Files
PaperClipAI/server/src/modules/wake-queue/domain/context.test.ts
T
DottaandClaude Opus 5.5 6ca7b151f7 feat: compact an agent's context from the task Properties panel (#19378)
## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work
> - A task's Properties panel shows the assignee agent's context window
(paperclipai/paperclip#19273)
> - The board can see that the context is nearly full, but it cannot act
on it
> - A full context makes the agent compact at an unplanned time, often
in the middle of work
> - This pull request adds "Compact now" to the Context hover card
> - The benefit is that the board can compact the agent's context
between runs, at a time it chooses

## Linked Issues or Issue Description

Refs paperclipai/paperclip#19273

**Problem**
The Context row shows how full the agent's context window is. The board
cannot ask the agent to compact it.

**Proposed solution**
A "Compact now" button in the Context hover card. It runs the harness's
own compaction: Codex `thread/compact/start`, and Claude's `/compact`
command through ACP.

**Alternatives considered**
A separate PRP `session.compact` command. Both harnesses run compaction
as a turn, so a compaction turn keeps the existing durable turn binding,
interruption, and recovery. A separate command needs a second turn
lifecycle.

## What Changed

- UI: the Context hover card shows Compact now with three states:
available, Compacting…, and unavailable with a reason (agent mid-run,
harness unsupported, task closed). The Storybook story shows each state.
- Server: `POST /api/issues/:id/context/compact` (board only,
`decideIssueAccess` `issue:mutate`, activity log
`issue.context_compaction_requested`). It queues a short run marked by
`contextSnapshot.contextCompactionRequestId`. `GET
/issues/:id/context-usage` returns the `compaction` state.
- Server: a compaction run does no task work. The native status arbiter
preserves the task status. The lifecycle skips handoff, liveness
continuation, review-path disposition and the issue comment, as it does
for goal-control runs.
- Runner TS: `startTurn({ compact: true })`. The Codex harness session
sends `thread/compact/start`. The runnerd transport maps it to PRP
`turn.start` with `compact: true` (Codex) or `text: "/compact"`
(Claude/ACPX). The native runtime option `sessionCompaction` requires a
resumed session and settles with a synthesized yielded result.
- Runner Rust: `turn.start` accepts `compact: true` for Codex.
`CodexProvider::start_compaction_turn` sends `thread/compact/start` and
binds the turn from the `turn/started` that follows the empty response.
- Fix (from #19273): Codex emitted `context.compacted` on both the start
and the end of one compaction item. It now emits it once, and the count
is distinct by `compactionId`.
- Fix (from #19273): the conversation event view dropped
`context.compacted`, so a finished run never showed the divider. The
view now keeps compactions, plus context readings for runs that
compacted. A finished run's compactions show as thread dividers.
- Fix: the Codex harness stamps before/after sizes on the compaction
event. Codex reports the compacted size before the compaction item ends,
so the old neighbour-based guess showed the wrong size.

## Verification

- `pnpm -r typecheck`, `pnpm build`, `pnpm check:token-gates`, `node
scripts/storybook-catalog.mjs`: pass.
- New tests: `server/src/__tests__/context-compaction.test.ts`,
`status-arbiter.test.ts`, `issue-context-usage.test.ts` (duplicate
compaction counts once), `ui/.../context-usage-row.test.tsx`,
`native-session-runtime.test.ts` (context compaction), Codex driver and
runnerd transport tests, Rust
`codex_compaction_turn_binds_the_turn_reported_after_its_empty_response`.
Rust `codex_provider` suite: 115 passed.
- `pnpm test:run` locally: one failure in
`chat-channels.integration.test.ts`. It reads
`.claude/skills/slack/SKILL.md` from the main checkout, which is not
present in this worktree. It is not related to this change.
- Live, local worktree instance, Codex agent on the Paperclip runner:
clicked Compact now. The run succeeded. Context went from 35k to 9.4k
tokens, and later 9.4k to 9.2k. The task stayed In Review. The thread
shows "Context compacted · 9.4k → 9.2k tokens" and the meter dropped.
- Live Claude proof: pending. The local Claude agent needs an Anthropic
API key. claude-agent-acp handles `/compact` as an echo-less turn, and
the runner already maps its "Compacting completed." notice to
`context.compacted`.

## Risks

- A compaction run resumes the agent's session. If the session cannot
resume, the run fails with `native_context_compaction_unavailable` and
the task is unchanged.
- Compact now is not available while the agent runs on the task, because
compaction interrupts the active turn.
- The conversation view now returns context readings for runs that
compacted. Runs that never compacted return the same events as before.
- An old runner binary ignores `compact` and rejects the `turn.start`
because it has no text. It does not start an ordinary turn.

## Model Used

- Claude Opus 5.5 (`claude-opus-5-5`), Anthropic, through Claude Code
with tool use and code execution.

## 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
- [x] 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 22:07:12 -06:00

158 lines
7.3 KiB
TypeScript

import { describe, expect, it } from "vitest";
import { enrichPromotedWakeContext } from "./context.js";
describe("enrichPromotedWakeContext", () => {
it("clears stale derived comment projections when the canonical id list is empty, but keeps an independent interaction continuation", () => {
const contextSnapshot: Record<string, unknown> = {
// Normalization already dropped the canonical wake comment ids upstream
// of this function; no wakeCommentIds field remains on the snapshot.
paperclipWake: { commentId: "comment-2" },
paperclipWakeComment: { id: "comment-2", body: "stale body" },
paperclipTaskMarkdown: "stale markdown",
paperclipTaskMarkdownCompact: "stale compact markdown",
// Independent interaction continuation the promoted run must keep.
interactionId: "interaction-1",
interactionKind: "request_confirmation",
interactionStatus: "accepted",
};
const result = enrichPromotedWakeContext({
contextSnapshot,
reason: "issue_execution_promoted",
source: "automation",
triggerDetail: null,
payload: { mutation: "interaction" },
});
expect(result.contextSnapshot.wakeCommentIds).toBeUndefined();
expect(result.contextSnapshot.commentId).toBeUndefined();
expect(result.contextSnapshot.wakeCommentId).toBeUndefined();
expect(result.contextSnapshot.paperclipWake).toBeUndefined();
expect(result.contextSnapshot.paperclipWakeComment).toBeUndefined();
expect(result.contextSnapshot.paperclipTaskMarkdown).toBeUndefined();
expect(result.contextSnapshot.paperclipTaskMarkdownCompact).toBeUndefined();
// The independent interaction continuation survives the clear.
expect(result.contextSnapshot.interactionId).toBe("interaction-1");
expect(result.contextSnapshot.interactionStatus).toBe("accepted");
});
it("sets the canonical id and latest-id fields when the recomputed list has entries, and still clears the stale projections", () => {
const contextSnapshot: Record<string, unknown> = {
wakeCommentIds: ["comment-1"],
paperclipWake: { commentId: "comment-1" },
paperclipWakeComment: { id: "comment-1", body: "will be rebuilt" },
paperclipTaskMarkdown: "will be rebuilt",
paperclipTaskMarkdownCompact: "will be rebuilt",
};
const result = enrichPromotedWakeContext({
contextSnapshot,
reason: "issue_execution_promoted",
source: "automation",
triggerDetail: null,
payload: {},
});
expect(result.contextSnapshot.wakeCommentIds).toEqual(["comment-1"]);
expect(result.contextSnapshot.commentId).toBe("comment-1");
expect(result.contextSnapshot.wakeCommentId).toBe("comment-1");
// The derived projections are cleared so the run rebuilds them from the
// canonical ids instead of carrying forward a queue-time snapshot.
expect(result.contextSnapshot.paperclipWake).toBeUndefined();
expect(result.contextSnapshot.paperclipWakeComment).toBeUndefined();
expect(result.contextSnapshot.paperclipTaskMarkdown).toBeUndefined();
expect(result.contextSnapshot.paperclipTaskMarkdownCompact).toBeUndefined();
});
it("adds a new id from the payload to the canonical list and clears the stale projections", () => {
const contextSnapshot: Record<string, unknown> = {
wakeCommentIds: ["comment-1"],
paperclipWakeComment: { id: "comment-1", body: "stale body" },
};
const result = enrichPromotedWakeContext({
contextSnapshot,
reason: "issue_execution_promoted",
source: "automation",
triggerDetail: null,
payload: { commentId: "comment-2" },
});
expect(result.contextSnapshot.wakeCommentIds).toEqual(["comment-1", "comment-2"]);
expect(result.contextSnapshot.commentId).toBe("comment-2");
expect(result.contextSnapshot.wakeCommentId).toBe("comment-2");
expect(result.contextSnapshot.paperclipWakeComment).toBeUndefined();
});
it("keeps the raw issue, execution-stage, and accepted-plan fields a dispatch rebuild needs, alongside the cleared text projections", () => {
const contextSnapshot: Record<string, unknown> = {
wakeCommentIds: ["comment-1"],
paperclipWake: { commentId: "comment-1" },
paperclipTaskMarkdown: "stale markdown",
paperclipTaskMarkdownCompact: "stale compact markdown",
// Raw context a dispatch-time rebuild reads directly off the promoted
// run; none of it is derived from the comment ids above, so none of it
// should be cleared alongside the stale text projections.
issueId: "issue-1",
executionStage: { stage: "review" },
planReviewInteraction: { acceptedTargetRevision: { revisionId: "revision-1" } },
acceptedPlanWakeRouting: { targetAgentId: "agent-1" },
workspaceRefreshReason: "accepted_plan_confirmation",
};
const result = enrichPromotedWakeContext({
contextSnapshot,
reason: "issue_execution_promoted",
source: "automation",
triggerDetail: null,
payload: {},
});
// The rendered text is cleared; dispatch rebuilds it from the raw fields.
expect(result.contextSnapshot.paperclipWake).toBeUndefined();
expect(result.contextSnapshot.paperclipTaskMarkdown).toBeUndefined();
expect(result.contextSnapshot.paperclipTaskMarkdownCompact).toBeUndefined();
// The raw fields the rebuild needs are untouched.
expect(result.contextSnapshot.issueId).toBe("issue-1");
expect(result.contextSnapshot.executionStage).toEqual({ stage: "review" });
expect(result.contextSnapshot.planReviewInteraction).toEqual({
acceptedTargetRevision: { revisionId: "revision-1" },
});
expect(result.contextSnapshot.acceptedPlanWakeRouting).toEqual({ targetAgentId: "agent-1" });
expect(result.contextSnapshot.workspaceRefreshReason).toBe("accepted_plan_confirmation");
});
it("restores the issue scope of a payload-only receipt without overwriting a queued context", () => {
const payloadOnly = enrichPromotedWakeContext({
contextSnapshot: {},
reason: "task_retry",
source: "on_demand",
triggerDetail: "manual",
payload: { issueId: "issue-1", taskRetry: { schema: "paperclip.task-retry.v1" } },
});
expect(payloadOnly.contextSnapshot).toMatchObject({
issueId: "issue-1", taskId: "issue-1", taskKey: "issue-1", wakeReason: "task_retry",
});
const queued = enrichPromotedWakeContext({
contextSnapshot: { issueId: "issue-1", taskId: "task-1", taskKey: "TASK-1" },
reason: "issue_commented",
source: "automation",
triggerDetail: null,
payload: { issueId: "issue-2" },
});
expect(queued.contextSnapshot).toMatchObject({ issueId: "issue-1", taskId: "task-1", taskKey: "TASK-1" });
});
});
describe("context compaction wakes", () => {
it("never merge with ordinary wakes, in either order", async () => {
const { wakeMustNotJoinActiveRun } = await import("./context.js");
const compaction = { issueId: "issue-1", contextCompactionRequestId: "req-1" };
const comment = { issueId: "issue-1", wakeCommentId: "comment-1" };
expect(wakeMustNotJoinActiveRun(compaction, comment, false)).toBe(true);
expect(wakeMustNotJoinActiveRun(comment, compaction, false)).toBe(true);
expect(wakeMustNotJoinActiveRun(comment, { issueId: "issue-1", wakeCommentId: "comment-2" }, false)).toBe(false);
});
});