Files
PaperClipAI/server/src/services/issue-context-usage.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

120 lines
4.8 KiB
TypeScript

import { and, desc, eq, inArray, or, sql } from "drizzle-orm";
import type { Db } from "@paperclipai/db";
import { heartbeatRunEvents, heartbeatRuns } from "@paperclipai/db";
import type { IssueContextUsage } from "@paperclipai/shared";
/**
* Recent runs of the assignee searched for its newest usage report. The
* usage lookups use `heartbeat_run_events_usage_item_run_idx`, so they read
* only the few usage items of these runs.
*/
const RECENT_RUN_LIMIT = 3;
function count(value: unknown): number | null {
const parsed = typeof value === "string" ? Number(value) : value;
return typeof parsed === "number" && Number.isFinite(parsed) && parsed >= 0 ? parsed : null;
}
function record(value: unknown): Record<string, unknown> | null {
return value && typeof value === "object" && !Array.isArray(value) ? value as Record<string, unknown> : null;
}
/** Matches the predicate of `heartbeat_run_events_usage_item_run_idx`. */
const usageItem = sql`${heartbeatRunEvents.eventType} = 'item.completed' and (${heartbeatRunEvents.payload} -> 'prpEvent' -> 'payload' ->> 'kind') = 'usage'`;
/** Matches the key expression of `heartbeat_run_events_compaction_session_idx`. */
const sessionIdSql = sql<string | null>`(${heartbeatRunEvents.payload} -> 'prpEvent' ->> 'normalizedSessionId')`;
/**
* Reads the most recent provider-reported context occupancy for the current
* agent session on a task. The current session is the one behind the
* assignee's newest usage report: after a reassignment or a fresh session,
* older readings are not returned. Returns null until that session reports a
* context window.
*/
export async function issueContextUsage(
db: Db,
companyId: string,
issue: { id: string; assigneeAgentId: string | null },
): Promise<IssueContextUsage | null> {
if (!issue.assigneeAgentId) return null;
const runs = await db
.select({ id: heartbeatRuns.id })
.from(heartbeatRuns)
.where(and(
eq(heartbeatRuns.companyId, companyId),
eq(heartbeatRuns.agentId, issue.assigneeAgentId),
or(eq(heartbeatRuns.issueId, issue.id), eq(heartbeatRuns.nativeIssueId, issue.id)),
))
.orderBy(desc(heartbeatRuns.createdAt), desc(heartbeatRuns.id))
.limit(RECENT_RUN_LIMIT);
if (runs.length === 0) return null;
const runIds = runs.map((run) => run.id);
const recentUsage = and(
eq(heartbeatRunEvents.companyId, companyId),
inArray(heartbeatRunEvents.runId, runIds),
usageItem,
);
// The newest usage report names the current session.
const [current] = await db
.select({ sessionId: sessionIdSql })
.from(heartbeatRunEvents)
.where(recentUsage)
.orderBy(desc(heartbeatRunEvents.createdAt), desc(heartbeatRunEvents.id))
.limit(1);
const sessionId = current?.sessionId ?? null;
if (!sessionId) return null;
const [latest] = await db
.select({
runId: heartbeatRunEvents.runId,
agentId: heartbeatRunEvents.agentId,
createdAt: heartbeatRunEvents.createdAt,
usage: sql<unknown>`${heartbeatRunEvents.payload} -> 'prpEvent' -> 'payload' -> 'usage'`,
})
.from(heartbeatRunEvents)
.where(and(
recentUsage,
sql`${sessionIdSql} = ${sessionId}`,
sql`${heartbeatRunEvents.payload} -> 'prpEvent' -> 'payload' -> 'usage' ? 'context'`,
))
.orderBy(desc(heartbeatRunEvents.createdAt), desc(heartbeatRunEvents.id))
.limit(1);
if (!latest) return null;
const usage = record(latest.usage);
const context = record(usage?.context);
const usedTokens = count(context?.usedTokens);
const windowTokens = count(context?.windowTokens);
if (usedTokens === null || windowTokens === null || windowTokens < 1) return null;
// Every compaction of the session, across all of its runs. A provider can
// report one compaction through more than one notification; count each id once.
const [compactions] = await db
.select({
count: sql<number>`count(distinct coalesce(${heartbeatRunEvents.payload} -> 'prpEvent' -> 'payload' ->> 'compactionId', ${heartbeatRunEvents.id}::text))::int`,
})
.from(heartbeatRunEvents)
.where(and(
eq(heartbeatRunEvents.companyId, companyId),
eq(heartbeatRunEvents.eventType, "context.compacted"),
sql`${sessionIdSql} = ${sessionId}`,
));
const total = record(usage?.total);
const inputTokens = count(total?.inputTokens) ?? 0;
const cachedInputTokens = count(total?.cacheReadTokens) ?? count(total?.cachedInputTokens) ?? 0;
const outputTokens = count(total?.outputTokens) ?? 0;
const costUsd = count(total?.providerCostUsd);
return {
runId: latest.runId,
agentId: latest.agentId,
sessionId,
usedTokens,
windowTokens,
observedAt: latest.createdAt.toISOString(),
totals: inputTokens + outputTokens > 0 ? { inputTokens, cachedInputTokens, outputTokens } : null,
costUsd: costUsd && costUsd > 0 ? costUsd : null,
compactions: compactions?.count ?? 0,
};
}