mirror of https://github.com/openai/codex.git synced 2026-02-01 22:47:52 +00:00

Files

Charley Cunningham ec4a2d07e4 Plan mode: stream proposed plans, emit plan items, and render in TUI (#9786 )

## Summary
- Stream proposed plans in Plan Mode using `<proposed_plan>` tags parsed
in core, emitting plan deltas plus a plan `ThreadItem`, while stripping
tags from normal assistant output.
- Persist plan items and rebuild them on resume so proposed plans show
in thread history.
- Wire plan items/deltas through app-server protocol v2 and render a
dedicated proposed-plan view in the TUI, including the “Implement this
plan?” prompt only when a plan item is present.

## Changes

### Core (`codex-rs/core`)
- Added a generic, line-based tag parser that buffers each line until it
can disprove a tag prefix; implements auto-close on `finish()` for
unterminated tags. `codex-rs/core/src/tagged_block_parser.rs`
- Refactored proposed plan parsing to wrap the generic parser.
`codex-rs/core/src/proposed_plan_parser.rs`
- In plan mode, stream assistant deltas as:
  - **Normal text** → `AgentMessageContentDelta`
  - **Plan text** → `PlanDelta` + `TurnItem::Plan` start/completion  
  (`codex-rs/core/src/codex.rs`)
- Final plan item content is derived from the completed assistant
message (authoritative), not necessarily the concatenated deltas.
- Strips `<proposed_plan>` blocks from assistant text in plan mode so
tags don’t appear in normal messages.
(`codex-rs/core/src/stream_events_utils.rs`)
- Persist `ItemCompleted` events only for plan items for rollout replay.
(`codex-rs/core/src/rollout/policy.rs`)
- Guard `update_plan` tool in Plan Mode with a clear error message.
(`codex-rs/core/src/tools/handlers/plan.rs`)
- Updated Plan Mode prompt to:  
  - keep `<proposed_plan>` out of non-final reasoning/preambles  
  - require exact tag formatting  
  - allow only one `<proposed_plan>` block per turn  
  (`codex-rs/core/templates/collaboration_mode/plan.md`)

### Protocol / App-server protocol
- Added `TurnItem::Plan` and `PlanDeltaEvent` to core protocol items.
(`codex-rs/protocol/src/items.rs`, `codex-rs/protocol/src/protocol.rs`)
- Added v2 `ThreadItem::Plan` and `PlanDeltaNotification` with
EXPERIMENTAL markers and note that deltas may not match the final plan
item. (`codex-rs/app-server-protocol/src/protocol/v2.rs`)
- Added plan delta route in app-server protocol common mapping.
(`codex-rs/app-server-protocol/src/protocol/common.rs`)
- Rebuild plan items from persisted `ItemCompleted` events on resume.
(`codex-rs/app-server-protocol/src/protocol/thread_history.rs`)

### App-server
- Forward plan deltas to v2 clients and map core plan items to v2 plan
items. (`codex-rs/app-server/src/bespoke_event_handling.rs`,
`codex-rs/app-server/src/codex_message_processor.rs`)
- Added v2 plan item tests.
(`codex-rs/app-server/tests/suite/v2/plan_item.rs`)

### TUI
- Added a dedicated proposed plan history cell with special background
and padding, and moved “• Proposed Plan” outside the highlighted block.
(`codex-rs/tui/src/history_cell.rs`, `codex-rs/tui/src/style.rs`)
- Only show “Implement this plan?” when a plan item exists.
(`codex-rs/tui/src/chatwidget.rs`,
`codex-rs/tui/src/chatwidget/tests.rs`)

<img width="831" height="847" alt="Screenshot 2026-01-29 at 7 06 24 PM"
src="https://github.com/user-attachments/assets/69794c8c-f96b-4d36-92ef-c1f5c3a8f286"
/>

### Docs / Misc
- Updated protocol docs to mention plan deltas.
(`codex-rs/docs/protocol_v1.md`)
- Minor plumbing updates in exec/debug clients to tolerate plan deltas.
(`codex-rs/debug-client/src/reader.rs`, `codex-rs/exec/...`)

## Tests
- Added core integration tests:
  - Plan mode strips plan from agent messages.
  - Missing `</proposed_plan>` closes at end-of-message.  
  (`codex-rs/core/tests/suite/items.rs`)
- Added unit tests for generic tag parser (prefix buffering, non-tag
lines, auto-close). (`codex-rs/core/src/tagged_block_parser.rs`)
- Existing app-server plan item tests in v2.
(`codex-rs/app-server/tests/suite/v2/plan_item.rs`)

## Notes / Behavior
- Plan output no longer appears in standard assistant text in Plan Mode;
it streams via `PlanDelta` and completes as a `TurnItem::Plan`.
- The final plan item content is authoritative and may diverge from
streamed deltas (documented as experimental).
- Reasoning summaries are not filtered; prompt instructs the model not
to include `<proposed_plan>` outside the final plan message.

## Codex Author
`codex fork 019bec2d-b09d-7450-b292-d7bcdddcdbfb`

2026-01-30 18:59:30 +00:00

src

Plan mode: stream proposed plans, emit plan items, and render in TUI (#9786 )

2026-01-30 18:59:30 +00:00

Cargo.toml

chore: add small debug client (#8894 )

2026-01-08 13:40:14 +00:00

README.md

chore: add small debug client (#8894 )

2026-01-08 13:40:14 +00:00

README.md

WARNING: this code is mainly generated by Codex and should not be used in production

codex-debug-client

A tiny interactive client for codex app-server (protocol v2 only). It prints all JSON-RPC lines from the server and lets you send new turns as you type.

Usage

Start the app-server client (it will spawn codex app-server itself):

cargo run -p codex-debug-client -- \
  --codex-bin codex \
  --approval-policy on-request

You can resume a specific thread:

cargo run -p codex-debug-client -- --thread-id thr_123

CLI flags

--codex-bin <path>: path to the codex binary (default: codex).
-c, --config key=value: pass through --config overrides to codex.
--thread-id <id>: resume a thread instead of starting a new one.
--approval-policy <policy>: untrusted, on-failure, on-request, never.
--auto-approve: auto-approve command/file-change approvals (default: decline).
--final-only: only show completed assistant messages and tool items.
--model <name>: optional model override for thread start/resume.
--model-provider <name>: optional provider override.
--cwd <path>: optional working directory override.

Interactive commands

Type a line to send it as a new turn. Commands are prefixed with ::

:help show help
:new start a new thread
:resume <thread-id> resume a thread
:use <thread-id> switch active thread without resuming
:refresh-thread list available threads
:quit exit

The prompt shows the active thread id. Client messages (help, errors, approvals) print to stderr; raw server JSON prints to stdout so you can pipe/record it unless --final-only is set.

Notes

The client performs the required initialize/initialized handshake.
It prints every server notification and response line as it arrives.
Approvals for item/commandExecution/requestApproval and item/fileChange/requestApproval are auto-responded to with decline unless --auto-approve is set.