type": "integer"
},
"tokenBudget": {
"format": "int64",
"type": [
"integer",
"null"
]
},
"tokensUsed": {
"format": "int64",
"type": "integer"
},
"updatedAt": {
"format": "int64",
"type": "integer"
}
},
"required": [
"createdAt",
"objective",
"status",
"threadId",
"timeUsedSeconds",
"tokensUsed",
"updatedAt"
],
"type": "object"
},
"ThreadGoalClearedNotification": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"threadId": {
"type": "string"
}
},
"required": [
"threadId"
],
"title": "ThreadGoalClearedNotification",
"type": "object"
},
"ThreadGoalStatus": {
"enum": [
"active",
"paused",
"budgetLimited",
"complete"
],
"type": "string"
},
"ThreadGoalUpdatedNotification": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"goal": {
"$ref": "#/definitions/v2/ThreadGoal"
},
"threadId": {
"type": "string"
},
"turnId": {
"type": [
"string",
"null"
]
}
},
"required": [
"goal",
"threadId"
],
"title": "ThreadGoalUpdatedNotification",
"type": "object"
},
"ThreadId": {
"type": "string"
},
@@ -15976,17 +15960,6 @@
"null"
]
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/v2/PermissionProfile"
},
{
"type": "null"
}
],
"description": "Full permissions override for the resumed thread. Cannot be combined with `sandbox`."
},
"personality": {
"anyOf": [
{
@@ -16065,18 +16038,6 @@
"modelProvider": {
"type": "string"
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/v2/PermissionProfile"
},
{
"type": "null"
}
],
"default": null,
"description": "Canonical active permissions view for this thread."
},
"reasoningEffort": {
"anyOf": [
{
@@ -16293,17 +16254,6 @@
"null"
]
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/v2/PermissionProfile"
},
{
"type": "null"
}
],
"description": "Full permissions override for this thread. Cannot be combined with `sandbox`."
},
"personality": {
"anyOf": [
{
@@ -16392,18 +16342,6 @@
"modelProvider": {
"type": "string"
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/v2/PermissionProfile"
},
{
"type": "null"
}
],
"default": null,
"description": "Canonical active permissions view for this thread."
},
"reasoningEffort": {
"anyOf": [
{
@@ -17109,17 +17047,6 @@
"outputSchema": {
"description": "Optional JSON Schema used to constrain the final assistant message for this turn."
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/v2/PermissionProfile"
},
{
"type": "null"
}
],
"description": "Override the full permissions profile for this turn and subsequent turns. Cannot be combined with `sandboxPolicy`."
},
"personality": {
"anyOf": [
{

View File

@@ -3055,17 +3055,6 @@
"null"
]
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/PermissionProfile"
},
{
"type": "null"
}
],
"description": "Optional full permissions profile for this command.\n\nDefaults to the user's configured permissions when omitted. Cannot be combined with `sandboxPolicy`."
},
"processId": {
"description": "Optional client-supplied, connection-scoped process id.\n\nRequired for `tty`, `streamStdin`, `streamStdoutStderr`, and follow-up `command/exec/write`, `command/exec/resize`, and `command/exec/terminate` calls. When omitted, buffered execution gets an internal id that is not exposed to the client.",
"type": [
@@ -4856,7 +4845,8 @@
"CONFIG",
"SKILLS",
"PLUGINS",
"MCP_SERVER_CONFIG"
"MCP_SERVER_CONFIG",
"SESSIONS"
],
"type": "string"
},
@@ -5092,21 +5082,6 @@
"title": "MinimalFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
"enum": [
"current_working_directory"
],
"type": "string"
}
},
"required": [
"kind"
],
"title": "CurrentWorkingDirectoryFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
@@ -5828,38 +5803,6 @@
"title": "GetAccountResponse",
"type": "object"
},
"GhostCommit": {
"description": "Details of a ghost commit created from a repository state.",
"properties": {
"id": {
"type": "string"
},
"parent": {
"type": [
"string",
"null"
]
},
"preexisting_untracked_dirs": {
"items": {
"type": "string"
},
"type": "array"
},
"preexisting_untracked_files": {
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"id",
"preexisting_untracked_dirs",
"preexisting_untracked_files"
],
"type": "object"
},
"GitInfo": {
"properties": {
"branch": {
@@ -7504,15 +7447,20 @@
"MigrationDetails": {
"properties": {
"plugins": {
"default": [],
"items": {
"$ref": "#/definitions/PluginsMigration"
},
"type": "array"
},
"sessions": {
"default": [],
"items": {
"$ref": "#/definitions/SessionMigration"
},
"type": "array"
}
},
"required": [
"plugins"
],
"type": "object"
},
"ModeKind": {
@@ -8942,53 +8890,6 @@
"title": "RawResponseItemCompletedNotification",
"type": "object"
},
"ReadOnlyAccess": {
"oneOf": [
{
"properties": {
"includePlatformDefaults": {
"default": true,
"type": "boolean"
},
"readableRoots": {
"default": [],
"items": {
"$ref": "#/definitions/AbsolutePathBuf"
},
"type": "array"
},
"type": {
"enum": [
"restricted"
],
"title": "RestrictedReadOnlyAccessType",
"type": "string"
}
},
"required": [
"type"
],
"title": "RestrictedReadOnlyAccess",
"type": "object"
},
{
"properties": {
"type": {
"enum": [
"fullAccess"
],
"title": "FullAccessReadOnlyAccessType",
"type": "string"
}
},
"required": [
"type"
],
"title": "FullAccessReadOnlyAccess",
"type": "object"
}
]
},
"RealtimeConversationVersion": {
"enum": [
"v1",
@@ -9460,12 +9361,6 @@
},
"type": "array"
},
"end_turn": {
"type": [
"boolean",
"null"
]
},
"id": {
"type": [
"string",
@@ -9865,26 +9760,6 @@
"title": "ImageGenerationCallResponseItem",
"type": "object"
},
{
"properties": {
"ghost_commit": {
"$ref": "#/definitions/GhostCommit"
},
"type": {
"enum": [
"ghost_snapshot"
],
"title": "GhostSnapshotResponseItemType",
"type": "string"
}
},
"required": [
"ghost_commit",
"type"
],
"title": "GhostSnapshotResponseItem",
"type": "object"
},
{
"properties": {
"encrypted_content": {
@@ -10197,16 +10072,6 @@
},
{
"properties": {
"access": {
"allOf": [
{
"$ref": "#/definitions/ReadOnlyAccess"
}
],
"default": {
"type": "fullAccess"
}
},
"networkAccess": {
"default": false,
"type": "boolean"
@@ -10263,16 +10128,6 @@
"default": false,
"type": "boolean"
},
"readOnlyAccess": {
"allOf": [
{
"$ref": "#/definitions/ReadOnlyAccess"
}
],
"default": {
"type": "fullAccess"
}
},
"type": {
"enum": [
"workspaceWrite"
@@ -10511,6 +10366,46 @@
"title": "Thread/name/updatedNotification",
"type": "object"
},
{
"properties": {
"method": {
"enum": [
"thread/goal/updated"
],
"title": "Thread/goal/updatedNotificationMethod",
"type": "string"
},
"params": {
"$ref": "#/definitions/ThreadGoalUpdatedNotification"
}
},
"required": [
"method",
"params"
],
"title": "Thread/goal/updatedNotification",
"type": "object"
},
{
"properties": {
"method": {
"enum": [
"thread/goal/cleared"
],
"title": "Thread/goal/clearedNotificationMethod",
"type": "string"
},
"params": {
"$ref": "#/definitions/ThreadGoalClearedNotification"
}
},
"required": [
"method",
"params"
],
"title": "Thread/goal/clearedNotification",
"type": "object"
},
{
"properties": {
"method": {
@@ -11542,6 +11437,27 @@
],
"type": "string"
},
"SessionMigration": {
"properties": {
"cwd": {
"type": "string"
},
"path": {
"type": "string"
},
"title": {
"type": [
"string",
"null"
]
}
},
"required": [
"cwd",
"path"
],
"type": "object"
},
"SessionSource": {
"oneOf": [
{
@@ -12429,17 +12345,6 @@
"null"
]
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/PermissionProfile"
},
{
"type": "null"
}
],
"description": "Full permissions override for the forked thread. Cannot be combined with `sandbox`."
},
"sandbox": {
"anyOf": [
{
@@ -12508,18 +12413,6 @@
"modelProvider": {
"type": "string"
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/PermissionProfile"
},
{
"type": "null"
}
],
"default": null,
"description": "Canonical active permissions view for this thread."
},
"reasoningEffort": {
"anyOf": [
{
@@ -12564,6 +12457,97 @@
"title": "ThreadForkResponse",
"type": "object"
},
"ThreadGoal": {
"properties": {
"createdAt": {
"format": "int64",
"type": "integer"
},
"objective": {
"type": "string"
},
"status": {
"$ref": "#/definitions/ThreadGoalStatus"
},
"threadId": {
"type": "string"
},
"timeUsedSeconds": {
"format": "int64",
"type": "integer"
},
"tokenBudget": {
"format": "int64",
"type": [
"integer",
"null"
]
},
"tokensUsed": {
"format": "int64",
"type": "integer"
},
"updatedAt": {
"format": "int64",
"type": "integer"
}
},
"required": [
"createdAt",
"objective",
"status",
"threadId",
"timeUsedSeconds",
"tokensUsed",
"updatedAt"
],
"type": "object"
},
"ThreadGoalClearedNotification": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"threadId": {
"type": "string"
}
},
"required": [
"threadId"
],
"title": "ThreadGoalClearedNotification",
"type": "object"
},
"ThreadGoalStatus": {
"enum": [
"active",
"paused",
"budgetLimited",
"complete"
],
"type": "string"
},
"ThreadGoalUpdatedNotification": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"goal": {
"$ref": "#/definitions/ThreadGoal"
},
"threadId": {
"type": "string"
},
"turnId": {
"type": [
"string",
"null"
]
}
},
"required": [
"goal",
"threadId"
],
"title": "ThreadGoalUpdatedNotification",
"type": "object"
},
"ThreadId": {
"type": "string"
},
@@ -13862,17 +13846,6 @@
"null"
]
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/PermissionProfile"
},
{
"type": "null"
}
],
"description": "Full permissions override for the resumed thread. Cannot be combined with `sandbox`."
},
"personality": {
"anyOf": [
{
@@ -13951,18 +13924,6 @@
"modelProvider": {
"type": "string"
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/PermissionProfile"
},
{
"type": "null"
}
],
"default": null,
"description": "Canonical active permissions view for this thread."
},
"reasoningEffort": {
"anyOf": [
{
@@ -14179,17 +14140,6 @@
"null"
]
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/PermissionProfile"
},
{
"type": "null"
}
],
"description": "Full permissions override for this thread. Cannot be combined with `sandbox`."
},
"personality": {
"anyOf": [
{
@@ -14278,18 +14228,6 @@
"modelProvider": {
"type": "string"
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/PermissionProfile"
},
{
"type": "null"
}
],
"default": null,
"description": "Canonical active permissions view for this thread."
},
"reasoningEffort": {
"anyOf": [
{
@@ -14995,17 +14933,6 @@
"outputSchema": {
"description": "Optional JSON Schema used to constrain the final assistant message for this turn."
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/PermissionProfile"
},
{
"type": "null"
}
],
"description": "Override the full permissions profile for this turn and subsequent turns. Cannot be combined with `sandboxPolicy`."
},
"personality": {
"anyOf": [
{

View File

@@ -146,21 +146,6 @@
"title": "MinimalFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
"enum": [
"current_working_directory"
],
"type": "string"
}
},
"required": [
"kind"
],
"title": "CurrentWorkingDirectoryFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
@@ -374,53 +359,6 @@
],
"type": "object"
},
"ReadOnlyAccess": {
"oneOf": [
{
"properties": {
"includePlatformDefaults": {
"default": true,
"type": "boolean"
},
"readableRoots": {
"default": [],
"items": {
"$ref": "#/definitions/AbsolutePathBuf"
},
"type": "array"
},
"type": {
"enum": [
"restricted"
],
"title": "RestrictedReadOnlyAccessType",
"type": "string"
}
},
"required": [
"type"
],
"title": "RestrictedReadOnlyAccess",
"type": "object"
},
{
"properties": {
"type": {
"enum": [
"fullAccess"
],
"title": "FullAccessReadOnlyAccessType",
"type": "string"
}
},
"required": [
"type"
],
"title": "FullAccessReadOnlyAccess",
"type": "object"
}
]
},
"SandboxPolicy": {
"oneOf": [
{
@@ -441,16 +379,6 @@
},
{
"properties": {
"access": {
"allOf": [
{
"$ref": "#/definitions/ReadOnlyAccess"
}
],
"default": {
"type": "fullAccess"
}
},
"networkAccess": {
"default": false,
"type": "boolean"
@@ -507,16 +435,6 @@
"default": false,
"type": "boolean"
},
"readOnlyAccess": {
"allOf": [
{
"$ref": "#/definitions/ReadOnlyAccess"
}
],
"default": {
"type": "fullAccess"
}
},
"type": {
"enum": [
"workspaceWrite"
@@ -587,17 +505,6 @@
"null"
]
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/PermissionProfile"
},
{
"type": "null"
}
],
"description": "Optional full permissions profile for this command.\n\nDefaults to the user's configured permissions when omitted. Cannot be combined with `sandboxPolicy`."
},
"processId": {
"description": "Optional client-supplied, connection-scoped process id.\n\nRequired for `tty`, `streamStdin`, `streamStdoutStderr`, and follow-up `command/exec/write`, `command/exec/resize`, and `command/exec/terminate` calls. When omitted, buffered execution gets an internal id that is not exposed to the client.",
"type": [

View File

@@ -39,22 +39,28 @@
"CONFIG",
"SKILLS",
"PLUGINS",
"MCP_SERVER_CONFIG"
"MCP_SERVER_CONFIG",
"SESSIONS"
],
"type": "string"
},
"MigrationDetails": {
"properties": {
"plugins": {
"default": [],
"items": {
"$ref": "#/definitions/PluginsMigration"
},
"type": "array"
},
"sessions": {
"default": [],
"items": {
"$ref": "#/definitions/SessionMigration"
},
"type": "array"
}
},
"required": [
"plugins"
],
"type": "object"
},
"PluginsMigration": {
@@ -74,6 +80,27 @@
"pluginNames"
],
"type": "object"
},
"SessionMigration": {
"properties": {
"cwd": {
"type": "string"
},
"path": {
"type": "string"
},
"title": {
"type": [
"string",
"null"
]
}
},
"required": [
"cwd",
"path"
],
"type": "object"
}
},
"properties": {

View File

@@ -39,22 +39,28 @@
"CONFIG",
"SKILLS",
"PLUGINS",
"MCP_SERVER_CONFIG"
"MCP_SERVER_CONFIG",
"SESSIONS"
],
"type": "string"
},
"MigrationDetails": {
"properties": {
"plugins": {
"default": [],
"items": {
"$ref": "#/definitions/PluginsMigration"
},
"type": "array"
},
"sessions": {
"default": [],
"items": {
"$ref": "#/definitions/SessionMigration"
},
"type": "array"
}
},
"required": [
"plugins"
],
"type": "object"
},
"PluginsMigration": {
@@ -74,6 +80,27 @@
"pluginNames"
],
"type": "object"
},
"SessionMigration": {
"properties": {
"cwd": {
"type": "string"
},
"path": {
"type": "string"
},
"title": {
"type": [
"string",
"null"
]
}
},
"required": [
"cwd",
"path"
],
"type": "object"
}
},
"properties": {

View File

@@ -184,21 +184,6 @@
"title": "MinimalFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
"enum": [
"current_working_directory"
],
"type": "string"
}
},
"required": [
"kind"
],
"title": "CurrentWorkingDirectoryFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {

View File

@@ -177,21 +177,6 @@
"title": "MinimalFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
"enum": [
"current_working_directory"
],
"type": "string"
}
},
"required": [
"kind"
],
"title": "CurrentWorkingDirectoryFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {

View File

@@ -143,38 +143,6 @@
}
]
},
"GhostCommit": {
"description": "Details of a ghost commit created from a repository state.",
"properties": {
"id": {
"type": "string"
},
"parent": {
"type": [
"string",
"null"
]
},
"preexisting_untracked_dirs": {
"items": {
"type": "string"
},
"type": "array"
},
"preexisting_untracked_files": {
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"id",
"preexisting_untracked_dirs",
"preexisting_untracked_files"
],
"type": "object"
},
"ImageDetail": {
"enum": [
"auto",
@@ -345,12 +313,6 @@
},
"type": "array"
},
"end_turn": {
"type": [
"boolean",
"null"
]
},
"id": {
"type": [
"string",
@@ -750,26 +712,6 @@
"title": "ImageGenerationCallResponseItem",
"type": "object"
},
{
"properties": {
"ghost_commit": {
"$ref": "#/definitions/GhostCommit"
},
"type": {
"enum": [
"ghost_snapshot"
],
"title": "GhostSnapshotResponseItemType",
"type": "string"
}
},
"required": [
"ghost_commit",
"type"
],
"title": "GhostSnapshotResponseItem",
"type": "object"
},
{
"properties": {
"encrypted_content": {

View File

@@ -183,21 +183,6 @@
"title": "MinimalFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
"enum": [
"current_working_directory"
],
"type": "string"
}
},
"required": [
"kind"
],
"title": "CurrentWorkingDirectoryFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
@@ -488,17 +473,6 @@
"null"
]
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/PermissionProfile"
},
{
"type": "null"
}
],
"description": "Full permissions override for the forked thread. Cannot be combined with `sandbox`."
},
"sandbox": {
"anyOf": [
{

View File

@@ -569,21 +569,6 @@
"title": "MinimalFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
"enum": [
"current_working_directory"
],
"type": "string"
}
},
"required": [
"kind"
],
"title": "CurrentWorkingDirectoryFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
@@ -1028,53 +1013,6 @@
],
"type": "object"
},
"ReadOnlyAccess": {
"oneOf": [
{
"properties": {
"includePlatformDefaults": {
"default": true,
"type": "boolean"
},
"readableRoots": {
"default": [],
"items": {
"$ref": "#/definitions/AbsolutePathBuf"
},
"type": "array"
},
"type": {
"enum": [
"restricted"
],
"title": "RestrictedReadOnlyAccessType",
"type": "string"
}
},
"required": [
"type"
],
"title": "RestrictedReadOnlyAccess",
"type": "object"
},
{
"properties": {
"type": {
"enum": [
"fullAccess"
],
"title": "FullAccessReadOnlyAccessType",
"type": "string"
}
},
"required": [
"type"
],
"title": "FullAccessReadOnlyAccess",
"type": "object"
}
]
},
"ReasoningEffort": {
"description": "See https://platform.openai.com/docs/guides/reasoning?api-mode=responses#get-started-with-reasoning",
"enum": [
@@ -1107,16 +1045,6 @@
},
{
"properties": {
"access": {
"allOf": [
{
"$ref": "#/definitions/ReadOnlyAccess"
}
],
"default": {
"type": "fullAccess"
}
},
"networkAccess": {
"default": false,
"type": "boolean"
@@ -1173,16 +1101,6 @@
"default": false,
"type": "boolean"
},
"readOnlyAccess": {
"allOf": [
{
"$ref": "#/definitions/ReadOnlyAccess"
}
],
"default": {
"type": "fullAccess"
}
},
"type": {
"enum": [
"workspaceWrite"
@@ -2567,18 +2485,6 @@
"modelProvider": {
"type": "string"
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/PermissionProfile"
},
{
"type": "null"
}
],
"default": null,
"description": "Canonical active permissions view for this thread."
},
"reasoningEffort": {
"anyOf": [
{

View File

@@ -0,0 +1,13 @@
{
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"threadId": {
"type": "string"
}
},
"required": [
"threadId"
],
"title": "ThreadGoalClearedNotification",
"type": "object"
}

View File

@@ -0,0 +1,80 @@
{
"$schema": "http://json-schema.org/draft-07/schema#",
"definitions": {
"ThreadGoal": {
"properties": {
"createdAt": {
"format": "int64",
"type": "integer"
},
"objective": {
"type": "string"
},
"status": {
"$ref": "#/definitions/ThreadGoalStatus"
},
"threadId": {
"type": "string"
},
"timeUsedSeconds": {
"format": "int64",
"type": "integer"
},
"tokenBudget": {
"format": "int64",
"type": [
"integer",
"null"
]
},
"tokensUsed": {
"format": "int64",
"type": "integer"
},
"updatedAt": {
"format": "int64",
"type": "integer"
}
},
"required": [
"createdAt",
"objective",
"status",
"threadId",
"timeUsedSeconds",
"tokensUsed",
"updatedAt"
],
"type": "object"
},
"ThreadGoalStatus": {
"enum": [
"active",
"paused",
"budgetLimited",
"complete"
],
"type": "string"
}
},
"properties": {
"goal": {
"$ref": "#/definitions/ThreadGoal"
},
"threadId": {
"type": "string"
},
"turnId": {
"type": [
"string",
"null"
]
}
},
"required": [
"goal",
"threadId"
],
"title": "ThreadGoalUpdatedNotification",
"type": "object"
}

View File

@@ -257,21 +257,6 @@
"title": "MinimalFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
"enum": [
"current_working_directory"
],
"type": "string"
}
},
"required": [
"kind"
],
"title": "CurrentWorkingDirectoryFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
@@ -417,38 +402,6 @@
}
]
},
"GhostCommit": {
"description": "Details of a ghost commit created from a repository state.",
"properties": {
"id": {
"type": "string"
},
"parent": {
"type": [
"string",
"null"
]
},
"preexisting_untracked_dirs": {
"items": {
"type": "string"
},
"type": "array"
},
"preexisting_untracked_files": {
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"id",
"preexisting_untracked_dirs",
"preexisting_untracked_files"
],
"type": "object"
},
"ImageDetail": {
"enum": [
"auto",
@@ -756,12 +709,6 @@
},
"type": "array"
},
"end_turn": {
"type": [
"boolean",
"null"
]
},
"id": {
"type": [
"string",
@@ -1161,26 +1108,6 @@
"title": "ImageGenerationCallResponseItem",
"type": "object"
},
{
"properties": {
"ghost_commit": {
"$ref": "#/definitions/GhostCommit"
},
"type": {
"enum": [
"ghost_snapshot"
],
"title": "GhostSnapshotResponseItemType",
"type": "string"
}
},
"required": [
"ghost_commit",
"type"
],
"title": "GhostSnapshotResponseItem",
"type": "object"
},
{
"properties": {
"encrypted_content": {
@@ -1401,17 +1328,6 @@
"null"
]
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/PermissionProfile"
},
{
"type": "null"
}
],
"description": "Full permissions override for the resumed thread. Cannot be combined with `sandbox`."
},
"personality": {
"anyOf": [
{

View File

@@ -569,21 +569,6 @@
"title": "MinimalFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
"enum": [
"current_working_directory"
],
"type": "string"
}
},
"required": [
"kind"
],
"title": "CurrentWorkingDirectoryFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
@@ -1028,53 +1013,6 @@
],
"type": "object"
},
"ReadOnlyAccess": {
"oneOf": [
{
"properties": {
"includePlatformDefaults": {
"default": true,
"type": "boolean"
},
"readableRoots": {
"default": [],
"items": {
"$ref": "#/definitions/AbsolutePathBuf"
},
"type": "array"
},
"type": {
"enum": [
"restricted"
],
"title": "RestrictedReadOnlyAccessType",
"type": "string"
}
},
"required": [
"type"
],
"title": "RestrictedReadOnlyAccess",
"type": "object"
},
{
"properties": {
"type": {
"enum": [
"fullAccess"
],
"title": "FullAccessReadOnlyAccessType",
"type": "string"
}
},
"required": [
"type"
],
"title": "FullAccessReadOnlyAccess",
"type": "object"
}
]
},
"ReasoningEffort": {
"description": "See https://platform.openai.com/docs/guides/reasoning?api-mode=responses#get-started-with-reasoning",
"enum": [
@@ -1107,16 +1045,6 @@
},
{
"properties": {
"access": {
"allOf": [
{
"$ref": "#/definitions/ReadOnlyAccess"
}
],
"default": {
"type": "fullAccess"
}
},
"networkAccess": {
"default": false,
"type": "boolean"
@@ -1173,16 +1101,6 @@
"default": false,
"type": "boolean"
},
"readOnlyAccess": {
"allOf": [
{
"$ref": "#/definitions/ReadOnlyAccess"
}
],
"default": {
"type": "fullAccess"
}
},
"type": {
"enum": [
"workspaceWrite"
@@ -2567,18 +2485,6 @@
"modelProvider": {
"type": "string"
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/PermissionProfile"
},
{
"type": "null"
}
],
"default": null,
"description": "Canonical active permissions view for this thread."
},
"reasoningEffort": {
"anyOf": [
{

View File

@@ -209,21 +209,6 @@
"title": "MinimalFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
"enum": [
"current_working_directory"
],
"type": "string"
}
},
"required": [
"kind"
],
"title": "CurrentWorkingDirectoryFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
@@ -541,17 +526,6 @@
"null"
]
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/PermissionProfile"
},
{
"type": "null"
}
],
"description": "Full permissions override for this thread. Cannot be combined with `sandbox`."
},
"personality": {
"anyOf": [
{

View File

@@ -569,21 +569,6 @@
"title": "MinimalFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
"enum": [
"current_working_directory"
],
"type": "string"
}
},
"required": [
"kind"
],
"title": "CurrentWorkingDirectoryFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
@@ -1028,53 +1013,6 @@
],
"type": "object"
},
"ReadOnlyAccess": {
"oneOf": [
{
"properties": {
"includePlatformDefaults": {
"default": true,
"type": "boolean"
},
"readableRoots": {
"default": [],
"items": {
"$ref": "#/definitions/AbsolutePathBuf"
},
"type": "array"
},
"type": {
"enum": [
"restricted"
],
"title": "RestrictedReadOnlyAccessType",
"type": "string"
}
},
"required": [
"type"
],
"title": "RestrictedReadOnlyAccess",
"type": "object"
},
{
"properties": {
"type": {
"enum": [
"fullAccess"
],
"title": "FullAccessReadOnlyAccessType",
"type": "string"
}
},
"required": [
"type"
],
"title": "FullAccessReadOnlyAccess",
"type": "object"
}
]
},
"ReasoningEffort": {
"description": "See https://platform.openai.com/docs/guides/reasoning?api-mode=responses#get-started-with-reasoning",
"enum": [
@@ -1107,16 +1045,6 @@
},
{
"properties": {
"access": {
"allOf": [
{
"$ref": "#/definitions/ReadOnlyAccess"
}
],
"default": {
"type": "fullAccess"
}
},
"networkAccess": {
"default": false,
"type": "boolean"
@@ -1173,16 +1101,6 @@
"default": false,
"type": "boolean"
},
"readOnlyAccess": {
"allOf": [
{
"$ref": "#/definitions/ReadOnlyAccess"
}
],
"default": {
"type": "fullAccess"
}
},
"type": {
"enum": [
"workspaceWrite"
@@ -2567,18 +2485,6 @@
"modelProvider": {
"type": "string"
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/PermissionProfile"
},
{
"type": "null"
}
],
"default": null,
"description": "Canonical active permissions view for this thread."
},
"reasoningEffort": {
"anyOf": [
{

View File

@@ -218,21 +218,6 @@
"title": "MinimalFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
"enum": [
"current_working_directory"
],
"type": "string"
}
},
"required": [
"kind"
],
"title": "CurrentWorkingDirectoryFileSystemSpecialPath",
"type": "object"
},
{
"properties": {
"kind": {
@@ -462,53 +447,6 @@
],
"type": "string"
},
"ReadOnlyAccess": {
"oneOf": [
{
"properties": {
"includePlatformDefaults": {
"default": true,
"type": "boolean"
},
"readableRoots": {
"default": [],
"items": {
"$ref": "#/definitions/AbsolutePathBuf"
},
"type": "array"
},
"type": {
"enum": [
"restricted"
],
"title": "RestrictedReadOnlyAccessType",
"type": "string"
}
},
"required": [
"type"
],
"title": "RestrictedReadOnlyAccess",
"type": "object"
},
{
"properties": {
"type": {
"enum": [
"fullAccess"
],
"title": "FullAccessReadOnlyAccessType",
"type": "string"
}
},
"required": [
"type"
],
"title": "FullAccessReadOnlyAccess",
"type": "object"
}
]
},
"ReasoningEffort": {
"description": "See https://platform.openai.com/docs/guides/reasoning?api-mode=responses#get-started-with-reasoning",
"enum": [
@@ -561,16 +499,6 @@
},
{
"properties": {
"access": {
"allOf": [
{
"$ref": "#/definitions/ReadOnlyAccess"
}
],
"default": {
"type": "fullAccess"
}
},
"networkAccess": {
"default": false,
"type": "boolean"
@@ -627,16 +555,6 @@
"default": false,
"type": "boolean"
},
"readOnlyAccess": {
"allOf": [
{
"$ref": "#/definitions/ReadOnlyAccess"
}
],
"default": {
"type": "fullAccess"
}
},
"type": {
"enum": [
"workspaceWrite"
@@ -911,17 +829,6 @@
"outputSchema": {
"description": "Optional JSON Schema used to constrain the final assistant message for this turn."
},
"permissionProfile": {
"anyOf": [
{
"$ref": "#/definitions/PermissionProfile"
},
{
"type": "null"
}
],
"description": "Override the full permissions profile for this turn and subsequent turns. Cannot be combined with `sandboxPolicy`."
},
"personality": {
"anyOf": [
{

View File

@@ -1,8 +0,0 @@
// GENERATED CODE! DO NOT MODIFY BY HAND!
// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
/**
* Details of a ghost commit created from a repository state.
*/
export type GhostCommit = { id: string, parent: string | null, preexisting_untracked_files: Array<string>, preexisting_untracked_dirs: Array<string>, };

View File

@@ -0,0 +1,5 @@
// GENERATED CODE! DO NOT MODIFY BY HAND!
// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
export type InternalSessionSource = "memory_consolidation";

View File

@@ -3,7 +3,6 @@
// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
import type { ContentItem } from "./ContentItem";
import type { FunctionCallOutputBody } from "./FunctionCallOutputBody";
import type { GhostCommit } from "./GhostCommit";
import type { LocalShellAction } from "./LocalShellAction";
import type { LocalShellStatus } from "./LocalShellStatus";
import type { MessagePhase } from "./MessagePhase";
@@ -11,8 +10,8 @@ import type { ReasoningItemContent } from "./ReasoningItemContent";
import type { ReasoningItemReasoningSummary } from "./ReasoningItemReasoningSummary";
import type { WebSearchAction } from "./WebSearchAction";
export type ResponseItem = { "type": "message", role: string, content: Array<ContentItem>, end_turn?: boolean, phase?: MessagePhase, } | { "type": "reasoning", summary: Array<ReasoningItemReasoningSummary>, content?: Array<ReasoningItemContent>, encrypted_content: string | null, } | { "type": "local_shell_call",
export type ResponseItem = { "type": "message", role: string, content: Array<ContentItem>, phase?: MessagePhase, } | { "type": "reasoning", summary: Array<ReasoningItemReasoningSummary>, content?: Array<ReasoningItemContent>, encrypted_content: string | null, } | { "type": "local_shell_call",
/**
* Set when using the Responses API.
*/
call_id: string | null, status: LocalShellStatus, action: LocalShellAction, } | { "type": "function_call", name: string, namespace?: string, arguments: string, call_id: string, } | { "type": "tool_search_call", call_id: string | null, status?: string, execution: string, arguments: unknown, } | { "type": "function_call_output", call_id: string, output: FunctionCallOutputBody, } | { "type": "custom_tool_call", status?: string, call_id: string, name: string, input: string, } | { "type": "custom_tool_call_output", call_id: string, name?: string, output: FunctionCallOutputBody, } | { "type": "tool_search_output", call_id: string | null, status: string, execution: string, tools: unknown[], } | { "type": "web_search_call", status?: string, action?: WebSearchAction, } | { "type": "image_generation_call", id: string, status: string, revised_prompt?: string, result: string, } | { "type": "ghost_snapshot", ghost_commit: GhostCommit, } | { "type": "compaction", encrypted_content: string, } | { "type": "other" };
call_id: string | null, status: LocalShellStatus, action: LocalShellAction, } | { "type": "function_call", name: string, namespace?: string, arguments: string, call_id: string, } | { "type": "tool_search_call", call_id: string | null, status?: string, execution: string, arguments: unknown, } | { "type": "function_call_output", call_id: string, output: FunctionCallOutputBody, } | { "type": "custom_tool_call", status?: string, call_id: string, name: string, input: string, } | { "type": "custom_tool_call_output", call_id: string, name?: string, output: FunctionCallOutputBody, } | { "type": "tool_search_output", call_id: string | null, status: string, execution: string, tools: unknown[], } | { "type": "web_search_call", status?: string, action?: WebSearchAction, } | { "type": "image_generation_call", id: string, status: string, revised_prompt?: string, result: string, } | { "type": "compaction", encrypted_content: string, } | { "type": "other" };

File diff suppressed because one or more lines are too long

View File

@@ -1,6 +1,7 @@
// GENERATED CODE! DO NOT MODIFY BY HAND!
// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
import type { InternalSessionSource } from "./InternalSessionSource";
import type { SubAgentSource } from "./SubAgentSource";
export type SessionSource = "cli" | "vscode" | "exec" | "mcp" | { "custom": string } | { "subagent": SubAgentSource } | "unknown";
export type SessionSource = "cli" | "vscode" | "exec" | "mcp" | { "custom": string } | { "internal": InternalSessionSource } | { "subagent": SubAgentSource } | "unknown";

View File

@@ -29,7 +29,6 @@ export type { GetAuthStatusParams } from "./GetAuthStatusParams";
export type { GetAuthStatusResponse } from "./GetAuthStatusResponse";
export type { GetConversationSummaryParams } from "./GetConversationSummaryParams";
export type { GetConversationSummaryResponse } from "./GetConversationSummaryResponse";
export type { GhostCommit } from "./GhostCommit";
export type { GitDiffToRemoteParams } from "./GitDiffToRemoteParams";
export type { GitDiffToRemoteResponse } from "./GitDiffToRemoteResponse";
export type { GitSha } from "./GitSha";
@@ -38,6 +37,7 @@ export type { InitializeCapabilities } from "./InitializeCapabilities";
export type { InitializeParams } from "./InitializeParams";
export type { InitializeResponse } from "./InitializeResponse";
export type { InputModality } from "./InputModality";
export type { InternalSessionSource } from "./InternalSessionSource";
export type { LocalShellAction } from "./LocalShellAction";
export type { LocalShellExecAction } from "./LocalShellExecAction";
export type { LocalShellStatus } from "./LocalShellStatus";

View File

@@ -2,7 +2,6 @@
// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
import type { CommandExecTerminalSize } from "./CommandExecTerminalSize";
import type { PermissionProfile } from "./PermissionProfile";
import type { SandboxPolicy } from "./SandboxPolicy";
/**
@@ -13,12 +12,10 @@ import type { SandboxPolicy } from "./SandboxPolicy";
* sent only after all `command/exec/outputDelta` notifications for that
* connection have been emitted.
*/
export type CommandExecParams = {
/**
export type CommandExecParams = {/**
* Command argv vector. Empty arrays are rejected.
*/
command: Array<string>,
/**
command: Array<string>, /**
* Optional client-supplied, connection-scoped process id.
*
* Required for `tty`, `streamStdin`, `streamStdoutStderr`, and follow-up
@@ -26,81 +23,63 @@ command: Array<string>,
* `command/exec/terminate` calls. When omitted, buffered execution gets an
* internal id that is not exposed to the client.
*/
processId?: string | null,
/**
processId?: string | null, /**
* Enable PTY mode.
*
* This implies `streamStdin` and `streamStdoutStderr`.
*/
tty?: boolean,
/**
tty?: boolean, /**
* Allow follow-up `command/exec/write` requests to write stdin bytes.
*
* Requires a client-supplied `processId`.
*/
streamStdin?: boolean,
/**
streamStdin?: boolean, /**
* Stream stdout/stderr via `command/exec/outputDelta` notifications.
*
* Streamed bytes are not duplicated into the final response and require a
* client-supplied `processId`.
*/
streamStdoutStderr?: boolean,
/**
streamStdoutStderr?: boolean, /**
* Optional per-stream stdout/stderr capture cap in bytes.
*
* When omitted, the server default applies. Cannot be combined with
* `disableOutputCap`.
*/
outputBytesCap?: number | null,
/**
outputBytesCap?: number | null, /**
* Disable stdout/stderr capture truncation for this request.
*
* Cannot be combined with `outputBytesCap`.
*/
disableOutputCap?: boolean,
/**
disableOutputCap?: boolean, /**
* Disable the timeout entirely for this request.
*
* Cannot be combined with `timeoutMs`.
*/
disableTimeout?: boolean,
/**
disableTimeout?: boolean, /**
* Optional timeout in milliseconds.
*
* When omitted, the server default applies. Cannot be combined with
* `disableTimeout`.
*/
timeoutMs?: number | null,
/**
timeoutMs?: number | null, /**
* Optional working directory. Defaults to the server cwd.
*/
cwd?: string | null,
/**
cwd?: string | null, /**
* Optional environment overrides merged into the server-computed
* environment.
*
* Matching names override inherited values. Set a key to `null` to unset
* an inherited variable.
*/
env?: { [key in string]?: string | null } | null,
/**
env?: { [key in string]?: string | null } | null, /**
* Optional initial PTY size in character cells. Only valid when `tty` is
* true.
*/
size?: CommandExecTerminalSize | null,
/**
size?: CommandExecTerminalSize | null, /**
* Optional sandbox policy for this command.
*
* Uses the same shape as thread/turn execution sandbox configuration and
* defaults to the user's configured policy when omitted. Cannot be
* combined with `permissionProfile`.
*/
sandboxPolicy?: SandboxPolicy | null,
/**
* Optional full permissions profile for this command.
*
* Defaults to the user's configured permissions when omitted. Cannot be
* combined with `sandboxPolicy`.
*/
permissionProfile?: PermissionProfile | null, };
sandboxPolicy?: SandboxPolicy | null};

View File

@@ -2,15 +2,12 @@
// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
import type { AbsolutePathBuf } from "../AbsolutePathBuf";
import type { AdditionalPermissionProfile } from "./AdditionalPermissionProfile";
import type { CommandAction } from "./CommandAction";
import type { CommandExecutionApprovalDecision } from "./CommandExecutionApprovalDecision";
import type { ExecPolicyAmendment } from "./ExecPolicyAmendment";
import type { NetworkApprovalContext } from "./NetworkApprovalContext";
import type { NetworkPolicyAmendment } from "./NetworkPolicyAmendment";
export type CommandExecutionRequestApprovalParams = { threadId: string, turnId: string, itemId: string,
/**
export type CommandExecutionRequestApprovalParams = {threadId: string, turnId: string, itemId: string, /**
* Unique identifier for this specific approval callback.
*
* For regular shell/unified_exec approvals, this is null.
@@ -19,40 +16,25 @@ export type CommandExecutionRequestApprovalParams = { threadId: string, turnId:
* one parent `itemId`, so `approvalId` is a distinct opaque callback id
* (a UUID) used to disambiguate routing.
*/
approvalId?: string | null,
/**
approvalId?: string | null, /**
* Optional explanatory reason (e.g. request for network access).
*/
reason?: string | null,
/**
reason?: string | null, /**
* Optional context for a managed-network approval prompt.
*/
networkApprovalContext?: NetworkApprovalContext | null,
/**
networkApprovalContext?: NetworkApprovalContext | null, /**
* The command to be executed.
*/
command?: string | null,
/**
command?: string | null, /**
* The command's working directory.
*/
cwd?: AbsolutePathBuf | null,
/**
cwd?: AbsolutePathBuf | null, /**
* Best-effort parsed command actions for friendly display.
*/
commandActions?: Array<CommandAction> | null,
/**
* Optional additional permissions requested for this command.
*/
additionalPermissions?: AdditionalPermissionProfile | null,
/**
commandActions?: Array<CommandAction> | null, /**
* Optional proposed execpolicy amendment to allow similar commands without prompting.
*/
proposedExecpolicyAmendment?: ExecPolicyAmendment | null,
/**
proposedExecpolicyAmendment?: ExecPolicyAmendment | null, /**
* Optional proposed network policy amendments (allow/deny host) for future requests.
*/
proposedNetworkPolicyAmendments?: Array<NetworkPolicyAmendment> | null,
/**
* Ordered list of decisions the client may present for this prompt.
*/
availableDecisions?: Array<CommandExecutionApprovalDecision> | null, };
proposedNetworkPolicyAmendments?: Array<NetworkPolicyAmendment> | null};

View File

@@ -2,4 +2,4 @@
// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
export type ExternalAgentConfigMigrationItemType = "AGENTS_MD" | "CONFIG" | "SKILLS" | "PLUGINS" | "MCP_SERVER_CONFIG";
export type ExternalAgentConfigMigrationItemType = "AGENTS_MD" | "CONFIG" | "SKILLS" | "PLUGINS" | "MCP_SERVER_CONFIG" | "SESSIONS";

View File

@@ -2,4 +2,4 @@
// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
export type FileSystemSpecialPath = { "kind": "root" } | { "kind": "minimal" } | { "kind": "current_working_directory" } | { "kind": "project_roots", subpath: string | null, } | { "kind": "tmpdir" } | { "kind": "slash_tmp" } | { "kind": "unknown", path: string, subpath: string | null, };
export type FileSystemSpecialPath = { "kind": "root" } | { "kind": "minimal" } | { "kind": "project_roots", subpath: string | null, } | { "kind": "tmpdir" } | { "kind": "slash_tmp" } | { "kind": "unknown", path: string, subpath: string | null, };

View File

@@ -2,5 +2,6 @@
// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
import type { PluginsMigration } from "./PluginsMigration";
import type { SessionMigration } from "./SessionMigration";
export type MigrationDetails = { plugins: Array<PluginsMigration>, };
export type MigrationDetails = { plugins: Array<PluginsMigration>, sessions: Array<SessionMigration>, };

View File

@@ -1,6 +0,0 @@
// GENERATED CODE! DO NOT MODIFY BY HAND!
// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
import type { AbsolutePathBuf } from "../AbsolutePathBuf";
export type ReadOnlyAccess = { "type": "restricted", includePlatformDefaults: boolean, readableRoots: Array<AbsolutePathBuf>, } | { "type": "fullAccess" };

View File

@@ -3,6 +3,5 @@
// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
import type { AbsolutePathBuf } from "../AbsolutePathBuf";
import type { NetworkAccess } from "./NetworkAccess";
import type { ReadOnlyAccess } from "./ReadOnlyAccess";
export type SandboxPolicy = { "type": "dangerFullAccess" } | { "type": "readOnly", access: ReadOnlyAccess, networkAccess: boolean, } | { "type": "externalSandbox", networkAccess: NetworkAccess, } | { "type": "workspaceWrite", writableRoots: Array<AbsolutePathBuf>, readOnlyAccess: ReadOnlyAccess, networkAccess: boolean, excludeTmpdirEnvVar: boolean, excludeSlashTmp: boolean, };
export type SandboxPolicy = { "type": "dangerFullAccess" } | { "type": "readOnly", networkAccess: boolean, } | { "type": "externalSandbox", networkAccess: NetworkAccess, } | { "type": "workspaceWrite", writableRoots: Array<AbsolutePathBuf>, networkAccess: boolean, excludeTmpdirEnvVar: boolean, excludeSlashTmp: boolean, };

View File

@@ -0,0 +1,5 @@
// GENERATED CODE! DO NOT MODIFY BY HAND!
// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
export type SessionMigration = { path: string, cwd: string, title: string | null, };

View File

@@ -5,7 +5,6 @@ import type { ServiceTier } from "../ServiceTier";
import type { JsonValue } from "../serde_json/JsonValue";
import type { ApprovalsReviewer } from "./ApprovalsReviewer";
import type { AskForApproval } from "./AskForApproval";
import type { PermissionProfile } from "./PermissionProfile";
import type { SandboxMode } from "./SandboxMode";
/**
@@ -18,27 +17,15 @@ import type { SandboxMode } from "./SandboxMode";
* Prefer using thread_id whenever possible.
*/
export type ThreadForkParams = {threadId: string, /**
* [UNSTABLE] Specify the rollout path to fork from.
* If specified, the thread_id param will be ignored.
*/
path?: string | null, /**
* Configuration overrides for the forked thread, if any.
*/
model?: string | null, modelProvider?: string | null, serviceTier?: ServiceTier | null | null, cwd?: string | null, approvalPolicy?: AskForApproval | null, /**
* Override where approval requests are routed for review on this thread
* and subsequent turns.
*/
approvalsReviewer?: ApprovalsReviewer | null, sandbox?: SandboxMode | null, /**
* Full permissions override for the forked thread. Cannot be combined
* with `sandbox`.
*/
permissionProfile?: PermissionProfile | null, config?: { [key in string]?: JsonValue } | null, baseInstructions?: string | null, developerInstructions?: string | null, ephemeral?: boolean, /**
approvalsReviewer?: ApprovalsReviewer | null, sandbox?: SandboxMode | null, config?: { [key in string]?: JsonValue } | null, baseInstructions?: string | null, developerInstructions?: string | null, ephemeral?: boolean, /**
* When true, return only thread metadata and live fork state without
* populating `thread.turns`. This is useful when the client plans to call
* `thread/turns/list` immediately after forking.
*/
excludeTurns?: boolean, /**
* If true, persist additional rollout EventMsg variants required to
* reconstruct a richer thread history on subsequent resume/fork/read.
*/
persistExtendedHistory: boolean};
excludeTurns?: boolean};

View File

@@ -6,26 +6,18 @@ import type { ReasoningEffort } from "../ReasoningEffort";
import type { ServiceTier } from "../ServiceTier";
import type { ApprovalsReviewer } from "./ApprovalsReviewer";
import type { AskForApproval } from "./AskForApproval";
import type { PermissionProfile } from "./PermissionProfile";
import type { SandboxPolicy } from "./SandboxPolicy";
import type { Thread } from "./Thread";
export type ThreadForkResponse = { thread: Thread, model: string, modelProvider: string, serviceTier: ServiceTier | null, cwd: AbsolutePathBuf,
/**
export type ThreadForkResponse = {thread: Thread, model: string, modelProvider: string, serviceTier: ServiceTier | null, cwd: AbsolutePathBuf, /**
* Instruction source files currently loaded for this thread.
*/
instructionSources: Array<AbsolutePathBuf>, approvalPolicy: AskForApproval,
/**
instructionSources: Array<AbsolutePathBuf>, approvalPolicy: AskForApproval, /**
* Reviewer currently used for approval requests on this thread.
*/
approvalsReviewer: ApprovalsReviewer,
/**
approvalsReviewer: ApprovalsReviewer, /**
* Legacy sandbox policy retained for compatibility. New clients should use
* `permissionProfile` when present as the canonical active permissions
* view.
*/
sandbox: SandboxPolicy,
/**
* Canonical active permissions view for this thread.
*/
permissionProfile: PermissionProfile | null, reasoningEffort: ReasoningEffort | null, };
sandbox: SandboxPolicy, reasoningEffort: ReasoningEffort | null};

View File

@@ -0,0 +1,6 @@
// GENERATED CODE! DO NOT MODIFY BY HAND!
// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
import type { ThreadGoalStatus } from "./ThreadGoalStatus";
export type ThreadGoal = { threadId: string, objective: string, status: ThreadGoalStatus, tokenBudget: number | null, tokensUsed: number, timeUsedSeconds: number, createdAt: number, updatedAt: number, };

View File

@@ -0,0 +1,5 @@
// GENERATED CODE! DO NOT MODIFY BY HAND!
// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
export type ThreadGoalClearedNotification = { threadId: string, };

View File

@@ -0,0 +1,5 @@
// GENERATED CODE! DO NOT MODIFY BY HAND!
// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
export type ThreadGoalStatus = "active" | "paused" | "budgetLimited" | "complete";

View File

@@ -0,0 +1,6 @@
// GENERATED CODE! DO NOT MODIFY BY HAND!
// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
import type { ThreadGoal } from "./ThreadGoal";
export type ThreadGoalUpdatedNotification = { threadId: string, turnId: string | null, goal: ThreadGoal, };

View File

@@ -2,12 +2,10 @@
// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
import type { Personality } from "../Personality";
import type { ResponseItem } from "../ResponseItem";
import type { ServiceTier } from "../ServiceTier";
import type { JsonValue } from "../serde_json/JsonValue";
import type { ApprovalsReviewer } from "./ApprovalsReviewer";
import type { AskForApproval } from "./AskForApproval";
import type { PermissionProfile } from "./PermissionProfile";
import type { SandboxMode } from "./SandboxMode";
/**
@@ -22,32 +20,15 @@ import type { SandboxMode } from "./SandboxMode";
* Prefer using thread_id whenever possible.
*/
export type ThreadResumeParams = {threadId: string, /**
* [UNSTABLE] FOR CODEX CLOUD - DO NOT USE.
* If specified, the thread will be resumed with the provided history
* instead of loaded from disk.
*/
history?: Array<ResponseItem> | null, /**
* [UNSTABLE] Specify the rollout path to resume from.
* If specified, the thread_id param will be ignored.
*/
path?: string | null, /**
* Configuration overrides for the resumed thread, if any.
*/
model?: string | null, modelProvider?: string | null, serviceTier?: ServiceTier | null | null, cwd?: string | null, approvalPolicy?: AskForApproval | null, /**
* Override where approval requests are routed for review on this thread
* and subsequent turns.
*/
approvalsReviewer?: ApprovalsReviewer | null, sandbox?: SandboxMode | null, /**
* Full permissions override for the resumed thread. Cannot be combined
* with `sandbox`.
*/
permissionProfile?: PermissionProfile | null, config?: { [key in string]?: JsonValue } | null, baseInstructions?: string | null, developerInstructions?: string | null, personality?: Personality | null, /**
approvalsReviewer?: ApprovalsReviewer | null, sandbox?: SandboxMode | null, config?: { [key in string]?: JsonValue } | null, baseInstructions?: string | null, developerInstructions?: string | null, personality?: Personality | null, /**
* When true, return only thread metadata and live-resume state without
* populating `thread.turns`. This is useful when the client plans to call
* `thread/turns/list` immediately after resuming.
*/
excludeTurns?: boolean, /**
* If true, persist additional rollout EventMsg variants required to
* reconstruct a richer thread history on subsequent resume/fork/read.
*/
persistExtendedHistory: boolean};
excludeTurns?: boolean};

View File

@@ -6,26 +6,18 @@ import type { ReasoningEffort } from "../ReasoningEffort";
import type { ServiceTier } from "../ServiceTier";
import type { ApprovalsReviewer } from "./ApprovalsReviewer";
import type { AskForApproval } from "./AskForApproval";
import type { PermissionProfile } from "./PermissionProfile";
import type { SandboxPolicy } from "./SandboxPolicy";
import type { Thread } from "./Thread";
export type ThreadResumeResponse = { thread: Thread, model: string, modelProvider: string, serviceTier: ServiceTier | null, cwd: AbsolutePathBuf,
/**
export type ThreadResumeResponse = {thread: Thread, model: string, modelProvider: string, serviceTier: ServiceTier | null, cwd: AbsolutePathBuf, /**
* Instruction source files currently loaded for this thread.
*/
instructionSources: Array<AbsolutePathBuf>, approvalPolicy: AskForApproval,
/**
instructionSources: Array<AbsolutePathBuf>, approvalPolicy: AskForApproval, /**
* Reviewer currently used for approval requests on this thread.
*/
approvalsReviewer: ApprovalsReviewer,
/**
approvalsReviewer: ApprovalsReviewer, /**
* Legacy sandbox policy retained for compatibility. New clients should use
* `permissionProfile` when present as the canonical active permissions
* view.
*/
sandbox: SandboxPolicy,
/**
* Canonical active permissions view for this thread.
*/
permissionProfile: PermissionProfile | null, reasoningEffort: ReasoningEffort | null, };
sandbox: SandboxPolicy, reasoningEffort: ReasoningEffort | null};

View File

@@ -6,7 +6,6 @@ import type { ServiceTier } from "../ServiceTier";
import type { JsonValue } from "../serde_json/JsonValue";
import type { ApprovalsReviewer } from "./ApprovalsReviewer";
import type { AskForApproval } from "./AskForApproval";
import type { PermissionProfile } from "./PermissionProfile";
import type { SandboxMode } from "./SandboxMode";
import type { ThreadStartSource } from "./ThreadStartSource";
@@ -14,16 +13,4 @@ export type ThreadStartParams = {model?: string | null, modelProvider?: string |
* Override where approval requests are routed for review on this thread
* and subsequent turns.
*/
approvalsReviewer?: ApprovalsReviewer | null, sandbox?: SandboxMode | null, /**
* Full permissions override for this thread. Cannot be combined with
* `sandbox`.
*/
permissionProfile?: PermissionProfile | null, config?: { [key in string]?: JsonValue } | null, serviceName?: string | null, baseInstructions?: string | null, developerInstructions?: string | null, personality?: Personality | null, ephemeral?: boolean | null, sessionStartSource?: ThreadStartSource | null, /**
* If true, opt into emitting raw Responses API items on the event stream.
* This is for internal use only (e.g. Codex Cloud).
*/
experimentalRawEvents: boolean, /**
* If true, persist additional rollout EventMsg variants required to
* reconstruct a richer thread history on resume/fork/read.
*/
persistExtendedHistory: boolean};
approvalsReviewer?: ApprovalsReviewer | null, sandbox?: SandboxMode | null, config?: { [key in string]?: JsonValue } | null, serviceName?: string | null, baseInstructions?: string | null, developerInstructions?: string | null, personality?: Personality | null, ephemeral?: boolean | null, sessionStartSource?: ThreadStartSource | null};

View File

@@ -6,26 +6,18 @@ import type { ReasoningEffort } from "../ReasoningEffort";
import type { ServiceTier } from "../ServiceTier";
import type { ApprovalsReviewer } from "./ApprovalsReviewer";
import type { AskForApproval } from "./AskForApproval";
import type { PermissionProfile } from "./PermissionProfile";
import type { SandboxPolicy } from "./SandboxPolicy";
import type { Thread } from "./Thread";
export type ThreadStartResponse = { thread: Thread, model: string, modelProvider: string, serviceTier: ServiceTier | null, cwd: AbsolutePathBuf,
/**
export type ThreadStartResponse = {thread: Thread, model: string, modelProvider: string, serviceTier: ServiceTier | null, cwd: AbsolutePathBuf, /**
* Instruction source files currently loaded for this thread.
*/
instructionSources: Array<AbsolutePathBuf>, approvalPolicy: AskForApproval,
/**
instructionSources: Array<AbsolutePathBuf>, approvalPolicy: AskForApproval, /**
* Reviewer currently used for approval requests on this thread.
*/
approvalsReviewer: ApprovalsReviewer,
/**
approvalsReviewer: ApprovalsReviewer, /**
* Legacy sandbox policy retained for compatibility. New clients should use
* `permissionProfile` when present as the canonical active permissions
* view.
*/
sandbox: SandboxPolicy,
/**
* Canonical active permissions view for this thread.
*/
permissionProfile: PermissionProfile | null, reasoningEffort: ReasoningEffort | null, };
sandbox: SandboxPolicy, reasoningEffort: ReasoningEffort | null};

View File

@@ -1,7 +1,6 @@
// GENERATED CODE! DO NOT MODIFY BY HAND!
// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
import type { CollaborationMode } from "../CollaborationMode";
import type { Personality } from "../Personality";
import type { ReasoningEffort } from "../ReasoningEffort";
import type { ReasoningSummary } from "../ReasoningSummary";
@@ -9,7 +8,6 @@ import type { ServiceTier } from "../ServiceTier";
import type { JsonValue } from "../serde_json/JsonValue";
import type { ApprovalsReviewer } from "./ApprovalsReviewer";
import type { AskForApproval } from "./AskForApproval";
import type { PermissionProfile } from "./PermissionProfile";
import type { SandboxPolicy } from "./SandboxPolicy";
import type { UserInput } from "./UserInput";
@@ -27,10 +25,6 @@ approvalsReviewer?: ApprovalsReviewer | null, /**
* Override the sandbox policy for this turn and subsequent turns.
*/
sandboxPolicy?: SandboxPolicy | null, /**
* Override the full permissions profile for this turn and subsequent
* turns. Cannot be combined with `sandboxPolicy`.
*/
permissionProfile?: PermissionProfile | null, /**
* Override the model for this turn and subsequent turns.
*/
model?: string | null, /**
@@ -49,11 +43,4 @@ personality?: Personality | null, /**
* Optional JSON Schema used to constrain the final assistant message for
* this turn.
*/
outputSchema?: JsonValue | null, /**
* EXPERIMENTAL - Set a pre-set collaboration mode.
* Takes precedence over model, reasoning_effort, and developer instructions if set.
*
* For `collaboration_mode.settings.developer_instructions`, `null` means
* "use the built-in instructions for the selected mode".
*/
collaborationMode?: CollaborationMode | null};
outputSchema?: JsonValue | null};

View File

@@ -276,7 +276,6 @@ export type { RateLimitReachedType } from "./RateLimitReachedType";
export type { RateLimitSnapshot } from "./RateLimitSnapshot";
export type { RateLimitWindow } from "./RateLimitWindow";
export type { RawResponseItemCompletedNotification } from "./RawResponseItemCompletedNotification";
export type { ReadOnlyAccess } from "./ReadOnlyAccess";
export type { ReasoningEffortOption } from "./ReasoningEffortOption";
export type { ReasoningSummaryPartAddedNotification } from "./ReasoningSummaryPartAddedNotification";
export type { ReasoningSummaryTextDeltaNotification } from "./ReasoningSummaryTextDeltaNotification";
@@ -295,6 +294,7 @@ export type { SandboxWorkspaceWrite } from "./SandboxWorkspaceWrite";
export type { SendAddCreditsNudgeEmailParams } from "./SendAddCreditsNudgeEmailParams";
export type { SendAddCreditsNudgeEmailResponse } from "./SendAddCreditsNudgeEmailResponse";
export type { ServerRequestResolvedNotification } from "./ServerRequestResolvedNotification";
export type { SessionMigration } from "./SessionMigration";
export type { SessionSource } from "./SessionSource";
export type { SkillDependencies } from "./SkillDependencies";
export type { SkillErrorInfo } from "./SkillErrorInfo";
@@ -327,6 +327,10 @@ export type { ThreadCompactStartParams } from "./ThreadCompactStartParams";
export type { ThreadCompactStartResponse } from "./ThreadCompactStartResponse";
export type { ThreadForkParams } from "./ThreadForkParams";
export type { ThreadForkResponse } from "./ThreadForkResponse";
export type { ThreadGoal } from "./ThreadGoal";
export type { ThreadGoalClearedNotification } from "./ThreadGoalClearedNotification";
export type { ThreadGoalStatus } from "./ThreadGoalStatus";
export type { ThreadGoalUpdatedNotification } from "./ThreadGoalUpdatedNotification";
export type { ThreadInjectItemsParams } from "./ThreadInjectItemsParams";
export type { ThreadInjectItemsResponse } from "./ThreadInjectItemsResponse";
export type { ThreadItem } from "./ThreadItem";

View File

@@ -736,11 +736,11 @@ fn find_top_level_brace_span(input: &str) -> Option<(usize, usize)> {
let mut state = ScanState::default();
let mut open_index = None;
for (index, ch) in input.char_indices() {
if !state.in_string() && ch == '{' && state.depth.is_top_level() {
if !state.in_ignored_syntax() && ch == '{' && state.depth.is_top_level() {
open_index = Some(index);
}
state.observe(ch);
if !state.in_string()
if !state.in_ignored_syntax()
&& ch == '}'
&& state.depth.is_top_level()
&& let Some(open) = open_index
@@ -760,7 +760,7 @@ fn split_top_level_multi(input: &str, delimiters: &[char]) -> Vec<String> {
let mut start = 0usize;
let mut parts = Vec::new();
for (index, ch) in input.char_indices() {
if !state.in_string() && state.depth.is_top_level() && delimiters.contains(&ch) {
if !state.in_ignored_syntax() && state.depth.is_top_level() && delimiters.contains(&ch) {
let part = input[start..index].trim();
if !part.is_empty() {
parts.push(part.to_string());
@@ -882,22 +882,58 @@ struct ScanState {
depth: Depth,
string_delim: Option<char>,
escape: bool,
block_comment: bool,
line_comment: bool,
previous_char: Option<char>,
}
impl ScanState {
fn observe(&mut self, ch: char) {
if self.line_comment {
if ch == '\n' {
self.line_comment = false;
}
self.previous_char = Some(ch);
return;
}
if self.block_comment {
if self.previous_char == Some('*') && ch == '/' {
self.block_comment = false;
self.previous_char = None;
} else {
self.previous_char = Some(ch);
}
return;
}
if let Some(delim) = self.string_delim {
if self.escape {
self.escape = false;
self.previous_char = Some(ch);
return;
}
if ch == '\\' {
self.escape = true;
self.previous_char = Some(ch);
return;
}
if ch == delim {
self.string_delim = None;
}
self.previous_char = Some(ch);
return;
}
if self.previous_char == Some('/') && ch == '/' {
self.line_comment = true;
self.previous_char = Some(ch);
return;
}
if self.previous_char == Some('/') && ch == '*' {
self.block_comment = true;
self.previous_char = Some(ch);
return;
}
@@ -919,10 +955,11 @@ impl ScanState {
}
_ => {}
}
self.previous_char = Some(ch);
}
fn in_string(&self) -> bool {
self.string_delim.is_some()
fn in_ignored_syntax(&self) -> bool {
self.string_delim.is_some() || self.block_comment || self.line_comment
}
}
@@ -2694,6 +2731,79 @@ export type Config = { stableField: Keep, unstableField: string | null } & ({ [k
Ok(())
}
#[test]
fn experimental_type_fields_ts_filter_handles_generated_command_params_shape() -> Result<()> {
let output_dir = std::env::temp_dir().join(format!("codex_ts_filter_{}", Uuid::now_v7()));
fs::create_dir_all(&output_dir)?;
struct TempDirGuard(PathBuf);
impl Drop for TempDirGuard {
fn drop(&mut self) {
let _ = fs::remove_dir_all(&self.0);
}
}
let _guard = TempDirGuard(output_dir.clone());
let path = output_dir.join("CommandExecParams.ts");
let content = r#"import type { CommandExecTerminalSize } from "./CommandExecTerminalSize";
import type { PermissionProfile } from "./PermissionProfile";
import type { SandboxPolicy } from "./SandboxPolicy";
export type CommandExecParams = {/**
* Command argv vector. Empty arrays are rejected.
*/
command: Array<string>, /**
* Optional environment overrides merged into the server-computed
* environment.
*/
env?: { [key in string]?: string | null } | null, /**
* Optional initial PTY size in character cells. Only valid when `tty` is
* true.
*/
size?: CommandExecTerminalSize | null, /**
* Optional sandbox policy for this command.
*
* Uses the same shape as thread/turn execution sandbox configuration and
* defaults to the user's configured policy when omitted. Cannot be
* combined with `permissionProfile`.
*/
sandboxPolicy?: SandboxPolicy | null,
/**
* Optional full permissions profile for this command.
*
* Defaults to the user's configured permissions when omitted. Cannot be
* combined with `sandboxPolicy`.
*/
permissionProfile?: PermissionProfile | null};
"#;
fs::write(&path, content)?;
static CUSTOM_FIELD: crate::experimental_api::ExperimentalField =
crate::experimental_api::ExperimentalField {
type_name: "CommandExecParams",
field_name: "permissionProfile",
reason: "command/exec.permissionProfile",
};
filter_experimental_type_fields_ts(&output_dir, &[&CUSTOM_FIELD])?;
let filtered = fs::read_to_string(&path)?;
assert_eq!(
filtered.contains("permissionProfile?: PermissionProfile"),
false
);
assert_eq!(
filtered.contains(r#"import type { PermissionProfile } from "./PermissionProfile";"#),
false
);
assert_eq!(filtered.contains("sandboxPolicy?: SandboxPolicy"), true);
assert_eq!(
filtered.contains(r#"import type { SandboxPolicy } from "./SandboxPolicy";"#),
true
);
Ok(())
}
#[test]
fn stable_schema_filter_removes_mock_experimental_method() -> Result<()> {
let output_dir = std::env::temp_dir().join(format!("codex_schema_{}", Uuid::now_v7()));

View File

@@ -285,6 +285,21 @@ client_request_definitions! {
params: v2::ThreadSetNameParams,
response: v2::ThreadSetNameResponse,
},
#[experimental("thread/goal/set")]
ThreadGoalSet => "thread/goal/set" {
params: v2::ThreadGoalSetParams,
response: v2::ThreadGoalSetResponse,
},
#[experimental("thread/goal/get")]
ThreadGoalGet => "thread/goal/get" {
params: v2::ThreadGoalGetParams,
response: v2::ThreadGoalGetResponse,
},
#[experimental("thread/goal/clear")]
ThreadGoalClear => "thread/goal/clear" {
params: v2::ThreadGoalClearParams,
response: v2::ThreadGoalClearResponse,
},
ThreadMetadataUpdate => "thread/metadata/update" {
params: v2::ThreadMetadataUpdateParams,
response: v2::ThreadMetadataUpdateResponse,
@@ -566,6 +581,7 @@ client_request_definitions! {
/// Execute a standalone command (argv vector) under the server's sandbox.
OneOffCommandExec => "command/exec" {
params: v2::CommandExecParams,
inspect_params: true,
response: v2::CommandExecResponse,
},
/// Write stdin bytes to a running `command/exec` session or close stdin.
@@ -1027,6 +1043,10 @@ server_notification_definitions! {
ThreadClosed => "thread/closed" (v2::ThreadClosedNotification),
SkillsChanged => "skills/changed" (v2::SkillsChangedNotification),
ThreadNameUpdated => "thread/name/updated" (v2::ThreadNameUpdatedNotification),
#[experimental("thread/goal/updated")]
ThreadGoalUpdated => "thread/goal/updated" (v2::ThreadGoalUpdatedNotification),
#[experimental("thread/goal/cleared")]
ThreadGoalCleared => "thread/goal/cleared" (v2::ThreadGoalClearedNotification),
ThreadTokenUsageUpdated => "thread/tokenUsage/updated" (v2::ThreadTokenUsageUpdatedNotification),
TurnStarted => "turn/started" (v2::TurnStartedNotification),
HookStarted => "hook/started" (v2::HookStartedNotification),
@@ -2030,6 +2050,33 @@ mod tests {
let reason = crate::experimental_api::ExperimentalApi::experimental_reason(&request);
assert_eq!(reason, Some("mock/experimentalMethod"));
}
#[test]
fn command_exec_permission_profile_is_marked_experimental() {
let request = ClientRequest::OneOffCommandExec {
request_id: RequestId::Integer(1),
params: v2::CommandExecParams {
command: vec!["pwd".to_string()],
process_id: None,
tty: false,
stream_stdin: false,
stream_stdout_stderr: false,
output_bytes_cap: None,
disable_output_cap: false,
disable_timeout: false,
timeout_ms: None,
cwd: None,
env: None,
size: None,
sandbox_policy: None,
permission_profile: Some(v2::PermissionProfile::Disabled),
},
};
let reason = crate::experimental_api::ExperimentalApi::experimental_reason(&request);
assert_eq!(reason, Some("command/exec.permissionProfile"));
}
#[test]
fn thread_realtime_start_is_marked_experimental() {
let request = ClientRequest::ThreadRealtimeStart {
@@ -2046,6 +2093,76 @@ mod tests {
let reason = crate::experimental_api::ExperimentalApi::experimental_reason(&request);
assert_eq!(reason, Some("thread/realtime/start"));
}
#[test]
fn thread_goal_methods_are_marked_experimental() {
let set_request = ClientRequest::ThreadGoalSet {
request_id: RequestId::Integer(1),
params: v2::ThreadGoalSetParams {
thread_id: "thr_123".to_string(),
objective: Some("ship goal mode".to_string()),
status: Some(v2::ThreadGoalStatus::Active),
token_budget: Some(Some(10_000)),
},
};
let get_request = ClientRequest::ThreadGoalGet {
request_id: RequestId::Integer(2),
params: v2::ThreadGoalGetParams {
thread_id: "thr_123".to_string(),
},
};
let clear_request = ClientRequest::ThreadGoalClear {
request_id: RequestId::Integer(3),
params: v2::ThreadGoalClearParams {
thread_id: "thr_123".to_string(),
},
};
assert_eq!(
crate::experimental_api::ExperimentalApi::experimental_reason(&set_request),
Some("thread/goal/set")
);
assert_eq!(
crate::experimental_api::ExperimentalApi::experimental_reason(&get_request),
Some("thread/goal/get")
);
assert_eq!(
crate::experimental_api::ExperimentalApi::experimental_reason(&clear_request),
Some("thread/goal/clear")
);
}
#[test]
fn thread_goal_notifications_are_marked_experimental() {
let goal = v2::ThreadGoal {
thread_id: "thr_123".to_string(),
objective: "ship goal mode".to_string(),
status: v2::ThreadGoalStatus::Active,
token_budget: Some(10_000),
tokens_used: 123,
time_used_seconds: 45,
created_at: 1_700_000_000,
updated_at: 1_700_000_123,
};
let updated = ServerNotification::ThreadGoalUpdated(v2::ThreadGoalUpdatedNotification {
thread_id: "thr_123".to_string(),
turn_id: None,
goal,
});
let cleared = ServerNotification::ThreadGoalCleared(v2::ThreadGoalClearedNotification {
thread_id: "thr_123".to_string(),
});
assert_eq!(
crate::experimental_api::ExperimentalApi::experimental_reason(&updated),
Some("thread/goal/updated")
);
assert_eq!(
crate::experimental_api::ExperimentalApi::experimental_reason(&cleared),
Some("thread/goal/cleared")
);
}
#[test]
fn thread_realtime_started_notification_is_marked_experimental() {
let notification =

View File

@@ -3096,7 +3096,6 @@ mod tests {
content: vec![codex_protocol::models::ContentItem::InputText {
text: "plain text".into(),
}],
end_turn: None,
phase: None,
}),
RolloutItem::EventMsg(EventMsg::TurnComplete(TurnCompleteEvent {

View File

@@ -83,7 +83,6 @@ use codex_protocol::protocol::PatchApplyStatus as CorePatchApplyStatus;
use codex_protocol::protocol::RateLimitReachedType as CoreRateLimitReachedType;
use codex_protocol::protocol::RateLimitSnapshot as CoreRateLimitSnapshot;
use codex_protocol::protocol::RateLimitWindow as CoreRateLimitWindow;
use codex_protocol::protocol::ReadOnlyAccess as CoreReadOnlyAccess;
use codex_protocol::protocol::RealtimeAudioFrame as CoreRealtimeAudioFrame;
use codex_protocol::protocol::RealtimeConversationVersion;
use codex_protocol::protocol::RealtimeOutputModality;
@@ -97,6 +96,7 @@ use codex_protocol::protocol::SkillMetadata as CoreSkillMetadata;
use codex_protocol::protocol::SkillScope as CoreSkillScope;
use codex_protocol::protocol::SkillToolDependency as CoreSkillToolDependency;
use codex_protocol::protocol::SubAgentSource as CoreSubAgentSource;
use codex_protocol::protocol::ThreadGoalStatus as CoreThreadGoalStatus;
use codex_protocol::protocol::TokenUsage as CoreTokenUsage;
use codex_protocol::protocol::TokenUsageInfo as CoreTokenUsageInfo;
use codex_protocol::request_permissions::PermissionGrantScope as CorePermissionGrantScope;
@@ -808,10 +808,6 @@ const fn default_enabled() -> bool {
true
}
const fn default_include_platform_defaults() -> bool {
true
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS, ExperimentalApi)]
#[serde(rename_all = "snake_case")]
#[ts(export_to = "v2/")]
@@ -1095,6 +1091,9 @@ pub enum ExternalAgentConfigMigrationItemType {
#[serde(rename = "MCP_SERVER_CONFIG")]
#[ts(rename = "MCP_SERVER_CONFIG")]
McpServerConfig,
#[serde(rename = "SESSIONS")]
#[ts(rename = "SESSIONS")]
Sessions,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq, JsonSchema, TS)]
@@ -1109,11 +1108,23 @@ pub struct PluginsMigration {
pub plugin_names: Vec<String>,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq, JsonSchema, TS)]
#[serde(rename_all = "camelCase")]
#[ts(export_to = "v2/")]
pub struct SessionMigration {
pub path: PathBuf,
pub cwd: PathBuf,
pub title: Option<String>,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq, JsonSchema, TS)]
#[serde(rename_all = "camelCase")]
#[ts(export_to = "v2/")]
pub struct MigrationDetails {
#[serde(default)]
pub plugins: Vec<PluginsMigration>,
#[serde(default)]
pub sessions: Vec<SessionMigration>,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq, JsonSchema, TS)]
@@ -1438,7 +1449,7 @@ v2_enum_from_core!(
pub enum FileSystemSpecialPath {
Root,
Minimal,
CurrentWorkingDirectory,
#[serde(alias = "current_working_directory")]
ProjectRoots {
subpath: Option<PathBuf>,
},
@@ -1455,7 +1466,6 @@ impl From<CoreFileSystemSpecialPath> for FileSystemSpecialPath {
match value {
CoreFileSystemSpecialPath::Root => Self::Root,
CoreFileSystemSpecialPath::Minimal => Self::Minimal,
CoreFileSystemSpecialPath::CurrentWorkingDirectory => Self::CurrentWorkingDirectory,
CoreFileSystemSpecialPath::ProjectRoots { subpath } => Self::ProjectRoots { subpath },
CoreFileSystemSpecialPath::Tmpdir => Self::Tmpdir,
CoreFileSystemSpecialPath::SlashTmp => Self::SlashTmp,
@@ -1469,7 +1479,6 @@ impl From<FileSystemSpecialPath> for CoreFileSystemSpecialPath {
match value {
FileSystemSpecialPath::Root => Self::Root,
FileSystemSpecialPath::Minimal => Self::Minimal,
FileSystemSpecialPath::CurrentWorkingDirectory => Self::CurrentWorkingDirectory,
FileSystemSpecialPath::ProjectRoots { subpath } => Self::ProjectRoots { subpath },
FileSystemSpecialPath::Tmpdir => Self::Tmpdir,
FileSystemSpecialPath::SlashTmp => Self::SlashTmp,
@@ -1719,54 +1728,7 @@ pub enum NetworkAccess {
Enabled,
}
#[derive(Serialize, Deserialize, Debug, Default, Clone, PartialEq, Eq, JsonSchema, TS)]
#[serde(tag = "type", rename_all = "camelCase")]
#[ts(tag = "type")]
#[ts(export_to = "v2/")]
pub enum ReadOnlyAccess {
#[serde(rename_all = "camelCase")]
#[ts(rename_all = "camelCase")]
Restricted {
#[serde(default = "default_include_platform_defaults")]
include_platform_defaults: bool,
#[serde(default)]
readable_roots: Vec<AbsolutePathBuf>,
},
#[default]
FullAccess,
}
impl ReadOnlyAccess {
pub fn to_core(&self) -> CoreReadOnlyAccess {
match self {
ReadOnlyAccess::Restricted {
include_platform_defaults,
readable_roots,
} => CoreReadOnlyAccess::Restricted {
include_platform_defaults: *include_platform_defaults,
readable_roots: readable_roots.clone(),
},
ReadOnlyAccess::FullAccess => CoreReadOnlyAccess::FullAccess,
}
}
}
impl From<CoreReadOnlyAccess> for ReadOnlyAccess {
fn from(value: CoreReadOnlyAccess) -> Self {
match value {
CoreReadOnlyAccess::Restricted {
include_platform_defaults,
readable_roots,
} => ReadOnlyAccess::Restricted {
include_platform_defaults,
readable_roots,
},
CoreReadOnlyAccess::FullAccess => ReadOnlyAccess::FullAccess,
}
}
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq, JsonSchema, TS)]
#[derive(Serialize, Debug, Clone, PartialEq, Eq, JsonSchema, TS)]
#[serde(tag = "type", rename_all = "camelCase")]
#[ts(tag = "type")]
#[ts(export_to = "v2/")]
@@ -1775,8 +1737,6 @@ pub enum SandboxPolicy {
#[serde(rename_all = "camelCase")]
#[ts(rename_all = "camelCase")]
ReadOnly {
#[serde(default)]
access: ReadOnlyAccess,
#[serde(default)]
network_access: bool,
},
@@ -1792,7 +1752,36 @@ pub enum SandboxPolicy {
#[serde(default)]
writable_roots: Vec<AbsolutePathBuf>,
#[serde(default)]
read_only_access: ReadOnlyAccess,
network_access: bool,
#[serde(default)]
exclude_tmpdir_env_var: bool,
#[serde(default)]
exclude_slash_tmp: bool,
},
}
#[derive(Deserialize)]
#[serde(tag = "type", rename_all = "camelCase")]
enum SandboxPolicyDeserialize {
DangerFullAccess,
#[serde(rename_all = "camelCase")]
ReadOnly {
#[serde(default)]
network_access: bool,
#[serde(default)]
access: Option<LegacyReadOnlyAccess>,
},
#[serde(rename_all = "camelCase")]
ExternalSandbox {
#[serde(default)]
network_access: NetworkAccess,
},
#[serde(rename_all = "camelCase")]
WorkspaceWrite {
#[serde(default)]
writable_roots: Vec<AbsolutePathBuf>,
#[serde(default)]
read_only_access: Option<LegacyReadOnlyAccess>,
#[serde(default)]
network_access: bool,
#[serde(default)]
@@ -1802,19 +1791,68 @@ pub enum SandboxPolicy {
},
}
#[derive(Deserialize)]
#[serde(tag = "type", rename_all = "camelCase")]
enum LegacyReadOnlyAccess {
FullAccess,
Restricted,
}
impl<'de> Deserialize<'de> for SandboxPolicy {
fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>
where
D: serde::Deserializer<'de>,
{
match SandboxPolicyDeserialize::deserialize(deserializer)? {
SandboxPolicyDeserialize::DangerFullAccess => Ok(SandboxPolicy::DangerFullAccess),
SandboxPolicyDeserialize::ReadOnly {
network_access,
access,
} => {
if matches!(access, Some(LegacyReadOnlyAccess::Restricted)) {
return Err(serde::de::Error::custom(
"readOnly.access is no longer supported; use permissionProfile for restricted reads",
));
}
Ok(SandboxPolicy::ReadOnly { network_access })
}
SandboxPolicyDeserialize::ExternalSandbox { network_access } => {
Ok(SandboxPolicy::ExternalSandbox { network_access })
}
SandboxPolicyDeserialize::WorkspaceWrite {
writable_roots,
read_only_access,
network_access,
exclude_tmpdir_env_var,
exclude_slash_tmp,
} => {
if matches!(read_only_access, Some(LegacyReadOnlyAccess::Restricted)) {
return Err(serde::de::Error::custom(
"workspaceWrite.readOnlyAccess is no longer supported; use permissionProfile for restricted reads",
));
}
Ok(SandboxPolicy::WorkspaceWrite {
writable_roots,
network_access,
exclude_tmpdir_env_var,
exclude_slash_tmp,
})
}
}
}
}
impl SandboxPolicy {
pub fn to_core(&self) -> codex_protocol::protocol::SandboxPolicy {
match self {
SandboxPolicy::DangerFullAccess => {
codex_protocol::protocol::SandboxPolicy::DangerFullAccess
}
SandboxPolicy::ReadOnly {
access,
network_access,
} => codex_protocol::protocol::SandboxPolicy::ReadOnly {
access: access.to_core(),
network_access: *network_access,
},
SandboxPolicy::ReadOnly { network_access } => {
codex_protocol::protocol::SandboxPolicy::ReadOnly {
network_access: *network_access,
}
}
SandboxPolicy::ExternalSandbox { network_access } => {
codex_protocol::protocol::SandboxPolicy::ExternalSandbox {
network_access: match network_access {
@@ -1825,13 +1863,11 @@ impl SandboxPolicy {
}
SandboxPolicy::WorkspaceWrite {
writable_roots,
read_only_access,
network_access,
exclude_tmpdir_env_var,
exclude_slash_tmp,
} => codex_protocol::protocol::SandboxPolicy::WorkspaceWrite {
writable_roots: writable_roots.clone(),
read_only_access: read_only_access.to_core(),
network_access: *network_access,
exclude_tmpdir_env_var: *exclude_tmpdir_env_var,
exclude_slash_tmp: *exclude_slash_tmp,
@@ -1846,13 +1882,9 @@ impl From<codex_protocol::protocol::SandboxPolicy> for SandboxPolicy {
codex_protocol::protocol::SandboxPolicy::DangerFullAccess => {
SandboxPolicy::DangerFullAccess
}
codex_protocol::protocol::SandboxPolicy::ReadOnly {
access,
network_access,
} => SandboxPolicy::ReadOnly {
access: ReadOnlyAccess::from(access),
network_access,
},
codex_protocol::protocol::SandboxPolicy::ReadOnly { network_access } => {
SandboxPolicy::ReadOnly { network_access }
}
codex_protocol::protocol::SandboxPolicy::ExternalSandbox { network_access } => {
SandboxPolicy::ExternalSandbox {
network_access: match network_access {
@@ -1863,13 +1895,11 @@ impl From<codex_protocol::protocol::SandboxPolicy> for SandboxPolicy {
}
codex_protocol::protocol::SandboxPolicy::WorkspaceWrite {
writable_roots,
read_only_access,
network_access,
exclude_tmpdir_env_var,
exclude_slash_tmp,
} => SandboxPolicy::WorkspaceWrite {
writable_roots,
read_only_access: ReadOnlyAccess::from(read_only_access),
network_access,
exclude_tmpdir_env_var,
exclude_slash_tmp,
@@ -1981,6 +2011,8 @@ impl From<CoreSessionSource> for SessionSource {
CoreSessionSource::Exec => SessionSource::Exec,
CoreSessionSource::Mcp => SessionSource::AppServer,
CoreSessionSource::Custom(source) => SessionSource::Custom(source),
// We do not want to render those at the app-server level.
CoreSessionSource::Internal(_) => SessionSource::Unknown,
CoreSessionSource::SubAgent(sub) => SessionSource::SubAgent(sub),
CoreSessionSource::Unknown => SessionSource::Unknown,
}
@@ -3148,7 +3180,7 @@ pub struct CommandExecTerminalSize {
/// The final `command/exec` response is deferred until the process exits and is
/// sent only after all `command/exec/outputDelta` notifications for that
/// connection have been emitted.
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS, ExperimentalApi)]
#[serde(rename_all = "camelCase")]
#[ts(export_to = "v2/")]
pub struct CommandExecParams {
@@ -3227,6 +3259,7 @@ pub struct CommandExecParams {
///
/// Defaults to the user's configured permissions when omitted. Cannot be
/// combined with `sandboxPolicy`.
#[experimental("command/exec.permissionProfile")]
#[ts(optional = nullable)]
pub permission_profile: Option<PermissionProfile>,
}
@@ -3349,6 +3382,7 @@ pub struct ThreadStartParams {
pub sandbox: Option<SandboxMode>,
/// Full permissions override for this thread. Cannot be combined with
/// `sandbox`.
#[experimental("thread/start.permissionProfile")]
#[ts(optional = nullable)]
pub permission_profile: Option<PermissionProfile>,
#[ts(optional = nullable)]
@@ -3432,6 +3466,7 @@ pub struct ThreadStartResponse {
/// view.
pub sandbox: SandboxPolicy,
/// Canonical active permissions view for this thread.
#[experimental("thread/start.permissionProfile")]
#[serde(default)]
pub permission_profile: Option<PermissionProfile>,
pub reasoning_effort: Option<ReasoningEffort>,
@@ -3493,6 +3528,7 @@ pub struct ThreadResumeParams {
pub sandbox: Option<SandboxMode>,
/// Full permissions override for the resumed thread. Cannot be combined
/// with `sandbox`.
#[experimental("thread/resume.permissionProfile")]
#[ts(optional = nullable)]
pub permission_profile: Option<PermissionProfile>,
#[ts(optional = nullable)]
@@ -3536,6 +3572,7 @@ pub struct ThreadResumeResponse {
/// view.
pub sandbox: SandboxPolicy,
/// Canonical active permissions view for this thread.
#[experimental("thread/resume.permissionProfile")]
#[serde(default)]
pub permission_profile: Option<PermissionProfile>,
pub reasoning_effort: Option<ReasoningEffort>,
@@ -3588,6 +3625,7 @@ pub struct ThreadForkParams {
pub sandbox: Option<SandboxMode>,
/// Full permissions override for the forked thread. Cannot be combined
/// with `sandbox`.
#[experimental("thread/fork.permissionProfile")]
#[ts(optional = nullable)]
pub permission_profile: Option<PermissionProfile>,
#[ts(optional = nullable)]
@@ -3631,6 +3669,7 @@ pub struct ThreadForkResponse {
/// view.
pub sandbox: SandboxPolicy,
/// Canonical active permissions view for this thread.
#[experimental("thread/fork.permissionProfile")]
#[serde(default)]
pub permission_profile: Option<PermissionProfile>,
pub reasoning_effort: Option<ReasoningEffort>,
@@ -3731,6 +3770,103 @@ pub struct ThreadUnarchiveParams {
#[ts(export_to = "v2/")]
pub struct ThreadSetNameResponse {}
v2_enum_from_core! {
pub enum ThreadGoalStatus from CoreThreadGoalStatus {
Active,
Paused,
BudgetLimited,
Complete,
}
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[serde(rename_all = "camelCase")]
#[ts(export_to = "v2/")]
pub struct ThreadGoal {
pub thread_id: String,
pub objective: String,
pub status: ThreadGoalStatus,
#[ts(type = "number | null")]
pub token_budget: Option<i64>,
#[ts(type = "number")]
pub tokens_used: i64,
#[ts(type = "number")]
pub time_used_seconds: i64,
#[ts(type = "number")]
pub created_at: i64,
#[ts(type = "number")]
pub updated_at: i64,
}
impl From<codex_protocol::protocol::ThreadGoal> for ThreadGoal {
fn from(value: codex_protocol::protocol::ThreadGoal) -> Self {
Self {
thread_id: value.thread_id.to_string(),
objective: value.objective,
status: value.status.into(),
token_budget: value.token_budget,
tokens_used: value.tokens_used,
time_used_seconds: value.time_used_seconds,
created_at: value.created_at,
updated_at: value.updated_at,
}
}
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Default, JsonSchema, TS)]
#[serde(rename_all = "camelCase")]
#[ts(export_to = "v2/")]
pub struct ThreadGoalSetParams {
pub thread_id: String,
#[ts(optional = nullable)]
pub objective: Option<String>,
#[ts(optional = nullable)]
pub status: Option<ThreadGoalStatus>,
#[serde(
default,
deserialize_with = "super::serde_helpers::deserialize_double_option",
serialize_with = "super::serde_helpers::serialize_double_option",
skip_serializing_if = "Option::is_none"
)]
#[ts(optional = nullable, type = "number | null")]
pub token_budget: Option<Option<i64>>,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[serde(rename_all = "camelCase")]
#[ts(export_to = "v2/")]
pub struct ThreadGoalSetResponse {
pub goal: ThreadGoal,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[serde(rename_all = "camelCase")]
#[ts(export_to = "v2/")]
pub struct ThreadGoalGetParams {
pub thread_id: String,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[serde(rename_all = "camelCase")]
#[ts(export_to = "v2/")]
pub struct ThreadGoalGetResponse {
pub goal: Option<ThreadGoal>,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[serde(rename_all = "camelCase")]
#[ts(export_to = "v2/")]
pub struct ThreadGoalClearParams {
pub thread_id: String,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[serde(rename_all = "camelCase")]
#[ts(export_to = "v2/")]
pub struct ThreadGoalClearResponse {
pub cleared: bool,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[serde(rename_all = "camelCase")]
#[ts(export_to = "v2/")]
@@ -5072,6 +5208,7 @@ pub struct TurnStartParams {
pub sandbox_policy: Option<SandboxPolicy>,
/// Override the full permissions profile for this turn and subsequent
/// turns. Cannot be combined with `sandboxPolicy`.
#[experimental("turn/start.permissionProfile")]
#[ts(optional = nullable)]
pub permission_profile: Option<PermissionProfile>,
/// Override the model for this turn and subsequent turns.
@@ -6254,6 +6391,22 @@ pub struct ThreadNameUpdatedNotification {
pub thread_name: Option<String>,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[serde(rename_all = "camelCase")]
#[ts(export_to = "v2/")]
pub struct ThreadGoalUpdatedNotification {
pub thread_id: String,
pub turn_id: Option<String>,
pub goal: ThreadGoal,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[serde(rename_all = "camelCase")]
#[ts(export_to = "v2/")]
pub struct ThreadGoalClearedNotification {
pub thread_id: String,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[serde(rename_all = "camelCase")]
#[ts(export_to = "v2/")]
@@ -7578,7 +7731,6 @@ mod tests {
use codex_protocol::items::WebSearchItem;
use codex_protocol::models::WebSearchAction as CoreWebSearchAction;
use codex_protocol::protocol::NetworkAccess as CoreNetworkAccess;
use codex_protocol::protocol::ReadOnlyAccess as CoreReadOnlyAccess;
use codex_protocol::user_input::UserInput as CoreUserInput;
use codex_utils_absolute_path::test_support::PathBufExt;
use codex_utils_absolute_path::test_support::test_path_buf;
@@ -7704,11 +7856,50 @@ mod tests {
marketplace_name: "team-marketplace".to_string(),
plugin_names: vec!["asana".to_string()],
}],
sessions: Vec::new(),
}),
}
);
}
#[test]
fn external_agent_config_import_params_accept_legacy_plugin_details() {
let params: ExternalAgentConfigImportParams = serde_json::from_value(json!({
"migrationItems": [{
"itemType": "PLUGINS",
"description": "Install supported plugins from Claude settings",
"cwd": absolute_path_string("repo"),
"details": {
"plugins": [
{
"marketplaceName": "team-marketplace",
"pluginNames": ["asana"]
}
]
}
}]
}))
.expect("legacy plugin import params should deserialize");
assert_eq!(
params,
ExternalAgentConfigImportParams {
migration_items: vec![ExternalAgentConfigMigrationItem {
item_type: ExternalAgentConfigMigrationItemType::Plugins,
description: "Install supported plugins from Claude settings".to_string(),
cwd: Some(PathBuf::from(absolute_path_string("repo"))),
details: Some(MigrationDetails {
plugins: vec![PluginsMigration {
marketplace_name: "team-marketplace".to_string(),
plugin_names: vec!["asana".to_string()],
}],
sessions: Vec::new(),
}),
}],
}
);
}
#[test]
fn command_execution_request_approval_rejects_relative_additional_permission_paths() {
let err = serde_json::from_value::<CommandExecutionRequestApprovalParams>(json!({
@@ -7982,6 +8173,26 @@ mod tests {
.expect_err("zero glob scan depth should fail deserialization");
}
#[test]
fn legacy_current_working_directory_special_path_deserializes_as_project_roots() {
let special_path = serde_json::from_value::<FileSystemSpecialPath>(json!({
"kind": "current_working_directory",
}))
.expect("legacy cwd special path should deserialize");
assert_eq!(
special_path,
FileSystemSpecialPath::ProjectRoots { subpath: None }
);
assert_eq!(
serde_json::to_value(&special_path).expect("serialize special path"),
json!({
"kind": "project_roots",
"subpath": null,
})
);
}
#[test]
fn permissions_request_approval_response_uses_granted_permission_profile_without_macos() {
let read_only_path = if cfg!(windows) {
@@ -8784,13 +8995,8 @@ mod tests {
}
#[test]
fn sandbox_policy_round_trips_read_only_access() {
let readable_root = test_absolute_path();
fn sandbox_policy_round_trips_read_only_network_access() {
let v2_policy = SandboxPolicy::ReadOnly {
access: ReadOnlyAccess::Restricted {
include_platform_defaults: false,
readable_roots: vec![readable_root.clone()],
},
network_access: true,
};
@@ -8798,10 +9004,6 @@ mod tests {
assert_eq!(
core_policy,
codex_protocol::protocol::SandboxPolicy::ReadOnly {
access: CoreReadOnlyAccess::Restricted {
include_platform_defaults: false,
readable_roots: vec![readable_root],
},
network_access: true,
}
);
@@ -9425,14 +9627,9 @@ mod tests {
}
#[test]
fn sandbox_policy_round_trips_workspace_write_read_only_access() {
let readable_root = test_absolute_path();
fn sandbox_policy_round_trips_workspace_write_access() {
let v2_policy = SandboxPolicy::WorkspaceWrite {
writable_roots: vec![],
read_only_access: ReadOnlyAccess::Restricted {
include_platform_defaults: false,
readable_roots: vec![readable_root.clone()],
},
network_access: true,
exclude_tmpdir_env_var: false,
exclude_slash_tmp: false,
@@ -9443,10 +9640,6 @@ mod tests {
core_policy,
codex_protocol::protocol::SandboxPolicy::WorkspaceWrite {
writable_roots: vec![],
read_only_access: CoreReadOnlyAccess::Restricted {
include_platform_defaults: false,
readable_roots: vec![readable_root],
},
network_access: true,
exclude_tmpdir_env_var: false,
exclude_slash_tmp: false,
@@ -9458,40 +9651,78 @@ mod tests {
}
#[test]
fn sandbox_policy_deserializes_legacy_read_only_without_access_field() {
let policy: SandboxPolicy = serde_json::from_value(json!({
"type": "readOnly"
fn sandbox_policy_deserializes_legacy_read_only_full_access_field() {
let policy = serde_json::from_value::<SandboxPolicy>(json!({
"type": "readOnly",
"access": {
"type": "fullAccess"
},
"networkAccess": true
}))
.expect("read-only policy should deserialize");
.expect("read-only policy should ignore legacy fullAccess field");
assert_eq!(
policy,
SandboxPolicy::ReadOnly {
access: ReadOnlyAccess::FullAccess,
network_access: false,
network_access: true
}
);
}
#[test]
fn sandbox_policy_deserializes_legacy_workspace_write_without_read_only_access_field() {
let policy: SandboxPolicy = serde_json::from_value(json!({
fn sandbox_policy_deserializes_legacy_workspace_write_full_access_field() {
let writable_root = absolute_path("/workspace");
let policy = serde_json::from_value::<SandboxPolicy>(json!({
"type": "workspaceWrite",
"writableRoots": [writable_root],
"readOnlyAccess": {
"type": "fullAccess"
},
"networkAccess": true,
"excludeTmpdirEnvVar": true,
"excludeSlashTmp": true
}))
.expect("workspace-write policy should ignore legacy fullAccess field");
assert_eq!(
policy,
SandboxPolicy::WorkspaceWrite {
writable_roots: vec![absolute_path("/workspace")],
network_access: true,
exclude_tmpdir_env_var: true,
exclude_slash_tmp: true,
}
);
}
#[test]
fn sandbox_policy_rejects_legacy_read_only_restricted_access_field() {
let err = serde_json::from_value::<SandboxPolicy>(json!({
"type": "readOnly",
"access": {
"type": "restricted",
"includePlatformDefaults": false,
"readableRoots": []
}
}))
.expect_err("read-only policy should reject removed restricted access field");
assert!(err.to_string().contains("readOnly.access"));
}
#[test]
fn sandbox_policy_rejects_legacy_workspace_write_restricted_read_access_field() {
let err = serde_json::from_value::<SandboxPolicy>(json!({
"type": "workspaceWrite",
"writableRoots": [],
"readOnlyAccess": {
"type": "restricted",
"includePlatformDefaults": false,
"readableRoots": []
},
"networkAccess": false,
"excludeTmpdirEnvVar": false,
"excludeSlashTmp": false
}))
.expect("workspace-write policy should deserialize");
assert_eq!(
policy,
SandboxPolicy::WorkspaceWrite {
writable_roots: vec![],
read_only_access: ReadOnlyAccess::FullAccess,
network_access: false,
exclude_tmpdir_env_var: false,
exclude_slash_tmp: false,
}
);
.expect_err("workspace-write policy should reject removed restricted readOnlyAccess field");
assert!(err.to_string().contains("workspaceWrite.readOnlyAccess"));
}
#[test]
@@ -10130,6 +10361,27 @@ mod tests {
plugin_id: "gmail@openai-curated".to_string(),
},
);
assert_eq!(
serde_json::to_value(PluginUninstallParams {
plugin_id: "plugins~Plugin_gmail".to_string(),
})
.unwrap(),
json!({
"pluginId": "plugins~Plugin_gmail",
}),
);
assert_eq!(
serde_json::from_value::<PluginUninstallParams>(json!({
"pluginId": "plugins~Plugin_gmail",
"forceRemoteSync": true,
}))
.unwrap(),
PluginUninstallParams {
plugin_id: "plugins~Plugin_gmail".to_string(),
},
);
}
#[test]

View File

@@ -48,7 +48,6 @@ use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::LoginAccountResponse;
use codex_app_server_protocol::ModelListParams;
use codex_app_server_protocol::ModelListResponse;
use codex_app_server_protocol::ReadOnlyAccess;
use codex_app_server_protocol::RequestId;
use codex_app_server_protocol::SandboxPolicy;
use codex_app_server_protocol::ServerNotification;
@@ -743,7 +742,6 @@ async fn trigger_zsh_fork_multi_cmd_approval(
};
turn_params.approval_policy = Some(AskForApproval::OnRequest);
turn_params.sandbox_policy = Some(SandboxPolicy::ReadOnly {
access: ReadOnlyAccess::FullAccess,
network_access: false,
});
@@ -885,7 +883,6 @@ async fn trigger_cmd_approval(
experimental_api: true,
approval_policy: Some(AskForApproval::OnRequest),
sandbox_policy: Some(SandboxPolicy::ReadOnly {
access: ReadOnlyAccess::FullAccess,
network_access: false,
}),
dynamic_tools,
@@ -912,7 +909,6 @@ async fn trigger_patch_approval(
experimental_api: true,
approval_policy: Some(AskForApproval::OnRequest),
sandbox_policy: Some(SandboxPolicy::ReadOnly {
access: ReadOnlyAccess::FullAccess,
network_access: false,
}),
dynamic_tools,

View File

@@ -5,7 +5,13 @@ codex_rust_crate(
crate_name = "codex_app_server",
integration_test_timeout = "long",
test_shard_counts = {
"app-server-all-test": 8,
# Note app-server-all-test has a large number of integration tests, so
# even a single shard can be quite slow. When there is a legitimate
# test failure in a shard, it will still get run 3x in total, which
# can cause us to exhaust our CI timeout if the shard happens to run
# long. Using a higher shard count for app-server-all-test should help
# mitigate this risk.
"app-server-all-test": 16,
"app-server-unit-tests": 8,
},
test_tags = ["no-sandbox"],

Some files were not shown because too many files have changed in this diff Show More