Files
PaperClipAI/ui/src/components/task-chat/task-chat-activity-presentation.ts
T
DottaandClaude Opus 5.5 22281d4b3a feat(task-chat): approve harness-proposed plans (Codex plan mode, Claude ExitPlanMode) (#19291)
## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work
> - Agents run through the native runner. Codex and Claude Code each
have their own plan mode, and each produces a proposed-plan document.
> - Paperclip already has a planning work mode, an issue `plan`
document, and a `request_confirmation` approval gate for plans.
> - These parts were not connected. The Codex proposed-plan item was
transcript text only. The server path never put Codex into plan mode.
Claude was never put into plan mode, and its ExitPlanMode plan was
dropped. A planning run could close its task as done with no approval.
> - This pull request turns a harness's own proposed plan into the
issue's Plan document and the existing approval gate, for Codex and
Claude.
> - The benefit is that users approve or send back the agent's real plan
from the task chat. Approve resumes the agent. Request changes sends the
reason back to the agent.

## Linked Issues or Issue Description

Refs #19252

**Subsystem affected**
Native runner provider events (Codex and ACPX Claude), the runner Codex
provider (Rust), server native plan synchronization, and the task chat
UI.

**Problem or motivation**
Codex and Claude both produce a proposed-plan document in their native
plan mode. Paperclip did not use it. In live tests on the server path, a
Codex planning run was not in Codex plan mode, saved its own
`implementation-plan` document, and marked the task done without
approval. Claude planning runs were not in Claude plan mode, and the
ExitPlanMode plan text never reached Paperclip.

**Proposed solution**
Add a canonical `plan.proposed` event for a harness's proposed plan. Put
Codex and Claude into their native plan mode for planning runs. Save a
completed proposal as the issue `plan` document with the existing
`request_confirmation` gate. Agents can also propose a plan on a
standard task; the work mode stays standard.

**Alternatives considered**
Reuse `plan.updated`. Its schema is the within-turn checklist and is not
the durable Plan document, so a separate event keeps the two clear.
Stronger prompt text without native plan mode. Live tests showed that
the model kept its own document workflow.

**Roadmap alignment**
This reuses the issue plan document, planning work mode and approval
gate that already exist. It adds one canonical provider event.

## What Changed

- `packages/paperclip-runner/protocol/schemas/*`: add the
`plan.proposed` event (`paperclip.plan.proposed.v1`: `proposalId`,
`status`, `markdown` up to 60k characters, `source`). Regenerate the
schema bundle, validators and manifest.
- `packages/paperclip-runner/src/provider-events.ts`: map the Codex
`plan` item and a `<proposed_plan>` block in a completed Codex message
to `plan.proposed`. Add `claudePlanProposalEvent`.
-
`packages/paperclip-runner/runner/crates/runner-core/src/codex_provider.rs`:
send Codex's native `collaborationMode: plan` on `turn/start` for a
read-only (planning) Codex run. Before this change the server path never
sent it.
- `runner-core/src/acpx_event_payload.rs`: admit `plan.proposed` as ACPX
rich display activity.
- `drivers/acpx/codex-runtime-adapter.ts`: set Claude Code to native
plan mode for a read-only run. Capture Claude's ExitPlanMode plan from
its permission request, record it, and decline the native "Ready to
code?" prompt.
- `drivers/acpx/codex-acpx-driver.ts`, `cli/acpx-runtime-sidecar.ts`:
emit the captured proposal as a rich event. Complete that turn instead
of reporting it as cancelled.
- `backends/codex-native-backend.ts`: per-harness plan-mode
instructions, and a short opt-in hint for Claude on standard tasks.
- `server/src/services/native-runtime/native-session-executor.ts`:
synchronize a completed `plan.proposed` into the `plan` document and a
`request_confirmation` in planning and standard mode. Do not change the
issue status during the run (that revoked the run's lease). The run
finalizer turns the pending confirmation into the review wait.
- `server/src/services/heartbeat-run-summary.ts`: keep a
`<proposed_plan>` block out of the posted reply.
- UI: new `plan_proposal` provider family. The task chat shows a live
"Writing plan" card while a proposal streams and a one-line record when
it completes. Resolved plan reviews keep a receipt ("Approved Plan v1",
"Requested changes to Plan v1: reason"). Plan previews skip section
headings.
- Storybook: `Tasks and conversations/.../Task chat/Proposed plan
approval` shows the journey.
- `doc/SPEC-implementation.md`: describe harness-proposed plan approval.

## Verification

- `cargo test -p paperclip-runner-core --lib` (new:
`read_only_codex_turns_use_native_plan_collaboration_mode`)
- `cd packages/paperclip-runner && npx vitest run
src/provider-events.test.ts
src/drivers/acpx/codex-runtime-adapter.test.ts`
- `cd server && npx vitest run
src/__tests__/native-plan-proposal-sync.test.ts
src/__tests__/heartbeat-run-summary.test.ts`
- `cd ui && npx vitest run
src/components/transcript/native-run-events.test.ts
src/components/task-chat`
- Live test on a local worktree instance with real harnesses:
- Codex (`gpt-5.6-sol`), planning task: Codex asked one question, then
produced a native plan item. The task showed Plan v1 with Approve plan /
Request changes and moved to in review. Approve changed the work mode to
standard. Codex then implemented the plan and its tests passed.
- Codex, Request changes with a reason: Codex woke in planning mode and
produced Plan v2 that includes the change.
- Claude (`claude-opus-5-5`), planning task: Claude was in plan mode.
ExitPlanMode became Plan v1 and the turn completed. Approve resumed
Claude in standard mode, and Claude implemented the plan.
- Claude, standard task that asks for a plan first: Claude stopped
before code changes and asked for plan approval. The work mode stayed
standard.
- Storybook: open `Proposed plan approval` and check each stage.

## Risks

- Codex planning runs now really use Codex plan mode on the server path.
Codex can ask a clarifying question before it proposes. This matches
Codex plan mode.
- Claude planning runs now use Claude plan mode. A declined ExitPlanMode
ends the Claude turn; the runner reports it as completed. Claude's tool
row for that request records a rejection from Claude's side.
- Codex does not stream the proposed plan on the server path yet, so the
live card shows a placeholder until the plan completes.
- A `<proposed_plan>` block in any completed Codex message on a standard
task now asks for approval. This is the documented opt-in path.

> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.

## Model Used

- Anthropic Claude Opus 5.5 (`claude-opus-5-5`), via Claude Code with
tool use (shell, file edits, browser). Long context. No extended
thinking mode was used.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [ ] I will address all Greptile and reviewer comments before
requesting merge

🤖 Generated with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-05 20:53:33 +00:00

273 lines
13 KiB
TypeScript
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
import {
AlertTriangle,
BookOpen,
Bot,
CircleCheck,
CircleDashed,
CircleX,
Box,
Clock3,
Database,
FileCheck2,
FilePenLine,
FileText,
Globe,
Info,
ListChecks,
PackageCheck,
Search,
TerminalSquare,
Users,
} from "lucide-react";
import type {
TaskChatMaterializedResourceItem,
TaskChatProtocolItem,
TaskChatProviderActivityItem,
TaskChatWorkspaceChangeItem,
TaskChatWorkspaceFileItem,
} from "./task-chat-model";
import {
humanizeToolName,
isGenericToolName,
mcpToolIdentity,
toolActivityPresentation,
type ToolIcon,
} from "./tool-taxonomy";
import { governancePresentation, type GovernanceTone } from "./governance-presentation";
export interface TaskChatActivityPresentation {
icon: ToolIcon;
runningLabel: string;
completedLabel: string;
failedLabel?: string;
interruptedLabel?: string;
detail?: string;
/** Governance rows tint a stopped action and carry its reason as a note. */
tone?: GovernanceTone;
note?: string;
}
export function providerNoticeSeverity(item: TaskChatProviderActivityItem): "info" | "warning" | "error" {
const severity = item.details.find((entry) => entry.label === "Severity")?.value;
if (item.status === "failed" || severity === "error") return "error";
return severity === "info" ? "info" : "warning";
}
function providerDetail(item: TaskChatProviderActivityItem, ...labels: string[]): string | undefined {
return item.details.find((entry) => labels.includes(entry.label))?.value;
}
function meaningfulToolDetail(value: string | undefined): string | undefined {
if (!value || isGenericToolName(value) || /^tool(?:\s+|_)call\b/i.test(value)) return undefined;
return value;
}
/** Host and path without scheme or query, for one-line web activity. */
export function compactUrl(href: string): string {
try {
const url = new URL(href);
const path = url.pathname === "/" ? "" : url.pathname.replace(/\/$/, "");
return `${url.hostname.replace(/^www\./, "")}${path}`;
} catch {
return href;
}
}
/** Whole-second duration such as "30s" or "2m 5s" from a millisecond detail. */
export function durationLabel(value: string | undefined): string | undefined {
if (!value) return undefined;
const ms = Number(value);
if (!Number.isFinite(ms) || ms < 0) return undefined;
const totalSeconds = Math.round(ms / 1000);
if (totalSeconds < 60) return `${totalSeconds}s`;
const minutes = Math.floor(totalSeconds / 60);
const seconds = totalSeconds % 60;
return seconds === 0 ? `${minutes}m` : `${minutes}m ${seconds}s`;
}
function modelRouteDetail(item: TaskChatProviderActivityItem): string | undefined {
const from = providerDetail(item, "From Model") ?? providerDetail(item, "Requested Model");
const to = providerDetail(item, "Effective Model");
if (!to || to === "unknown") return undefined;
const reason = providerDetail(item, "Reason");
const route = from && from !== "unknown" && from !== to ? `${from} → ${to}` : to;
return reason && reason !== "provider reroute" ? `${route} · ${reason}` : route;
}
export function providerActivityPresentation(item: TaskChatProviderActivityItem): TaskChatActivityPresentation {
const detail = item.summary
?? providerDetail(item, "Query", "URL", "Target", "Name", "Reference", "Reason", "Summary");
switch (item.family) {
case "research": {
const action = providerDetail(item, "Action")?.toLowerCase();
const query = providerDetail(item, "Query");
const url = providerDetail(item, "Url");
if (action === "open_page") {
return { icon: Globe, runningLabel: "Opening a web page", completedLabel: "Opened a web page", failedLabel: "Couldn’t open the web page", interruptedLabel: "Stopped opening the web page", detail: url ? compactUrl(url) : detail };
}
if (action === "find_in_page") {
const pattern = providerDetail(item, "Pattern");
return { icon: Search, runningLabel: "Searching the page", completedLabel: "Searched the page", failedLabel: "Page search failed", interruptedLabel: "Page search stopped", detail: [pattern ? `“${pattern}”` : undefined, url ? compactUrl(url) : undefined].filter(Boolean).join(" in ") || detail };
}
return { icon: Search, runningLabel: "Searching the web", completedLabel: "Searched the web", failedLabel: "Web search failed", interruptedLabel: "Web search stopped", detail: query ? `“${query}”` : detail };
}
case "tool_execution": {
const name = providerDetail(item, "Name");
const target = providerDetail(item, "Target");
const progress = providerDetail(item, "Progress");
const tool = toolActivityPresentation({
name,
transport: providerDetail(item, "Transport"),
namespace: providerDetail(item, "Namespace"),
operation: providerDetail(item, "Operation"),
target,
progress,
});
const boundedActivity = meaningfulToolDetail(item.summary)
?? meaningfulToolDetail(progress)
?? meaningfulToolDetail(target);
const activityIsIdentity = Boolean(
boundedActivity && name && humanizeToolName(boundedActivity) === humanizeToolName(name),
);
const technicalName = name ? mcpToolIdentity(name)?.name ?? name : tool.displayName;
const source = tool.sourceLabel
? `${tool.sourceLabel} · ${technicalName}`
: name && !isGenericToolName(name) && humanizeToolName(name) !== tool.runningLabel.replace(/^Running /, "")
? name
: undefined;
return {
icon: tool.icon,
runningLabel: tool.runningLabel,
completedLabel: tool.completedLabel,
failedLabel: tool.failedLabel,
interruptedLabel: tool.interruptedLabel,
detail: [activityIsIdentity ? undefined : boundedActivity, source].filter(Boolean).join(" · ") || undefined,
};
}
case "plan_proposal":
return { icon: FileText, runningLabel: "Writing a plan", completedLabel: "Proposed a plan", failedLabel: "Plan proposal failed", interruptedLabel: "Plan proposal stopped", detail };
case "plan":
return { icon: ListChecks, runningLabel: "Updating the plan", completedLabel: "Updated the plan", failedLabel: "Plan update failed", interruptedLabel: "Plan update stopped", detail };
case "delegation": {
const action = providerDetail(item, "Action")?.toLowerCase();
if (action === "message") return { icon: Users, runningLabel: "Messaging a subagent", completedLabel: "Messaged a subagent", failedLabel: "Subagent message failed", interruptedLabel: "Subagent message stopped", detail };
if (action === "resume") return { icon: Users, runningLabel: "Resuming a subagent", completedLabel: "Resumed a subagent", failedLabel: "Couldn’t resume the subagent", interruptedLabel: "Subagent resume stopped", detail };
if (action === "close") return { icon: Users, runningLabel: "Closing a subagent", completedLabel: "Closed a subagent", failedLabel: "Couldn’t close the subagent", interruptedLabel: "Subagent close stopped", detail };
if (action === "wait") return { icon: Users, runningLabel: "Waiting for subagents", completedLabel: "Finished waiting for subagents", failedLabel: "Subagent wait failed", interruptedLabel: "Stopped waiting for subagents", detail };
return { icon: Users, runningLabel: "Starting a subagent", completedLabel: "Started a subagent", failedLabel: "Subagent start failed", interruptedLabel: "Subagent start stopped", detail };
}
case "model_identity":
return item.eventType === "model.route.changed"
? { icon: Bot, runningLabel: "Switching models", completedLabel: "Switched models", failedLabel: "Model switch failed", interruptedLabel: "Model switch stopped", detail: modelRouteDetail(item) ?? detail }
: { icon: Bot, runningLabel: "Verifying the model", completedLabel: "Verified the model", failedLabel: "Model verification failed", interruptedLabel: "Model verification stopped", detail };
case "context":
return { icon: Database, runningLabel: "Compacting context", completedLabel: "Compacted context", failedLabel: "Context compaction failed", interruptedLabel: "Context compaction stopped", detail };
case "artifact": {
const viewed = item.eventType === "artifact.viewed";
return viewed
? { icon: Box, runningLabel: "Viewing an artifact", completedLabel: "Viewed an artifact", failedLabel: "Couldn’t view the artifact", interruptedLabel: "Artifact view stopped", detail }
: { icon: Box, runningLabel: "Generating an artifact", completedLabel: "Generated an artifact", failedLabel: "Artifact generation failed", interruptedLabel: "Artifact generation stopped", detail };
}
case "review": {
const state = providerDetail(item, "State")?.toLowerCase();
return state === "exited"
? { icon: FileCheck2, runningLabel: "Leaving review mode", completedLabel: "Left review mode", failedLabel: "Couldn’t leave review mode", interruptedLabel: "Review-mode change stopped", detail }
: { icon: FileCheck2, runningLabel: "Entering review mode", completedLabel: "Entered review mode", failedLabel: "Couldn’t enter review mode", interruptedLabel: "Review-mode change stopped", detail };
}
case "hook":
case "safety": {
const governance = governancePresentation(item)!;
return {
icon: governance.icon,
runningLabel: governance.label,
completedLabel: governance.label,
failedLabel: governance.label,
interruptedLabel: governance.label,
detail: governance.detail,
tone: governance.tone,
note: governance.note,
};
}
case "memory":
return { icon: BookOpen, runningLabel: "Checking memory", completedLabel: "Referenced memory", failedLabel: "Memory lookup failed", interruptedLabel: "Memory lookup stopped", detail };
case "terminal":
return { icon: TerminalSquare, runningLabel: "Sending terminal input", completedLabel: "Sent terminal input", failedLabel: "Terminal input failed", interruptedLabel: "Terminal input stopped", detail };
case "wait": {
const planned = durationLabel(providerDetail(item, "Planned Duration Ms"));
const elapsed = durationLabel(providerDetail(item, "Elapsed Duration Ms"));
return {
icon: Clock3,
runningLabel: planned ? `Waiting ${planned}` : "Waiting",
completedLabel: elapsed ?? planned ? `Waited ${elapsed ?? planned}` : "Finished waiting",
failedLabel: "Wait failed",
interruptedLabel: elapsed ? `Stopped waiting after ${elapsed}` : "Wait stopped",
};
}
case "verification": {
const status = providerDetail(item, "Status");
return {
icon: status === "passed" ? CircleCheck : status === "failed" ? CircleX : CircleDashed,
runningLabel: "Running a check",
completedLabel: status === "not_run" ? "Check not run" : "Check passed",
failedLabel: "Check failed",
interruptedLabel: "Check not run",
detail: item.summary,
};
}
case "provider_notice":
return { icon: providerNoticeSeverity(item) === "info" ? Info : AlertTriangle, runningLabel: "Provider notice", completedLabel: "Provider notice", failedLabel: "Provider error", interruptedLabel: "Provider notice", detail };
}
}
function workspaceChangePresentation(item: TaskChatWorkspaceChangeItem): TaskChatActivityPresentation {
const count = item.totals.files || item.files.length;
const detail = count > 0 ? `${count} ${count === 1 ? "file" : "files"}` : undefined;
return { icon: FilePenLine, runningLabel: "Editing files", completedLabel: "Edited files", detail };
}
function workspaceFilePresentation(item: TaskChatWorkspaceFileItem): TaskChatActivityPresentation {
return {
icon: FileText,
runningLabel: "Referencing a file",
completedLabel: "Referenced a file",
detail: item.line == null ? item.path : `${item.path}:${item.line}`,
};
}
function resourcePresentation(item: TaskChatMaterializedResourceItem): TaskChatActivityPresentation {
return {
icon: item.resourceKind === "document" ? FileText : PackageCheck,
runningLabel: "Saving a resource",
completedLabel: item.resourceKind === "document" ? "Added a document" : "Added a deliverable",
detail: item.title,
};
}
export function protocolActivityPresentation(item: TaskChatProtocolItem): TaskChatActivityPresentation | null {
switch (item.surface) {
case "provider_activity": return providerActivityPresentation(item);
case "workspace_change": return workspaceChangePresentation(item);
case "workspace_file": return workspaceFilePresentation(item);
case "resource": return resourcePresentation(item);
case "runtime_request":
case "run_result":
case "run_terminal":
return null;
}
}
export function protocolActivityIsRunning(item: TaskChatProtocolItem): boolean {
if (item.surface === "provider_activity") return item.status === "running";
if (item.surface === "workspace_change") return !item.complete;
return false;
}
export function protocolActivityLabel(item: TaskChatProtocolItem, presentation: TaskChatActivityPresentation): string {
if (item.surface !== "provider_activity") {
return protocolActivityIsRunning(item) ? presentation.runningLabel : presentation.completedLabel;
}
if (item.status === "failed") return presentation.failedLabel ?? `${presentation.completedLabel} · failed`;
if (item.status === "interrupted") return presentation.interruptedLabel ?? `${presentation.completedLabel} · interrupted`;
return item.status === "running" ? presentation.runningLabel : presentation.completedLabel;
}