Skip to content

[pull] main from openai:main - #45

Merged
pull[bot] merged 13 commits into
bfloat16:mainfrom
openai:main
Sep 28, 2026
Merged

pull[bot] merged 13 commits into
bfloat16:mainfrom
openai:main

Conversation

@pull

@pull pull Bot commented Sep 28, 2026 •

Copy link
Copy Markdown

See Commits and Changes for more details.


Created by pull[bot] (v2.0.0-alpha.4)

Can you help keep this open source service alive? 💖 Please sponsor : )

jif-oai and others added 13 commits September 28, 2026 14:46
## Why

Best-effort workspace enrichment can time out independently of the detached
request metadata checked by the memory startup test.

## What changed

Keep the phase-one service-tier and detached-metadata test fixture outside Git
and assert that `workspaces` is absent. Update the header assertion message to
refer to turn metadata.

GitOrigin-RevId: 9541668fc62a28d1ff3131d7f71b351149b6e152
)

## Why

Microsoft Store PowerShell cannot run under MXC. The existing fallback to an unpackaged PowerShell executable only applied to the elevated Windows sandbox.

## What changed

Extend local PowerShell fallback discovery to MXC in `unified_exec`, using the executor's Windows sandbox selection. Keep discovery local and automatic `-NoProfile` insertion specific to the elevated sandbox. Skip this preparation for non-Windows target paths.

## Testing

Extend command-preparation tests to cover MXC and add a Windows integration test that replaces a Store PowerShell path before launch, writes a file successfully, and verifies `windows_mxc` sandbox metadata.

GitOrigin-RevId: 6c581396525a8fec7e1fb538b3e63b0de2ddb926
Older macOS policy compilers do not define the `TIOCSTI` symbol. Generate the sandbox CLI's Seatbelt deny rule with the numeric value from `libc::TIOCSTI` so it remains compatible while blocking terminal input injection.

GitOrigin-RevId: de8113fbab92bb399f37b9a22762c5c649f25972
Describe permissions and approvals explicitly in the Codex docs link text,
and clarify that the user's ChatGPT plan rate limits and training data
preferences apply. Remove the “Before you start” preamble to shorten the
success screen.

Update the rendering snapshot and hyperlink styling assertions for the
revised copy and layout.

GitOrigin-RevId: 5166ddade6a433191fa86c960899c4da5092b9f5
…9032)

## Why

Setting `auto_vacuum` on every connection can wait for a writer lock even when the mode is unchanged. Logging every span entry and exit can also block SQLx workers on undrained stderr while they hold a write transaction.

## What changed

- Set incremental vacuum only for empty databases or databases using full auto-vacuum, before enabling WAL. Preserve existing nonempty databases with auto-vacuum disabled.
- Emit span creation and closure events in app-server text and JSON stderr logs, preserving busy/idle timings and explicit events while omitting span entry and exit records.

## Testing

Add regression tests for opening and expanding writable pools while another connection holds a writer lock, and for transaction completion with undrained stderr in both log formats. Verify vacuum modes and retained log diagnostics.

GitOrigin-RevId: 40d4ef32c7efc49f4240b987277ba45551259335
## Why

The transcript supplied to Guardian may omit earlier user instructions, restrictions, or revoked permissions. History retrieval lets the reviewer check relevant authorization before approving actions with side effects.

## What changed

- Add the disabled-by-default `guardian_conversation_history_tools` feature. With Apps enabled, expose `user_message.search_messages` and `user_message.read_messages` through the parent's live Apps connection and conversation identity.
- Recheck the parent's current app and tool policy on each call, rejecting disabled tools and calls requiring approval.
- Add retrieval instructions that distinguish user authorization from assistant context and account for later revocations and incomplete results. Allow overrides through `auto_review.experimental_conversation_history_prompt`.
- Limit history responses to an estimated 4,000 tokens by default, configurable through `auto_review.conversation_history_max_output_tokens`, while preserving stricter parent and reviewer limits.
- Allow explicit extension registries for isolated sessions and prevent those sessions from inheriting the implicit Apps connection.

## Testing

Add scenarios covering history tool exposure, parent connection and identity reuse, custom prompts, output truncation, stricter reviewer budgets, and live permission changes on a reused reviewer. Extend configuration coverage for blank prompt overrides.

GitOrigin-RevId: 055a69b113c8548bd58e7d5618ea026ba6d1ffb1
## Why

The fullscreen status line showed Plan mode without explaining how to leave it.

## What changed

Show `Plan mode (shift+tab to cycle)` when the composer is idle and accepts input, and the hint fits alongside the status text. Fall back to the mode label when space is limited, and hide the shortcut during tasks, popups, interactive footer use, or other non-composer modes.

## Testing

Add a rendering snapshot and regression assertions for wide and narrow layouts, running tasks, interactive search, empty status text, disabled input, and parent-owned threads.

GitOrigin-RevId: a1cf2762b33f5442ab0611a15205f2e36c84b075
## Why

Guardian transcripts omitted encrypted agent messages, leaving reviews without evidence such as encrypted parent replies.

## What changed

- Carry encrypted `agent_message` items through synchronous reviews and asynchronous scoring, preserving their order, author, recipient, and ciphertext.
- Account for native messages in context budgets and omit them whole with an explicit notice when limits require it.
- Support mixed text and native messages during review admission while retaining user-content annotations.

## Testing

Add coverage for transcript ordering and budget eviction in both reviewer profiles, plus a mocked scenario verifying that an encrypted parent reply appears exactly once in each of two incremental Guardian reviews.

GitOrigin-RevId: abc2f1ce5accd83beb06f799ef9ed9d7fa2cd90a
## Why

Copying text selected entirely within inline code added Markdown backticks that were not part of the selected content.

## What changed

Return only the selected content as plain text when the selection is contained within one inline code span, including in a single table cell. Preserve Markdown formatting for selections that also include surrounding content, and continue filtering control characters from table copies.

## Testing

Add regression coverage for full and partial inline code selections, embedded backticks, Unicode, whitespace, wrapping and resizing, and table selections with mixed content or control characters.

GitOrigin-RevId: c63e13cb781f9fca28ae53500cb4f9ae08b72c96
## What changed

Update plan labels in the analytics views and status display:

- `PlanType::Pro`: `Pro (More)` → `Pro Extra`
- `PlanType::ProLite`: `Pro` → `Pro Standard`
- `PlanType::ProMax`: `Pro (Max)` → `Pro Max`

## Testing

Update the status display-name test expectations for all three Pro tiers.

GitOrigin-RevId: 9bd9f1cd8a701019fd40047cd8131e6193f66cb9
## What changed

Add the disabled-by-default `guardian_root_handoff_context` feature to select worker-specific root evidence for Guardian reviews. Use recorded `spawn_agent`, `send_message`, and `followup_task` calls targeting a worker or its ancestors to select the three preceding root messages per handoff, plus the three latest root messages so recent cancellations remain visible before another handoff.

Preserve verified tool answers and evidence without known ordering, and retain the existing shared message cap. Fall back to the existing root context when no usable handoff window remains or the latest authorization message is a heartbeat. Update the review context revision when the selection changes.

## Testing

Add a delegation scenario and Guardian request snapshot covering ancestor handoffs, separate worker branches, cancellation visibility, and fallback after compaction removes handoff calls. Extend heartbeat coverage to exercise the new feature and verify that the latest turn's trusted skills are retained.

GitOrigin-RevId: 87dc39158f78b2b7e9f4f2e4afc653257ea12025
## Why

Runtime ACL repair needs to handle nested files and directories beyond the legacy Windows path limit.

## What changed

Use Rust's `OpenOptions` for ACL reads and handle-based `SetSecurityInfo` for updates to support extended-length paths. Request ACL-write access only when grants need updating, and share allocation cleanup across success and error paths.

## Testing

Add a regression test covering long directory and file paths alongside a short-path control. Verify repeated repairs grant read/execute access without granting write, delete, or ACL-management rights, and that already-correct grants remain no-ops.

GitOrigin-RevId: 325c17085fa4379eebe982d49175dd2151b0681e
Refresh the Code Mode messaging snapshot to include a native `agent_message`
entry between transcript segments, with updated message and action numbering.
Adjust retained-instruction spacing in the encrypted parent reply snapshot and
refresh assertion-line metadata in both snapshots.

GitOrigin-RevId: 1ee003cfb9df89faabd2f35e9d656423f16e0501
@pull pull Bot locked and limited conversation to collaborators Sep 28, 2026
@pull pull Bot added the ⤵️ pull label Sep 28, 2026
@pull
pull Bot merged commit e07e58c into bfloat16:main Sep 28, 2026
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

9 participants