Files
codex/codex-rs/core/src/rollout/policy.rs
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

113 lines
4.4 KiB
Rust

use crate::protocol::EventMsg;
use crate::protocol::RolloutItem;
use codex_protocol::models::ResponseItem;
/// Whether a rollout `item` should be persisted in rollout files.
#[inline]
pub(crate) fn is_persisted_response_item(item: &RolloutItem) -> bool {
match item {
RolloutItem::ResponseItem(item) => should_persist_response_item(item),
RolloutItem::EventMsg(ev) => should_persist_event_msg(ev),
// Persist Codex executive markers so we can analyze flows (e.g., compaction, API turns).
RolloutItem::Compacted(_) | RolloutItem::TurnContext(_) | RolloutItem::SessionMeta(_) => {
true
}
}
}
/// Whether a `ResponseItem` should be persisted in rollout files.
#[inline]
pub(crate) fn should_persist_response_item(item: &ResponseItem) -> bool {
match item {
ResponseItem::Message { .. }
| ResponseItem::Reasoning { .. }
| ResponseItem::LocalShellCall { .. }
| ResponseItem::FunctionCall { .. }
| ResponseItem::FunctionCallOutput { .. }
| ResponseItem::CustomToolCall { .. }
| ResponseItem::CustomToolCallOutput { .. }
| ResponseItem::WebSearchCall { .. }
| ResponseItem::GhostSnapshot { .. }
| ResponseItem::Compaction { .. } => true,
ResponseItem::Other => false,
}
}
/// Whether an `EventMsg` should be persisted in rollout files.
#[inline]
pub(crate) fn should_persist_event_msg(ev: &EventMsg) -> bool {
match ev {
EventMsg::UserMessage(_)
| EventMsg::AgentMessage(_)
| EventMsg::AgentReasoning(_)
| EventMsg::AgentReasoningRawContent(_)
| EventMsg::TokenCount(_)
| EventMsg::ContextCompacted(_)
| EventMsg::EnteredReviewMode(_)
| EventMsg::ExitedReviewMode(_)
| EventMsg::ThreadRolledBack(_)
| EventMsg::UndoCompleted(_)
| EventMsg::TurnAborted(_) => true,
EventMsg::ItemCompleted(event) => {
// Plan items are derived from streaming tags and are not part of the
// raw ResponseItem history, so we persist their completion to replay
// them on resume without bloating rollouts with every item lifecycle.
matches!(event.item, codex_protocol::items::TurnItem::Plan(_))
}
EventMsg::Error(_)
| EventMsg::Warning(_)
| EventMsg::TurnStarted(_)
| EventMsg::TurnComplete(_)
| EventMsg::AgentMessageDelta(_)
| EventMsg::AgentReasoningDelta(_)
| EventMsg::AgentReasoningRawContentDelta(_)
| EventMsg::AgentReasoningSectionBreak(_)
| EventMsg::RawResponseItem(_)
| EventMsg::SessionConfigured(_)
| EventMsg::ThreadNameUpdated(_)
| EventMsg::McpToolCallBegin(_)
| EventMsg::McpToolCallEnd(_)
| EventMsg::WebSearchBegin(_)
| EventMsg::WebSearchEnd(_)
| EventMsg::ExecCommandBegin(_)
| EventMsg::TerminalInteraction(_)
| EventMsg::ExecCommandOutputDelta(_)
| EventMsg::ExecCommandEnd(_)
| EventMsg::ExecApprovalRequest(_)
| EventMsg::RequestUserInput(_)
| EventMsg::DynamicToolCallRequest(_)
| EventMsg::ElicitationRequest(_)
| EventMsg::ApplyPatchApprovalRequest(_)
| EventMsg::BackgroundEvent(_)
| EventMsg::StreamError(_)
| EventMsg::PatchApplyBegin(_)
| EventMsg::PatchApplyEnd(_)
| EventMsg::TurnDiff(_)
| EventMsg::GetHistoryEntryResponse(_)
| EventMsg::UndoStarted(_)
| EventMsg::McpListToolsResponse(_)
| EventMsg::McpStartupUpdate(_)
| EventMsg::McpStartupComplete(_)
| EventMsg::ListCustomPromptsResponse(_)
| EventMsg::ListSkillsResponse(_)
| EventMsg::PlanUpdate(_)
| EventMsg::ShutdownComplete
| EventMsg::ViewImageToolCall(_)
| EventMsg::DeprecationNotice(_)
| EventMsg::ItemStarted(_)
| EventMsg::AgentMessageContentDelta(_)
| EventMsg::PlanDelta(_)
| EventMsg::ReasoningContentDelta(_)
| EventMsg::ReasoningRawContentDelta(_)
| EventMsg::SkillsUpdateAvailable
| EventMsg::CollabAgentSpawnBegin(_)
| EventMsg::CollabAgentSpawnEnd(_)
| EventMsg::CollabAgentInteractionBegin(_)
| EventMsg::CollabAgentInteractionEnd(_)
| EventMsg::CollabWaitingBegin(_)
| EventMsg::CollabWaitingEnd(_)
| EventMsg::CollabCloseBegin(_)
| EventMsg::CollabCloseEnd(_) => false,
}
}